CN110033324A

CN110033324A - Data processing method, device, electronic equipment and computer readable storage medium

Info

Publication number: CN110033324A
Application number: CN201910291242.3A
Authority: CN
Inventors: 姜谷雨
Original assignee: Shanghai Lazhasi Information Technology Co Ltd
Current assignee: Shanghai Lazhasi Information Technology Co Ltd
Priority date: 2019-04-11
Filing date: 2019-04-11
Publication date: 2019-07-19

Abstract

The embodiment of the present disclosure discloses a kind of data processing method, device, electronic equipment and computer readable storage medium, the data processing method includes: to obtain user's history behavioral data, wherein, the user's history behavioral data includes the first historical behavior data and the second historical behavior data；The user behavior score based on time decaying is calculated according to the user's history behavioral data；Processing is combined for the first behavior score and the second behavior score, obtains user behavior score.The technical solution can effectively improve the accuracy of user behavior feature data, so as to provide better service for user, increase the chance for user service, improve the efficiency of service of internet, promote the service quality of internet.

Description

Data processing method and device, electronic equipment and computer readable storage medium

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a data processing method and apparatus, an electronic device, and a computer-readable storage medium.

Background

With the development of the internet technology, more and more merchants or service providers provide services for users through internet platforms, and the characteristics of the user behavior are obtained by insights, so that better services can be provided for the users, the opportunities for providing services for the users are increased, the service efficiency of the internet is improved, and the service quality of the internet is improved. However, in the prior art, the accuracy of research on the user behavior characteristics is low, and the requirements of merchants or service providers on improving the working efficiency and improving the service quality cannot be met.

Disclosure of Invention

The embodiment of the disclosure provides a data processing method and device, electronic equipment and a computer-readable storage medium.

In a first aspect, an embodiment of the present disclosure provides a data processing method.

Specifically, the data processing method includes:

acquiring historical behavior data of a user, wherein the historical behavior data of the user comprises first historical behavior data and second historical behavior data;

calculating a user behavior score based on time decay according to the user historical behavior data, wherein the user behavior score comprises a first behavior score and a second behavior score, the first behavior score is calculated according to the first historical behavior data, and the second behavior score is calculated according to the second historical behavior data;

and combining the first behavior score and the second behavior score to obtain a user behavior score.

With reference to the first aspect, in a first implementation manner of the first aspect, the first historical behavior data is explicit data, and includes one or more of the following data: user transaction data, user collection data and user tagging data; and/or the presence of a gas in the gas,

the second historical behavior data is implicit data and comprises one or more of the following data: user click data, user search data, and user browse data.

With reference to the first aspect and the first implementation manner of the first aspect, in a second implementation manner of the first aspect, the calculating a user behavior score based on a time decay according to the historical user behavior data includes:

determining a time attenuation factor;

calculating the time difference between the current time and the occurrence time of the historical behavior according to the historical behavior data of the user;

and calculating to obtain a user behavior score based on time attenuation based on the time attenuation factor and the time difference.

With reference to the first aspect, the first implementation manner of the first aspect, and the second implementation manner of the first aspect, in a third implementation manner of the first aspect, the calculating, based on the time decay factor and the time difference, a user behavior score based on time decay is implemented as:

and taking a value obtained by negating the product of the time attenuation factor and the time difference as an index of a natural constant, and calculating to obtain a user behavior score based on time attenuation.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, and the third implementation manner of the first aspect, in a fourth implementation manner of the first aspect, the calculating, based on the time decay factor and the time difference, a user behavior score based on time decay includes:

determining one or more behavioral factors;

calculating a behavior score vector corresponding to the user behavior based on the time attenuation factor and the time difference, wherein the behavior score vector is composed of scores corresponding to the one or more behavior factors;

and combining the behavior score vectors corresponding to the preset user behaviors to obtain the user behavior scores.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, and the fourth implementation manner of the first aspect, in a fifth implementation manner of the first aspect, the combining the first behavior score and the second behavior score to obtain the user behavior score includes:

determining a first combined weight for the first behavior score and a second combined weight for the second behavior score;

and according to the first combination weight and the second combination weight, carrying out weighted average on the first behavior score and the second behavior score to obtain a user behavior score.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, and the fifth implementation manner of the first aspect, in a sixth implementation manner of the first aspect, before the performing a combined process on the first behavior score and the second behavior score to obtain the user behavior score, the method further includes:

pre-processing the first and second behavior scores.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, and the sixth implementation manner of the first aspect, in a seventh implementation manner of the first aspect, the preprocessing the first behavior score and the second behavior score is implemented as:

calculating a first score mean value of scores corresponding to the behavioral factors in the first behavioral scores, and calculating a second score mean value of scores corresponding to the behavioral factors in the second behavioral scores;

calculating a first score standard deviation of the scores corresponding to the behavioral factors in the first behavioral scores, and calculating a first score standard deviation of the scores corresponding to the behavioral factors in the first behavioral scores;

calculating a first difference value between the corresponding score of the behavioral factor in the first behavioral score and the first mean score, and calculating a second difference value between the corresponding score of the behavioral factor in the second behavioral score and the second mean score;

and calculating a first percentage value between the first difference value and the first score standard deviation, determining the first behavior score after preprocessing, calculating a second percentage value between the second difference value and the second score standard deviation, and determining the second behavior score after preprocessing.

