CN116070007A

CN116070007A - Recommendation method, electronic device and storage medium

Info

Publication number: CN116070007A
Application number: CN202111276088.6A
Authority: CN
Inventors: 刘辉
Original assignee: Petal Cloud Technology Co Ltd
Current assignee: Petal Cloud Technology Co Ltd
Priority date: 2021-10-29
Filing date: 2021-10-29
Publication date: 2023-05-05
Also published as: WO2023071404A1

Abstract

The application provides a recommendation method, electronic equipment and a storage medium, and relates to the field of data processing. The method can match the characteristic information corresponding to the historical behavior information related to the first user in the second service with the characteristic information corresponding to the historical behavior information of one or more other users in the second service, determine the user grouping result of the first user in the second service, and based on the user grouping result of the first user in the second service, conduct personalized recommendation to the first user in the first service. The method can reduce the grouping result of the users, effectively improve the accuracy of personalized recommendation, and recommend more interesting recommendation results for the first user.

Description

Recommendation method, electronic device and storage medium

Technical Field

The present disclosure relates to the field of data processing, and in particular, to a recommendation method, an electronic device, and a storage medium.

Background

Personalized recommendation generally refers to recommending information or goods possibly of interest to a user by analyzing and mining historical behavior information of the user and finding personalized requirements and interest characteristics of the user. Personalized recommendations may be applied to a variety of aspects of e-commerce systems, social networks, advertisement recommendations, search engines, and the like.

Taking the application of personalized recommendation in a video platform as an example, the video platform can also comprise a recommendation system which is specially used for personalized recommendation, and the recommendation system can discover which type of video is more interested by a user by analyzing and mining historical videos watched by the user and recommend the video which is more interested by the user to the user. Alternatively, the recommendation system may also evaluate the similarity between the user and other users and recommend videos, etc., to the user that are of interest to other users similar to the user based on a user collaborative filtering (user collaboration filter, userCF) algorithm. For example, movies that user a once watched multiple times are all movies of the science fiction class, such as: science fiction movie 1, science fiction movie 2, etc., the recommendation system finds through data analysis that user B has also watched science fiction movie 1, science fiction movie 2 multiple times, and user B has also watched science fiction movie 3 multiple times, the recommendation system can recommend science fiction movie 3 to user a.

It can be seen that when personalized recommendation is performed to the user, the user needs to be recommended based on the historical behavior information of the user depending on the historical behavior information of the user. However, personalized recommendations often face incremental problems, such as: personalized recommendations for newly added users. The newly added user does not have historical behavior information for the recommendation system of personalized recommendation, and the recommendation system cannot conduct personalized recommendation to the user depending on the historical behavior information of the user.

Disclosure of Invention

The recommendation method, the electronic equipment and the storage medium can reduce the grouping result of the users, effectively improve the accuracy of personalized recommendation and recommend more interesting recommendation results for the users.

In a first aspect, the present application provides a recommendation method, the method comprising: the method comprises the steps that first equipment sends user information of a first user to a server; the server sends recommendation information to the first device; the recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

According to the method, the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service are matched, the user grouping result of the first user in the second service is determined, personalized recommendation is carried out on the first user in the first service based on the user grouping result of the first user in the second service, the user grouping result of the first user can be reduced, the accuracy of personalized recommendation is effectively improved, and more interesting recommendation results are recommended for the first user.

In one possible implementation, the first device includes a first service and a second service; the method further comprises the steps of: the first device sends feature information corresponding to the historical behavior information related to the first user in the second service to the server.

In this manner, both the first service and the second service may be provided by the first device.

Illustratively, the historical behavior information associated with the first user in the second service may include: historical behavior information corresponding to the first user in the second service, or historical behavior information corresponding to other accounts (family public accounts or accounts of other users) associated with the first user's account in the second service.

In another possible implementation, the first device includes a first service and the second device includes a second service; the method further comprises the steps of: and the second equipment sends the characteristic information corresponding to the historical behavior information related to the first user in the second service to the server.

In this manner, the first service may be provided by the first device and the second service may be provided by the second device.

The first device and the second device may be two terminal devices in a multi-device collaboration scenario, for example.

In a possible implementation manner, the first device sends user information of the first user to a server, including: the first device sends user information of the first user to the server through the third device. The server sends recommendation information to a first device, including: the server sends the recommendation information to the first device through the third device.

Optionally, in the method, the first device may be a device with fewer device resources and incapable of independent networking and/or man-machine interaction, and the third device may be a device with richer device resources and capable of independent networking and man-machine interaction.

Optionally, the sending, by the first device, feature information corresponding to the historical behavior information related to the first user in the second service to the server may include: and the first equipment sends the characteristic information corresponding to the historical behavior information related to the first user in the second service to the server through the third equipment.

Optionally, the sending, by the second device, feature information corresponding to the historical behavior information related to the first user in the second service to the server may include: and the second equipment sends the characteristic information corresponding to the historical behavior information related to the first user in the second service to the server through the fourth equipment.

The second device may be a device with fewer device resources and cannot be independently networked and/or man-machine interacted, and the fourth device may be a device with richer device resources and can be independently networked and man-machine interacted.

In a possible implementation manner, the user information of the first user includes: identification information of the first user, and/or identification information of the first user group.

For example, the identification information of the first user may be a user account of the first user.

Optionally, the method further comprises: the server determines a first user group according to characteristic information corresponding to the historical behavior information related to the first user in the second service and characteristic information corresponding to the historical behavior information of one or more other users in the second service; the server sends identification information of the first user group to the first device.

The historical behavior information of other users in the first user group in the second service has similarity to the historical behavior information of the second service related to the first user.

In a possible implementation manner, feature information corresponding to historical behavior information related to the first user in the second service includes: hash values corresponding to historical behavior information related to the first user in the second service. Characteristic information corresponding to historical behavior information of one or more other users in the second service comprises: hash values corresponding to historical behavior information of other one or more users in the second service.

Optionally, the hash value corresponding to the historical behavior information related to the first user in the second service is obtained by performing hash calculation on a first coding result by adopting a first hash algorithm, and the first coding result is obtained by performing coding processing on the historical behavior information related to the first user in the second service by adopting a first coding mode. The hash value corresponding to the historical behavior information of the other one or more users in the second service is obtained by carrying out hash calculation on a second coding result by adopting a first hash algorithm, and the second coding result is obtained by carrying out coding processing on the historical behavior information of the other one or more users in the second service by adopting a first coding mode.

Illustratively, the first hash algorithm may comprise: a locality sensitive hash (locality sensitive hashing, LSH) algorithm, a minimum hash (min-hash) algorithm using jaccard (jaccard) to measure data similarity, a P-stable hash (P-stable hash) algorithm using euclidean distance to measure data similarity, simhash algorithm, etc.

Optionally, the first hash algorithm has a characteristic of maintaining similarity of hash values after performing hash calculation on the data to be hashed.

Illustratively, the first encoding mode may include: single-hot (one-hot) coding, index (index) coding (dictionary-based coding), multiple-hot (multiple-hot) coding, etc.

Optionally, when the first coding mode is adopted to code the historical behavior information, the coding results (such as the first coding result and the second coding result) corresponding to different historical behavior information are unique.

In a possible implementation manner, the first device sends user information of the first user to a server, including: when detecting that the first user uses the first service for the first time, the first device transmits user information of the first user to the server.

In this manner, the personalized recommendation to the first user when the first user uses the first service for the first time may be referred to as performing a user cold start to the first user, and the recommendation accuracy when the user cold start is performed to the first user may be improved by using the method, and the effect of the user cold start may be better.

In a second aspect, the present application provides a recommendation system, which may implement the recommendation method according to the first aspect and any one of the possible implementation manners of the first aspect.

For example, the recommendation system may include: a first device and a server. The first device may be configured to send user information of the first user to the server. The server may be configured to send the recommendation information to the first device. The recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In one possible implementation, the first device includes a first service and a second service; the first device is further configured to send, to the server, feature information corresponding to the historical behavior information related to the first user in the second service.

In another possible implementation, the recommendation system further includes a second device. The first device includes a first service and the second device includes a second service. The second device may be configured to send, to the server, feature information corresponding to the historical behavior information associated with the first user in the second service.

In a possible implementation manner, the recommendation system further includes a third device, and the first device is specifically configured to send user information of the first user to the server through the third device. The server is specifically configured to send the recommendation information to the first device through the third device.

Optionally, the server is further configured to determine the first user group according to feature information corresponding to the historical behavior information related to the first user in the second service and feature information corresponding to the historical behavior information of one or more other users in the second service; and transmitting the identification information of the first user group to the first device.

In a possible implementation manner, the first device is specifically configured to send user information of the first user to the server when detecting that the first user uses the first service for the first time.

Similarly, the recommendation system may implement functions corresponding to all steps of the recommendation method as described in the first aspect and any possible implementation manner of the first aspect, which are not described in detail herein.

The advantages of the second aspect may be referred to in the first aspect, and will not be described herein.

In a third aspect, the present application provides a recommendation method, which may be applied to a first device. The method comprises the following steps: transmitting user information of a first user to a server; receiving recommendation information from a server; the recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

The method can reduce the result of user grouping on the first user, effectively improve the accuracy of personalized recommendation and recommend more interesting recommendation results for the first user.

In one possible implementation, the first device includes a first service and a second service; the method further comprises the steps of: and sending characteristic information corresponding to the historical behavior information related to the first user in the second service to the server.

In another possible implementation, the first device includes a first service and the second device includes a second service.

In a possible implementation manner, the sending, to a server, user information of the first user includes: and sending the user information of the first user to the server through the third device. The receiving recommendation information from the server includes: and receiving recommendation information from the server through the third device.

Optionally, the sending, to the server, feature information corresponding to the historical behavior information related to the first user in the second service may include: and sending characteristic information corresponding to the historical behavior information related to the first user in the second service to the server through the third equipment.

Optionally, the method further comprises: receiving identification information of a first user group sent by a server; the first user group is determined by the server according to the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In a possible implementation manner, the sending, to a server, user information of the first user includes: and when the first user is detected to use the first service for the first time, user information of the first user is sent to the server.

The advantageous effects of the partial implementation manner of the third aspect may be referred to in the first aspect and are not repeated.

In a fourth aspect, the present application provides a recommendation apparatus, which may be applied to an electronic device (such as the first device), so that the electronic device implements the recommendation method according to any one of the third aspect and the possible implementation manners of the third aspect. The functions of the device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software comprises one or more modules or units corresponding to the steps in the recommended method according to the third aspect and any possible implementation manner of the third aspect.

For example, the apparatus may include: a transmitting unit, a receiving unit, etc. The sending unit may be configured to send user information of the first user to the server; the receiving unit may be configured to receive recommendation information from a server; the recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In one possible implementation, the first device includes a first service and a second service; and the sending unit is also used for sending the characteristic information corresponding to the historical behavior information related to the first user in the second service to the server.

In a possible implementation manner, the sending unit is specifically configured to send, through the third device, user information of the first user to the server. And the receiving unit is specifically used for receiving the recommendation information from the server through the third device.

