CN111308027B

CN111308027B - Method, device and system for determining quality of uncooked food and computer readable storage medium

Info

Publication number: CN111308027B
Application number: CN202010073311.6A
Authority: CN
Inventors: 张小栓; 王想; 肖新清; 傅泽田; 冯欢欢; 张旭; 王文胜; 刘峰; 邢少华; 赵爽
Original assignee: China Agricultural University
Current assignee: Hefei Minglong Electronic Technology Co ltd
Priority date: 2020-01-22
Filing date: 2020-01-22
Publication date: 2021-03-16
Anticipated expiration: 2040-01-22
Also published as: CN111308027A

Abstract

The disclosure relates to a method, a device and a system for determining the quality of raw food and a computer readable storage medium, relating to the field of food safety detection. The method of the present disclosure comprises: acquiring the volume fraction of fresh-keeping gas in a logistics environment of uncooked food products, the temperature of the logistics environment and the logistics time; inputting the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time into a pre-trained quality perception model, and determining at least one quality parameter of the uncooked food product, wherein the at least one quality parameter comprises: at least one of texture parameters, sensory parameters, physicochemical parameters and microbial parameters; and determining the quality of the uncooked food product according to the quality parameters.

Description

Method, device and system for determining quality of uncooked food and computer readable storage medium

Technical Field

The present disclosure relates to the field of food safety detection, and in particular, to a method, an apparatus, a system, and a computer-readable storage medium for determining a quality of a raw food.

Background

The raw food products are directly eaten without cooking, such as stabs (fish, shrimp, seafood, raw beef), vegetables, fruits and the like, and are natural healthy foods.

However, the quality of the raw food may be deteriorated or rotten before the food reaches the dining table due to the current environmental conditions, social conditions, and physical conditions. Therefore, how to monitor the product quality in the cold-chain logistics process of raw food products is an important power for improving the cold-chain logistics management and traceability of the raw food products.

At present, the quality of the uncooked food is determined by mainly considering the influence of temperature and time on a certain quality index.

Disclosure of Invention

The inventor finds that: fresh-keeping gas can be filled into raw food products in the cold-chain logistics process, but the influence of temperature and time on a certain quality index is only considered in the existing determination method of the quality of the raw food, the change of the quality index along with the time and the temperature under the stress of the fresh-keeping gas is not considered, the quality influence factor of the raw food products in the cold-chain logistics process cannot be comprehensively considered, and the quality of the raw food products cannot be accurately monitored.

One technical problem to be solved by the present disclosure is: how to improve the accuracy of determining the quality of uncooked food products.

According to some embodiments of the present disclosure, there is provided a method for determining a quality of a raw food, including: acquiring the volume fraction of fresh-keeping gas in a logistics environment of uncooked food products, the temperature of the logistics environment and the logistics time; inputting the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time into a pre-trained quality perception model, and determining at least one quality parameter of the uncooked food product, wherein the at least one quality parameter comprises: at least one of texture parameters, sensory parameters, physicochemical parameters and microbial parameters; and determining the quality of the uncooked food product according to the quality parameters.

In some embodiments, determining at least one quality parameter of the uncooked food product comprises: under the condition that the quality parameters are texture parameters or sensory parameters or physical and chemical parameters, determining the change rate of the quality parameters according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment; determining the quality parameters of the uncooked food product according to the change rate of the quality parameters and the logistics time.

In some embodiments, determining the rate of change of the quality parameter as a function of the volume fraction of the fresh keeping gas and the temperature of the logistics environment comprises: under the condition that the quality parameters are texture parameters, determining the activation energy of the texture parameters according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters; determining a pre-factor of the texture parameter according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter; and inputting the activation energy of the texture parameters, namely the pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the texture parameters.

In some embodiments, determining the rate of change of the quality parameter as a function of the volume fraction of the fresh keeping gas and the temperature of the logistics environment comprises: determining sensory parameter activation energy according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy, which are trained in advance, under the condition that the quality parameters are sensory parameters; determining a sensory parameter pre-index factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the sensory parameter pre-index factor; and (3) inputting sensory parameter activation energy, wherein the sensory parameter refers to a pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the sensory parameter.

In some embodiments, determining the rate of change of the quality parameter as a function of the volume fraction of the fresh keeping gas and the temperature of the logistics environment comprises: under the condition that the quality parameters are physical and chemical parameters, determining physical and chemical parameter activation energy according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas and the physical and chemical parameter activation energy trained in advance; determining a physicochemical parameter pre-factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas trained in advance and the physicochemical parameter pre-factor; and inputting the physical and chemical parameter activation energy, wherein the physical and chemical parameter refers to a front factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the physical and chemical parameter.

In some embodiments, determining at least one quality parameter of the uncooked food product comprises: under the condition that the quality parameters are microbial parameters, determining the growth rate, growth retardation time and growth inhibition factors of the microbes according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment; determining the microbial parameters of the uncooked food product based on the growth rate of the microbes, the growth retardation time, the growth inhibitory factor and the logistics time.

In some embodiments, the growth rate of the microorganisms is determined based on the volume fraction of the preservative gas and the temperature of the logistics environment, and the growth retardation time and the growth inhibition factor comprise: determining a first regression coefficient according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient; determining a first theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the first theoretical temperature at which no microorganism survives; determining the growth rate of the microorganisms according to the temperature of the logistics environment, the first regression coefficient and the first theoretical temperature; determining a second regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second regression coefficient; determining a second theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second theoretical temperature at which no microorganism survives; determining the growth lag time of the microbial parameters according to the temperature of the logistics environment, the second regression coefficient and the second theoretical temperature; determining a third regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third regression coefficient; determining a third theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third theoretical temperature at which no microorganism survives; and determining the growth inhibition factor of the microbial parameter according to the temperature of the logistics environment, the third regression coefficient and the third theoretical temperature.

In some embodiments, the growth rate of the microorganism is determined using the following formula:

wherein r is_sRepresents the growth rate of the microorganism, b₁Representing a first regression coefficient, T represents the temperature of the logistics environment, T'₁Representing the first theoretical temperature; alternatively, the growth lag time of the microorganism is determined using the following formula:

wherein θ represents a growth retardation time of the microorganism, b₂Represents a second regression coefficient, T represents the temperature of the logistics environment, T'₂Representing the second theoretical temperature; alternatively, the growth inhibitory factor of the microorganism is determined using the following formula:

wherein k is_sRepresents a growth inhibitory factor of said microorganism, b₃Represents a third regression coefficient, T represents the temperature of the logistics environment, T'₃Represents the third theoretical temperature.

In some embodiments, the following formula is used to determine the microbial parameters of the uncooked food product:

wherein N represents the number of microorganisms, r represents the growth rate of the microorganisms, and θ represents the time when the growth of the microorganisms is retardedM, k_sRepresents a growth inhibitory factor of a microorganism.

In some embodiments, determining the quality of the uncooked food product from the quality parameter comprises: weighting various quality parameters to obtain comprehensive quality parameters; and determining the quality of the uncooked food product according to the comprehensive quality parameters.

In some embodiments, further comprising: collecting at least one quality parameter of a plurality of time points from an initial state to a critical state of inedibility of a raw food product under the conditions of different temperatures and different volume fractions of fresh-keeping gas in a logistics environment as training data; the quality perception model is trained using the training data.

In some embodiments, training the quality perception model using the training data comprises: under the condition that the quality parameters are texture parameters, determining the relation between the texture parameters and the logistics time according to the texture parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of a logistics environment; wherein the parameter to be determined in the relation between the texture parameter and the logistics time is the change rate of the texture parameter corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the texture parameters according to the change rate of the texture parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the texture parameters are the texture parameter activation energy and the texture parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters according to the activation energy of the texture parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter according to the pre-factor of the texture parameter corresponding to each volume fraction.

In some embodiments, training the quality perception model using the training data comprises: under the condition that the quality parameters are sensory parameters, determining the relationship between the sensory parameters and the logistics time according to the sensory parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of a logistics environment; wherein the parameter to be determined in the relationship between the sensory parameter and the logistics time is the change rate of the sensory parameter corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the sensory parameters according to the change rate of the sensory parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the sensory parameters are the sensory parameter activation energy and the sensory parameter pre-index factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy according to the sensory parameter activation energy corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter pre-index factor according to the sensory parameter pre-index factors corresponding to various volume fractions.

In some embodiments, training the quality perception model using the training data comprises: under the condition that the quality parameters are physical and chemical parameters, determining the relationship between the physical and chemical parameters and the logistics time according to the physical and chemical parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of a logistics environment; wherein, the parameter to be determined in the relationship between the physical and chemical parameters and the logistics time is the change rate of the physical and chemical parameters corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters according to the change rate of the physical and chemical parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters are physical and chemical parameter activation energy and physical and chemical parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters according to the activation energy of the physicochemical parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-index factors of the physicochemical parameters according to the pre-index factors of the physicochemical parameters corresponding to various volume fractions.

