CN117539163A - Intelligent household informatization control method based on artificial intelligence - Google Patents
Intelligent household informatization control method based on artificial intelligence Download PDFInfo
- Publication number
- CN117539163A CN117539163A CN202311814152.0A CN202311814152A CN117539163A CN 117539163 A CN117539163 A CN 117539163A CN 202311814152 A CN202311814152 A CN 202311814152A CN 117539163 A CN117539163 A CN 117539163A
- Authority
- CN
- China
- Prior art keywords
- devices
- neural network
- intelligent
- data
- graph
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 51
- 230000003993 interaction Effects 0.000 claims abstract description 46
- 230000001537 neural effect Effects 0.000 claims abstract description 33
- 238000011217 control strategy Methods 0.000 claims abstract description 18
- 238000003062 neural network model Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 12
- 230000006399 behavior Effects 0.000 claims description 29
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012098 association analyses Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 abstract description 7
- 238000005265 energy consumption Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 210000001503 joint Anatomy 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses an intelligent household informatization control method based on artificial intelligence, which comprises the following steps: s1, establishing a relation model among intelligent household devices in an intelligent household system by using a graph neural network, wherein each device is regarded as a node in the graph, and interaction among the devices serves as an edge among the nodes; s2, extracting characteristics of data input by each equipment node; s3, calculating influence and relevance among the devices through forward propagation of the graph neural network; s4, generating a control strategy for each device by using the self-adaptive neural fuzzy inference system according to the relevance among devices obtained from the graph neural network and the user behavior mode; and S5, in the using process, combining the graph neural network model and the self-adaptive neural fuzzy inference system, and dynamically adjusting the operation parameters of all the devices in the intelligent home system. According to the invention, by adopting the graphic neural network, the efficient integration among intelligent home devices produced by different manufacturers is effectively realized.
Description
Technical Field
The invention relates to the technical field of intelligent home, in particular to an intelligent home informatization control method based on artificial intelligence.
Background
In the current smart home technology field, smart home systems mainly rely on linkage and cooperation between a plurality of smart devices to realize automated management and control. These systems typically include various sensors, controllers, and actuators for performing a variety of functions such as environmental monitoring, security, energy management, and the like. However, the prior art has significant limitations in several key respects.
Firstly, smart home devices produced by different manufacturers often adopt respective communication protocols and data formats, resulting in poor compatibility and integration between devices. This lack of unified standards makes users face many difficulties in configuring and using multi-brand smart home devices, limiting the flexibility and extensibility of the system. Secondly, the existing intelligent home system is not mature enough in the aspects of intelligent coordination and data processing among devices. While some systems may implement basic device linkage, they still lack sufficient intelligence and adaptation capability in handling complex scenarios and user personalization requirements. For example, the system may not accurately understand and predict the behavior patterns of the user, or may not be able to effectively handle the effects of environmental changes. In addition, the prior art is also subject to improvement in terms of user interaction experience. Many smart home systems have an insufficiently intuitive user interface, resulting in a high learning cost for the user during operation. Meanwhile, the feedback and adjustment request processing of the system for the user is not sensitive and intelligent enough, and the overall quality of user experience is affected. Therefore, how to provide an intelligent household informatization control method based on artificial intelligence is a problem to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide an intelligent household informatization control method based on artificial intelligence, which effectively realizes the efficient integration among intelligent household devices produced by different manufacturers by adopting a graph neural network. By intelligently analyzing the relationship and interaction among the devices, seamless butt joint and cooperative work among the devices are realized, so that the flexibility and expansibility of the system are greatly improved.
According to the embodiment of the invention, the intelligent household informatization control method based on artificial intelligence comprises the following steps:
s1, establishing a relation model among intelligent household devices in an intelligent household system by using a graph neural network, wherein each device is regarded as a node in the graph, and interaction among the devices serves as an edge among the nodes;
s2, extracting characteristics of data input by each equipment node, wherein the characteristics comprise equipment states, operation histories and user preferences;
s3, calculating influence and relevance among the devices through forward propagation of the graph neural network;
s4, generating a control strategy for each device by using the self-adaptive neural fuzzy inference system according to the relevance among devices obtained from the graph neural network and the user behavior mode;
and S5, in the using process, combining the graph neural network model and the self-adaptive neural fuzzy inference system, and dynamically adjusting the operation parameters of all the devices in the intelligent home system.