With reference to the first aspect, the first implementation manner of the first aspect, the second implementation manner of the first aspect, the third implementation manner of the first aspect, the fourth implementation manner of the first aspect, the fifth implementation manner of the first aspect, the sixth implementation manner of the first aspect, and the seventh implementation manner of the first aspect, in an eighth implementation manner of the first aspect, the embodiment of the present invention further includes:

and executing preset operation according to the user behavior score.

In a second aspect, a data processing apparatus is provided in an embodiment of the present disclosure.

Specifically, the data processing apparatus includes:

the obtaining module is configured to obtain user historical behavior data, wherein the user historical behavior data comprises first historical behavior data and second historical behavior data;

a calculating module configured to calculate a user behavior score based on time decay according to the user historical behavior data, wherein the user behavior score comprises a first behavior score and a second behavior score, the first behavior score is calculated according to the first historical behavior data, and the second behavior score is calculated according to the second historical behavior data;

and the processing module is configured to perform combined processing on the first behavior score and the second behavior score to obtain a user behavior score.

With reference to the second aspect, in a first implementation manner of the second aspect, the first historical behavior data is explicit data, and includes one or more of the following data: user transaction data, user collection data and user tagging data; and/or the presence of a gas in the gas,

With reference to the second aspect and the first implementation manner of the second aspect, in a second implementation manner of the second aspect, the computing module includes:

a first determination submodule configured to determine a temporal attenuation factor;

the first calculation submodule is configured to calculate a time difference between the current time and the occurrence time of the historical behavior according to the historical behavior data of the user;

and the second calculation submodule is configured to calculate a user behavior score based on time attenuation based on the time attenuation factor and the time difference.

With reference to the second aspect, the first implementation manner of the second aspect, and the second implementation manner of the second aspect, in a third implementation manner of the second aspect, the second computation submodule is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, and the third implementation manner of the second aspect, in a fourth implementation manner of the second aspect, the embodiment of the present invention includes that the second computation submodule includes:

a second determination submodule configured to determine one or more behavioral factors;

a third calculation submodule configured to calculate a behavior score vector corresponding to a user behavior based on the time attenuation factor and the time difference, wherein the behavior score vector is composed of scores corresponding to the one or more behavior factors;

and the combination submodule is configured to combine the behavior score vectors corresponding to the preset user behaviors to obtain the user behavior scores.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, and the fourth implementation manner of the second aspect, in a fifth implementation manner of the second aspect, the embodiment of the present invention includes:

a third determination submodule configured to determine a first combined weight of the first behavior score and a second combined weight of the second behavior score;

and the weighted average submodule is configured to perform weighted average on the first behavior score and the second behavior score according to the first combination weight and the second combination weight to obtain a user behavior score.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, and the fifth implementation manner of the second aspect, in a sixth implementation manner of the second aspect, the embodiment of the present invention further includes, before the processing module, that:

a pre-processing module configured to pre-process the first and second behavior scores.

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, and the sixth implementation manner of the second aspect, in a seventh implementation manner of the second aspect, the preprocessing module is configured to:

With reference to the second aspect, the first implementation manner of the second aspect, the second implementation manner of the second aspect, the third implementation manner of the second aspect, the fourth implementation manner of the second aspect, the fifth implementation manner of the second aspect, the sixth implementation manner of the second aspect, and the seventh implementation manner of the second aspect, in an eighth implementation manner of the second aspect, the embodiment of the present invention further includes:

and the execution module is configured to execute preset operation according to the user behavior score.

In a third aspect, the disclosed embodiments provide an electronic device, including a memory and a processor, where the memory is configured to store one or more computer instructions, where the one or more computer instructions are executed by the processor to implement the method steps of the data processing method in the first aspect.

In a fourth aspect, the disclosed embodiments provide a computer-readable storage medium for storing computer instructions for a data processing apparatus, which contains computer instructions for executing the data processing method in the first aspect to the data processing apparatus.