In some embodiments, training the quality perception model using the training data comprises: under the condition that the quality parameters are microbial parameters, determining the relationship between microbial parameters and logistics time according to the microbial parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of a logistics environment, wherein the parameters to be determined in the relationship between the microbial parameters and the logistics time are the growth rate, growth delay time and growth inhibition factors of the microbes corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the growth rate of microorganisms according to the growth rates of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth rate of the microorganisms is a first regression coefficient corresponding to the volume fraction and a first theoretical temperature at which no microorganisms survive; determining the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient according to the first regression coefficient corresponding to each volume fraction; determining the relation between the volume fraction of the fresh-keeping gas and the first theoretical temperature according to the first theoretical temperature corresponding to various volume fractions; determining the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms according to the growth delay time of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the coefficients to be determined in the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms are a second regression coefficient corresponding to the volume fraction and a second theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient according to the second regression coefficient corresponding to each volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the second theoretical temperature according to the second theoretical temperature corresponding to various volume fractions; aiming at the volume fraction of a fresh-keeping gas, determining the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism according to the growth inhibition factors of the microorganism corresponding to various temperatures; wherein, the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism is a third regression coefficient corresponding to the volume fraction and a third theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient according to the third regression coefficient corresponding to each volume fraction; and determining the relationship between the volume fraction of the fresh-keeping gas and the third theoretical temperature according to the third theoretical temperature corresponding to various volume fractions.

In some embodiments, further comprising: in response to a query request sent by the user, returning to the user at least one of a quality parameter of the uncooked food product, a volume fraction of a fresh-keeping gas in the logistics environment, a temperature of the logistics environment, and a remaining shelf life of the uncooked food product.

According to further embodiments of the present disclosure, there is provided a method of determining a quality of a raw food, including: the acquisition module is used for acquiring the volume fraction of the fresh-keeping gas in the logistics environment of the uncooked food product, the temperature of the logistics environment and the logistics time; the quality parameter determining module is used for determining at least one quality parameter of the uncooked food product according to the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time, and the at least one quality parameter comprises: at least one of texture parameters, sensory parameters, physicochemical parameters and microbial parameters; determining the quality of the uncooked food product according to the quality parameters; and the quality determining module is used for determining the quality of the uncooked food product according to the quality parameters.

In some embodiments, the quality parameter determination module is configured to determine a change rate of the quality parameter according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, in case the quality parameter is a texture parameter or an organoleptic parameter or a physicochemical parameter; determining the quality parameters of the uncooked food product according to the change rate of the quality parameters and the logistics time.

In some embodiments, the quality parameter determination module is configured to determine the texture parameter activation energy according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the texture parameter activation energy, in case that the quality parameter is a texture parameter; determining a pre-factor of the texture parameter according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter; and inputting the activation energy of the texture parameters, namely the pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the texture parameters.

In some embodiments, the quality parameter determination module is configured to determine the sensory parameter activation energy according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy, in case that the quality parameter is the sensory parameter; determining a sensory parameter pre-index factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the sensory parameter pre-index factor; and (3) inputting sensory parameter activation energy, wherein the sensory parameter refers to a pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the sensory parameter.

In some embodiments, the quality parameter determination module is configured to determine the physicochemical parameter activation energy according to the volume fraction of the fresh-keeping gas and a relationship between the volume fraction of the fresh-keeping gas and the physicochemical parameter activation energy, which is trained in advance, when the quality parameter is the physicochemical parameter; determining a physicochemical parameter pre-factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas trained in advance and the physicochemical parameter pre-factor; and inputting the physical and chemical parameter activation energy, wherein the physical and chemical parameter refers to a front factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the physical and chemical parameter.

In some embodiments, the quality parameter determination module is configured to determine a growth rate, a growth retardation time, and a growth inhibition factor of the microorganisms according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, in case the quality parameter is a microorganism parameter; determining the microbial parameters of the uncooked food product based on the growth rate of the microbes, the growth retardation time, the growth inhibitory factor and the logistics time.

In some embodiments, the quality parameter determination module is configured to determine a first regression coefficient based on the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient; determining a first theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the first theoretical temperature at which no microorganism survives; determining the growth rate of the microorganisms according to the temperature of the logistics environment, the first regression coefficient and the first theoretical temperature; determining a second regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second regression coefficient; determining a second theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second theoretical temperature at which no microorganism survives; determining the growth lag time of the microbial parameters according to the temperature of the logistics environment, the second regression coefficient and the second theoretical temperature; determining a third regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third regression coefficient; determining a third theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third theoretical temperature at which no microorganism survives; and determining the growth inhibition factor of the microbial parameter according to the temperature of the logistics environment, the third regression coefficient and the third theoretical temperature.

wherein k is_sRepresents a growth inhibitory factor of said microorganism, b₃Represents a third regression coefficient, T represents the temperature of the logistics environment, T'₃Represents the third theoretical temperatureAnd (4) degree.

wherein N represents the number of microorganisms, r represents the growth rate of the microorganisms, θ represents the growth lag time of the microorganisms, and k_sRepresents a growth inhibitory factor of a microorganism.

In some embodiments, the quality determination module is configured to weight the various quality parameters to obtain a composite quality parameter; and determining the quality of the uncooked food product according to the comprehensive quality parameters.

In some embodiments, further comprising: the training module is used for acquiring at least one quality parameter of a plurality of time points from an initial state to a critical state incapable of being eaten of the uncooked food product under the conditions of different temperatures and different volume fractions of fresh-keeping gas in a logistics environment as training data; the quality perception model is trained using the training data.

In some embodiments, the training module is configured to determine, for a volume fraction of a fresh-keeping gas and a temperature of a logistics environment, a relationship between the texture parameter and the logistics time according to the texture parameter at different time points, if the quality parameter is the texture parameter; wherein the parameter to be determined in the relation between the texture parameter and the logistics time is the change rate of the texture parameter corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the texture parameters according to the change rate of the texture parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the texture parameters are the texture parameter activation energy and the texture parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters according to the activation energy of the texture parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter according to the pre-factor of the texture parameter corresponding to each volume fraction.

In some embodiments, the training module is configured to determine, for a volume fraction of a fresh-keeping gas and a temperature of a logistics environment, a relationship between the sensory parameters and the logistics time based on the sensory parameters at different time points, if the quality parameters are the sensory parameters; wherein the parameter to be determined in the relationship between the sensory parameter and the logistics time is the change rate of the sensory parameter corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the sensory parameters according to the change rate of the sensory parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the sensory parameters are the sensory parameter activation energy and the sensory parameter pre-index factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy according to the sensory parameter activation energy corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter pre-index factor according to the sensory parameter pre-index factors corresponding to various volume fractions.

In some embodiments, the training module is configured to determine, for a volume fraction of a fresh-keeping gas and a temperature of a logistics environment, a relationship between the physicochemical parameter and the logistics time according to the physicochemical parameters at different time points, when the quality parameter is the physicochemical parameter; wherein, the parameter to be determined in the relationship between the physical and chemical parameters and the logistics time is the change rate of the physical and chemical parameters corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters according to the change rate of the physical and chemical parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters are physical and chemical parameter activation energy and physical and chemical parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters according to the activation energy of the physicochemical parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-index factors of the physicochemical parameters according to the pre-index factors of the physicochemical parameters corresponding to various volume fractions.

In some embodiments, the training module is configured to determine, for a volume fraction of a fresh-keeping gas and a temperature of a logistics environment, a relationship between a microbial parameter and logistics time according to the microbial parameter at different time points, where the parameters to be determined in the relationship between the microbial parameter and logistics time are a growth rate, a growth retardation time, and a growth inhibition factor of a microorganism corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the growth rate of microorganisms according to the growth rates of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth rate of the microorganisms is a first regression coefficient corresponding to the volume fraction and a first theoretical temperature at which no microorganisms survive; determining the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient according to the first regression coefficient corresponding to each volume fraction; determining the relation between the volume fraction of the fresh-keeping gas and the first theoretical temperature according to the first theoretical temperature corresponding to various volume fractions; determining the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms according to the growth delay time of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the coefficients to be determined in the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms are a second regression coefficient corresponding to the volume fraction and a second theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient according to the second regression coefficient corresponding to each volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the second theoretical temperature according to the second theoretical temperature corresponding to various volume fractions; aiming at the volume fraction of a fresh-keeping gas, determining the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism according to the growth inhibition factors of the microorganism corresponding to various temperatures; wherein, the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism is a third regression coefficient corresponding to the volume fraction and a third theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient according to the third regression coefficient corresponding to each volume fraction; and determining the relationship between the volume fraction of the fresh-keeping gas and the third theoretical temperature according to the third theoretical temperature corresponding to various volume fractions.

In some embodiments, further comprising: and the query module is used for responding to a query request sent by the user and returning at least one of the quality parameter of the uncooked food product, the volume fraction of the fresh-keeping gas in the logistics environment, the temperature of the logistics environment and the remaining shelf life of the uncooked food product to the user.