Optionally, the S1 specifically includes:
s11, constructing a multi-modal diagram neural network model;
s12, determining interaction relations among devices through association analysis of multi-mode data, and determining dependency relations among the devices through analysis of behavior patterns and environment changes of users on different devices, wherein the dependency relations are expressed in the form of edges in a graph, and the weight of the edges is determined by interaction strength and frequency among the devices;
s13, deep learning is carried out on the equipment relationship in the intelligent home system by using the graph convolution network:
wherein,representing the adjacency matrix added with self-connection, A represents the original adjacency matrix, I represents the identity matrix,representation->Degree matrix of (H) (l) To represent the characteristic representation of the first layer, W (l) Representing the weight matrix of the layer.
Optionally, the multi-modal graph neural network model comprehensively processes data of various devices in the intelligent home, wherein the data comprises sensor data, device states and user interaction records, and the sensor data, the device states and the user interaction records are taken as node characteristics.
Optionally, the S2 specifically includes:
s21, collecting operation data of various devices in the intelligent home system;
s22, performing data cleaning, data standardization and missing value processing on the collected data;
s23, performing nonlinear dimension reduction processing through an automatic encoder, and extracting characteristics with more influence on intelligent home control from complex data:
z＝f(Wx+b)；
wherein x represents input original data, W and b represent weight and bias parameters of an encoder respectively, f represents an activation function, and z represents an extracted advanced feature representation;
s24, further analyzing and classifying the extracted high-level features by utilizing a random forest algorithm, and understanding and predicting the use mode of each device and the behavior habit of the user:
wherein Y represents the final prediction output, N represents the number of decision trees, Y i (X) represents the predicted output of the ith decision tree on input X;
s25, taking a prediction result of the random forest as input of each equipment node in the graphic neural network, and optimizing cooperative work strategy and user interaction experience among the equipment in the intelligent home system.
Optionally, the step S3 specifically includes:
s31, defining a multi-mode graph neural network model, wherein the connection between nodes represents potential interaction relations between different intelligent devices, and the interaction relations are based on data flow and user operation modes between the devices;
s32, calculating influence and relevance among devices by using a forward propagation mechanism of the graph neural network:
wherein,representing a characteristic representation of a node v at layer l+1, N (v) representing a set of neighbor nodes of the node v, c vu Represents a normalization constant, W (l) Representing a weight matrix of the first layer, sigma representing an activation function;
s33, the intelligent home system understands and predicts the mutual influence among the devices.
Optionally, the step S4 specifically includes:
s41, analyzing the output of the graph neural network by using the self-adaptive neural fuzzy inference system;
s42, defining fuzzy rules and membership functions, wherein the fuzzy rules are used for mapping interdependencies and behavior patterns among devices based on states of the devices in the intelligent home system, historical interaction data of users and environmental factors;
s43, fuzzy rule reasoning is carried out, and the relationship between devices and the user behavior mode output by the graphic neural network are converted into a specific device control strategy:
wherein F (x) represents the final control strategy output, n represents the number of fuzzy rules, w i Weights representing the ith rule, f i (x) Representing the output function of the ith rule.
Optionally, the training process of the adaptive neural fuzzy inference system includes:
converting the device state and the user behavior mode into fuzzy values by using fuzzy rules;
the membership function and the rule parameters are adjusted through a feedforward neural network;
the weights and parameters are optimized using back propagation and least squares estimation.
Optionally, the step S5 specifically includes applying the output of the graph neural network model and the adaptive neural fuzzy inference system to the intelligent home system, and intelligently adjusting parameters of each device:
P new ＝P current +α·ΔP；
wherein P is new Representing the adjusted device parameters, P current Representing the current equipment parameters, alpha represents the learning rate, and delta P represents the parameter adjustment quantity based on the output of the graph neural network and the adaptive neural fuzzy inference system.