Optionally, the sending unit is specifically configured to send, to the server through the third device, feature information corresponding to the historical behavior information related to the first user in the second service.

Optionally, the receiving unit is further configured to receive identification information of the first user group sent by the server; the first user group is determined by the server according to the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In a possible implementation manner, the sending unit is specifically configured to send user information of the first user to the server when it is detected that the first user uses the first service for the first time.

Similarly, the apparatus may implement functions corresponding to all steps of the recommendation method as described in any one of the third aspect and any one of the possible implementation manners of the third aspect, which are not described in detail herein.

In a fifth aspect, the present application provides an electronic device, e.g. the electronic device may be the first device described above. An electronic device includes: a processor, a memory for storing processor-executable instructions; the processor is configured to execute the instructions, to cause the electronic device to implement the recommendation method as described in any one of the possible implementations of the third aspect and the third aspect.

In a sixth aspect, the present application provides a computer-readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by an electronic device, cause the electronic device to implement the recommendation method as described in any one of the possible implementations of the third aspect and the third aspect.

In a seventh aspect, the present application provides a computer program product comprising computer readable code, or a non-transitory computer readable storage medium carrying computer readable code, which when run in an electronic device, causes a processor in the electronic device to implement the recommendation method according to any one of the possible implementations of the third aspect and the third aspect.

The advantages of the fourth to seventh aspects are described with reference to the third aspect, and are not described herein.

In an eighth aspect, the present application provides a recommendation method, which may be applied to a server. The method comprises the following steps: receiving user information of a first user sent by first equipment; and sending the recommendation information to the first device. The recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In one possible implementation, the first device includes a first service and a second service; the method further comprises the steps of: and receiving characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the first equipment.

In another possible implementation, the first device includes a first service and the second device includes a second service; the method further comprises the steps of: and receiving characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the second equipment.

In a possible implementation manner, the receiving the user information from the first user sent by the first device includes: user information from a first user transmitted by a first device is received by a third device. The sending the recommendation information to the first device includes: and sending the recommendation information to the first device through the third device.

Optionally, the receiving, from the second service sent by the first device, feature information corresponding to the historical behavior information related to the first user may include: and receiving characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the first device through the third device.

Optionally, the receiving, from the second service sent by the second device, feature information corresponding to the historical behavior information related to the first user may include: and receiving characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the second device through the fourth device.

Optionally, the method further comprises: determining a first user group according to characteristic information corresponding to the historical behavior information related to the first user in the second service and characteristic information corresponding to the historical behavior information of one or more other users in the second service; identification information of the first user group is sent to the first device.

In one possible implementation, the first user is a first use of the first service.

The advantageous effects of some implementation manners in the eighth aspect may be described with reference to the first aspect, and are not repeated.

In a ninth aspect, the present application provides a recommendation apparatus, which may be applied to an electronic device (such as a server), so that the electronic device implements the recommendation method according to any one of the possible implementation manners of the eighth aspect and the eighth aspect. The functions of the device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software comprises one or more modules or units corresponding to the steps in the recommendation method according to any one of the possible implementation manners of the eighth aspect and the eighth aspect.

For example, the apparatus may include: a receiving unit and a transmitting unit. The receiving unit may be configured to receive user information of a first user transmitted from a first device; the transmitting unit may be configured to transmit the recommendation information to the first device. The recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In one possible implementation, the first device includes a first service and a second service; and the receiving unit is also used for receiving the characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the first equipment.

In another possible implementation, the first device includes a first service and the second device includes a second service; and the receiving unit is also used for receiving the characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the second equipment.

In a possible implementation manner, the receiving unit is specifically configured to receive, by the third device, user information from the first user sent by the first device. And the sending unit is specifically used for sending the recommendation information to the first device through the third device.

Optionally, the receiving unit is specifically configured to receive, by using the third device, feature information corresponding to the historical behavior information related to the first user in the second service sent by the first device.

Optionally, the receiving unit is specifically configured to receive, by using the fourth device, feature information corresponding to the historical behavior information related to the first user in the second service sent by the second device.

Optionally, the apparatus further comprises: and a processing unit. The processing unit may be configured to determine the first user group according to feature information corresponding to the historical behavior information related to the first user in the second service and feature information corresponding to the historical behavior information of one or more other users in the second service. And the sending unit is also used for sending the identification information of the first user group to the first equipment.

Similarly, the apparatus may cooperate with the functions corresponding to all the steps of the recommendation method described in the eighth aspect and any possible implementation manner of the eighth aspect, which are not described in detail herein.

In a tenth aspect, the present application provides an electronic device, e.g. the electronic device may be a server as described above. An electronic device includes: a processor, a memory for storing processor-executable instructions; the processor is configured to execute the instructions to cause the electronic device to implement the recommendation method as described in any one of the possible implementations of the eighth aspect and the eighth aspect.

In an eleventh aspect, the present application provides a computer-readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by an electronic device, cause the electronic device to implement the recommendation method as described in any one of the possible implementations of the eighth and eighth aspects.

In a twelfth aspect, the present application provides a computer program product comprising computer readable code, or a non-transitory computer readable storage medium carrying computer readable code, which when run in an electronic device, causes a processor in the electronic device to implement the recommendation method according to any one of the possible implementations of the eighth and eighth aspects.

The advantageous effects of the ninth to twelfth aspects may be referred to as the eighth aspect, and are not described herein.

Alternatively, the servers described in the first to twelfth aspects may be a server cluster or a cloud server, or the servers may be separated into two servers, such as: the recommendation server and the user portrait server.

It should be appreciated that the description of technical features, aspects, benefits or similar language in this application does not imply that all of the features and advantages may be realized with any single embodiment. Conversely, it should be understood that the description of features or advantages is intended to include, in at least one embodiment, the particular features, aspects, or advantages. Therefore, the description of technical features, technical solutions or advantageous effects in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and advantageous effects described in the present embodiment may also be combined in any appropriate manner. Those of skill in the art will appreciate that an embodiment may be implemented without one or more particular features, aspects, or benefits of a particular embodiment. In other embodiments, additional features and advantages may be recognized in certain embodiments that may not be present in all embodiments.

Drawings

Fig. 1 is a schematic diagram of a recommendation system according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a terminal device 110 according to an embodiment of the present application;

fig. 3 is a schematic flow chart of a recommendation method provided in an embodiment of the present application;

FIG. 4 is another flow chart of the recommendation method according to the embodiment of the present application;

FIG. 5 is a schematic flow chart of another embodiment of the recommendation method;

fig. 6 is a schematic diagram of an application scenario provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a recommending apparatus according to an embodiment of the present application;

fig. 8 is another schematic structural diagram of a recommending apparatus according to an embodiment of the present application.

Detailed Description

The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in the specification and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include, for example, "one or more" such forms of expression, unless the context clearly indicates to the contrary. It should also be understood that in the various embodiments herein below, "at least one", "one or more" means one or more than two (including two). The character "/" generally indicates that the context-dependent object is an "or" relationship.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise. The term "coupled" includes both direct and indirect connections, unless stated otherwise.

The terms "first" and "second" are used below for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature.

In the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

For example, taking the application of personalized recommendation in an e-commerce platform as an example, the e-commerce platform may include a recommendation system dedicated to personalized recommendation, which may discover which items the user is more interested in and recommend items of more interest to the user by analyzing and mining the user's historical shopping behavior.

For another example, taking the application of personalized recommendation in a video platform as an example, the video platform may also include a recommendation system dedicated to personalized recommendation, which may discover what type of video is more interesting to the user by analyzing and mining historical videos watched by the user, and recommend videos of more interest to the user. Alternatively, the recommendation system may also evaluate the similarity between the user and other users and recommend videos, etc., to the user that are of interest to other users similar to the user based on a user collaborative filtering (user collaboration filter, userCF) algorithm. For example, movies that user a once watched multiple times are all movies of the science fiction class, such as: science fiction movie 1, science fiction movie 2, etc., the recommendation system finds through data analysis that user B has also watched science fiction movie 1, science fiction movie 2 multiple times, and user B has also watched science fiction movie 3 multiple times, the recommendation system can recommend science fiction movie 3 to user a.

For example, taking the application of personalized recommendation in the e-commerce platform as an example, for the e-commerce platform, when a new user is registered and logged in to the e-commerce platform, the new user is a new user. The historical shopping behavior of the new user is not recorded in the e-commerce platform, and at this time, the recommendation system of the e-commerce platform cannot conduct personalized recommendation of commodities to the user according to the historical shopping behavior of the user.

In personalized recommendation, how a recommendation system performs reasonable personalized recommendation for a newly added user without historical behavior information is generally called "user cold start". For example, the recommendation system can adopt some strategies of 'user cold start', perform personalized recommendation to the user, accumulate and collect historical behavior information of the user in the process of using services (such as e-commerce services provided by an e-commerce platform, video watching services provided by a video platform and the like) by the user, and complete recommendation in the mode of analyzing and mining the historical behavior information of the user to perform personalized recommendation after collecting a certain amount of the historical behavior information of the user. In the process of accumulating and collecting the historical behavior information of the user, the process of accumulating the historical behavior information of the user from 0 to 1 (namely from none to none) is a cold start process.

At present, the common strategy of "user cold start" is: the recommender system gathers some known user information of the user, such as: device information, device location, etc. of a device used by the user; with this known user information, the recommendation system may group users and then the recommendation system may personalize the same grouped users with a UserCF algorithm (or co-recommendation algorithm).

For example, taking the application of personalized recommendation in the e-commerce platform as an example, for a certain newly added user in the e-commerce platform, the recommendation system of the e-commerce platform may collect device information and device positions of a mobile phone used by the newly added user, where, for example, it is assumed that the device information of the mobile phone used by the newly added user includes: the brand of the mobile phone is brand P, and the position of the device is X city. Then, the recommendation system may group the newly added user with other users in the e-commerce platform according to the device information and the device position of the mobile phone used by the newly added user, for example: the recommender system may attribute the newly added user to the "brand P + X market" crowd. The recommendation system may then recommend to the newly added user, based on UserCF algorithms, items of interest to other users in the "brand p+x market" population.

However, the current "user cold start" strategy has limited available known user information, and the user clusters are too large, so that the effect of personalized recommendation is general. Such as: the user may not be interested in the recommendation results of the personalized recommendation.

The embodiment of the application provides a recommendation method which can be suitable for a scene of personalized recommendation in a first service (the service can also be called as a business, a field and the like). For example, the first service may include a function of performing personalized recommendation to a user, and the recommendation method provided in the embodiment of the present application may be applied to the function of performing personalized recommendation to a user in the first service, where, when personalized recommendation to a new user in the first service is required, knowledge migration is performed on the new user in the first service by using historical behavior information of the new user in the second service, a user grouping result of the new user in the second service is determined, and collaborative recommendation is performed on the new user in the first service based on the user grouping result of the new user in the second service, so as to implement cold start of the user of the new user in the first service. Wherein the first service and the second service are different.

The method can reduce the grouping result of the users, effectively improve the accuracy of personalized recommendation, recommend more interesting recommendation results for newly added users, and enable the cold starting effect of the users to be better.