According to still further embodiments of the present disclosure, there is provided a method for determining a quality of a raw food, including: a processor; and a memory coupled to the processor for storing instructions that, when executed by the processor, cause the processor to perform a method of determining uncooked food quality as in any of the preceding embodiments.

According to still further embodiments of the disclosure, there is provided a non-transitory computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the steps of any of the foregoing embodiment methods.

According to still further embodiments of the present disclosure, there is provided a system for determining a quality of a raw food, including: the uncooked food quality determining apparatus of any of the foregoing embodiments; the gas sensor is used for collecting the volume fraction of the fresh-keeping gas in the logistics environment of the uncooked food product and sending the volume fraction to the uncooked food quality determining device; the temperature sensor is used for acquiring the temperature of the logistics environment and sending the temperature to the uncooked food quality determining device; and the timer is used for acquiring the logistics time and sending the logistics time to the determining device for the uncooked food quality.

In some embodiments, further comprising: the receiver is used for receiving a query request sent by a user; a transmitter for returning to the user at least one of a quality parameter of the uncooked food product, a volume fraction of the fresh-keeping gas in the logistics environment, a temperature of the logistics environment, and a remaining shelf life of the uncooked food product.

In the method, a quality perception model is trained in advance, the volume fraction of fresh-keeping gas in a logistics environment where uncooked food products are located can be obtained in real time in a cold-chain logistics process, the temperature and the logistics time of the logistics environment are obtained, at least one quality parameter of the uncooked food products is obtained by using the quality perception model according to the obtained information, and the quality of the uncooked food products is determined according to the quality parameter. The influence of the temperature, the logistics time and the fresh-keeping gas stress of the logistics environment on the quality of the uncooked food products is considered at the same time, and the quality perception model is quantitatively analyzed and trained on the temperature, the logistics time and the volume fraction of the fresh-keeping gas of the logistics environment, so that the quality of the uncooked food products can be accurately determined in real time by utilizing the pre-trained quality perception model subsequently, and the accuracy of determining the quality of the uncooked food products is improved.

Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.

Fig. 1 illustrates a flow diagram of a method of determining a raw food quality of some embodiments of the present disclosure.

Fig. 2 shows a flow diagram of a method of determining uncooked food quality according to further embodiments of the disclosure.

Fig. 3 shows a schematic configuration diagram of a raw food quality determination apparatus according to some embodiments of the present disclosure.

Fig. 4 shows a schematic configuration diagram of a device for determining uncooked food quality according to other embodiments of the present disclosure.

Fig. 5 shows a schematic structural diagram of a device for determining the quality of uncooked food according to further embodiments of the present disclosure.

Fig. 6 shows a schematic configuration diagram of a raw food quality determination system of some embodiments of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

The present disclosure provides a method for determining the quality of a raw food, described below in conjunction with fig. 1.

Fig. 1 is a flow chart of some embodiments of the disclosed method for determining raw food quality. As shown in fig. 1, the method of this embodiment includes: steps S102 to S106.

In step S102, the volume fraction of the fresh-keeping gas in the logistics environment in which the uncooked food product is located, the temperature of the logistics environment, and the logistics time are obtained.

The logistics process of the uncooked food product comprises the following steps: the product quality can be monitored in all links such as harvesting (capturing), transportation, storage, processing and sale. Fresh-keeping gas, e.g. SO₂And the volume fraction represents the concentration of the freshness gas. The logistics time represents the time from the start of raw food product picking or capture to the present time. The volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time can be respectively obtained by arranging a gas sensor, a temperature sensor and a timer.

In step S104, the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time are input into a quality perception model trained in advance, and at least one quality parameter of the uncooked food product is determined.

The at least one quality parameter includes, for example: at least one of texture parameters, sensory parameters, physical and chemical parameters and microbial parameters. Texture parameters include, for example, at least one of hardness, crunchiness, elasticity, chewiness, firmness, toughness, fiber strength, tackiness, cohesiveness, yield point, ductility, recoverability, gel strength. Sensory parameters include, for example: at least one sensory characteristic of color, fragrance, taste, shape, etc. The physicochemical parameters include, for example: at least one of protein content, fat content, carbohydrate content, dietary fiber content, vitamin content, mineral content, pH. Microbial parameters include, for example: the number of microorganisms. The texture parameters, the sensory parameters, the physical and chemical parameters and the microbial parameters can also be selected from other parameters according to actual requirements, and are not limited to the examples. The texture parameters and the sensory parameters are expressed in a numerical form according to preset rules.

The quality perception model is obtained by training in advance according to training data and can represent the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the relationship between the logistics time and various quality parameters. The training process will be described in detail in the following embodiments.

In some embodiments, the quality perception model may include one or more modules, such as at least one of a texture quality determination module, a sensory quality determination module, a physicochemical quality determination module, and a microbiological quality determination module. Each module may in turn include one or more sub-modules, for example, the texture quality determination module may include: at least one of a hardness determination sub-module, a crispness determination sub-module, an elasticity determination sub-module, a chewiness determination sub-module, etc. (corresponding to the type of the aforementioned texture parameters), and similarly, each of the other modules may also include a sub-module corresponding to the parameters. After the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time are input into the pre-trained quality perception model, the input data can enter each submodule to be operated, and finally corresponding quality parameters are obtained.

In some embodiments, the operation processes of the various texture parameters, sensory parameters and physicochemical parameters in the respective sub-modules are similar, i.e. the structures of the respective sub-modules are similar. For example, in the case that the quality parameter is a texture parameter, an organoleptic parameter or a physicochemical parameter, the rate of change of the quality parameter is determined according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment; determining the quality parameters of the uncooked food product according to the change rate of the quality parameters and the logistics time. For example, the change rate of the texture parameters is determined according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, the texture parameters of the uncooked food product are determined according to the change rate of the texture parameters and the logistics time, and the sensory parameters and the physicochemical parameters of the uncooked food product can be determined in the same way.

Further, for example, in the case where the quality parameter is a texture parameter, the texture parameter activation energy is determined based on the volume fraction of the fresh-keeping gas and a relationship between the volume fraction of the fresh-keeping gas and the texture parameter activation energy trained in advance; determining a pre-factor of the texture parameter according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter; and inputting the activation energy of the texture parameters, namely the pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the texture parameters. For various texture parameters, such as hardness, crispness, elasticity, chewiness, etc., the corresponding rate of change may be determined according to the methods described above. The relationship between the volume fraction of the fresh-keeping gas corresponding to different texture parameters and the activation energy of the texture parameters, the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters and the coefficients in the Arrhenius formula can be different.

For another example, in the case that the quality parameter is a sensory parameter, determining the activation energy of the sensory parameter according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the sensory parameter, which is trained in advance; determining a sensory parameter pre-index factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the sensory parameter pre-index factor; and (3) inputting sensory parameter activation energy, wherein the sensory parameter refers to a pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the sensory parameter. The respective rates of change can be determined according to the above-described method for various sensory parameters, such as color, aroma, taste, shape, etc. The relationship between the volume fraction of the fresh-keeping gas corresponding to different sensory parameters and the activation energy of the sensory parameters, the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the sensory parameters and the coefficients in the arrhenius formula can be different.

For another example, in the case that the quality parameter is a physicochemical parameter, the physicochemical parameter activation energy is determined according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas and the physicochemical parameter activation energy trained in advance; determining a physicochemical parameter pre-factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas trained in advance and the physicochemical parameter pre-factor; and inputting the physical and chemical parameter activation energy, wherein the physical and chemical parameter refers to a front factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the physical and chemical parameter. The corresponding rate of change can be determined according to the above method for various physicochemical parameters, such as protein content, fat content, carbohydrate content, etc. The relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters corresponding to different physicochemical parameters, the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters and the coefficients in the arrhenius equation can be different.

The Arrhenius equation (Arrhenius), which is a relationship between the temperature of the logistics environment and the change rate of the quality parameter, can be expressed by the following equation.

k＝A*exp(-E/RT) (1)

In the formula (1), k represents the change rate of the quality parameter, a represents a pre-factor, E represents the activation energy of the quality parameter, R is the molar gas constant, and T is the temperature of the stream environment. For example, the quality parameter is a certain texture parameter, k represents a change rate of the texture parameter, a represents a pre-index factor corresponding to the texture parameter, and E represents an activation energy corresponding to the texture parameter. For different quality parameters, k, a and E have different meanings, and the values of a and E may also be different. The relationship (or equation) between the volume fraction G of the fresh-keeping gas and A can be obtained by training, and the value of G is substituted into the relationship to obtain A. The relationship of G and a may be different for different quality parameters. The relationship (or equation) between the volume fraction G of the fresh-keeping gas and E can be obtained by training, and the value of G is substituted into the relationship to obtain E. The relationship of G and E may be different for different quality parameters. After obtaining the values of A and E, substituting the values of A and E and the temperature T of the material flow environment into the formula (1) to obtain k.