Optionally, the adjustment of the device parameter is based on two-way output: on one hand, the relevance and influence information between devices provided by the graphic neural network, and on the other hand, the control strategy based on the user behavior mode provided by the adaptive neural fuzzy inference system.
The beneficial effects of the invention are as follows:
(1) According to the invention, by adopting the graphic neural network, the efficient integration among intelligent home devices produced by different manufacturers is effectively realized. By intelligently analyzing the relationship and interaction among the devices, seamless butt joint and cooperative work among the devices are realized, so that the flexibility and expansibility of the system are greatly improved. By combining the self-adaptive neural fuzzy inference system, the user behavior mode can be more accurately understood and predicted, and the equipment setting can be automatically adjusted according to the environmental change, so that the system can effectively cope with complex scenes, and the personalized requirements of users are met.
(2) According to the intelligent home system control method and the intelligent home system control system, the user interface and the interaction flow are optimized through the intelligent algorithm, so that a user is more visual and convenient when operating the intelligent home system, the user can more easily control equipment and configure the system, and the system can respond to feedback and adjustment requests of the user more quickly and intelligently.
(3) The intelligent home system can effectively reduce energy consumption and improve energy efficiency by accurately controlling the running state of each device. The method not only reduces the economic burden of the user, but also is beneficial to environmental protection, and has remarkable progress in the aspects of enhancing the compatibility of equipment, improving the self-adaptive capacity of the system, optimizing the user experience, improving the energy efficiency and the like, thereby bringing important innovation and development to the field of intelligent home.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
fig. 1 is a flowchart of an intelligent home informatization control method based on artificial intelligence.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings. The drawings are simplified schematic representations which merely illustrate the basic structure of the invention and therefore show only the structures which are relevant to the invention.
Referring to fig. 1, an intelligent home informatization control method based on artificial intelligence includes the following steps:
s1, establishing a relation model among intelligent household devices in an intelligent household system by using a graph neural network, wherein each device is regarded as a node in the graph, and interaction among the devices serves as an edge among the nodes;
in this embodiment, S1 specifically includes:
s11, constructing a multi-modal diagram neural network model;
s12, determining interaction relations among devices through association analysis of multi-mode data, determining dependency relations among the devices through analysis of behavior patterns and environment changes of users on different devices, wherein the dependency relations are expressed in the form of edges in a graph, and the weight of the edges is determined by interaction strength and frequency among the devices;
s13, deep learning is carried out on the equipment relationship in the intelligent home system by using the graph convolution network:
wherein,representing the adjacency matrix added with self-connection, A represents the original adjacency matrix, I represents the identity matrix,representation->Degree matrix of (H) (l) To represent the characteristic representation of the first layer, W (l) Representing the weight matrix of the layer.
In this embodiment, the multi-modal map neural network model comprehensively processes data of various devices in the smart home, where the data includes sensor data, device states, and user interaction records, and uses the sensor data, the device states, and the user interaction records as node features.
The multi-modal graph neural network can automatically learn and adapt to the change of the home environment, and the operation strategy and parameter setting of each device in the intelligent home system are dynamically adjusted according to the use mode of the device and the behavior habit of the user, so that the performance and user experience of the whole system are optimized. By introducing the multi-mode graph neural network and graph rolling network technology, the method for modeling and optimizing the relationship between the devices, which is more fit with the intelligent home environment, is provided, and the cooperative working capacity and the intelligent level of the intelligent home system are enhanced.
S2, extracting characteristics of data input by each equipment node, wherein the characteristics comprise equipment states, operation histories and user preferences;
in this embodiment, S2 specifically includes:
s21, collecting operation data of various devices in the intelligent home system, wherein in an embodiment, the operation data comprise brightness adjustment records of intelligent lamps, temperature setting data of an intelligent thermostat, activity detection records of safety monitoring devices, interaction logs of an intelligent sound box and the like;
s22, performing data cleaning, data standardization and missing value processing on the collected data;
s23, performing nonlinear dimension reduction processing through an automatic encoder, and extracting characteristics with more influence on intelligent home control from complex data:
z＝f(Wx+b)；
wherein x represents input original data, W and b represent weight and bias parameters of an encoder respectively, f represents an activation function, and z represents an extracted advanced feature representation;
s24, further analyzing and classifying the extracted high-level features by utilizing a random forest algorithm, and understanding and predicting the use mode of each device and the behavior habit of the user:
wherein Y represents the final prediction output, N represents the number of decision trees, Y i (X) represents the predicted output of the ith decision tree on input X;
s25, taking a prediction result of the random forest as input of each equipment node in the graphic neural network, and optimizing cooperative work strategy and user interaction experience among the equipment in the intelligent home system.