The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:

according to the technical scheme, the user historical behavior data of different categories are obtained, the corresponding user behavior scores are obtained through calculation, and the accurate user behavior evaluation values can be obtained through preset combination processing of the obtained user behavior scores. According to the technical scheme, the accuracy of the user behavior characteristic data can be effectively improved, so that better service can be provided for the user, the opportunity of serving the user is increased, the service efficiency of the internet is improved, and the service quality of the internet is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

Other features, objects, and advantages of the present disclosure will become more apparent from the following detailed description of non-limiting embodiments when taken in conjunction with the accompanying drawings. In the drawings:

FIG. 1 shows a flow diagram of a data processing method according to an embodiment of the present disclosure;

FIG. 2 shows a flow chart of step S102 of the data processing method according to the embodiment shown in FIG. 1;

FIG. 3 shows a flow chart of step S203 of the data processing method according to the embodiment shown in FIG. 2;

FIG. 4 shows a flow chart of step S103 of the data processing method according to the embodiment shown in FIG. 1;

FIG. 5 shows a flow diagram of a data processing method according to another embodiment of the present disclosure;

FIG. 6 shows a flow diagram of a data processing method according to yet another embodiment of the present disclosure;

FIG. 7 shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure;

FIG. 8 is a block diagram illustrating the structure of a calculation module 702 of the data processing apparatus according to the embodiment shown in FIG. 7;

fig. 9 is a block diagram showing the structure of a second calculation sub-module 803 of the data processing apparatus according to the embodiment shown in fig. 8;

fig. 10 shows a block diagram of a processing module 703 of the data processing apparatus according to the embodiment shown in fig. 7;

fig. 11 shows a block diagram of a data processing apparatus according to another embodiment of the present disclosure;

fig. 12 is a block diagram showing a configuration of a data processing apparatus according to still another embodiment of the present disclosure;

FIG. 13 shows a block diagram of an electronic device according to an embodiment of the present disclosure;

FIG. 14 is a schematic block diagram of a computer system suitable for use in implementing a data processing method according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. Also, for the sake of clarity, parts not relevant to the description of the exemplary embodiments are omitted in the drawings.

In the present disclosure, it is to be understood that terms such as "including" or "having," etc., are intended to indicate the presence of the disclosed features, numbers, steps, behaviors, components, parts, or combinations thereof, and are not intended to preclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or combinations thereof may be present or added.

It should be further noted that the embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

According to the technical scheme provided by the embodiment of the disclosure, the user historical behavior data of different types are obtained, the corresponding user behavior scores are obtained through calculation, and the obtained user behavior scores are subjected to preset combination processing, so that the accurate user behavior evaluation value can be obtained. According to the technical scheme, the accuracy of the user behavior characteristic data can be effectively improved, so that better service can be provided for the user, the opportunity of serving the user is increased, the service efficiency of the internet is improved, and the service quality of the internet is improved.

Fig. 1 shows a flow diagram of a data processing method according to an embodiment of the present disclosure. As shown in fig. 1, the data processing method includes the following steps S101 to S103:

in step S101, obtaining user historical behavior data, where the user historical behavior data includes first historical behavior data and second historical behavior data;

in step S102, calculating a user behavior score based on time decay according to the user historical behavior data, where the user behavior score includes a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data;

in step S103, the first behavior score and the second behavior score are combined to obtain a user behavior score.

As mentioned above, with the development of internet technology, more and more merchants or service providers provide services for users through internet platforms, and the characteristics of understanding user behaviors can be beneficial to providing better services for users, increasing opportunities for providing services for users, improving the service efficiency of the internet, and improving the service quality of the internet. However, in the prior art, the accuracy of research on the user behavior characteristics is low, and the requirements of merchants or service providers on improving the working efficiency and improving the service quality cannot be met.

In view of the above drawbacks, in this embodiment, a data processing method is provided, in which user historical behavior data of different categories are acquired, corresponding user behavior scores are obtained through calculation, and the obtained user behavior scores are subjected to a preset combination process, so that an accurate user behavior evaluation value can be obtained. According to the technical scheme, the accuracy of the user behavior characteristic data can be effectively improved, so that better service can be provided for the user, the opportunity of serving the user is increased, the service efficiency of the internet is improved, and the service quality of the internet is improved.

In an optional implementation manner of the embodiment, the user historical behavior data refers to behavior data of a certain user that can be acquired within a preset historical time, the behavioral data may include user transaction data, user collection data, user tagging data, user click data, user search data, user browsing data, and the like, wherein the user transaction data refers to data generated by a user performing ordering, purchasing, etc., and similarly, the user collection data refers to data generated by the user executing collection and other operations, the user tagging data refers to data generated by the user clicking favorite and executing star adding and other operations, the user click data refers to data generated by a user executing operations such as clicking, the user search data refers to data generated by the user executing operations such as searching and retrieving, and the user browsing data refers to data generated by the user executing operations such as browsing.