Further, determining the quality parameter q of the uncooked food product according to k and the logistics time t. For example, the relationship between the quality parameter change rate k, the material flow time t, and the quality parameter q is obtained by training in advance, and the quality parameter q can be obtained by substituting the values of k and t into the relationship. For example, the quality parameter q is inversely related to the product of the rate of change of the quality parameter k and the time of stream t. For example, the relationship between the rate of change k of the quality parameter, the flow time t, and the quality parameter q can be expressed by the following formula (2) or (3).

q＝q₀-k*t (2)

q＝q₀*exp(-k*t) (3)

Q in formulae (2) and (3)₀Is the initial value of the quality parameter. For different quality parameters, q₀And k may be different. The formula (2) or (3) can be determined and selected according to the fitting degree of the historical data to the formula (2) and the formula (3) in the training process, and the following embodiments will be described in detail.

In some embodiments, the determination of the microbial parameters is different from the determination of the texture parameters, sensory parameters, and physicochemical parameters described above. Under the condition that the quality parameters are microbial parameters, determining the growth rate, growth retardation time and growth inhibition factors of the microbes according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment; determining the microbial parameters of the uncooked food product based on the growth rate of the microbes, the growth retardation time, the growth inhibitory factor and the logistics time.

Further, the growth rate of the microorganism can be determined using the following method: determining a first regression coefficient according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient; determining a first theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the first theoretical temperature at which no microorganism survives; and determining the growth rate of the microorganisms according to the temperature of the logistics environment, the first regression coefficient and the first theoretical temperature.

Volume fraction G and first regression coefficient b of fresh-keeping gas₁Can be trained, and substituting the value of G into the relationship can yield b₁. For different quality parameters, G and b₁The relationship of (c) may be different. Volume fraction G of fresh-keeping gas and first theoretical temperature T'₁Can be obtained by training the relation (or equation) of (A), and the value of G is substituted into the relation to obtain T'₁. For different quality parameters, G and T'₁The relationship of (c) may be different. To obtain b₁And T'₁After the value of (b), b₁And T'₁Substituting the value of (3) and the temperature T of the logistics environment into the relationship among the temperature of the logistics environment, the first regression coefficient, the first theoretical temperature and the growth rate of the microorganisms to obtain the growth rate r of the microorganisms.

The relationship among the temperature of the logistics environment, the first regression coefficient, the first theoretical temperature and the growth rate of the microorganisms is obtained through pre-training. For example, the growth rate r of the microorganisms is related to the temperature T of the stream environment and the first theoretical temperature T'₁The difference of (a) is positively correlated. E.g. temperature T of the logistic environment, first regression coefficient b₁A first theoretical temperature T'₁And the growth rate r of the microorganism can be expressed by the following equation.

Further, the growth retardation time of the microorganism can be determined by the following method: determining a second regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second regression coefficient; determining a second theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second theoretical temperature at which no microorganism survives; and determining the growth lag time of the microbial parameters according to the temperature of the logistics environment, the second regression coefficient and the second theoretical temperature.

Volume fraction G and second regression coefficient b of fresh-keeping gas₂Can be trained, and substituting the value of G into the relationship can yield b₂. For different quality parameters, G and b₂The relationship of (c) may be different. Volume fraction G of fresh-keeping gas and second theoretical temperature T'₂Can be obtained by training the relation (or equation) of (A), and the value of G is substituted into the relation to obtain T'₂. For different quality parameters, G and T'₂The relationship of (c) may be different. To obtain b₂And T'₂After the value of (b), b₂And T'₂Substituting the value of (3) and the temperature T of the logistics environment into the relationship among the temperature of the logistics environment, the second regression coefficient, the second theoretical temperature and the growth delay time of the microorganisms to obtain the growth delay time theta of the microorganisms.

The relationship among the temperature of the logistics environment, the second regression coefficient, the second theoretical temperature and the growth delay time of the microorganisms is obtained through pre-training. For example, the growth retardation time theta of the microorganisms is related to the temperature T of the logistics environment and the second theoretical temperature T'₂The difference of (a) is inversely related. E.g. temperature T of the environment of the stream, second regression coefficient b₂And a second theoretical temperature T'₂And the growth delay time θ of the microorganism can be expressed by the following equation.

Further, the growth inhibitory factor of the microorganism can be determined by the following method: determining a third regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third regression coefficient; determining a third theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third theoretical temperature at which no microorganism survives; and determining the growth inhibition factor of the microbial parameter according to the temperature of the logistics environment, the third regression coefficient and the third theoretical temperature.

Volume fraction G and third regression coefficient b of fresh-keeping gas₃Can be trained, and substituting the value of G into the relationship can yield b₃. For different quality parameters, G and b₃The relationship of (c) may be different. Volume fraction G of fresh-keeping gas and third theoretical temperature T'₃Can be trained to obtainT 'can be obtained by substituting the value of G into the relationship'₃. For different quality parameters, G and T'₃The relationship of (c) may be different. To obtain b₃And T'₃After the value of (b), b₃And T'₃Substituting the value of (a) and the temperature T of the logistics environment into the relationship among the temperature of the logistics environment, the third regression coefficient, the third theoretical temperature and the growth inhibition factor of the microorganism to obtain the growth inhibition factor k of the microorganism_s。

The relationship among the temperature of the logistics environment, the third regression coefficient, the third theoretical temperature and the growth inhibition factor of the microorganisms is obtained through pre-training. For example, growth inhibitory factor k of microorganisms_sTemperature T from the environment of the stream and a third theoretical temperature T'₃The difference of (a) is inversely related. E.g. temperature T of the environment of the stream, third regression coefficient b₃And a third theoretical temperature T'₃And growth inhibitory factor k of microorganisms_sThe relationship of (c) can be expressed by the following formula.

The growth rate r, growth retardation time theta and growth inhibition factor k of the microorganism were obtained according to the above examples_sFurther, according to the growth rate r, growth retardation time theta, growth inhibitory factor k of the microorganism_sThe relationship between the logistics time t and the microbial parameters of the uncooked food products, namely the microbial growth-inhibition equation under the gas stress, and the microbial parameters can be obtained.

For example, the growth-inhibition equation of microorganisms under gas stress can be expressed by the following equation.

In step S106, the quality of the uncooked food product is determined according to the quality parameter.

Based on the above embodiments, the texture parameters, sensory parameters, physicochemical parameters, and microbial parameters of the microorganisms can be obtained. In some embodiments, the various quality parameters are weighted to obtain a composite quality parameter; and determining the quality of the uncooked food product according to the comprehensive quality parameters. For example, the overall quality parameter can be obtained according to the following formula.

Q＝α₁*q₁+α₂*q₂+α₃*q₃+α₄*q₄ (8)

Wherein q is₁，q₂，q₃，q₄Respectively representing texture parameters, sensory parameters, physicochemical parameters and microbial parameters. Alpha is alpha₁，α₂，α₃，α₄Each represents q₁，q₂，q₃，q₄The weight of (c). There may be more than q₁A plurality of q₂A plurality of q₃A plurality of q₄The weights may be multiplied and added together.

In some embodiments, uncooked food products include, for example: at least one of fruits, vegetables and aquatic products. In case the uncooked food product is fruit, α may be set₂>α₃>>α₁>α₄That is, for fruits, the weight of sensory parameters and physicochemical parameters is higher, and the weight of texture parameters and microbial parameters is lower. In case the uncooked food product is a vegetable, α may be set₂>α₃>>α₁>α₄That is, for vegetables, the weight of sensory parameters and physicochemical parameters is larger, and the weight of microbial parameters and texture parameters is smaller. In case the uncooked food product is a microbial parameter, α may be set₂>α₄>>α₃>α₁Namely, the weight of the sensory parameters and the microbial parameters of the aquatic products is larger, and the weight of the physicochemical parameters and the sensory parameters is smaller. The weights of the different quality parameters can be set according to the actual situation, and are not limited to the illustrated examples.

Different quality grades can be preset corresponding to different comprehensive quality parameter ranges, and the comprehensive quality parameter range where the comprehensive quality parameters are located is determined, so that the quality grade is determined.

In the above embodiment, the quality perception model is trained in advance, the volume fraction of the fresh-keeping gas in the logistics environment where the uncooked food product is located, the temperature of the logistics environment and the logistics time can be obtained in real time in the cold-chain logistics process, at least one quality parameter of the uncooked food product is obtained by using the quality perception model according to the obtained information, and the quality of the uncooked food product is determined according to the quality parameter. In the embodiment, the influence of the temperature of the logistics environment, the logistics time and the fresh-keeping gas stress on the quality of the uncooked food products is considered at the same time, and the quality perception model is quantitatively analyzed and trained on the temperature of the logistics environment, the logistics time and the volume fraction of the fresh-keeping gas, so that the quality of the uncooked food products can be accurately determined in real time by using the pre-trained quality perception model in the follow-up process, and the accuracy of determining the quality of the uncooked food products is improved.

The training process of the quality perception model in the present disclosure is described below in conjunction with fig. 2.