And taking a prediction result of the random forest as an important input of each equipment node in the graph neural network, so as to optimize a cooperative work strategy and user interaction experience among the equipment in the intelligent home system.
Through the steps, not only is an efficient feature extraction and processing method provided, but also the processing methods are tightly connected with the actual application scene of the intelligent household equipment, so that the overall intelligent level and the user satisfaction of the intelligent household system are improved.
S3, calculating influence and relevance among the devices through forward propagation of the graph neural network;
in the smart home environment in this embodiment, each smart device is defined as a node in the graph neural network, and the connection between the nodes reflects a direct or indirect relationship between the devices, such as a relationship between an air conditioner and a temperature sensor, or a relationship between a security camera and a door lock, and S3 specifically includes:
s31, defining a multi-mode graph neural network model, wherein the connection between nodes represents potential interaction relations between different intelligent devices, and the interaction relations are based on data flow between the devices and a user operation mode, for example, data interaction between environment control devices and environment sensing devices or a response chain between user interaction devices and home automation devices;
s32, calculating influence and relevance among devices by using a forward propagation mechanism of the graph neural network:
wherein,representing a characteristic representation of a node v at layer l+1, N (v) representing a set of neighbor nodes of the node v, c vu Represents a normalization constant, W (l) Representing a weight matrix of the first layer, sigma representing an activation function;
s33, the intelligent home system understands and predicts the mutual influence among the devices.
Step S31-step S33 enable the intelligent home system to automatically adjust the running state of the equipment according to the interaction among the equipment and the user behavior mode, such as adjusting the environment control equipment in a specific scene or adjusting the working mode of the safety monitoring equipment according to the safety protocol. An innovative solution is provided for intelligent interaction and cooperative work among devices in the intelligent home system, and the self-adaptability of the system and the intellectualization of user interaction are enhanced.
S4, generating a control strategy for each device by using the self-adaptive neural fuzzy inference system according to the relevance among devices obtained from the graph neural network and the user behavior mode;
in this embodiment, S4 specifically includes:
s41, analyzing the output of the graph neural network by utilizing a self-adaptive neural fuzzy reasoning system, wherein the self-adaptive neural fuzzy reasoning system combines the learning capacity of the neural network and the reasoning capacity of fuzzy logic, and can process the situation with higher uncertainty and ambiguity;
s42, defining fuzzy rules and membership functions, wherein the fuzzy rules are used for mapping interdependencies and behavior patterns among devices based on states of the devices in the intelligent home system, historical interaction data of users and environmental factors;
a set of fuzzy rules is defined that are based on factors such as interactions between smart home devices, user behavior data, and environmental changes. These rules are then adaptively learned using a neural network to optimize the accuracy and adaptability of the rules.
S43, fuzzy rule reasoning is carried out, and the relationship between devices and the user behavior mode output by the graphic neural network are converted into a specific device control strategy:
wherein F (x) represents the final control strategy output, n represents the number of fuzzy rules, w i Weights representing the ith rule, f i (x) Representing the output function of the ith rule.
The self-adaptive neural fuzzy inference system in the steps S41-S43 can dynamically adjust working parameters of each intelligent device according to real-time device states and user demands, such as adjusting illumination intensity, temperature setting or sensitivity of safety monitoring, so as to optimize living environment of users and improve energy efficiency; the response flexibility and the intelligent regulation and control capability of the intelligent home system are improved, so that the system can more accurately meet the personalized demands of users, the running states of all devices are effectively coordinated, and the overall performance and the user satisfaction of the system are improved. By combining the self-adaptive neural fuzzy inference system and the graphic neural network, a highly self-adaptive and accurate equipment control strategy is provided for the intelligent home system, and the intellectualization and user experience of the system are effectively improved.