Illustratively, the function of making a personalized recommendation to the user included in the first service may be referred to as "guessing you like", "related recommendation", "personalized recommendation", "user subscribes to personalized recommendation", "search intention recognition", etc., and the name of the function of personalized recommendation is not limited herein.

In some embodiments, the first service may refer to a single service, for example, a search service (e.g., a service that the search platform may provide search information to a user through a browser or other application), an information flow service (e.g., a service that the browser may provide news, information, etc. to a user through an information flow service), an e-commerce service (e.g., a service that the e-commerce platform may provide goods to a user through some application (App), a music service that the music platform provides to a user through some application (e.g., listening to songs), a video service that the video platform provides to a user through some application (e.g., watching movies or short videos), a reading service that the reading platform provides to a user through some application (e.g., e-book reading), etc. Similar to the first service, the second service may also include the aforementioned search service, information flow service, e-commerce service, music service, video service, reading service, etc., but the second service is different from the first service. Such as: the first service is an information flow service and the second service is a search service.

For example, assume that a browser is installed on a mobile phone of user 1, and services provided in the browser include: search services and information streaming services. User 1 has previously used the search service and has more historical search behavior information (e.g., search terms, clicking on a search results page, etc.), but user 1 has not used the traffic service (i.e., has not read the traffic). For the information flow service, when the user 1 uses the information flow service for the first time, the user 1 is a new user. However, since the user 1 uses the information flow service for the first time, the personalized recommendation system related to the information flow service does not know the interests and preferences of the user, and cannot recommend according to the historical behavior information of the user 1 in the information flow service. The recommendation method provided by the embodiment of the application can utilize the historical behavior information of the user 1 in the search service to carry out knowledge migration, determine the user grouping result of the user 1 in the search service, and then recommend the information streams interested by other users in the same grouping to the user 1 based on the user grouping result of the user 1 in the search service, thereby solving the problem of cold start of the user 1 when the information stream service is used for the first time.

Optionally, the second service may include one or more, and is not limited in this application. For example, the first service is a streaming service, and the second service may include a search service, a reading service, a video service, and the like. In addition, the examples of the first service and the second service are only some examples, and the specific types of the first service and the second service are not limited in the present application.

In other embodiments, the first service may also refer broadly to a service provided by an application, and not to a single service (e.g., the streaming service, the search service, etc.), and the second service may refer to a service provided by another application. For example, the first service may be a service provided by a browser, and may specifically include a plurality of services such as a search service, an information flow service, a video service, and the like; the second service may be a service provided by a reading App, and may specifically include an electronic book reading service. The application providing the first service and the application providing the second service are different, and the first service and the second service may be considered to be different.

For example, it is assumed that a browser a and a short video application B are installed on a mobile phone of the user 1, where the browser a may provide multiple services such as a search service, an information flow service, a reading service, a video service, and the like for the user 1, and the short video application B may provide a short video browsing service for the user 1. User 1 has previously used the service provided by browser a (i.e., the second service), and there is more historical behavior information in browser a (e.g., used the search service, read the information stream, etc.), but user 1 has not used the service provided by short video application B (i.e., the first service). For the service provided by the short video application B, when the user 1 uses the service provided by the short video application B for the first time, the user 1 is a new user. However, since the user 1 uses the service provided by the short video application B for the first time, the personalized recommendation system related to the service provided by the short video application B does not know the interests and preferences of the user, and cannot recommend according to the historical behavior information of the user 1 in the service provided by the short video application B. The recommendation method provided by the embodiment of the invention can utilize the historical behavior information of the user 1 in the service provided by the browser A to carry out knowledge migration, determine the user grouping result of the user 1 in the service provided by the browser A, and then recommend the short videos interested by other users in the same grouping to the user 1 based on the user grouping result of the user 1 in the service provided by the browser A, thereby solving the problem of cold start of the user 1 when the user 1 uses the service provided by the short video application B for the first time.

Alternatively, the second service may comprise a service provided by one or more applications, i.e., the second service may comprise one or more, without limitation. For example, the first service may be a service provided by application a, and the second service may include a service provided by application B, a service provided by application C, and so on.

It should be noted that, in the embodiment of the present application, the relationship between the first service and the second service is not limited. In some possible embodiments, the first service and the second service may be two services of different types (e.g., a search service and an information flow service) as described in the foregoing embodiments, or services provided by different applications.

In other possible embodiments, the first service and the second service may be the same type, but two services with different service channels. For example, the first service and the second service are both search services, but the first service provides search services using the search engine 1 and the second service provides services using the search engine 2. As another example, the first service and the second service are both video services, but the first service is a video service provided by the video platform 1, and the second service is a video service provided by the video platform 2, and so on.

In still other possible embodiments, the first service and the second service may also be two different services provided by the same application (e.g., a search service and a streaming service provided by a browser), or the first service and the second service may be two different services provided by the same service provider (e.g., a reading service and a streaming service provided by service provider a).

In some possible embodiments, for a user (e.g., user 1), user 1 may have the same user account, such as account 1, in the first service and the second service. The historical behavior information of the user 1 in the second service may refer to: and the account number 1 corresponds to the historical behavior information in the second service, namely the user 1 uses the second service through the account number 1. In the recommendation method provided in the embodiment of the present application, knowledge migration is performed by using historical behavior information corresponding to the user 1 in the second service, a user grouping result of the user 1 in the second service is determined, and collaborative recommendation is performed to the user 1 in the first service based on the user grouping result of the user 1 in the second service, which may include: and carrying out knowledge migration by utilizing historical behavior information corresponding to the account 1 in the second service, determining a user grouping result of the account 1 in the second service, and carrying out collaborative recommendation on the account 1 in the first service based on the user grouping result of the account 1 in the second service.

In other possible embodiments, for a user (e.g., user 1), user 1 may have different user accounts in a first service and a second service, user 1 having account 1 in the first service and account 2 in the second service. The historical behavior information of the user 1 in the second service may refer to: and the account number 2 corresponds to the historical behavior information in the second service, namely the user 1 uses the second service through the account number 2. In the recommendation method provided in the embodiment of the present application, knowledge migration is performed by using historical behavior information corresponding to the user 1 in the second service, a user grouping result of the user 1 in the second service is determined, and collaborative recommendation is performed to the user 1 in the first service based on the user grouping result of the user 1 in the second service, which may include: and carrying out knowledge migration by utilizing the historical behavior information corresponding to the account number 2 in the second service, determining a user grouping result of the account number 2 in the second service, and carrying out collaborative recommendation on the account number 1 in the first service based on the user grouping result of the account number 2 in the second service.

In still other possible embodiments, for a user (e.g., user 1), user 1 has an account number 1 in a first service and no account number in a second service, but there is an account number 2 associated with account number 1 in the second service. For example, the account 2 may be an account of the user 2, but the account 2 and the account 1 have an association relationship of binding, sharing, and the like. For another example, the account 2 may be a home public account of the user 1, but the account 2 has an association with the account 1, or the account 1 may be a home public account of the user 1, the account 2 may be an account of the user 2, but the account 2 has an association with the account 1, and so on. For the case that the user 1 has the account 1 in the first service and has no account in the second service, but the second service has the account 2 associated with the account 1, the recommendation method provided in the embodiment of the present application may also perform knowledge migration by using the historical behavior information corresponding to the account 2 in the second service, determine the user grouping result of the account 2 in the second service, and perform collaborative recommendation to the account 1 in the first service based on the user grouping result of the account 2 in the second service. The historical behavior information corresponding to the account 2 in the second service may also be considered as the historical behavior information related to the user 1 in the second service, and the user grouping result of the account 2 in the second service may be considered as the user grouping result of the user 1 in the second service (possibly, the user 1 does not directly generate the historical behavior information in the second service). Whereas the historical behavior information of the user 1 in the second service described in the foregoing embodiment may also be regarded as the historical behavior information related to the user 1 in the second service.

That is, according to the recommendation method provided by the embodiment of the application, knowledge migration can be performed by using historical behavior information related to the user in the second service, a user grouping result of the user in the second service is determined, and collaborative recommendation is performed on the user in the first service based on the user grouping result of the user in the second service. Wherein, the historical behavior information related to the user in the second service may include: historical behavior information corresponding to the user in the second service, or historical behavior information corresponding to other accounts (family public accounts or accounts of other users) associated with the user's account. The following embodiments include only the historical behavior information related to the user in the second service: the historical behavior information corresponding to the user in the second service is described as an example, and is not limited.

The recommendation method provided in the embodiment of the present application is described below with reference to some specific examples.

The recommendation method provided in the embodiment of the present application may be applied to a recommendation system, and fig. 1 is a schematic diagram of the composition of the recommendation system provided in the embodiment of the present application. As shown in fig. 1, the recommendation system provided in the embodiment of the present application may include: terminal equipment 110, recommendation server 120, and user portrait server 130. The terminal device 110, the recommendation server 120, and the user profile server 130 may be connected to each other via a wired network or a wireless network.

The terminal device 110 may be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (personal digital assistant, PDA), or the like, which is not limited to the specific type of the terminal device 110 in the embodiment of the present application.

Taking the terminal device 110 as a mobile phone as an example, fig. 2 is a schematic structural diagram of the terminal device 110 according to an embodiment of the present application. As shown in fig. 2, the terminal device 110 may include: processor 210, external memory interface 220, internal memory 221, universal serial bus (universal serial bus, USB) interface 230, charge management module 240, power management module 241, battery 242, antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, audio module 270, speaker 270A, receiver 270B, microphone 270C, headset interface 270D, sensor module 280, keys 290, motor 291, indicator 292, camera 293, display 294, and subscriber identity module (subscriber identification module, SIM) card interface 295, among others.

Processor 210 may include one or more processing units such as, for example: the processor 210 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.

The controller can be a neural center and a command center of the electronic device. The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution.

A memory may also be provided in the processor 210 for storing instructions and data. In some embodiments, the memory in the processor 210 is a cache memory. The memory may hold instructions or data that the processor 210 has just used or recycled.

In some embodiments, processor 210 may include one or more interfaces. The interfaces may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver transmitter (universal asynchronous receiver/transmitter, UART) interface, a mobile industry processor interface (mobile industry processor interface, MIPI), a general-purpose input/output (GPIO) interface, a subscriber identity module (subscriber identity module, SIM) interface, and/or a universal serial bus (universal serial bus, USB) interface, among others.

It should be understood that the interfacing relationship between the modules illustrated in the present embodiment is only illustrative, and does not constitute a structural limitation of the terminal device 110. In other embodiments, the terminal device 110 may also use different interfacing manners in the above embodiments, or a combination of multiple interfacing manners.

The charge management module 240 is configured to receive a charge input from a charger. The charging management module 240 may also provide power to the electronic device through the power management module 241 while charging the battery 242.