Wherein the behavior data may include user identification information (such as a user ID), behavior operation category information, behavior operation object information (such as a merchant ID), behavior operation sub-object information (such as a commodity ID), behavior operation price information, behavior occurrence time and the like for uniquely identifying the user identity, the specific content of the behavior data may differ according to the user behavior, for example, if the user a purchases a commodity with a price of 100 at the merchant a at 2019.1.1, the corresponding behavior data may be represented as { user ID, purchase, merchant ID, commodity ID, 100 yuan, 2019.1.1}, if the user a collects or marks the merchant a at 2019.1.1, the corresponding behavior data may be represented as { user ID, collection/mark, merchant ID, 2019.1.1}, if the merchant a clicks or browses the commodity a at 2019.1.1 or in the merchant a, then the corresponding behavior data may be represented as { user ID, click/browse, merchandise ID, merchant ID, 2019.1.1}, and if user a performed a search operation at 2019.1.1, then the corresponding behavior data may be represented as { user ID, search content, 2019.1.1 }.

The preset historical time can be set according to the requirements of practical application and the characteristics of user behavior data, and the specific value of the preset historical time is not particularly limited.

Considering that different user behaviors have different effects on acquiring behavior characteristics, for example, a ordering operation performed by the user a on the merchant a can better reflect the preference of the user a on the merchant a than a clicking operation performed by the merchant a. Therefore, in order to obtain more accurate user behavior feature information, the user historical behavior data needs to be divided into two different types of data for processing, and in an optional implementation manner of this embodiment, the user historical behavior data is divided into first historical behavior data embodied as explicit data and second historical behavior data embodied as implicit data, where the explicit data, that is, the first historical behavior data may include data capable of explicitly representing a user behavior feature, such as: user transaction data, user collection data, user tagging data, and the like; the implicit data, i.e. the second historical behavior data, may include data implicitly representing the behavior characteristics of the user, such as: user click data, user search data, and user browse data, among others. And subsequently, corresponding behavior scores can be respectively calculated according to the behavior data of different categories, and then the behavior scores are combined to obtain a final user behavior evaluation score.

In an optional implementation manner of this embodiment, the user behavior score is used to represent feature information of a user behavior, and specific content of the feature information is related to a behavior factor considered when calculating the user behavior score, for example, if the behavior factor is set to a user operation category of transaction, collection, tagging, clicking, searching, browsing, and the like, then the corresponding behavior score may represent an operation behavior characteristic of the user, and if the behavior factor is set to a commodity characteristic of a different merchant, then the corresponding behavior score may represent a selection preference characteristic of the user, and the like.

Considering that the user behavior has a certain relationship with the change of time, that is, the user behavior closest to the current time can more accurately reflect the behavior characteristics of the user, and compared with the user behavior farther from the current time, the user behavior farther from the current time has a lower contribution to the behavior characteristics of the user. Therefore, in an alternative implementation manner of the embodiment, when calculating the user behavior score, a time attenuation factor is added, that is, the user behavior score based on time attenuation refers to a user behavior score obtained by considering time attenuation, and the time attenuation refers to a characteristic that a value of a calculation result is reduced with the passage of time.

In an optional implementation manner of this embodiment, as shown in fig. 2, the step S102 of calculating a user behavior score based on time decay according to the user historical behavior data includes steps S201 to S203:

in step S201, a time attenuation factor is determined;

in step S202, calculating a time difference between a current time and a historical behavior occurrence time according to the historical behavior data of the user;

in step S203, a user behavior score based on the time decay is calculated based on the time decay factor and the time difference.

As mentioned above, there is a certain relationship between the user behavior and the change of time, that is, the user behavior closest to the current time can reflect the behavior characteristics of the user more accurately, and compared with the user behavior farther from the current time, the user behavior farther from the current time has a lower contribution to the behavior characteristics of the user. Therefore, a time-decaying factor is added when calculating the user behavior score. Specifically, in an optional implementation manner of this embodiment, when a user behavior score based on time decay is calculated according to the user historical behavior data, a time decay factor is first determined, where the time decay factor is used to characterize an influence of time decay on the calculation of the user behavior score; then calculating according to the historical behavior data of the user to obtain the time difference between the current time and the occurrence time of the historical behavior; and finally, calculating to obtain a user behavior score based on time attenuation based on the time attenuation factor and the time difference.