In this embodiment, the training process of the adaptive neural fuzzy inference system includes:
converting the device state and the user behavior mode into fuzzy values by using fuzzy rules;
the membership function and the rule parameters are adjusted through a feedforward neural network;
the weights and parameters are optimized using back propagation and least squares estimation.
And S5, in the using process, combining the graph neural network model and the self-adaptive neural fuzzy inference system, and dynamically adjusting the operation parameters of all the devices in the intelligent home system.
In this embodiment, S5 specifically includes applying the output of the graph neural network model and the adaptive neural fuzzy inference system to the smart home system, and intelligently adjusting parameters of each device:
P new ＝P current +α·ΔP；
wherein P is new Representing the adjusted device parameters, P current Representing the current equipment parameters, alpha represents the learning rate, and delta P represents the parameter adjustment quantity based on the output of the graph neural network and the adaptive neural fuzzy inference system.
Through continuous study and adjustment, the intelligent home system can more accurately adapt to the living habit and preference of a user, and meanwhile, the energy efficiency and the automation level of the whole system are improved, so that the system can optimize the overall synergistic effect while keeping the independent functions of all devices, such as adjusting the settings of devices such as illumination, temperature, safety monitoring and the like in different time periods or specific scenes, so as to adapt to the specific requirements of the user, and an innovative solution is provided for realizing the efficient collaborative work among the devices and the comprehensive optimization of user experience by combining the advantages of the graph neural network and the self-adaptive neural fuzzy inference system to the intelligent home system.
In this embodiment, the adjustment of the device parameters is based on two-way output: on one hand, the relevance and influence information between devices provided by the graphic neural network, and on the other hand, the control strategy based on the user behavior mode provided by the adaptive neural fuzzy inference system.
In the above embodiment, the relationship model between devices is established using a graph neural network: this approach can capture complex interactions and dependencies between devices, even if the devices come from different manufacturers and use different communication protocols. The neural network can understand and predict how the devices affect each other by learning the interaction pattern between the devices.
The self-adaptive neuro-fuzzy reasoning system is used for formulating a control strategy: the self-adaptive neural fuzzy reasoning system combines the learning capability of the neural network and the reasoning capability of the fuzzy logic, and is suitable for processing the uncertainty and the complexity in the intelligent home environment. The system can generate a proper control strategy for each device based on the user behavior mode and the environment change, so that the cooperative work among the devices is realized.
Example 1:
in a typical smart home environment, the method of the present invention is implemented. The environment includes various intelligent devices, and the system includes various intelligent devices, such as intelligent lighting, intelligent thermostats, intelligent security systems, and the like. These devices were originally produced by different vendors, using different communication protocols and data formats, faced compatibility and integration challenges.
The present embodiment first applies a graph neural network to construct a relationship model between devices. Specifically, the following formula is used to analyze and optimize interactions between devices:
in this model, each smart device is considered a node and the interactions between them are considered edges between nodes. In this way, the collaboration policy between devices can be precisely adjusted to improve overall efficiency and user experience. In practical application, through the graphic neural network model, intelligent lighting and intelligent thermostats learn to automatically adjust the running mode of the intelligent lighting and intelligent thermostats according to the home/away state of a user, so that more intelligent energy management is realized. This collaborative strategy reduces overall energy consumption by 15% within one month after implementation.
Next, the present embodiment utilizes an adaptive neuro-fuzzy inference system to process user behavior and environmental changes, generating specific device control strategies. The following formula is used:
the adaptive neural fuzzy inference system can adjust the temperature setting of the thermostat according to the daily activity pattern of the user and adjust the illumination intensity according to the indoor light variation. In practice, when the user goes home later in the evening, the system will automatically lower the indoor temperature to save energy and gradually adjust to the comfort temperature before the user arrives. This adjustment helps the user save about 20% of the heating costs in one quarter after implementation.