FIG. 2 is a flow chart of an alternate embodiment of the disclosed method for determining the quality of uncooked food. As shown in fig. 2, the method of this embodiment includes: steps S202 to S204.

In step S202, at least one quality parameter of the uncooked food product at a plurality of time points from an initial state to a critical state of inedibility is collected as training data under different temperatures and different volume fractions of the fresh-keeping gas in the logistics environment.

For example, a first preset number of temperature values that can cover a range of the temperature of the logistics environment and a second preset number of volume fraction values that can cover a range of the volume fraction of the freshness gas in the logistics environment may be set. The first preset number and the second preset number can be the same or different, and the trained quality perception model is more accurate under the same condition. For example, 6 temperature values T may be set₁、T₂、T₃、T₄、T₅、T₆6 volume fraction values G of fresh-keeping gas₁、G₂、G₃、G₄、G₅、G₆. Further collecting different temperature values and volume fraction values, and measuring a plurality of times from the initial state to the critical state of inedibilityQuality parameters of the intermediate points. For example, the temperature value T is collected₁Value of volume fraction G₁Under the condition, texture parameters, sensory parameters, physical and chemical parameters and microbial parameters of the uncooked food product at a plurality of time points from an initial state to a critical state incapable of being eaten can be obtained by analogy, at least one of the texture parameters, the sensory parameters, the physical and chemical parameters and the microbial parameters at different temperatures and volume fractions can be obtained, and which quality parameter needs to be determined in the subsequent application process, the corresponding quality parameter is used as training data for training in the training process.

In step S204, the quality perception model is trained using the training data.

In the case of quality parameters being texture parameters or sensory parameters or physicochemical parameters, the training process may be similar, as follows.

In some embodiments, in the case of quality parameters being texture parameters or sensory parameters or physicochemical parameters, the relationship between the quality parameters and the logistics time is determined for the volume fraction of a freshness gas and the temperature of a logistics environment from the quality parameters at different points in time; wherein the parameter to be determined in the relationship between the quality parameter and the material flow time is the change rate of the quality parameter corresponding to the volume fraction and the temperature. And determining the relationship between the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the change rate of the quality parameters according to the volume fractions and the change rates of the quality parameters corresponding to the temperatures.

For example, volume fraction G for a freshness-retaining gas₁Temperature T of a logistic environment₁The training subset is G₁And T₁A quality parameter, e.g., hardness, corresponding to different times. Fitting the equations expressed by the formulas (2) and (3) by using a training subset to respectively obtain the change rate of the parameter k expressing the hardness, and obtaining the fitting degree corresponding to the formula (2) and the fitting degree corresponding to the formula (3), and selecting the equation with high fitting degree as the equation expressing the relationship between the hardness and the logistics time. Volume fraction G can be obtained by a similar method₁In the case of (2), various temperatures T₁、T₂、T₃、T₄、T₅、T₆Corresponding relation between hardness and logistics time, namely obtaining volume fraction G₁In the case of (2), a plurality of hardness change rates k₁、k₂、k₃、k₄、k₅、k₆. A similar method can be used to obtain a volume fraction G₁In the case of (1), the relationship between various texture parameters, sensory parameters, or physicochemical parameters and the physical distribution time at various temperatures.

Further, determining the volume fraction of the freshness gas, the relationship between the temperature of the logistics environment and the rate of change of the quality parameter, for example, comprises: under the condition that the quality parameters are texture parameters, determining the relationship between the temperature of the logistics environment and the change rate of the texture parameters according to the change rate of the texture parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the texture parameters are the texture parameter activation energy and the texture parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters according to the activation energy of the texture parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter according to the pre-factor of the texture parameter corresponding to each volume fraction.

For example, the volume fraction of gas is G₁In the case of (2), various temperatures T₁、T₂、T₃、T₄、T₅、T₆Corresponding to a hardness change rate of k₁、k₂、k₃、k₄、k₅、k₆Fitting formula (1), namely an Arrhenius formula, by using the temperature and the change rate values to obtain a pre-exponential factor A of hardness₁And activation energy E₁Thereby determining the volume fraction as G₁In the case of (3), the rate of change of hardness and temperature. The pre-exponential factor and activation energy of hardness can be determined for various volume fractions using similar methods. For example, determine A₂、A₃、A₄、A₃、A₆，E₂、E₃、E₄、E₃、E₆. By adopting a similar method, pre-exponential factors and activation energy corresponding to various volume fractions and various texture parameters can be determined.

Further, for example, the relationship between the volume fraction of the fresh-keeping gas and the pre-indication factor is fitted by using the pre-indication factors of hardness corresponding to various volume fractions, the degree of fitting is determined, various types of equations can be selected for fitting, and the equation with the degree of fitting higher than the threshold value is selected as the relationship between the volume fraction of the fresh-keeping gas corresponding to hardness and the pre-indication factor. The relationship between the preservative gas volume fraction and the activation energy corresponding to the hardness can be determined by adopting a similar method.

The similar method can determine the relationship between the volume fraction of the fresh-keeping gas corresponding to various texture parameters, physicochemical parameters or sensory parameters and the pre-index factor, and the relationship between the volume fraction of the fresh-keeping gas and the activation energy. For example, the volume fraction of a fresh-keeping gas is determined according to the change rate of the sensory parameters corresponding to various temperatures, and the relationship between the temperature of the logistics environment and the change rate of the sensory parameters is determined; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the sensory parameters are the sensory parameter activation energy and the sensory parameter pre-index factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy according to the sensory parameter activation energy corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter pre-index factor according to the sensory parameter pre-index factors corresponding to various volume fractions.

For another example, for the volume fraction of a fresh-keeping gas, the relationship between the temperature of the logistics environment and the change rate of the physicochemical parameters is determined according to the change rate of the physicochemical parameters corresponding to various temperatures; wherein, the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters are physical and chemical parameter activation energy and physical and chemical parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters according to the activation energy of the physicochemical parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-index factors of the physicochemical parameters according to the pre-index factors of the physicochemical parameters corresponding to various volume fractions.

In the case of the quality parameter being a microbial parameter, the training process is as follows.

In some embodiments, in the case that the quality parameter is a microbial parameter, determining a relationship between the microbial parameter and the logistics time according to the microbial parameter at different time points for the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, wherein the parameters to be determined in the relationship between the microbial parameter and the logistics time are the growth rate, the growth retardation time and the growth inhibition factor of the microbes corresponding to the volume fraction and the temperature; determining the relationship among the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the growth rate of the microorganisms according to the growth rates of the microorganisms at various volume fractions and various temperatures; determining the relationship among the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the growth delay time of the microorganisms according to the growth delay time of the microorganisms with various volume fractions and various temperatures; and determining the relationship between the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the growth inhibition factor of the microorganisms according to the growth inhibition factors of the microorganisms at various volume fractions and various temperatures.

For example, G at the volume fraction of the freshness-retaining gas₁At a temperature of T₁In case of training subset G₁And T₁Corresponding to the number of microorganisms at different times. Fitting the equation expressed by the formula (7) by using the training subset to obtain the parameters of the equation, namely the growth rate r, the growth retardation time theta and the growth inhibition factor k of the microorganism_s. Volume fraction G can be obtained by a similar method₁In the case of (2), various temperatures T₁、T₂、T₃、T₄、T₃、T₆The corresponding relation between the microbial quantity and the logistics time is obtained, namely the volume fraction G₁In the case of (2), a plurality of growth rates r₁、r₂、r₃、r₄、r₅、r₆Multiple growth lag time θ₁、θ₂、θ₃、θ₄、θ₅、θ₆Multiple growth ofInhibition factor k_s1、k_s2、k_s3、k_s4、k_s3、k_s6。

Further, determining the volume fraction of the freshness gas, the relationship between the temperature of the logistics environment and the growth rate of the microorganisms comprises: determining the relationship between the temperature of the logistics environment and the growth rate of microorganisms according to the growth rates of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth rate of the microorganisms is a first regression coefficient corresponding to the volume fraction and a first theoretical temperature at which no microorganisms survive; determining the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient according to the first regression coefficient corresponding to each volume fraction; and determining the relation between the volume fraction of the fresh-keeping gas and the first theoretical temperature according to the first theoretical temperature corresponding to various volume fractions.

For example, the volume fraction of gas is G₁In the case of (2), various temperatures T₁、T₂、T₃、T₄、T₅、T₆Corresponding microorganism growth rate r₁、r₂、r₃、r₄、r₅、r₆The values of these temperatures and growth rates can be used to fit equation (4) to obtain a first regression coefficient b₁A first theoretical temperature T'₁. The first regression coefficient and the first theoretical temperature, e.g. b, for various volume fractions can be determined in a similar way₁₁、b₁₂、b₁₃、b₁₄、b₁₃、b₁₆，T′₁₁、T′₁₂、T′₁₃、T′₁₄、T′₁₃、T′₁₆。

Further, for example, the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient is fitted by using the first regression coefficients corresponding to various volume fractions, the degree of fitting is determined, various types of equations can be selected for fitting, and the equation with the degree of fitting higher than the threshold value is selected as the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient. A similar method can be used to determine the preservative gas volume fraction versus the first theoretical temperature.