In an optional implementation manner of this embodiment, the time decay factor may be determined according to historical statistical data and data characteristics of the behavior data, such as a half-life characteristic, and may be a fixed value or a variable value, for example, if the half-life is set to 120 days, that is, after the user behavior score is added to the time decay factor calculation, 120 days are required to reach a half value, the time decay factor may be a fixed value 0.005776.

In an optional implementation manner of this embodiment, the step S203, that is, the step of calculating the user behavior score based on the time decay factor and the time difference, may be implemented as: taking a value obtained by taking the negative of the product of the time decay factor and the time difference as an index of a natural constant, and calculating to obtain a user behavior score based on time decay, namely calculating to obtain the user behavior score based on time decay based on the time decay factor and the time difference by using the following formula:

e^{-1*weight*deltaDay}

wherein, weight represents a time attenuation factor, deltaDay represents a time difference between the current time and the occurrence time of the historical behavior, and deltaDay is the current time-the occurrence time of the historical behavior.

In an optional implementation manner of this embodiment, as shown in fig. 3, the step S203 of calculating a user behavior score based on time decay based on the time decay factor and the time difference includes steps S301 to S303:

in step S301, one or more behavioral factors are determined;

in step S302, calculating a behavior score vector corresponding to a user behavior based on the time attenuation factor and the time difference, wherein the behavior score vector is composed of scores corresponding to the one or more behavior factors;

in step S303, a behavior score vector corresponding to a preset user behavior is combined to obtain a user behavior score.

Considering that the user behavior operation object may further include a plurality of sub-objects, for example, a plurality of commodities exist under a certain merchant, or a plurality of behavior factors exist in the user behavior operation object, for example, a service provided by a certain merchant has a plurality of categories, dishes provided by a certain merchant have a plurality of tastes, and the like, in an optional implementation manner of the embodiment, when the user behavior score based on the time decay is calculated based on the time decay factor and the time difference, one or more behavior factors are first determined; then based on the time attenuation factor and the time difference, calculating to obtain user behavior scores corresponding to the one or more behavior factors, and forming a behavior score vector corresponding to the user behavior; and finally, combining the behavior score vectors corresponding to the preset user behaviors to obtain the user behavior scores. The preset user behavior refers to user behavior of the same user for different behavior objects.

When the user behavior score is calculated by using the time attenuation-based user behavior score calculation method provided by the previous embodiment, the calculated behavior score of a certain user for a certain business is obtained, and when the business has a plurality of behavior factors, the calculated behavior score of the business can be used as a score corresponding to each behavior factor to form a corresponding behavior score vector.

Wherein the combining of the behavior score vectors corresponding to the preset user behavior to obtain the user behavior score may be implemented as: and adding the scores corresponding to the same behavior factor in the behavior score vectors corresponding to the preset user behaviors to obtain a combined behavior score vector, and taking the combined behavior score vector as the user behavior score.

For example, if the merchant a and the merchant B are merchants who provide different tastes of meals, and it is known that the merchant a can provide tastes, that is, the corresponding behavior factors include: [ "taste Z", "taste X" ], the taste that merchant B can provide, i.e. its corresponding behavioral factors include: [ "taste M", "taste X" ], the time decay factor is set to 0.005776, then for the user behavior data: { user a, purchase, merchant a, 2019.2.1} and { user a, purchase, merchant B, 2018.10.3}, according to the user behavior score calculation method provided in the previous embodiment, a behavior score vector corresponding to the behavior factors of user a and merchant a can be calculated as follows: the behavior score vector corresponding to the behavior factors of the user A and the merchant B can be calculated and obtained by the following steps: 0.5 for taste M and 0.5 for taste X. Combining the two behavior score vectors, and adding the scores corresponding to the same behavior factor to obtain the behavior score of the user A as follows: { 'taste Z': 1 ',' taste X ': 1.5', 'taste M': 0.5 }.

In an optional implementation manner of this embodiment, as shown in fig. 4, the step S103 of performing a combination process on the first behavior score and the second behavior score to obtain a user behavior score includes steps S401 to S402:

in step S401, a first combined weight of the first behavior score and a second combined weight of the second behavior score are determined;

in step S402, the first behavior score and the second behavior score are weighted and averaged according to the first combination weight and the second combination weight, so as to obtain a user behavior score.

As mentioned above, the explicit data and the implicit data have different effects on the acquisition of the user behavior feature, and therefore, in order to improve the accuracy of the user behavior feature data, in an optional implementation manner of this embodiment, different weights are first set for a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data, for example, a first combination weight is set for the first behavior score, and a second combination weight is set for the second behavior score, where the first combination weight is higher than the second combination weight; and then, according to the first combination weight and the second combination weight, carrying out weighted average on the first behavior score and the second behavior score to obtain more accurate user behavior score.

In an optional implementation manner of this embodiment, the step S103, that is, before the first behavior score and the second behavior score are combined to obtain the user behavior score, further includes a step of preprocessing the first behavior score and the second behavior score, that is, as shown in fig. 5, the method includes the following steps S501 to S504:

in step S501, obtaining user historical behavior data, where the user historical behavior data includes first historical behavior data and second historical behavior data;

in step S502, a user behavior score based on time decay is calculated according to the user historical behavior data, where the user behavior score includes a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data;

in step S503, preprocessing the first behavior score and the second behavior score;

in step S504, the first behavior score and the second behavior score are combined to obtain a user behavior score.

In order to avoid the influence of abnormal values in the user behavior data and make the score data more standardized, in an optional implementation manner of the embodiment, the first behavior score and the second behavior score are subjected to a preprocessing operation before being combined, wherein the preprocessing operation may include one or more of the following operations: denoising, normalizing, etc.

In an optional implementation manner of this embodiment, the preprocessing is normalization, and in this implementation manner, specifically, the step S503 may be implemented as:

The above implementation can be represented by the following formula:

wherein, x represents the score corresponding to the behavior factor in the behavior score, mean represents the mean value of the score corresponding to the behavior factor in the behavior score, and standard represents the standard deviation of the score corresponding to the behavior factor in the behavior score.

In an optional implementation manner of this embodiment, the method further includes a step of performing a preset operation according to the user behavior score, that is, as shown in fig. 6, the method includes the following steps S601 to S604:

in step S601, obtaining user historical behavior data, where the user historical behavior data includes first historical behavior data and second historical behavior data;

in step S602, calculating a user behavior score based on time decay according to the user historical behavior data, where the user behavior score includes a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data;

in step S603, performing a combination process on the first behavior score and the second behavior score to obtain a user behavior score;

in step S604, a preset operation is performed according to the user behavior score.

In an optional implementation manner of this embodiment, the preset operation may include one or more of the following operations: merchant, service, taste, etc. recommendation operations, statistical operations, etc.

When the preset operation is a recommendation operation, the step S604, that is, the step of performing the preset operation according to the user behavior score, may be implemented as:

ranking the user behavior scores;

and executing recommendation operation according to the sorting result.

In an optional implementation manner of this embodiment, when the user behavior scores are sorted, when the user behavior scores are a single numerical value, the user behavior scores are directly sorted; when the user behavior scores comprise scores corresponding to different behavior factors, the scores corresponding to the different behavior factors can be sorted, and the sum of the scores of the behavior factors of different behavior objects can also be sorted.

When the sorting is carried out, the sorting can be carried out according to the sequence of scores from large to small and also according to the sequence of scores from small to large.

In an optional implementation manner of this embodiment, when the recommendation operation is performed according to the sorting result, the child object of the behavior factor with the highest score may be recommended to the user according to the sorting result, the behavior object related to the behavior factor with the highest score may also be recommended, and the behavior object with the highest score sum of the behavior factors may also be recommended. By way of example above, assume that merchant a is able to provide tastes, i.e., its corresponding behavioral factors include: [ "taste Z", "taste X" ], the taste that merchant B can provide, i.e. its corresponding behavioral factors include: [ "taste M", "taste X" ], the behavior of the user a is divided into: { "taste Z": 1, "taste X": 1.5, "taste M": 0.5}, then if the scores corresponding to different behavior factors are sorted, the sorting results of different behavior factors can be obtained: the taste X is more than the taste Z is more than the taste M, and at the moment, dishes with the taste X can be recommended to the user A, and merchants capable of providing products with the taste X can also be recommended to the user A; if the sum of the behavior factor scores of different behavior objects is sorted, the sorting result of the behavior objects is obtained: and the merchant A is larger than the merchant B, and at the moment, the merchant A with a higher total score can be recommended to the user A.

The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods.

Fig. 7 shows a block diagram of a data processing apparatus according to an embodiment of the present disclosure, which may be implemented as part or all of an electronic device by software, hardware, or a combination of both. As shown in fig. 7, the data processing apparatus includes:

an obtaining module 701 configured to obtain user historical behavior data, where the user historical behavior data includes first historical behavior data and second historical behavior data;

a calculating module 702 configured to calculate a time decay-based user behavior score according to the user historical behavior data, wherein the user behavior score includes a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data;

a processing module 703 configured to perform a combination process on the first behavior score and the second behavior score to obtain a user behavior score.

In view of the above drawbacks, in this embodiment, a data processing apparatus is provided, which obtains different types of user historical behavior data, calculates a corresponding user behavior score, and performs a preset combination process on the obtained user behavior score to obtain an accurate user behavior evaluation value. According to the technical scheme, the accuracy of the user behavior characteristic data can be effectively improved, so that better service can be provided for the user, the opportunity of serving the user is increased, the service efficiency of the internet is improved, and the service quality of the internet is improved.