Finally, the present embodiment dynamically adjusts the device parameters using the following formula:
P new ＝P current +α·ΔP；
this formula helps the present embodiment adjust the operating parameters of the device based on the output of the graph neural network and the adaptive neural fuzzy inference system. The intelligent lighting system automatically adjusts the brightness according to the habit of the user and the ambient light, in the scene, the energy consumption of the intelligent lighting system is reduced by 10% compared with the prior art after continuous adjustment for one month, and meanwhile, the adaptability and the comfort of the user feedback lighting system are obviously improved.
In summary, by combining the intelligent control strategy of the graph neural network and the adaptive neural fuzzy inference system, the intelligent home system of the embodiment not only solves the problems of compatibility and integration between devices in practical application, but also remarkably improves energy efficiency and user experience. User satisfaction surveys have shown that overall satisfaction with the system is improved by about 25%, particularly in terms of ease of use and adaptivity. The embodiment effectively proves the practicability and the innovation of the method provided by the embodiment, and brings important progress to the field of intelligent home.
The statistics of the data were performed 3 months after the practice of the method of the invention, as shown in the following table:
TABLE 1 energy consumption comparison
Table 2 user satisfaction survey
According to tables 1 and 2 above, the data of energy consumption show significant differences before and after the intelligent home system implements the artificial intelligence control method. Intelligent lighting system: before implementation, the monthly energy consumption was 100kWh. After implementation, this number is reduced to 85kWh and the energy saving ratio reaches 15%. This shows that the intelligent lighting system effectively reduces energy waste by more accurate control and adjustment. Intelligent thermostat: the energy consumption of the thermostat is 150 kWh/month before implementation, and the energy is reduced to 120 kWh/month after implementation, so that 20% energy conservation is realized. This may be due to the more intelligent temperature regulation of the thermostat and the mode of operation that is more consistent with the user's habits. The whole system comprises: overall, the smart home system reduces the monthly energy consumption from 250kWh to 205kWh before implementation, with an overall energy saving ratio of 18%. This illustrates that the smart home system as a whole enables more efficient energy management and use.
According to the invention, by adopting the graphic neural network, the efficient integration among intelligent home devices produced by different manufacturers is effectively realized. By intelligently analyzing the relationship and interaction among the devices, seamless butt joint and cooperative work among the devices are realized, so that the flexibility and expansibility of the system are greatly improved. By combining the self-adaptive neural fuzzy inference system, the user behavior mode can be more accurately understood and predicted, and the equipment setting can be automatically adjusted according to the environmental change, so that the system can effectively cope with complex scenes, and the personalized requirements of users are met.
According to the intelligent home system control method and the intelligent home system control system, the user interface and the interaction flow are optimized through the intelligent algorithm, so that a user is more visual and convenient when operating the intelligent home system, the user can more easily control equipment and configure the system, and the system can respond to feedback and adjustment requests of the user more quickly and intelligently.
The intelligent home system can effectively reduce energy consumption and improve energy efficiency by accurately controlling the running state of each device. The method not only reduces the economic burden of the user, but also is beneficial to environmental protection, and has remarkable progress in the aspects of enhancing the compatibility of equipment, improving the self-adaptive capacity of the system, optimizing the user experience, improving the energy efficiency and the like, thereby bringing important innovation and development to the field of intelligent home.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art, who is within the scope of the present invention, should make equivalent substitutions or modifications according to the technical scheme of the present invention and the inventive concept thereof, and should be covered by the scope of the present invention.
Claims (9)
1. An intelligent household informatization control method based on artificial intelligence is characterized by comprising the following steps:
s1, establishing a relation model among intelligent household devices in an intelligent household system by using a graph neural network, wherein each device is regarded as a node in the graph, and interaction among the devices serves as an edge among the nodes;
s2, extracting characteristics of data input by each equipment node, wherein the characteristics comprise equipment states, operation histories and user preferences;
s3, calculating influence and relevance among the devices through forward propagation of the graph neural network;
s4, generating a control strategy for each device by using the self-adaptive neural fuzzy inference system according to the relevance among devices obtained from the graph neural network and the user behavior mode;
and S5, in the using process, combining the graph neural network model and the self-adaptive neural fuzzy inference system, and dynamically adjusting the operation parameters of all the devices in the intelligent home system.