Further, determining the volume fraction of the fresh-keeping gas, the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms comprises: determining the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms according to the growth delay time of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the coefficients to be determined in the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms are a second regression coefficient corresponding to the volume fraction and a second theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient according to the second regression coefficient corresponding to each volume fraction; and determining the relationship between the volume fraction of the fresh-keeping gas and the second theoretical temperature according to the second theoretical temperature corresponding to various volume fractions.

For example, the volume fraction of gas is G₁In the case of (2), various temperatures T₁、T₂、T₃、T₄、T₃、T₆Corresponding growth retardation time theta₁、θ₂、θ₃、θ₄、θ₅、θ₆The values of these temperatures and growth lag times can be used to fit equation (5) to obtain a second regression coefficient b₂And a second theoretical temperature T'₂. The second regression coefficient and the second theoretical temperature, for example, b, for various volume fractions can be determined in a similar manner₂₁、b₂₂、b₂₃、b₂₄、b₂₅、b₂₆，T′₂₁、T′₂₂、T′₂₃、T′₂₄、T′₂₅、T′₂₆。

Further, for example, the relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient is fitted by using the second regression coefficient corresponding to each volume fraction, the degree of fitting is determined, various types of equations can be selected for fitting, and the equation with the degree of fitting higher than the threshold value is selected as the relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient. A similar method can be used to determine the preservative gas volume fraction versus the second theoretical temperature.

Further, determining the volume fraction of the fresh-keeping gas, the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganisms comprises: aiming at the volume fraction of a fresh-keeping gas, determining the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism according to the growth inhibition factors of the microorganism corresponding to various temperatures; wherein, the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism is a third regression coefficient corresponding to the volume fraction and a third theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient according to the third regression coefficient corresponding to each volume fraction; and determining the relationship between the volume fraction of the fresh-keeping gas and the third theoretical temperature according to the third theoretical temperature corresponding to various volume fractions.

For example, the volume fraction of gas is G₁In the case of (2), various temperatures T₁、T₂、T₃、T₄、T₅、T₆Corresponding growth inhibitory factor k_s1、k_s2、k_s3、k_s4、k_s5、k_s6The values of these temperature and growth inhibition factors can be used to fit equation (6) to obtain a third regression coefficient b₃And a third theoretical temperature T'₃. The third regression coefficient and the third theoretical temperature, e.g. b, for various volume fractions can be determined using similar methods₃₁、b₃₂、b₃₃、b₃₄、b₃₅、b₃₆，T′₃₁、T′₃₂、T′₃₃、T′₃₄、T′₃₅、T′₃₆。

Further, for example, the relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient is fitted by using the third regression coefficient corresponding to each volume fraction, and the degree of fitting is determined, and various types of equations may be selected for fitting, and an equation with the degree of fitting higher than a threshold value (for example, 0.85) is selected as the relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient. A similar method can be used to determine the preservative gas volume fraction versus the third theoretical temperature.

The fresh-keeping gas in the above embodiments may be different according to the actual application scenario, and may be carbon dioxide (CO) for example₂) Nitrogen (N)₂) Or a plurality of gases are mixed, and different fresh-keeping gases can be applied to the method of the embodiment. In the above embodiment, the training data includes data of 6 different volume fractions and data of 6 different temperatures, and in practical application, the number of values of the volume fractions and the number of values of the temperatures may be determined according to requirements, for example, the number of values of the volume fractions and the number of values of the temperatures are more than 4, and the accuracy of the model is high.

In some embodiments, a query request sent by a user may be received, and at least one of a quality parameter of the uncooked food product, a volume fraction of the fresh-keeping gas in the logistics environment, a temperature of the logistics environment, and a remaining shelf life of the uncooked food product may be returned to the user. For example, the logistics time length is determined according to the current volume fraction of the fresh gas, the temperature of the logistics environment and the lowest quality parameter (the lowest quality parameter indicates that the fresh gas cannot be eaten), and the remaining shelf life of the uncooked food product is obtained by subtracting the current logistics time from the logistics time length.

The present disclosure also provides a device for determining the quality of a raw food, as described below in conjunction with fig. 3.

Fig. 3 is a block diagram of some embodiments of the disclosed uncooked food quality determination apparatus. As shown in fig. 3, the apparatus 30 of this embodiment includes: an acquisition module 310, a quality parameter determination module 320, and a quality determination module 330.

The obtaining module 310 is configured to obtain a volume fraction of the fresh-keeping gas in the logistics environment where the raw food product is located, a temperature of the logistics environment, and a logistics time.

The quality parameter determination module 320 is configured to determine at least one quality parameter of the uncooked food product according to the volume fraction of the fresh-keeping gas, the temperature of the logistics environment, and the logistics time, where the at least one quality parameter includes: at least one of texture parameters, sensory parameters, physicochemical parameters and microbial parameters; and determining the quality of the uncooked food product according to the quality parameters.

In some embodiments, the quality parameter determining module 320 is configured to determine a change rate of the quality parameter according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment in the case that the quality parameter is a texture parameter or an organoleptic parameter or a physicochemical parameter; determining the quality parameters of the uncooked food product according to the change rate of the quality parameters and the logistics time.

In some embodiments, the quality parameter determination module 320 is configured to determine the texture parameter activation energy according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the texture parameter activation energy, if the quality parameter is the texture parameter; determining a pre-factor of the texture parameter according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter; and inputting the activation energy of the texture parameters, namely the pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the texture parameters.

In some embodiments, the quality parameter determining module 320 is configured to determine the sensory parameter activation energy according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy, in case that the quality parameter is the sensory parameter; determining a sensory parameter pre-index factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the sensory parameter pre-index factor; and (3) inputting sensory parameter activation energy, wherein the sensory parameter refers to a pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the sensory parameter.

In some embodiments, the quality parameter determining module 320 is configured to determine the physicochemical parameter activation energy according to the volume fraction of the fresh-keeping gas and a relationship between the volume fraction of the fresh-keeping gas and the physicochemical parameter activation energy, which is trained in advance, in the case that the quality parameter is the physicochemical parameter; determining a physicochemical parameter pre-factor according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas trained in advance and the physicochemical parameter pre-factor; and inputting the physical and chemical parameter activation energy, wherein the physical and chemical parameter refers to a front factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the physical and chemical parameter.

In some embodiments, the quality parameter determining module 320 is configured to determine the growth rate, the growth retardation time, and the growth inhibition factor of the microorganisms according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment in the case that the quality parameter is the microorganism parameter; determining the microbial parameters of the uncooked food product based on the growth rate of the microbes, the growth retardation time, the growth inhibitory factor and the logistics time.

In some embodiments, the quality parameter determination module 320 is configured to determine a first regression coefficient based on the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient; determining a first theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the first theoretical temperature at which no microorganism survives; determining the growth rate of the microorganisms according to the temperature of the logistics environment, the first regression coefficient and the first theoretical temperature; determining a second regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second regression coefficient; determining a second theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the second theoretical temperature at which no microorganism survives; determining the growth lag time of the microbial parameters according to the temperature of the logistics environment, the second regression coefficient and the second theoretical temperature; determining a third regression coefficient according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third regression coefficient; determining a third theoretical temperature according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the pre-trained fresh-keeping gas and the third theoretical temperature at which no microorganism survives; and determining the growth inhibition factor of the microbial parameter according to the temperature of the logistics environment, the third regression coefficient and the third theoretical temperature.

wherein k is_sRepresents a growth inhibitory factor of said microorganism, b₃Denotes the third regression coefficient, T denotes the temperature of the stream environment, T₃Represents the third theoretical temperature.

The quality determination module 330 is used to determine the quality of the uncooked food product based on the quality parameters.

In some embodiments, the quality determination module 330 is configured to weight the various quality parameters to obtain a composite quality parameter; and determining the quality of the uncooked food product according to the comprehensive quality parameters.

In some embodiments, the apparatus 30 further comprises: the training module 340 is used for acquiring at least one quality parameter of a plurality of time points from an initial state to a critical state which cannot be eaten of the uncooked food product under the conditions of different temperatures and different volume fractions of the fresh-keeping gas in the logistics environment as training data; the quality perception model is trained using the training data.

In some embodiments, the training module 340 is configured to determine a relationship between the texture parameter and the logistics time according to the texture parameter at different time points, for the volume fraction of the fresh-keeping gas and the temperature of the logistics environment when the quality parameter is the texture parameter; wherein the parameter to be determined in the relation between the texture parameter and the logistics time is the change rate of the texture parameter corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the texture parameters according to the change rate of the texture parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the texture parameters are the texture parameter activation energy and the texture parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters according to the activation energy of the texture parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter according to the pre-factor of the texture parameter corresponding to each volume fraction.

In some embodiments, the training module 340 is configured to determine, for the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, a relationship between the sensory parameter and the logistics time according to the sensory parameter at different time points, in case that the quality parameter is the sensory parameter; wherein the parameter to be determined in the relationship between the sensory parameter and the logistics time is the change rate of the sensory parameter corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the sensory parameters according to the change rate of the sensory parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the sensory parameters are the sensory parameter activation energy and the sensory parameter pre-index factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy according to the sensory parameter activation energy corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter pre-index factor according to the sensory parameter pre-index factors corresponding to various volume fractions.

In some embodiments, the training module 340 is configured to determine, according to the physicochemical parameters at different time points, a relationship between the physicochemical parameters and the logistics time, for the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, when the quality parameter is the physicochemical parameter; wherein, the parameter to be determined in the relationship between the physical and chemical parameters and the logistics time is the change rate of the physical and chemical parameters corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters according to the change rate of the physical and chemical parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters are physical and chemical parameter activation energy and physical and chemical parameter pre-factor corresponding to the volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters according to the activation energy of the physicochemical parameters corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-index factors of the physicochemical parameters according to the pre-index factors of the physicochemical parameters corresponding to various volume fractions.

In some embodiments, the training module 340 is configured to determine a relationship between a microbial parameter and a logistics time according to the microbial parameter at different time points for a volume fraction of a fresh-keeping gas and a temperature of a logistics environment when the quality parameter is the microbial parameter, where the parameters to be determined in the relationship between the microbial parameter and the logistics time are a growth rate, a growth retardation time, and a growth inhibition factor of a microorganism corresponding to the volume fraction and the temperature; determining the relationship between the temperature of the logistics environment and the growth rate of microorganisms according to the growth rates of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth rate of the microorganisms is a first regression coefficient corresponding to the volume fraction and a first theoretical temperature at which no microorganisms survive; determining the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient according to the first regression coefficient corresponding to each volume fraction; determining the relation between the volume fraction of the fresh-keeping gas and the first theoretical temperature according to the first theoretical temperature corresponding to various volume fractions; determining the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms according to the growth delay time of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the coefficients to be determined in the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms are a second regression coefficient corresponding to the volume fraction and a second theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient according to the second regression coefficient corresponding to each volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the second theoretical temperature according to the second theoretical temperature corresponding to various volume fractions; aiming at the volume fraction of a fresh-keeping gas, determining the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism according to the growth inhibition factors of the microorganism corresponding to various temperatures; wherein, the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism is a third regression coefficient corresponding to the volume fraction and a third theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient according to the third regression coefficient corresponding to each volume fraction; and determining the relationship between the volume fraction of the fresh-keeping gas and the third theoretical temperature according to the third theoretical temperature corresponding to various volume fractions.

In some embodiments, the apparatus 30 further comprises: and the query module 350 is used for responding to a query request sent by the user and returning at least one of the quality parameter of the uncooked food product, the volume fraction of the fresh-keeping gas in the logistics environment, the temperature of the logistics environment and the remaining shelf life of the uncooked food product to the user.

The determination means of the quality of the uncooked food in the embodiment of the present disclosure may each be implemented by various computing devices or computer systems, which are described below in conjunction with fig. 4 and 5.

Fig. 4 is a block diagram of some embodiments of the disclosed uncooked food quality determination apparatus. As shown in fig. 4, the apparatus 40 of this embodiment includes: a memory 410 and a processor 420 coupled to the memory 410, the processor 420 configured to perform a method of determining a quality of a raw food product in any of the embodiments of the present disclosure based on instructions stored in the memory 410.

Memory 410 may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), a database, and other programs.

Fig. 5 is a block diagram of another embodiment of the disclosed uncooked food quality determining apparatus. As shown in fig. 5, the apparatus 50 of this embodiment includes: memory 510 and processor 520 are similar to memory 410 and processor 420, respectively. An input output interface 530, a network interface 540, a storage interface 550, and the like may also be included. These

interfaces

530, 540, 550 and the connections between the memory 510 and the processor 520 may be, for example, via a bus 560. The input/output interface 530 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 540 provides a connection interface for various networking devices, such as a database server or a cloud storage server. The storage interface 550 provides a connection interface for external storage devices such as an SD card and a usb disk.

The present disclosure also provides a system for determining the quality of a raw food product, as described below in conjunction with fig. 6.

Fig. 6 is a block diagram of some embodiments of the disclosed uncooked food quality determination system. As shown in fig. 6, the system 6 of this embodiment includes: the uncooked food quality determination device 30/40/50 of any of the foregoing embodiments; and a gas sensor 62, a temperature sensor 64, a timer 66.

The gas sensor 62 is used for collecting the volume fraction of the fresh-keeping gas in the logistics environment of the uncooked food product and sending the volume fraction to the uncooked food quality determining device 30/40/50.

The temperature sensor 64 is used for collecting the temperature of the logistics environment and sending the temperature to the uncooked food quality determining device 30/40/50.

The timer 66 is used for collecting the logistics time and sending the logistics time to the uncooked food quality determining device 30/40/50.

In some embodiments, further comprising: a receiver 68 for receiving a query request sent by a user; a transmitter 70 for returning to the user at least one of a quality parameter of the uncooked food product, a volume fraction of the fresh-keeping gas in the logistics environment, a temperature of the logistics environment, and a remaining shelf life of the uncooked food product.

As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only exemplary of the present disclosure and is not intended to limit the present disclosure, so that any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims

1. A method for determining the quality of a raw food product, comprising:

acquiring the volume fraction of fresh-keeping gas in a logistics environment in which uncooked food products are located, and the temperature and the logistics time of the logistics environment;

inputting the volume fraction of the fresh-keeping gas, the temperature of the logistics environment and the logistics time into a pre-trained quality perception model, and determining the quality parameters of the uncooked food product, wherein the quality parameters comprise: texture parameters, at least one of sensory parameters and physicochemical parameters, and microbial parameters;

determining the quality of the uncooked food product according to the quality parameters;

wherein the determining quality parameters of the uncooked food product comprises:

under the condition that the quality parameters are microbial parameters, determining the growth rate, growth retardation time and growth inhibition factors of the microbes according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment;

determining microbial parameters of said uncooked food product based on growth rate of said microbes, growth retardation time, growth inhibitory factor and said logistics time;

wherein the determining the growth rate of the microorganisms according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment, and the growth retardation time and the growth inhibition factor comprise:

determining a first regression coefficient according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient;

determining a first theoretical temperature according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the first theoretical temperature at which no microorganisms survive;

determining the growth rate of the microorganisms according to the temperature of the logistics environment, the first regression coefficient and the first theoretical temperature;

determining a second regression coefficient according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the second regression coefficient;

determining a second theoretical temperature according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the second theoretical temperature at which no microorganisms survive;

determining the growth lag time of the microbial parameters according to the temperature of the logistics environment, the second regression coefficient and the second theoretical temperature;

determining a third regression coefficient according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the third regression coefficient;

determining a third theoretical temperature according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the third theoretical temperature at which no microorganisms survive;

determining a growth inhibition factor of the microbial parameter according to the temperature of the logistics environment, the third regression coefficient and the third theoretical temperature;

wherein the growth rate of the microorganism is determined using the following formula:

wherein r represents the growth rate of the microorganism, b₁Representing a first regression coefficient, T represents the temperature of the logistics environment, T'₁Representing the first theoretical temperature;

determining the growth retardation time of said microorganism using the following formula:

wherein θ represents a growth retardation time of the microorganism, b₂Represents a second regression coefficient, T represents the temperature of the logistics environment, T'₂Representing the second theoretical temperature;

determining a growth inhibitory factor of said microorganism using the following formula:

wherein k is_sRepresents a growth inhibitory factor of said microorganism, b₃Represents a third regression coefficient, T represents the temperature of the logistics environment, T'₃Representing the third theoretical temperature;

wherein the microbial parameters of the uncooked food product are determined using the following formula:

wherein N represents the number of microorganisms, r represents the growth rate of the microorganisms, θ represents the growth lag time of the microorganisms, and k_sRepresents a growth inhibitory factor of said microorganism.

2. The method of determining a texture of a raw food according to claim 1,

said determining quality parameters of said uncooked food product comprises:

determining the change rate of the quality parameter according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment under the condition that the quality parameter is a texture parameter, an organoleptic parameter or a physicochemical parameter;

determining a quality parameter of the uncooked food product based on the rate of change of the quality parameter and the logistics time.

3. The method of determining a texture of a raw food according to claim 2,

said determining a rate of change of said quality parameter as a function of said volume fraction of fresh-keeping gas and said temperature of said logistics environment comprises:

under the condition that the quality parameter is a texture parameter, determining the activation energy of the texture parameter according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameter;

determining a pre-factor of a texture parameter according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the pre-factor of the texture parameter;

and inputting the activation energy of the texture parameters, wherein the texture parameters refer to a pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the texture parameters.