The power management module 241 is used for connecting the battery 242, and the charge management module 240 and the processor 210. The power management module 241 receives input from the battery 242 and/or the charge management module 240 and provides power to the processor 210, the internal memory 221, the external memory, the display 294, the camera 293, the wireless communication module 260, and the like. The power management module 241 may also be configured to monitor battery capacity, battery cycle times, battery health (leakage, impedance), and other parameters. In other embodiments, the power management module 241 may also be disposed in the processor 210. In other embodiments, the power management module 241 and the charge management module 240 may be disposed in the same device.

The wireless communication function of the electronic device may be implemented by the antenna 1, the antenna 2, the mobile communication module 250, the wireless communication module 260, a modem processor, a baseband processor, and the like.

The antennas 1 and 2 are used for transmitting and receiving electromagnetic wave signals. The mobile communication module 250 may provide a solution for wireless communication including 2G/3G/4G/5G or the like applied on the terminal device 110. The mobile communication module 250 may include at least one filter, switch, power amplifier, low noise amplifier (low noise amplifier, LNA), etc. The mobile communication module 250 may receive electromagnetic waves from the antenna 1, perform processes such as filtering, amplifying, and the like on the received electromagnetic waves, and transmit the processed electromagnetic waves to the modem processor for demodulation. The mobile communication module 250 can amplify the signal modulated by the modem processor, and convert the signal into electromagnetic waves through the antenna 1 to radiate. In some embodiments, at least some of the functional modules of the mobile communication module 250 may be disposed in the processor 210. In some embodiments, at least some of the functional modules of the mobile communication module 250 may be provided in the same device as at least some of the modules of the processor 210.

The modem processor may include a modulator and a demodulator. In some embodiments, the modem processor may be a stand-alone device. In other embodiments, the modem processor may be provided in the same device as the mobile communication module 250 or other functional module, independent of the processor 210.

The wireless communication module 260 may provide solutions for wireless communication including wireless local area network (wireless local area networks, WLAN) (e.g., wireless fidelity (wireless fidelity, wi-Fi) network), bluetooth (BT), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field wireless communication technology (near field communication, NFC), infrared technology (IR), etc. applied on the terminal device 110. The wireless communication module 260 may be one or more devices that integrate at least one communication processing module. The wireless communication module 260 receives electromagnetic waves via the antenna 2, modulates the electromagnetic wave signals, filters the electromagnetic wave signals, and transmits the processed signals to the processor 210. The wireless communication module 260 may also receive a signal to be transmitted from the processor 210, frequency modulate it, amplify it, and convert it to electromagnetic waves for radiation via the antenna 2.

In some embodiments, antenna 1 of terminal device 110 is coupled to mobile communication module 250 and antenna 2 is coupled to wireless communication module 260 such that terminal device 110 may communicate with a network and other devices (e.g., recommendation server 120, user portrayal server 130) via wireless communication techniques. The wireless communication techniques may include the Global System for Mobile communications (global system for mobile communications, GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (code division multiple access, CDMA), wideband code division multiple access (wideband code division multiple access, WCDMA), time division code division multiple access (time-division code division multiple access, TD-SCDMA), long term evolution (long term evolution, LTE), BT, GNSS, WLAN, NFC, FM, and/or IR techniques, among others. The GNSS may include a global satellite positioning system (global positioning system, GPS), a global navigation satellite system (global navigation satellite system, GLONASS), a beidou satellite navigation system (beidou navigation satellite system, BDS), a quasi zenith satellite system (quasi-zenith satellite system, QZSS) and/or a satellite based augmentation system (satellite based augmentation systems, SBAS). For example, in the embodiment of the present application, the terminal device 110 may establish a wireless connection with the recommendation server 120 and the user portrayal server 130 through a wireless communication technology by using the wireless communication module 260. Based on the established wireless connection, terminal device 110 may send information or messages to recommendation server 120, user portrayal server 130, and may also receive information or messages from recommendation server 120, user portrayal server 130.

Terminal device 110 implements display functions via a GPU, display screen 294, and application processor, etc. The GPU is a microprocessor for image processing, and is connected to the display screen 294 and the application processor. Processor 210 may include one or more GPUs that execute program instructions to generate or change display information.

The display 294 is used to display images, videos, and the like. The display 294 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light emitting diode (AMOLED), a flexible light-emitting diode (flex), a mini, a Micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, QLED), or the like. In some embodiments, terminal device 110 may include 1 or N displays 294, N being a positive integer greater than 1.

The terminal device 110 may implement a photographing function through an ISP, a camera 293, a video codec, a GPU, a display 294, an application processor, and the like. The ISP is used to process the data fed back by the camera 293. In some embodiments, the ISP may be provided in the camera 293. The camera 293 is used to capture still images or video. In some embodiments, terminal device 110 may include 1 or N cameras 293, N being a positive integer greater than 1. Video codecs are used to compress or decompress digital video. The electronic device may support one or more video codecs.

The external memory interface 220 may be used to connect an external memory card, such as a Micro SD card, to realize expansion of the memory capability of the terminal device 110. The external memory card communicates with the processor 210 through an external memory interface 220 to implement data storage functions. For example, files such as music, video, etc. are stored in an external memory card.

Internal memory 221 may be used to store computer executable program code that includes instructions. The processor 210 executes various functional applications of the terminal device 110 and data processing by executing instructions stored in the internal memory 221. For example, in the present embodiment, the processor 210 may establish a connection with the recommendation server 120, the user portrayal server 130, and data interaction with the recommendation server 120, the user portrayal server 130 through the wireless communication module 260 by executing instructions stored in the internal memory 221. The internal memory 221 may include a storage program area and a storage data area. The storage program area may store an application program (such as a sound playing function, an image playing function, etc.) required for at least one function of the operating system, etc. The storage data area may store data created during use of the electronic device (e.g., audio data, phonebook, etc.), and so forth. In addition, the internal memory 221 may include a high-speed random access memory, and may further include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like.

Terminal device 110 may implement audio functionality via audio module 270, speaker 270A, receiver 270B, microphone 270C, ear-headphone interface 270D, and an application processor, among others. Such as talking, music playing, recording, etc.

The audio module 270 is used to convert digital audio information into an analog audio signal output and also to convert an analog audio input into a digital audio signal. The audio module 270 may also be used to encode and decode audio signals. In some embodiments, the audio module 270 may be disposed in the processor 210, or some functional modules of the audio module 270 may be disposed in the processor 210.

Speaker 270A, also referred to as a "horn," is used to convert audio electrical signals into sound signals. Terminal device 110 may listen to music, or to hands-free calls, through speaker 270A.

A receiver 270B, also referred to as a "earpiece", is used to convert the audio electrical signal into a sound signal. When terminal device 110 receives a call or voice message, it can receive voice by placing receiver 270B close to the human ear.

Microphone 270C, also referred to as a "microphone" or "microphone," is used to convert sound signals into electrical signals. When making a call or transmitting voice information, the user can sound near the microphone 270C through the mouth, inputting a sound signal to the microphone 270C. The electronic device may be provided with at least one microphone 270C. In other embodiments, the electronic device may be provided with two microphones 270C, and may implement a noise reduction function in addition to collecting sound signals. In other embodiments, the terminal device 110 may be further provided with three, four or more microphones 270C to collect sound signals, reduce noise, identify the source of sound, implement directional recording functions, etc.

The earphone interface 270D is for connecting a wired earphone. Earphone interface 270D may be USB interface 230 or a 3.5mm open mobile electronic device platform (open mobile terminal platform, OMTP) standard interface, american cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.

The sensor module 280 may include a pressure sensor 280A, a gyroscope sensor 280B, a barometric pressure sensor 280C, a magnetic sensor 280D, an acceleration sensor 280E, a distance sensor 280F, a proximity sensor 280G, a fingerprint sensor 280H, a temperature sensor 280J, a touch sensor 280K, an ambient light sensor 280L, a bone conduction sensor 280M, and the like.

It is to be understood that the structure of the terminal device 110 shown in fig. 2 does not constitute a specific limitation on the terminal device 110. In other embodiments, when terminal device 110 is a tablet, desktop, laptop, handheld computer, notebook, UMPC, netbook, or other device such as a cellular telephone, PDA, AR/VR device, terminal device 110 may include more or fewer components than shown in FIG. 2, or may combine certain components, or may split certain components, or may be arranged in different components. The components shown in fig. 2 may be implemented in hardware, software, or a combination of software and hardware. The embodiment of the present application does not limit the specific structure of the terminal device 110.

In the recommendation system shown in fig. 1, the recommendation server 120 and the user portrayal server 130 are shown separately, but in some possible embodiments, the recommendation server 120 and the user portrayal server 130 may be the same server, or the recommendation server 120 and the user portrayal server 130 may be the same server cluster or cloud server, which is not limited herein.

In this application, the terminal device 110 may provide services to the user through App, such as: the terminal device 110 may be provided with a first App, where the first App may provide a first service, a second service, and the like for the user. Alternatively, the terminal device 110 may be provided with a first App and a second App, where the first App may provide a first service for the user, the second App may provide a second service for the user, and so on. The first service and the second service may be described with reference to the foregoing embodiments, and will not be described again. When the terminal device 110 provides a service for a user, the personalized recommendation function in the service can be realized based on the recommendation system shown in fig. 1.

Taking the example that the terminal device 110 provides the first service and the second service for the user, assuming that the user uses the second service provided by the terminal device 110, the terminal device 110 may record or collect the historical behavior information of the user in the second service during the process that the user uses the second service. The user portrayal server 130 may calculate and analyze the interests of the user in the second service based on the historical behavior information of the user in the second service, knowing the interests and preferences of the user in the second service. The recommendation server 120 may recommend service contents of the second service of interest to the user based on the result of the calculation and analysis of the user's interest in the second service by the user portrayal server 130. For example, the second service may be a streaming service, and the user portrayal server 130 calculates and analyzes the interests of the user in the second service to obtain the user's interest in the game comparison, and the recommendation server 120 may recommend the game-related streaming information, such as information, to the user. The specific algorithm for calculating and analyzing the interests of the user in the second service by the user portrayal server 130 and the specific algorithm for recommending the user by the recommendation server 120 according to the result of calculating and analyzing the interests of the user in the second service by the user portrayal server 130 are not limited.

The user portrayal server 130 may also cluster (i.e., group) the users with other users to obtain one or more user groups based on the historical behavior information of the users in the second service and the historical behavior information of other users in the second service. The recommendation server 120 may also recommend service contents of a second service of interest to other users in the same user group as the user to the user based on the result of the user grouping of the user by the user portrayal server 130. That is, the recommendation server 120 may also perform collaborative recommendation to the user in the second service based on the result of the user portrayal server 130 grouping the users in the second service. For example, the service content of the second service that is of interest to the other user may be the service content of the second service that the other user browses, or the service content of the second service that is recommended to the other user according to the result of calculation and analysis of the interest of the other user in the second service by the user portrayal server 130.

When the user uses the first service for the first time, the terminal device 110 needs to make a personalized recommendation to the user in the first service. In the recommendation method provided in the embodiment of the present application, the recommendation server 120 may recommend, to the user, service content of a first service interested by other users in the same user group with the user according to a result of the user portrait server 130 performing user grouping on the user in the second service, so as to solve a problem of cold start of the user in the first service. For example, the service content of the first service that is of interest to the other user may be the service content of the first service that the other user browses, or the service content of the first service that is recommended to the other user according to the result of calculation and analysis of the interest of the other user in the first service by the user portrait server 130.