2. The intelligent household informatization control method based on artificial intelligence according to claim 1, wherein the S1 specifically comprises:
s11, constructing a multi-modal diagram neural network model;
s12, determining interaction relations among devices through association analysis of multi-mode data, and determining dependency relations among the devices through analysis of behavior patterns and environment changes of users on different devices, wherein the dependency relations are expressed in the form of edges in a graph, and the weight of the edges is determined by interaction strength and frequency among the devices;
s13, deep learning is carried out on the equipment relationship in the intelligent home system by using the graph convolution network:
wherein,represents an adjoining matrix added with self-connection, A represents an original adjoining matrix, I represents an identity matrix,/I>Representation ofDegree matrix of (H) (l) To represent the characteristic representation of the first layer, W (l) Representing the weight matrix of the layer.
3. The intelligent household informatization control method based on artificial intelligence according to claim 2, wherein the multi-modal graph neural network model comprehensively processes data of various devices in the intelligent household, wherein the data comprises sensor data, device states and user interaction records, and the sensor data, the device states and the user interaction records are taken as node characteristics.
4. The intelligent household informatization control method based on artificial intelligence according to claim 2, wherein the step S2 specifically comprises:
s21, collecting operation data of various devices in the intelligent home system;
s22, performing data cleaning, data standardization and missing value processing on the collected data;
s23, performing nonlinear dimension reduction processing through an automatic encoder, and extracting characteristics with more influence on intelligent home control from complex data:
z＝f(Wx+b)；
wherein x represents input original data, W and b represent weight and bias parameters of an encoder respectively, f represents an activation function, and z represents an extracted advanced feature representation;
s24, further analyzing and classifying the extracted high-level features by utilizing a random forest algorithm, and understanding and predicting the use mode of each device and the behavior habit of the user:
wherein Y represents the final prediction output, N represents the number of decision trees, Y i (X) represents the predicted output of the ith decision tree on input X;
s25, taking a prediction result of the random forest as input of each equipment node in the graphic neural network, and optimizing cooperative work strategy and user interaction experience among the equipment in the intelligent home system.
5. The intelligent household informatization control method based on artificial intelligence according to claim 4, wherein the step S3 specifically comprises:
s31, defining a multi-mode graph neural network model, wherein the connection between nodes represents potential interaction relations between different intelligent devices, and the interaction relations are based on data flow and user operation modes between the devices;
s32, calculating influence and relevance among devices by using a forward propagation mechanism of the graph neural network:
wherein,representing a characteristic representation of a node v at layer l+1, N (v) representing a set of neighbor nodes of the node v, c vu Represents a normalization constant, W (l) Representing a weight matrix of the first layer, sigma representing an activation function;
s33, the intelligent home system understands and predicts the mutual influence among the devices.
6. The intelligent household informatization control method based on artificial intelligence according to claim 1, wherein the step S4 specifically comprises:
s41, analyzing the output of the graph neural network by using the self-adaptive neural fuzzy inference system;
s42, defining fuzzy rules and membership functions, wherein the fuzzy rules are used for mapping interdependencies and behavior patterns among devices based on states of the devices in the intelligent home system, historical interaction data of users and environmental factors;
s43, fuzzy rule reasoning is carried out, and the relationship between devices and the user behavior mode output by the graphic neural network are converted into a specific device control strategy:
wherein F (x) represents the final control strategy output, n represents the number of fuzzy rules, w i Weights representing the ith rule, f i (x) Representing the output function of the ith rule.
7. The intelligent household informatization control method based on artificial intelligence according to claim 6, wherein the training process of the adaptive neural fuzzy inference system comprises the following steps:
converting the device state and the user behavior mode into fuzzy values by using fuzzy rules;
the membership function and the rule parameters are adjusted through a feedforward neural network;
the weights and parameters are optimized using back propagation and least squares estimation.