4. The method of determining a texture of a raw food according to claim 2,

determining the sensory parameter activation energy according to the volume fraction of the fresh-keeping gas and the pre-trained relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy under the condition that the quality parameter is a sensory parameter;

determining a sensory parameter pre-factor according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the sensory parameter pre-factor;

and inputting the sensory parameter activation energy, wherein the sensory parameter refers to a pre-factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the sensory parameter.

5. The method of determining a texture of a raw food according to claim 2,

under the condition that the quality parameters are physical and chemical parameters, determining the physical and chemical parameter activation energy according to the volume fraction of the fresh-keeping gas and the relationship between the volume fraction of the fresh-keeping gas and the physical and chemical parameter activation energy trained in advance;

determining a physicochemical parameter pre-factor according to the volume fraction of the fresh-keeping gas and a pre-trained relationship between the volume fraction of the fresh-keeping gas and the physicochemical parameter pre-factor;

and inputting the physical and chemical parameter activation energy, wherein the physical and chemical parameter refers to a front factor and the temperature of the logistics environment into an Arrhenius formula, and determining the change rate of the physical and chemical parameter.

6. The method of determining a texture of a raw food according to claim 1,

said determining the quality of the uncooked food product according to the quality parameter comprises:

weighting various quality parameters to obtain comprehensive quality parameters;

determining the quality of the uncooked food product according to the comprehensive quality parameters.

7. The method of determining a texture of a raw food according to claim 1, further comprising:

collecting at least one quality parameter of a plurality of time points from an initial state to a critical state of inedibility of the uncooked food product under the condition of different temperatures and different volume fractions of fresh-keeping gas in a logistics environment as training data;

and training a quality perception model by using the training data.

8. The method of determining a texture of a raw food according to claim 7,

the training a quality perception model using the training data comprises:

under the condition that the quality parameters are texture parameters, determining the relation between the texture parameters and the logistics time according to the texture parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of the logistics environment; wherein the parameter to be determined in the relation between the texture parameter and the material flow time is the change rate of the texture parameter corresponding to the volume fraction and the temperature;

determining the relationship between the temperature of the logistics environment and the change rate of the texture parameters according to the change rate of the texture parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the texture parameters are the texture parameter activation energy and the texture parameter pre-factor corresponding to the volume fraction;

determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the texture parameters according to the activation energy of the texture parameters corresponding to various volume fractions;

and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-indication factor of the texture parameter according to the pre-indication factors of the texture parameter corresponding to various volume fractions.

9. The method of determining a texture of a raw food according to claim 7,

the training a quality perception model using the training data comprises:

under the condition that the quality parameters are sensory parameters, determining the relationship between the sensory parameters and the logistics time according to the sensory parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of the logistics environment; wherein the parameter to be determined in the relationship between the sensory parameter and the logistics time is the change rate of the sensory parameter corresponding to the volume fraction and the temperature;

determining the relationship between the temperature of the logistics environment and the change rate of the sensory parameters according to the change rate of the sensory parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the sensory parameters are the sensory parameter activation energy and the sensory parameter pre-index factor corresponding to the volume fraction;

determining the relationship between the volume fraction of the fresh-keeping gas and the sensory parameter activation energy according to the sensory parameter activation energy corresponding to various volume fractions;

and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-sensory parameter pre-sensory factor according to the pre-sensory parameter pre-sensory factors corresponding to the various volume fractions.

10. The method of determining a texture of a raw food according to claim 7,

the training a quality perception model using the training data comprises:

under the condition that the quality parameters are physical and chemical parameters, determining the relationship between the physical and chemical parameters and the logistics time according to the physical and chemical parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of the logistics environment; wherein the parameter to be determined in the relationship between the physical and chemical parameters and the logistics time is the volume fraction and the change rate of the physical and chemical parameters corresponding to the temperature;

determining the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters according to the change rate of the physical and chemical parameters corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein, the parameters to be determined in the relationship between the temperature of the logistics environment and the change rate of the physical and chemical parameters are physical and chemical parameter activation energy and physical and chemical parameter pre-leading factors corresponding to the volume fraction;

determining the relationship between the volume fraction of the fresh-keeping gas and the activation energy of the physicochemical parameters according to the activation energy of the physicochemical parameters corresponding to various volume fractions;

and determining the relationship between the volume fraction of the fresh-keeping gas and the pre-pointing factor of the physicochemical parameter according to the pre-pointing factor of the physicochemical parameter corresponding to each volume fraction.

11. The method of determining a texture of a raw food according to claim 7,

the training a quality perception model using the training data comprises:

under the condition that the quality parameters are microbial parameters, determining the relation between the microbial parameters and the logistics time according to the microbial parameters at different time points aiming at the volume fraction of a fresh-keeping gas and the temperature of a logistics environment, wherein the parameters to be determined in the relation between the microbial parameters and the logistics time are the growth rate, the growth retardation time and the growth inhibition factor of the microbes corresponding to the volume fraction and the temperature;

determining the relationship between the temperature of the logistics environment and the growth rate of the microorganisms according to the growth rates of the microorganisms corresponding to various temperatures aiming at the volume fraction of a fresh-keeping gas; wherein the coefficient to be determined in the relationship between the temperature of the logistics environment and the growth rate of the microorganisms is a first regression coefficient corresponding to the volume fraction and a first theoretical temperature at which no microorganisms survive; determining the relationship between the volume fraction of the fresh-keeping gas and the first regression coefficient according to the first regression coefficient corresponding to each volume fraction; determining the relation between the volume fraction of the fresh-keeping gas and the first theoretical temperature according to the first theoretical temperature corresponding to various volume fractions;

aiming at the volume fraction of a fresh-keeping gas, determining the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms according to the growth delay time of the microorganisms corresponding to various temperatures; wherein, the coefficients to be determined in the relationship between the temperature of the logistics environment and the growth delay time of the microorganisms are a second regression coefficient corresponding to the volume fraction and a second theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and a second regression coefficient according to the second regression coefficient corresponding to each volume fraction; determining the relationship between the volume fraction of the fresh-keeping gas and the second theoretical temperature according to the second theoretical temperature corresponding to various volume fractions;

aiming at the volume fraction of a fresh-keeping gas, determining the relationship between the temperature of the logistics environment and the growth inhibition factor of the microorganism according to the growth inhibition factors of the microorganism corresponding to various temperatures; wherein, the coefficient to be determined in the relation between the temperature of the logistics environment and the growth inhibition factor of the microorganism is a third regression coefficient corresponding to the volume fraction and a third theoretical temperature at which no microorganism survives; determining the relationship between the volume fraction of the fresh-keeping gas and a third regression coefficient according to the third regression coefficient corresponding to various volume fractions; and determining the relationship between the volume fraction of the fresh-keeping gas and the third theoretical temperature according to the third theoretical temperature corresponding to various volume fractions.

12. The method of determining a texture of a raw food according to claim 1, further comprising:

returning to the user at least one of the quality parameter of the uncooked food product, the volume fraction of the fresh keeping gas in the logistics environment, the temperature of the logistics environment, and the remaining shelf life of the uncooked food product in response to a query request sent by the user.

13. A device for determining the quality of a raw food, comprising:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring the volume fraction of fresh-keeping gas in a logistics environment in which uncooked food products are located, and the temperature and the logistics time of the logistics environment;

a quality parameter determination module, configured to determine a quality parameter of the uncooked food product according to the volume fraction of the fresh-keeping gas, the temperature of the logistics environment, and the logistics time, where the quality parameter includes: texture parameters, at least one of sensory parameters and physicochemical parameters, and microbial parameters;

the quality determining module is used for determining the quality of the uncooked food product according to the quality parameters;

the quality parameter determining module is used for determining the growth rate, growth retardation time and growth inhibition factor of microorganisms according to the volume fraction of the fresh-keeping gas and the temperature of the logistics environment under the condition that the quality parameter is a microorganism parameter; determining microbial parameters of said uncooked food product based on growth rate of said microbes, growth retardation time, growth inhibitory factor and said logistics time;

14. A device for determining the quality of a raw food, comprising:

a processor; and

a memory coupled to the processor for storing instructions that, when executed by the processor, cause the processor to perform the method of determining a raw food quality of any of claims 1-12.

15. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements the steps of the method of any of claims 1-12.

16. A system for determining the quality of a raw food product comprising: a raw food quality determining apparatus according to claim 13 or 14; and

the gas sensor is used for collecting the volume fraction of the fresh-keeping gas in the logistics environment of the uncooked food product and sending the volume fraction to the uncooked food quality determining device;

the temperature sensor is used for collecting the temperature of the logistics environment and sending the temperature to the uncooked food quality determining device;

and the timer is used for acquiring logistics time and sending the logistics time to the uncooked food quality determining device.

17. The uncooked food quality determination system of claim 16, further comprising:

the receiver is used for receiving a query request sent by a user;

a transmitter for returning to a user at least one of the quality parameter of the uncooked food product, a volume fraction of a fresh-keeping gas in the logistics environment, a temperature of the logistics environment, and a remaining shelf life of the uncooked food product.