In an optional implementation manner of this embodiment, as shown in fig. 8, the calculating module 702 includes:

a first determination submodule 801 configured to determine a temporal attenuation factor;

a first calculating submodule 802 configured to calculate a time difference between a current time and a historical behavior occurrence time according to the user historical behavior data;

a second calculating sub-module 803 configured to calculate a user behavior score based on the time decay factor and the time difference.

As mentioned above, there is a certain relationship between the user behavior and the change of time, that is, the user behavior closest to the current time can reflect the behavior characteristics of the user more accurately, and compared with the user behavior farther from the current time, the user behavior farther from the current time has a lower contribution to the behavior characteristics of the user. Therefore, a time-decaying factor is added when calculating the user behavior score. Specifically, in an optional implementation manner of this embodiment, when the calculating module 702 calculates a user behavior score based on time decay according to the user historical behavior data, the first determining sub-module 801 first determines a time decay factor, where the time decay factor is used to characterize an influence of time decay on the calculation of the user behavior score; the first calculating submodule 802 calculates a time difference between the current time and the occurrence time of the historical behavior according to the historical behavior data of the user; the second calculation sub-module 803 calculates a user behavior score based on the time decay factor and the time difference.

In an optional implementation manner of this embodiment, the second calculating sub-module 803 may be configured to: taking a value obtained by taking the negative of the product of the time decay factor and the time difference as an index of a natural constant, and calculating to obtain a user behavior score based on time decay, namely calculating to obtain the user behavior score based on time decay based on the time decay factor and the time difference by using the following formula:

e^{-1*weight*deltaDay}，

In an optional implementation manner of this embodiment, as shown in fig. 9, the second computing sub-module 803 includes:

a second determining submodule 901 configured to determine one or more behavioral factors;

a third computing submodule 902 configured to compute a behavior score vector corresponding to the user behavior based on the time decay factor and the time difference, wherein the behavior score vector is composed of scores corresponding to the one or more behavior factors;

and the combining submodule 903 is configured to combine the behavior score vectors corresponding to the preset user behaviors to obtain the user behavior scores.

Considering that the user behavior operation object may further include a plurality of sub-objects, for example, a plurality of commodities exist under a certain merchant, or a plurality of behavior factors exist in the user behavior operation object, for example, a service provided by a certain merchant has a plurality of categories, dishes provided by a certain merchant have a plurality of tastes, etc., in an optional implementation manner of the present embodiment, when the second calculating sub-module 803 calculates the user behavior score based on the time decay factor and the time difference, the second determining sub-module 901 first determines one or more behavior factors; the third computation submodule 902 calculates, based on the time decay factor and the time difference, a user behavior score corresponding to the one or more behavior factors to form a behavior score vector corresponding to the user behavior; the combining submodule 903 combines the behavior score vectors corresponding to the preset user behavior to obtain the user behavior score. The preset user behavior refers to user behavior of the same user for different behavior objects.

Wherein the combining sub-module 903 may be configured to: and adding the scores corresponding to the same behavior factor in the behavior score vectors corresponding to the preset user behaviors to obtain a combined behavior score vector, and taking the combined behavior score vector as the user behavior score.

In an optional implementation manner of this embodiment, as shown in fig. 10, the processing module 703 includes:

a third determination submodule 1001 configured to determine a first combined weight of the first behavior score and a second combined weight of the second behavior score;

a weighted average sub-module 1002, configured to perform a weighted average on the first behavior score and the second behavior score according to the first combination weight and the second combination weight, so as to obtain a user behavior score.

As mentioned above, the explicit data and the implicit data have different effects on the acquisition of the user behavior feature, and therefore, in order to improve the accuracy of the user behavior feature data, in an optional implementation manner of this embodiment, the third determining sub-module 1001 sets different weights for a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data, for example, sets a first combination weight for the first behavior score and sets a second combination weight for the second behavior score, where the first combination weight is higher than the second combination weight; the weighted average sub-module 1002 performs weighted average on the first behavior score and the second behavior score according to the first combination weight and the second combination weight, so as to obtain a more accurate user behavior score.

In an optional implementation manner of this embodiment, before the processing module 703, a part for preprocessing the first behavior score and the second behavior score is further included, that is, as shown in fig. 11, the apparatus includes:

an obtaining module 1101 configured to obtain user historical behavior data, wherein the user historical behavior data includes first historical behavior data and second historical behavior data;

a calculating module 1102 configured to calculate a time decay-based user behavior score according to the user historical behavior data, wherein the user behavior score includes a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data;

a pre-processing module 1103 configured to pre-process the first behavior score and the second behavior score;

and the processing module 1104 is configured to perform combined processing on the first behavior score and the second behavior score to obtain a user behavior score.

In order to avoid the influence of abnormal values in the user behavior data and make the score data more standardized, in an optional implementation manner of the present embodiment, the preprocessing module 1103 performs a preprocessing operation on the first behavior score and the second behavior score before combining them, where the preprocessing may include one or more of the following operations: denoising, normalizing, etc.

In an optional implementation manner of this embodiment, the preprocessing is normalization, and in this implementation manner, specifically, the preprocessing module 1103 may be configured to:

The above implementation can be represented by the following formula:

In an optional implementation manner of this embodiment, the apparatus further includes a part that performs a preset operation according to the user behavior score, that is, as shown in fig. 12, the apparatus includes:

an obtaining module 1201 configured to obtain user historical behavior data, wherein the user historical behavior data includes first historical behavior data and second historical behavior data;

a calculating module 1202 configured to calculate a time decay-based user behavior score according to the user historical behavior data, wherein the user behavior score includes a first behavior score calculated according to the first historical behavior data and a second behavior score calculated according to the second historical behavior data;

a processing module 1203 configured to perform a combination process on the first behavior score and the second behavior score to obtain a user behavior score;

an executing module 1204 configured to execute a preset operation according to the user behavior score.

When the preset operation is a recommendation operation, the execution module 1204 may be configured to:

ranking the user behavior scores;

and executing recommendation operation according to the sorting result.

The present disclosure also discloses an electronic device, fig. 13 shows a block diagram of the electronic device according to an embodiment of the present disclosure, as shown in fig. 13, the electronic device 1300 includes a memory 1301 and a processor 1302; wherein,

the memory 1301 is used to store one or more computer instructions, which are executed by the processor 1302 to implement the above-described method steps.

As shown in fig. 14, the computer system 1400 includes a Central Processing Unit (CPU)1401 which can execute various processes in the above-described embodiments according to a program stored in a Read Only Memory (ROM)1402 or a program loaded from a storage portion 1408 into a Random Access Memory (RAM) 1403. In the RAM1403, various programs and data necessary for the operation of the system 1400 are also stored. The CPU1401, ROM1402, and RAM1403 are connected to each other via a bus 1404. An input/output (I/O) interface 1405 is also connected to bus 1404.

The following components are connected to the I/O interface 1405: an input portion 1406 including a keyboard, a mouse, and the like; an output portion 1407 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker and the like; a storage portion 1408 including a hard disk and the like; and a communication portion 1409 including a network interface card such as a LAN card, a modem, or the like. The communication section 1409 performs communication processing via a network such as the internet. The driver 1410 is also connected to the I/O interface 1405 as necessary. A removable medium 1411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 1410 as necessary, so that a computer program read out therefrom is installed into the storage section 1408 as necessary.

In particular, the above described methods may be implemented as computer software programs, according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a medium readable thereby, the computer program comprising program code for performing the above-described data processing method. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 1409 and/or installed from the removable media 1411.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams may represent a module, a program segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present disclosure may be implemented by software or hardware. The units or modules described may also be provided in a processor, and the names of the units or modules do not in some cases constitute a limitation of the units or modules themselves.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be the computer-readable storage medium included in the apparatus in the above-described embodiment; or it may be a separate computer readable storage medium not incorporated into the device. The computer readable storage medium stores one or more programs for use by one or more processors in performing the methods described in the present disclosure.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Claims

1. A data processing method, comprising:

2. The method of claim 1, wherein the first historical behavior data is explicit data comprising one or more of: user transaction data, user collection data and user tagging data; and/or the presence of a gas in the gas,

3. The method according to claim 1 or 2, wherein calculating a time decay-based user behavior score from the user historical behavior data comprises:

determining a time attenuation factor;

4. The method according to claim 3, wherein the calculating a time decay based user behavior score based on the time decay factor and the time difference is implemented as:

5. A data processing apparatus, comprising:

6. The apparatus of claim 5, wherein the first historical behavior data is explicit data comprising one or more of: user transaction data, user collection data and user tagging data; and/or the presence of a gas in the gas,

7. The apparatus of claim 5 or 6, wherein the computing module comprises:

8. The apparatus of claim 7, wherein the second computation submodule is configured to:

9. An electronic device comprising a memory and a processor; wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method steps of any of claims 1-4.

10. A computer-readable storage medium having stored thereon computer instructions, characterized in that the computer instructions, when executed by a processor, carry out the method steps of any of claims 1-4.