For example, for a certain service (such as the first service or the second service), the historical behavior information may include specific service contents browsed by the user in the process of using the service, and the specific content of the historical behavior information is not limited in this application, where the relevant information includes clicking times, browsing times, sharing times, browsing duration, negative feedback (such as complaints or feedback is not interested) of a certain item or items of service contents (such as a certain group of information streams). For example, the historical behavior information may include information such as web page addresses (abbreviated as web addresses) browsed by the user, keywords searched by the user, click pages searched by the user, time periods for the user to view the web pages, and the like.

In this application, after the terminal device 110 records or collects the historical behavior information of the user in the second service, the historical behavior information of the user in the second service may not need to be uploaded or sent to the user portrait server 130, so that the user portrait server 130 calculates and analyzes the interests of the user in the second service according to the historical behavior information of the user in the second service. After recording or collecting the historical behavior information of the user in the second service, the terminal device 110 may perform encoding processing on the historical behavior information of the user in the second service, and perform hash calculation on the result after the encoding processing to obtain a hash value corresponding to the historical behavior information of the user in the second service. Then, the terminal device 110 may send the hash value corresponding to the historical behavior information of the user in the second service to the user portrait server 130, and the user portrait server 130 may group the users according to the hash value corresponding to the historical behavior information of the user in the second service, so as to determine the user group where the user is located. Different user groups have different group identifications (e.g., group IDs), which may also be referred to as group identifications. User portrayal server 130 may send to terminal device 110 a group identification of the user group in which the user is located, which may be referred to as a group identification of the user group in which the user is located in the second service.

The grouping identification of the user group in which the user is located in the second service is the result of user grouping of the user in the second service by the user portrait server 130 in the present application. When the user uses the first service for the first time, the terminal device 110 may send a grouping identifier of a user group in which the user is located in the second service to the recommendation server 120; the recommendation server 120 may send service contents of the first service interested by other users in the same user group as the user in the second service to the terminal device 110 according to the group identification of the user group in which the user is in the second service. The terminal device 110 may recommend the service contents of the first service, which are of interest to other users in the same user group as the user in the second service, to the user as the personalized recommendation result.

In the application, the terminal device 110 uploads or sends the hash value corresponding to the historical behavior information of the user in the second service to the user portrait server 130, and the user portrait server 130 groups the users according to the hash value corresponding to the historical behavior information of the user in the second service, so that the privacy of the users can be better protected. The user portrait server 130 groups users according to hash values corresponding to the historical behavior information of the users in the second service, and can reduce the grouping result of the users. Based on the user grouping result of the user portrait server 130, the terminal device 110 recommends the service content of the first service interested by other users in the same user group in the second service as the personalized recommendation result to the user, so that the cold start of the user in the first service by using knowledge migration in other services (the second service) is realized, the accuracy of personalized recommendation is effectively improved, the recommendation result more interested by the user can be recommended to the newly added user, and the cold start effect of the user can be better.

In this application, the service content of the first service interested by other users in the same user group in the second service may be referred to as recommendation information, where the recommendation information is related to the user group in which the user is in the second service.

Taking the terminal device 110 to provide the first service and the second service, the first user uses the first service for the first time, and the first user is the user who uses the second service as an example, fig. 3 is a flowchart of a recommendation method provided in an embodiment of the present application. As shown in fig. 3, the recommendation method may include S301-S309.

S301, the terminal device 110 obtains historical behavior information of the first user in the second service.

For example, taking the second service as an example of the search service, the first user may perform a search on the terminal device 110 using the search service, and the historical behavior information of the first user in the second service may include: the search terms searched by the first user in the search service, the search times of the search terms, and the like.

S302, the terminal equipment 110 adopts a first coding mode to code the historical behavior information of the first user in the second service, and a coding result corresponding to the historical behavior information of the first user in the second service is obtained.

In one possible implementation, the first encoding mode may include one-hot (encoding). The one-hot code, also called one-bit efficient code, mainly uses N (N is an integer greater than 1) bit status registers to code N states, each with a separate register bit and only one bit at any time. For example, the encoding result of one-hot encoding may be an N-dimensional vector in which only one dimension has a value of 1 and the remaining dimensions have values of 0. After the one-hot encoding is adopted to encode the historical behavior information of the first user in the second service, the encoding results corresponding to different historical behavior information can be different, and the encoding results can be unique for each piece of historical behavior information.

Illustratively, taking the second service as the search service as an example, it is assumed that the historical behavior information of the first user in the second service includes three search websites, which are respectively: web site a, web site B, and web site C. The terminal device 110 may use a one-hot encoding method to encode the website a, the website B, and the website C, where the encoding results corresponding to the website a, the website B, and the website C respectively may be as follows:

Encoding results corresponding to the website A: [0,1,0,0,0,0,0,0];

encoding results corresponding to the website B: [0,0,1,0,0,0,0,0];

encoding results corresponding to the website C: [0,0,0,0,0,1,0,0].

It can be seen that, in the encoding results corresponding to the website a, the website B, and the website C, the encoding result corresponding to each website may be an 8-dimensional vector (or regarded as an 8-bit array), but only one dimension of the encoding result corresponding to each website has a value of 1, and the other dimensions have values of 0. For example, the value of the 2 nd dimension in the code result corresponding to the website a is 1, the value of the 3 rd dimension in the code result corresponding to the website B is 1, and the value of the 6 th dimension in the code result corresponding to the website C is 1.

It should be noted thatIt should be noted that the encoding result is only an 8-dimensional vector or an 8-dimensional array, and the number of bits in the vector or the array is not limited. For example, in other examples, the encoding result may be a 64-bit array, and terminal device 110 may be a 2-to-2 ⁶⁴ (64 times of 2) websites, and the encoding results of different websites can be different.

In other possible implementations, the first encoding method may further include: index (index) coding (dictionary-based coding), multiple-hot (multiple-hot) coding, and the like, the first coding scheme is not limited herein.

S303, the terminal equipment 110 adopts a first hash algorithm to perform hash calculation on the encoding result corresponding to the historical behavior information of the first user in the second service, so as to obtain a hash value corresponding to the historical behavior information of the first user in the second service.

When the terminal device 110 performs hash calculation on the encoding results corresponding to the historical behavior information of the first user in the second service by using the first hash algorithm, if the similarity of the two encoding results is higher, the hash values obtained by performing hash calculation on the two encoding results by using the first hash algorithm also have a certain similarity. That is, the first hash algorithm is adopted to perform hash calculation on the encoding result, so that the similarity of the encoding result can be maintained. Since the first hash algorithm is used to perform hash calculation on the encoding result, the similarity of the encoding result can be maintained, so in S305, the user portrait server 130 can divide users with similar historical behavior information into the same user group when the users are grouped according to the hash value corresponding to the historical behavior information of the users in the second service.

Illustratively, the first hash algorithm may be a locality sensitive hash (locality sensitive hashing, LSH) algorithm, or referred to as an LSH function. After hash calculation is carried out on the coding result by adopting the LSH algorithm, the data is irreversible, namely the coding result cannot be decrypted reversely according to the hash value obtained by calculation of the LSH algorithm. In addition, the LSH algorithm is adopted to carry out hash calculation on the coding result, so that the similarity of the coding result can be maintained.

Taking the encoding result corresponding to the historical behavior information of the first user in the second service as the example given in the foregoing S302, the step of performing, by the terminal device 110, hash computation on the encoding results corresponding to the website a, the website B, and the website C by using the LSH algorithm may include: combining the coding results corresponding to the website A, the website B and the website C respectively to obtain combined coding results; and carrying out hash calculation on the combined coding results by adopting an LSH algorithm to obtain a first hash value, wherein the first hash value is a hash value commonly corresponding to the website A, the website B and the website C.

For example, the encoding result corresponding to the website a is: [0,1,0,0,0,0,0,0], the code result corresponding to the website B is: [0,0,1,0,0,0,0,0], the code result corresponding to the website C is: [0,0,0,0,0,1,0,0] after combining the coding results corresponding to the website A, the website B and the website C respectively, the obtained combined coding result may be: [0,1,1,0,0,1,0,0]. The terminal device 110 may then perform a hash calculation on [0,1,1,0,0,1,0,0] using the LSH algorithm to obtain a first hash value. The first hash value is a hash value corresponding to historical behavior information of the first user in the search service. The hash value may also be referred to as a hash fingerprint.

Alternatively, in the embodiment of the present application, the LSH algorithm may use any one of the following: the minimum hash (min-hash) algorithm using jaccard (jaccard) to measure data similarity, the P-stable hash (P-stable hash) algorithm using euclidean distance to measure data similarity, simhash algorithm, and the like are not limited herein.

S304, the terminal equipment 110 sends the hash value corresponding to the historical behavior information of the first user in the second service to the user portrait server 130.

Accordingly, the user portrayal server 130 may receive a hash value corresponding to the historical behavior information of the first user in the second service.

S305, the user portrait server 130 groups the first users according to the hash value corresponding to the historical behavior information of the first users in the second service, and determines the user group of the first users in the second service.

Illustratively, the user portrayal server 130 performs user grouping on the first user according to the hash value corresponding to the historical behavior information of the first user in the second service, which may include: the user portrayal server 130 performs cluster grouping calculation on the hash value corresponding to the historical behavior information of the first user in the second service and the hash value corresponding to the historical behavior information of one or more other users (such as the second user, the third user and the like) in the second service to obtain one or more user groups, where each user group may have a unique grouping identifier, for example: grouping ID. The hash value corresponding to the historical behavior information of the other user (e.g., the second user, the third user, etc.) in the second service may be sent to the user portrait server 130 by the terminal device of the other user, which is the same as the principle that the terminal device 110 obtains the hash value corresponding to the historical behavior information of the first user in the second service and sends the hash value to the user portrait server 130, and will not be described again.

In the present application, a coding result obtained by coding historical behavior information related to a first user in a second service by using a first coding manner may be referred to as a first coding result, and a coding result obtained by coding historical behavior information of one or more other users in the second service by using the first coding manner may be referred to as a second coding result.

Alternatively, the user portrait server 130 may perform user grouping on the first user according to the hash value corresponding to the historical behavior information of the first user in the second service, and the method may further include: the user portrayal server 130 calculates a similarity between a hash value corresponding to the historical behavior information of the first user in the second service and a hash value corresponding to the historical behavior information of other users in the existing user group in the second service, and determines that the first user belongs to the existing user group when the similarity between the hash value corresponding to the historical behavior information of other users in the certain existing user group in the second service and the hash value corresponding to the historical behavior information of the first user in the second service is greater than a certain threshold (e.g., 90%, 80%, etc.). The existing user group in the second service is obtained by clustering and grouping hash values corresponding to historical behavior information of other users (such as the second user and the third user) in the second service. The other users in the existing user group may be any one of the users in the existing user group. Alternatively, the hash value corresponding to the historical behavior information of the other users in the existing user group in the second service may be calculated according to the hash values corresponding to the historical behavior information of the plurality of other users in the existing user group in the second service, where the hash values are as follows: and (5) averaging.

S306, the user portrait server 130 sends the grouping identification of the user group where the first user is in the second service to the terminal device 110.

The group identification may be used to indicate which user group the first user belongs to in the second service.

Accordingly, the terminal device 110 may receive and store the group identifier of the user group where the first user is located in the second service.

S307, when detecting that the first user uses the first service for the first time, the terminal device 110 sends the group identifier of the user group where the first user is located in the second service to the recommendation server 120.

Accordingly, the recommendation server 120 may receive a group identification of the user group in which the first user is located in the second service.

For example, the first user may log in to the user account of the first user on the terminal device 110 or an App installed on the terminal device 110 for providing the first service, and the terminal device 110 detects that the first user uses the first service for the first time, that is, the terminal device 110 detects that the user account of the first user opens or starts the first service. For example, the terminal device 110 may be a mobile phone, and a browser may be installed on the mobile phone, where the browser includes an information flow service, and the information flow service may be the first service. The first user can log in the user account of the first user on the browser, and when the mobile phone detects that the user account of the first user starts the information flow service for the first time, the first user uses the information flow service for the first time.

The grouping identification of the user group where the first user is located in the second service may refer to: grouping identification of the user group in which the user account of the first user is located in the second service.

And S308, the recommendation server 120 sends service contents of the first service interested by other users in the same user group in the second service with the first user to the terminal equipment 110 according to the grouping identification of the user group in the second service.

For example, for the user portrayal server 130 performing cluster grouping calculation on the hash value corresponding to the historical behavior information of the first user in the second service and the hash value corresponding to the historical behavior information of other users (such as the second user, the third user, etc.) in the second service, the recommendation server 120 may record which service contents of the first service are interested by the user corresponding to each user group. It should be noted that, the recommendation server 120 may only record which service contents of the first service are interested by the user corresponding to each user group, and may not pay attention to which specific user in the user group is interested in which service contents of the first service.

The recommendation server 120 may query, according to the group identifier of the user group in which the first user is located in the second service, which service contents of the first service are interested in the user corresponding to the group identifier, that is, may query which service contents of the first service are interested in other users (such as the second user, the third user, etc.) included in the group identifier corresponding to the group identifier. The recommendation server 120 may then send the service content of the first service of interest to other users of the same user group as the first user in the second service to the terminal device 110.

As described above, the service contents of the first service, which are of interest to other users in the same user group as the first user in the second service, may include: the service content of the first service browsed by the other users, or the service content of the first service recommended to the other users according to the result of calculation and analysis of the interests of the other users in the first service by the user portrait server 130.

S309, the terminal device 110 displays the service content of the first service that is of interest to other users in the same user group as the first user in the second service.

That is, the terminal device 110 may recommend the service content of the first service, which is of interest to other users in the same user group as the first user in the second service, to the first user as the personalized recommendation result.

For example, taking the first service as an information flow service and the second service as a search service as an example, the terminal device 110 may recommend information flows interested by other users in the same user group as the first user in the search service to the first user as personalized recommendation results in the information flow service.

It can be understood that in the recommendation method shown in fig. 3, the steps S301 to S306 are a process of grouping the users when the users use the second service. The steps of S307-S309 are a process of implementing a cold start of the user based on the user grouping result of S301-S306 when the user uses the first service for the first time.

In some embodiments, terminal device 110 may perform the steps described in S301-S304 periodically, according to a first periodicity. For example, the first period may be one day, one week, one month, etc. Accordingly, user portrayal server 130 can perform the steps described in S305-S306 periodically with a first period. In S301, the historical behavior information of the first user in the second service acquired by the terminal device 110 may be the historical behavior information of the first user in the second service in the first period. For example, the first time period may be the last month (i.e., last week), etc. In this way, the user grouping result of the first user can be dynamically updated according to the first period along with the change of the historical behavior information of the first user in the second service. The user grouping result of the first user is dynamically updated according to the first period along with the change of the historical behavior information of the first user in the second service, so that the accuracy of the user grouping result can be improved, and the safety of user privacy can be improved.

Taking the first period as the last month and the first period as one week as an example, the terminal device 110 may at least keep the historical behavior information of the first user in the second service in the last month during the process of using the second service by the first user. Every other week, the terminal device 110 may obtain the historical behavior information of the first user in the second service in the last month, perform coding processing on the historical behavior information of the first user in the second service in the last month by adopting a first coding manner, perform hash calculation on the coding result corresponding to the historical behavior information of the first user in the second service in the last month by adopting a first hash algorithm, obtain a hash value corresponding to the historical behavior information of the first user in the second service in the last month, and send the hash value to the user portrait server 130. Accordingly, the user portrayal server 130 may perform the steps described in S305-S306 above based on the hash value corresponding to the historical behavior information of the first user in the second service in the last month, so that the group identifier of the user group where the first user is located in the second service received by the terminal device 110 may be updated every other week. It should be appreciated that the grouping identification of the user group in which the first user is located in the second service may be the same after each update, or may be different, e.g., the first user may be partitioned into a new user group.

Optionally, in the embodiment of the present application, the first user may also set on the terminal device 110, and choose to refuse to authorize the terminal device 110 to collect the historical behavior information of the first user in the service. After the first user selects to refuse to authorize the terminal device 110 to collect the historical behavior information of the first user in the service, the terminal device 110 may not calculate the corresponding hash value according to the historical behavior information of the first user in the service any more.

Optionally, in some embodiments, the user portrait server 130 may keep the number of users in each user group below a fixed number when users are grouped according to hash values corresponding to historical behavior information of the users (which may include the first user, other users, etc.) in the second service, for example: the number of users in each user group may be kept to be less than 5000 to avoid too single personalized recommendation results for recommendation based on the user grouping results.

In the embodiment shown in fig. 3, the step of encoding the historical behavior information of the first user in the second service by using the first encoding method is performed by the terminal device 110. In other embodiments, the step of encoding the historical behavior information of the first user in the second service by using the first encoding method may be completed at the user portrait server 130 side, and the process of encoding the historical behavior information of the first user in the second service by using the first encoding method is placed at the user portrait server 130 side, so that the computing pressure at the terminal device 110 side may be reduced, and the load of the terminal device 110 may be reduced.

For example, fig. 4 is another flow chart of the recommendation method provided in the embodiment of the present application. As shown in fig. 4, the recommendation method may include S401 to S411.

S401, the terminal device 110 obtains historical behavior information of the first user in the second service.

The steps described in S401 may be described with reference to S301, and will not be described again.

S402, the terminal equipment 110 sends the historical behavior information of the first user in the second service to the user portrait server 130.

Accordingly, user portrayal server 130 can receive historical behavior information of the first user in the second service.

To better protect the privacy of the user, the terminal device 110 may send only the historical behavior information of the first user in the second service to the user portrait server 130, and may not carry the user information related to the first user, such as: user identification (user account), device information of the terminal device 110, etc.

S403, the user portrait server 130 adopts a first coding mode to code the historical behavior information of the first user in the second service, and a coding result corresponding to the historical behavior information of the first user in the second service is obtained.

The process of the user portrait server 130 for encoding the historical behavior information of the first user in the second service by using the first encoding method may be the same as the process of the terminal device 110 for encoding the historical behavior information of the first user in the second service by using the first encoding method described in the foregoing embodiment, which is not described herein again.

S404, the user portrait server 130 sends the encoding result corresponding to the historical behavior information of the first user in the second service to the terminal device 110.

Accordingly, the terminal device 110 may receive the encoding result corresponding to the historical behavior information of the first user in the second service.

S405, the terminal equipment 110 adopts a first hash algorithm to perform hash calculation on the encoding result corresponding to the historical behavior information of the first user in the second service, so as to obtain a hash value corresponding to the historical behavior information of the first user in the second service.

S406, the terminal equipment 110 sends the hash value corresponding to the historical behavior information of the first user in the second service to the user portrait server 130.

S407, the user portrait server 130 groups the first users according to the hash value corresponding to the historical behavior information of the first users in the second service, and determines the user group of the first users in the second service.

S408, the user portrait server 130 sends the grouping identification of the user group where the first user is in the second service to the terminal device 110.

S409, when detecting that the first user uses the first service for the first time, the terminal device 110 sends the group identifier of the user group where the first user is located in the second service to the recommendation server 120.

S410, the recommendation server 120 sends, to the terminal device 110, service content of the first service interested by other users in the same user group as the first user in the second service according to the group identification of the user group in which the first user is in the second service.

S411, the terminal device 110 displays the service content of the first service that is of interest to other users in the same user group as the first user in the second service.

The steps of S405-S411 may be described with reference to S303-S309, and will not be described again.

Alternatively, the functions of the terminal device 110 described in the embodiments of the present application may be implemented by an App installed on the terminal device 110. For example, the terminal device 110 is provided with a browser, and the browser may include the first service and the second service, and all the functions of the terminal device 110 described in the foregoing embodiments may be implemented by the browser.

The embodiments shown in fig. 3 and fig. 4 above take the terminal device 110 to provide the first service and the second service, where the first user uses the first service for the first time, and the first user is the user who uses the second service as an example, the recommendation method provided in the embodiments of the present application is described. Alternatively, in other embodiments, the recommendation method provided in the embodiments of the present application may also be applied to a scenario of multi-device collaboration, where the first service and the second service may be provided by two different devices. For example, a plurality of (e.g., at least two) terminal devices such as a mobile phone, a tablet computer, a personal computer (personal computer, PC), a smart home device (e.g., a television) and the like may be cooperatively used, and a scenario in which a plurality of terminal devices cooperate may be referred to as a multi-device cooperation scenario. In a multi-device collaboration scenario, a first user may have multiple devices that may cooperate, such as: terminal device 1, terminal device 2, etc.

In the multi-device collaboration scenario, the terminal device 1 (e.g. a mobile phone) includes a first service, and the terminal device 2 (e.g. a television) includes a second service, and fig. 5 is a schematic flow chart of a recommendation method according to an embodiment of the present application. The first service and the second service refer to the foregoing embodiments, and are not described in detail. As shown in fig. 5, the recommendation method may include S501-S511.

S501, the terminal device 2 obtains historical behavior information of the first user in the second service.

The steps described in S501 may be described with reference to S301, and will not be described again.

S502, the terminal device 2 sends the historical behavior information of the first user in the second service to the user portrait server 130.

For better protection of user privacy, the terminal device 2 may send only the historical behavior information of the first user in the second service to the user portrait server 130, and may not carry the user information related to the first user, such as: user identification (user account), device information of the terminal device 2, etc.

S503, the user portrait server 130 adopts a first coding mode to code the historical behavior information of the first user in the second service, and a coding result corresponding to the historical behavior information of the first user in the second service is obtained.

The process of the user portrait server 130 for encoding the historical behavior information of the first user in the second service by using the first encoding method may be the same as the process of encoding the historical behavior information of the first user in the second service by using the first encoding method described in the foregoing embodiment, which is not described herein.

S504, the user portrait server 130 sends the encoding result corresponding to the historical behavior information of the first user in the second service to the terminal device 2.

Accordingly, the terminal device 2 may receive the encoding result corresponding to the historical behavior information of the first user in the second service.

Alternatively, as described in the foregoing embodiment, the process of encoding the historical behavior information of the first user in the second service by using the first encoding manner may also be completed by the terminal device 2. That is, the steps described in S502 to S504 may be replaced with: the terminal device 2 adopts a first coding mode to code the historical behavior information of the first user in the second service, and a coding result corresponding to the historical behavior information of the first user in the second service is obtained.

S505, the terminal device 2 adopts a first hash algorithm to perform hash calculation on the encoding result corresponding to the historical behavior information of the first user in the second service, so as to obtain a hash value corresponding to the historical behavior information of the first user in the second service.

S506, the terminal device 2 sends the hash value corresponding to the historical behavior information of the first user in the second service to the user portrait server 130.

S507, the user portrait server 130 groups the first users according to the hash value corresponding to the historical behavior information of the first users in the second service, and determines the user group of the first users in the second service.

S508, the user portrait server 130 sends the grouping identification of the user group where the first user is in the second service to the terminal device 1.

Accordingly, the terminal device 1 may receive and store the group identification of the user group in which the first user is located in the second service.

Alternatively, the user portrayal server 130 may send the group identification of the user group in which the first user is in the second service to the terminal device 2, and the terminal device 1 may obtain the group identification of the user group in which the first user is in the second service from the terminal device 2.

S509, when detecting that the first user uses the first service for the first time, the terminal device 1 sends the recommendation server 120 a group identification of a user group in which the first user is located in the second service.

S510, the recommendation server 120 sends, to the terminal device 1, service content of the first service interested by other users in the same user group as the first user in the second service according to the group identification of the user group in which the first user is in the second service.

S511, the terminal device 1 displays the service content of the first service that is of interest to other users in the same user group as the first user in the second service.

The steps of S505-S511 may be described with reference to S303-S309, and will not be repeated.

In some possible implementation scenarios, in the embodiments of the present application, the terminal device (may be the same terminal device or different terminal devices) capable of providing the first service and the second service may be a device resource (such as a CPU resource, a memory resource, a storage resource, etc.) that is relatively abundant, and may be independently networked and interacted with by a human machine, for example: a mobile phone, a tablet computer, a notebook computer, etc.

In other possible scenarios, the terminal device capable of providing the first service and/or the second service in the embodiments of the present application may also be a device with fewer device resources, which cannot be independently networked and/or interacted with, for example: handwriting board, earphone, VR glasses, vehicle-mounted equipment, electric cooker, stereo set, treadmill etc.. When the terminal equipment providing the first service is equipment with fewer equipment resources and cannot be independently networked and/or interacted with by human, the interaction between the terminal equipment providing the first service and the server (such as a recommendation server and a user portrait service) can be completed through other equipment with rich equipment resources and can be independently networked and interacted with by human. Similarly, when the terminal device providing the second service is a device with less device resources and cannot be independently networked and/or interacted with by a human machine, the interaction between the terminal device providing the second service and the server (such as a recommendation server and a user portrait service) can be completed by other devices with rich device resources and can be independently networked and interacted with by a human machine.

Fig. 6 is a schematic diagram of an application scenario provided in an embodiment of the present application. As shown in fig. 6, one possible application scenario may include: a mobile phone 601, a watch 602, a smart screen 603, a sound 604, a refrigerator 605 and other devices. Local area network connection can be realized between the mobile phone 601 and the watch 602, the smart screen 603, the sound 604 and the refrigerator 605 through the router 606. In the scenario shown in fig. 6, the mobile phone 601, the watch 602, the smart screen 603 and the like can be considered as devices with rich device resources, and can be independently connected with each other and interacted with each other by man-machine; the stereo 604, refrigerator 605, etc. may be considered as devices that have fewer device resources, cannot be independently networked and/or man-machine interacted with.

In one implementation, the first service may be a menu recommendation service provided by the refrigerator 605 and the second service may be an information flow service provided by the mobile phone 601. That is, the refrigerator 605 may be the terminal device 1 mentioned in the flow shown in fig. 5 described above, and the mobile phone 601 may be the terminal device 2 mentioned in the flow shown in fig. 5 described above. At this time, the refrigerator 605 can complete the interaction with the server (such as the recommendation server and the user portrait service) through the mobile phone 601, the watch 602, the intelligent screen 603 and other devices with rich resources and independent networking and man-machine interaction. For example, the user portrayal server may send the group identification of the user group in which the first user is in the second service to the mobile phone 601, and the mobile phone 601 may forward the group identification of the user group in which the first user is in the second service to the refrigerator 605; the refrigerator 605 may send the group identifier of the user group where the first user is located in the second service to the mobile phone 601, and the mobile phone 601 may forward the group identifier of the user group where the first user is located in the second service to the recommendation server; the recommendation server may send the service content of the first service of interest to other users of the same user group as the first user in the second service to the mobile phone 601, and the mobile phone 601 may forward the service content of the first service of interest to other users of the same user group as the first user in the second service to the refrigerator 605.

In another implementation, the first service may be a recipe recommendation service provided by the refrigerator 605 and the second service may be a music recommendation service provided by the stereo 604. That is, the refrigerator 605 may be the terminal device 1 mentioned in the flow shown in fig. 5 described above, and the sound 604 may be the terminal device 2 mentioned in the flow shown in fig. 5 described above. At this time, the refrigerator 605 can complete the interaction with the server (such as the recommendation server and the user portrait service) through the mobile phone 601, the watch 602, the intelligent screen 603 and other devices with rich resources and independent networking and man-machine interaction. The stereo 604 can also be used for completing the interaction with a server (such as a recommendation server and a user portrait service) through the mobile phone 601, the watch 602, the intelligent screen 603 and other devices with rich resources and can be independently connected with the Internet and used for human-computer interaction, and the interaction is not illustrated.

Optionally, in the embodiment of the present application, the device with abundant device resources and capable of independent networking and man-machine interaction may be referred to as a rich device, and the device with fewer device resources and incapable of independent networking and/or man-machine interaction may be referred to as a light device.

Optionally, the recommendation method provided by the embodiment of the application can also be applied to a scene of cold start of a non-user. For example, the first user may be a user who has used the first service, instead of a new user in the first service. That is, the first user has generated some historical behavior information in the first service. For this scenario, in the recommendation method provided in the embodiment of the present application, knowledge migration may also be performed by using historical behavior information related to the first user in the second service, to determine a user grouping result of the first user in the second service, and to perform collaborative recommendation to the user in the first service based on the user grouping result of the first user in the second service. For example, the first user may be a user who has used the first service, but the first user has less historical behavior information in the first service. The present application does not limit whether the first user uses the first service for the first time, and the amount of historical behavior information of the first user in the first service.

In the embodiments illustrated in fig. 3 and 4 described above, the terminal device 110 may be referred to as a first device. In the embodiment shown in fig. 5 described above, the terminal device 1 may be referred to as a first device and the terminal device 2 may be referred to as a second device. When the first device interacts with the server through the other terminal device, the other terminal device may be referred to as a third device. Such as: the first device may be the light device described above and the third device may be the rich device described above. Similarly, when the second device interacts with the server through the other terminal device, the other terminal device may be referred to as a fourth device. Such as: the first device may be the light device described above and the fourth device may be the rich device described above.

Optionally, in some possible embodiments, the first device may further send identification information (such as a user account) of the first user to the server. For example, the first device may send user information of the first user to the server, the user information of the first user including: identification information of the first user and identification information of the first user group.

Alternatively, in still other possible embodiments, the first device may not sense the group identifier of the user group where the first user is located in the second service, and after obtaining the group identifier of the user group where the first user is located in the second service, the server may establish, at the server side, an association relationship between the group identifier of the user group where the first user is located in the second service and the identification information (such as the user account) of the first user. The first device may send identification information of the first user to the server, and the server may query according to the identification information of the first user to obtain a grouping identification of a user group where the first user is located in the second service, that is, the server may query according to the identification information of the first user to obtain which user group the first user belongs to in the second service.

In this application, a user group in which a first user is in a second service may be referred to as a first user group, and a group identification of the user group in which the first user is in the second service is identification information of the first user group. That is, the first device may send user information of the first user to the server, and the user information of the first user may include: identification information of the first user, and/or identification information of the first user group. Wherein the user information of the first user is related to the first user group.

It should be noted that, in the foregoing embodiments of the present application, the server may determine, by using, as an example, a user group in which the first user is located in the second service (i.e., the first user group) according to that the hash value corresponding to the historical behavior information related to the first user in the second service matches with the hash value corresponding to the historical behavior information of one or more other users in the second service, but in other possible embodiments, the hash value may be replaced by a result obtained by performing feature extraction on the encoding result corresponding to the historical behavior information by using other feature extraction algorithms.

Optionally, the similarity of the encoding results can be maintained by using other feature extraction algorithms to obtain the results after feature extraction of the encoding results corresponding to the historical behavior information, and other feature extraction algorithms can also have the characteristic of being incapable of reversely decrypting the encoding results.

The hash value corresponding to the historical behavior information, the result obtained by extracting the features of the encoding result corresponding to the historical behavior information by adopting other feature extraction algorithms, and the like can be called as feature information corresponding to the historical behavior information. That is, in the present application, the user group where the first user is located in the second service may be determined according to matching between feature information corresponding to the historical behavior information related to the first user in the second service and feature information corresponding to the historical behavior information of one or more other users in the second service.

It should be understood that what has been described in the foregoing embodiments is merely illustrative of the recommended methods provided for embodiments of the application. In other possible implementations, some of the steps performed in the embodiments described above may be omitted or added, or the order of some of the steps described in the embodiments may be modified, which is not limited in this application.

Corresponding to the recommendation method described in the foregoing embodiments, the present application provides a recommendation system, which may implement the recommendation method described in the foregoing embodiments.

For example, the recommendation system may include: a first device and a server. The first device and the server may be as described in the previous embodiments. The first device may be configured to send user information of the first user to the server. The server may be configured to send the recommendation information to the first device. The recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

Similarly, the recommendation system may implement the functions corresponding to all the steps of the recommendation method described in the foregoing embodiments, which are not described in detail herein.

The embodiment of the application also provides a recommending device, which can be applied to an electronic device (such as a first device) to enable the electronic device to implement the steps executed by the first device in the recommending method in the previous embodiment. The functions of the device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software comprises one or more modules or units corresponding to the steps performed by the first device in the recommended method described in the previous embodiment. For example, fig. 7 is a schematic structural diagram of a recommending apparatus provided in an embodiment of the present application. As shown in fig. 7, the apparatus may include: a transmitting unit 701, a receiving unit 702, and the like.

The transmitting unit 701 may be configured to transmit user information of the first user to the server; the receiving unit 702 may be configured to receive recommendation information from a server; the recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In one possible implementation, the first device includes a first service and a second service; the sending unit 701 is further configured to send, to the server, feature information corresponding to the historical behavior information related to the first user in the second service.

In a possible implementation manner, the sending unit 701 is specifically configured to send, through the third device, user information of the first user to the server. The receiving unit 702 is specifically configured to receive, by the third device, the recommendation information from the server.

Optionally, the sending unit 701 is specifically configured to send, to the server through the third device, feature information corresponding to the historical behavior information related to the first user in the second service.

Optionally, the receiving unit 702 is further configured to receive identification information of the first user group sent by the server; the first user group is determined by the server according to the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In a possible implementation manner, the sending unit 701 is specifically configured to send, when detecting that the first user uses the first service for the first time, user information of the first user to the server.

Similarly, the apparatus may implement functions corresponding to all steps executed by the first device in the recommendation method described in the foregoing embodiments, which are not described in detail herein.

The embodiment of the application also provides a recommending device, which can be applied to the electronic equipment (such as a server) to enable the electronic equipment to realize the steps executed by the server in the recommending method in the previous embodiment. The functions of the device can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules or units corresponding to the steps performed by the server in the recommended method described in the previous embodiment. For example, fig. 8 is another schematic structural diagram of a recommending apparatus provided in an embodiment of the present application. As shown in fig. 8, the apparatus may include: a transmitting unit 801, a receiving unit 802.

The receiving unit 801 may be configured to receive user information from a first user transmitted by a first device; the transmitting unit 802 may be configured to transmit the recommendation information to the first device. The recommendation information is information related to the use of the first service by users in the first user group; the user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

In one possible implementation, the first device includes a first service and a second service; the receiving unit 801 is further configured to receive feature information corresponding to the historical behavior information related to the first user in the second service sent by the first device.

In another possible implementation, the first device includes a first service and the second device includes a second service; the receiving unit 801 is further configured to receive feature information corresponding to the historical behavior information related to the first user in the second service sent by the second device.

In a possible implementation manner, the receiving unit 801 is specifically configured to receive, by using the third device, user information from the first user sent by the first device. The sending unit 802 is specifically configured to send, through the third device, the recommendation information to the first device.

Optionally, the receiving unit 801 is specifically configured to receive, by using the third device, feature information corresponding to the historical behavior information related to the first user in the second service sent by the first device.

Optionally, the receiving unit 801 is specifically configured to receive, by using the fourth device, feature information corresponding to the historical behavior information related to the first user in the second service sent by the second device.

Optionally, with continued reference to fig. 8, the apparatus may further include: a processing unit 803. The processing unit 803 may be configured to determine the first user group according to feature information corresponding to the historical behavior information related to the first user in the second service and feature information corresponding to the historical behavior information of one or more other users in the second service. The sending unit 802 is further configured to send identification information of the first user group to the first device.

Similarly, the device may implement functions corresponding to all steps executed by the server in the recommendation method described in the foregoing embodiments, which are not described in detail herein.

It should be understood that the division of the units (or called modules) in the above apparatus is merely a division of logic functions, and may be fully or partially integrated into one physical entity or may be physically separated. And the units in the device can be all realized in the form of software calls through the processing element; or can be realized in hardware; it is also possible that part of the units are implemented in the form of software, which is called by the processing element, and part of the units are implemented in the form of hardware.

For example, each unit may be a processing element that is set up separately, may be implemented as integrated in a certain chip of the apparatus, or may be stored in a memory in the form of a program, and the functions of the unit may be called and executed by a certain processing element of the apparatus. Furthermore, all or part of these units may be integrated together or may be implemented independently. The processing element described herein, which may also be referred to as a processor, may be an integrated circuit with signal processing capabilities. In implementation, each step of the above method or each unit above may be implemented by an integrated logic circuit of hardware in a processor element or in the form of software called by a processing element.

In one example, the units in the above apparatus may be one or more integrated circuits configured to implement the above method, for example: one or more application specific integrated circuits (application specific integrated circuit, ASIC), or one or more digital signal processors (digital signal process, DSP), or one or more field programmable logic gate arrays (field programmable gate array, FPGA), or a combination of at least two of these integrated circuit forms.

For another example, when the units in the apparatus may be implemented in the form of a scheduler of processing elements, the processing elements may be general-purpose processors, such as a central processing unit (central processing unit, CPU) or other processor that may invoke the program. For another example, the units may be integrated together and implemented in the form of a system-on-a-chip (SOC).

In one implementation, the above means for implementing each corresponding step in the above method may be implemented in the form of a processing element scheduler. For example, the apparatus may comprise a processing element and a storage element, the processing element invoking a program stored in the storage element to perform the steps performed by the first device or server in the recommended method described in the method embodiments above. The memory element may be a memory element on the same chip as the processing element, i.e. an on-chip memory element.

In another implementation, the program for performing the above method may be on a memory element on a different chip than the processing element, i.e. an off-chip memory element. At this time, the processing element calls or loads a program from the off-chip storage element onto the on-chip storage element to call and execute the steps executed by the first device or the server in the recommended method described in the above method embodiment.

The embodiment of the application also provides electronic equipment. The electronic device may be the first device or the server described above. An electronic device includes: a processor, a memory for storing processor-executable instructions; the processor is configured to, when executing the instructions, cause the electronic device to implement the steps performed by the first device or the server in the recommendation method as described in the method embodiments above. The memory may be located within the electronic device or may be located external to the electronic device. And the processor includes one or more.

In yet another implementation, the electronic device may implement the units of the steps of the above method as one or more processing elements, where the processing elements may be integrated circuits, for example: one or more ASICs, or one or more DSPs, or one or more FPGAs, or a combination of these types of integrated circuits. These integrated circuits may be integrated together to form a chip.

For example, the embodiment of the application also provides a chip, and the chip can be applied to the electronic equipment. The chip includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected through a circuit; the processor receives and executes computer instructions from the memory of the electronic device via the interface circuit to implement the steps performed by the first device or the server in the recommended method as described in the method embodiments above.

From the foregoing description of the embodiments, it will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of functional modules is illustrated, and in practical application, the above-described functional allocation may be implemented by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to implement all or part of the functions described above.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a readable storage medium.

With such understanding, the technical solutions of the embodiments of the present application may be essentially or partly contributing to the prior art or all or part of the technical solutions may be embodied in the form of a software product, such as: and (5) program. The software product is stored in a program product, such as a computer readable storage medium, comprising instructions for causing a device (which may be a single-chip microcomputer, chip or the like) or processor (processor) to perform all or part of the steps of the methods described in the various embodiments of the application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.

For example, embodiments of the present application also provide a computer-readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by an electronic device, cause the electronic device to perform the steps performed by the first device or the server in the recommendation method as described in the method embodiments above.

For another example, embodiments of the present application also provide a computer program product comprising: computer readable code, or a non-transitory computer readable storage medium carrying computer readable code, which when run in an electronic device, a processor in the electronic device implements the steps performed by the first device or server in the recommended method as described in the method embodiments above.

The foregoing is merely a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A recommendation method, the method comprising:

the method comprises the steps that first equipment sends user information of a first user to a server;

The server sends recommendation information to the first device; the recommendation information is information related to the use of the first service by users in the first user group; user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

2. The method of claim 1, wherein the first device comprises the first service and the second service; the method further comprises the steps of:

and the first equipment sends characteristic information corresponding to the historical behavior information related to the first user in the second service to the server.

3. The method of claim 1, wherein the first device comprises the first service and a second device comprises the second service; the method further comprises the steps of:

and the second equipment sends characteristic information corresponding to the historical behavior information related to the first user in the second service to the server.

4. A method according to any of claims 1-3, wherein the first device sending user information of the first user to the server comprises:

the first device sends user information of a first user to a server through third equipment;

the server sending recommendation information to the first device, comprising:

and the server sends recommendation information to the first device through the third device.

5. The method according to any of claims 1-4, wherein the user information of the first user comprises: identification information of the first user and/or identification information of the first user group.

6. The method of claim 5, wherein the method further comprises:

the server determines the first user group according to characteristic information corresponding to the historical behavior information related to the first user in the second service and characteristic information corresponding to the historical behavior information of one or more other users in the second service;

the server sends identification information of the first user group to the first device.

7. The method according to any one of claims 1-6, wherein the feature information corresponding to the historical behavior information related to the first user in the second service includes: hash values corresponding to the historical behavior information related to the first user in the second service;

And the characteristic information corresponding to the historical behavior information of the other one or more users in the second service comprises: hash values corresponding to historical behavior information of the other one or more users in the second service.

8. The method of claim 7, wherein the hash value corresponding to the historical behavior information related to the first user in the second service is obtained by performing a hash calculation on a first encoding result by using a first hash algorithm, and the first encoding result is obtained by performing an encoding process on the historical behavior information related to the first user in the second service by using a first encoding mode;

the hash value corresponding to the historical behavior information of the other one or more users in the second service is obtained by performing hash calculation on a second coding result by adopting a first hash algorithm, and the second coding result is obtained by performing coding processing on the historical behavior information of the other one or more users in the second service by adopting a first coding mode.

9. The method according to any of claims 1-8, wherein the first device sending user information of the first user to the server comprises:

When detecting that the first user uses the first service for the first time, the first device sends user information of the first user to the server.

10. A recommendation method, wherein the method is applied to a first device, the method comprising:

transmitting user information of a first user to a server;

receiving recommendation information from the server; the recommendation information is information related to the use of the first service by users in the first user group; user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

11. The method of claim 10, wherein the first device comprises the first service and the second service; the method further comprises the steps of:

and sending characteristic information corresponding to the historical behavior information related to the first user in the second service to the server.

12. The method of claim 10, wherein the first device comprises the first service and the second device comprises the second service.

13. The method according to any one of claims 10-12, wherein the sending the user information of the first user to the server comprises:

transmitting user information of the first user to a server through third equipment;

the receiving recommendation information from the server includes:

and receiving recommendation information from the server through the third equipment.

14. A recommendation method, wherein the method is applied to a server, the method comprising:

receiving user information of a first user sent by first equipment;

transmitting recommendation information to the first device; the recommendation information is information related to the use of the first service by users in the first user group; user information of the first user is related to the first user group; the first user group is determined according to the matching of the characteristic information corresponding to the historical behavior information related to the first user in the second service and the characteristic information corresponding to the historical behavior information of one or more other users in the second service.

15. The method of claim 14, wherein the first device comprises the first service and the second service; the method further comprises the steps of:

And receiving characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the first equipment.

16. The method of claim 14, wherein the first device comprises the first service and a second device comprises the second service; the method further comprises the steps of:

and receiving characteristic information corresponding to the historical behavior information related to the first user in the second service sent by the second equipment.

17. An electronic device, comprising: a processor, a memory for storing instructions executable by the processor;

the processor is configured to, when executing the instructions, cause the electronic device to implement the method of any one of claims 10-13 or the method of any one of claims 14-16.

18. A computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by an electronic device, cause the electronic device to implement the method of any one of claims 10-13 or the method of any one of claims 14-16.

19. A computer program product comprising computer readable code, or a non-transitory computer readable storage medium carrying computer readable code, characterized in that a processor in an electronic device implements the method according to any of claims 10-13, or the method according to any of claims 14-16, when the computer readable code is run in the electronic device.