8. The intelligent household informatization control method based on artificial intelligence according to claim 1, wherein the step S5 specifically comprises the steps of comprehensively applying the output of the graph neural network model and the adaptive neural fuzzy inference system to the intelligent household system, and intelligently adjusting parameters of each device:
P new ＝P current +α·ΔP；
wherein P is new Representing the adjusted device parameters, P current Representing the current equipment parameters, alpha represents the learning rate, and delta P represents the parameter adjustment quantity based on the output of the graph neural network and the adaptive neural fuzzy inference system.
9. The intelligent household informatization control method based on artificial intelligence according to claim 8, wherein the adjustment of the device parameters is based on two-aspect output: on one hand, the relevance and influence information between devices provided by the graphic neural network, and on the other hand, the control strategy based on the user behavior mode provided by the adaptive neural fuzzy inference system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311814152.0A CN117539163A (en) | 2023-12-27 | 2023-12-27 | Intelligent household informatization control method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311814152.0A CN117539163A (en) | 2023-12-27 | 2023-12-27 | Intelligent household informatization control method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117539163A true CN117539163A (en) | 2024-02-09 |
Family
ID=89790247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311814152.0A Pending CN117539163A (en) | 2023-12-27 | 2023-12-27 | Intelligent household informatization control method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117539163A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118393891A (en) * | 2024-05-09 | 2024-07-26 | 中山市名迪电器有限公司 | Intelligent household appliance user behavior sensing and controlling system |
| CN118778469A (en) * | 2024-09-10 | 2024-10-15 | 杭州瑞德设计股份有限公司 | Intelligent home control system based on artificial intelligence |
-
2023
- 2023-12-27 CN CN202311814152.0A patent/CN117539163A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118393891A (en) * | 2024-05-09 | 2024-07-26 | 中山市名迪电器有限公司 | Intelligent household appliance user behavior sensing and controlling system |
| CN118778469A (en) * | 2024-09-10 | 2024-10-15 | 杭州瑞德设计股份有限公司 | Intelligent home control system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117539163A (en) | Intelligent household informatization control method based on artificial intelligence | |
| Doctor et al. | A fuzzy embedded agent-based approach for realizing ambient intelligence in intelligent inhabited environments | |
| Sandhu et al. | Wireless sensor networks for commercial lighting control: Decision making with multi-agent systems | |
| Alcalá et al. | Fuzzy control of HVAC systems optimized by genetic algorithms | |
| Fallah-Mehdipour et al. | Real-time operation of reservoir system by genetic programming | |
| Jin et al. | A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development | |
| Dounis et al. | Advanced control systems engineering for energy and comfort management in a building environment—A review | |
| CN111556630B (en) | Intelligent lamp self-adaptive scene recognition system and method based on Bayesian network | |
| CN108536030A (en) | A kind of intelligent domestic system and its working method based on ANFIS algorithms | |
| CN118042684A (en) | Light control method and system based on artificial intelligence | |
| CN105652677A (en) | Intelligent home control method, device and system based on user behavior analysis | |
| CN117193019A (en) | Intelligent building control system for building design | |
| CN115239133A (en) | Multi-heat-source heat supply system collaborative optimization scheduling method based on layered reinforcement learning | |
| CN111338227B (en) | Electronic appliance control method and control device based on reinforcement learning and storage medium | |
| CN117872790A (en) | Intelligent household Internet of things control system | |
| CN113739386A (en) | Control method, system, equipment and medium for public space thermal environment air conditioning system | |
| Paulauskaite-Taraseviciene et al. | The usage of artificial neural networks for intelligent lighting control based on resident’s behavioural pattern | |
| Arun et al. | Internet of things and deep learning-enhanced monitoring for energy efficiency in older buildings | |
| CN116996546A (en) | Control method, device and equipment of Internet of things equipment and storage medium | |
| Verma et al. | Making smart homes smarter: optimizing energy consumption with human in the loop | |
| Chenaru et al. | IoT gateway for personalized user comfort management in smart home applications | |
| Chen et al. | A novel multi-agent framework for the design of home automation | |
| Akhai et al. | Wireless networking solutions for climate control and comfort in modern air conditioning systems | |
| Jabeur et al. | A Fuzzy Logic controller Controls a Smart lighting system for energy savings | |
| CN109495359A (en) | A kind of effective intelligent home control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |