Method for generating and displaying recommended information, electronic device and storage medium

Abstract

The present invention discloses a method for generating and displaying recommendation information, an electronic device and a storage medium, which can be applied to the Internet field. The method for generating recommendation information includes: receiving a recommendation request sent by a first terminal; determining a target group according to the recommendation request; and analyzing and processing the behavior data of the target group to obtain the information to be recommended. The information to be recommended generated based on the method can break the limitations of the current user's own preferences and prevent the user from falling into an information cocoon. Based on the information to be recommended, differentiated information that is different from the user's own preferences can be recommended to the user, helping the user to broaden his horizons.

Description

Technical Field

[0001] The present disclosure relates to the field of the Internet, and in particular to a method for generating and displaying recommendation information, an electronic device, and a storage medium. Background Art

[0002] With the development of Internet technology and information technology, the amount of information has exploded. When users perform various operations based on applications on terminal devices, a large amount of user data will be generated.

[0003] In scenarios where users obtain information about books, movies, short videos, news, takeaways, amusement parks, and tourist attractions, whether it is the user's own choice of information or the device's recommendation of information to the user based on a recommendation algorithm, information is recommended in a targeted manner based on the user's own preferences. Taking user A reading an e-book as an example, some recommendation algorithms calculate the reading preferences of user A by analyzing the user's historical reading data, and then filter out books that users tend to click based on the above preferences, and recommend the above books to the user after sorting them.

[0004] However, the above recommendation method makes the recommendation information fall into a closed loop, making the scope of content that each user is exposed to increasingly limited, and thus making the user's knowledge increasingly narrow. Summary of the invention

[0005] In order to solve the above technical problem or at least partially solve the above technical problem, an embodiment of the present disclosure provides a method for generating and displaying recommendation information, an electronic device, and a storage medium.

[0006] In a first aspect, an embodiment of the present disclosure provides a method for generating recommendation information. The method for generating recommendation information includes: receiving a recommendation request sent by a first terminal; determining a target group according to the recommendation request; and analyzing and processing the behavior data of the target group to obtain the information to be recommended.

[0007] In a second aspect, an embodiment of the present disclosure provides a method for displaying recommendation information. The method for displaying recommendation information includes: receiving user tag selection information of a first user selecting a user tag; generating a recommendation request according to the user tag selection information, and sending the recommendation request to a server; receiving target information sent by the server and displaying it on a user interface; wherein the target information includes: information to be recommended for a target group, and the target group is obtained according to the user tag selection information.

[0008] In a third aspect, an embodiment of the present disclosure provides an electronic device. The electronic device is, for example, a server. The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following steps: receiving a recommendation request sent by a first terminal; determining a target group according to the recommendation request; and analyzing and processing the behavior data of the target group to obtain information to be recommended.

[0009] In a fourth aspect, an embodiment of the present disclosure provides an electronic device. The electronic device is, for example, a terminal device. The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following steps: receiving user tag selection information of a first user selecting a user tag; generating a recommendation request based on the user tag selection information, and sending the recommendation request to a server; receiving target information sent by the server and displaying it on a user interface; wherein the target information includes: information to be recommended for a target group, and the target group is obtained based on the user tag selection information.

[0010] According to an embodiment of the present disclosure, in the method for generating recommendation information provided in the first aspect or in the electronic device provided in the third aspect, the recommendation request carries user tag selection information related to the first user received by the first terminal. According to the recommendation request, determining the target group includes the following steps: detecting whether the user tag selection information carries the user tag selected by the first user; when it is detected that the user tag information carries the user tag selected by the first user, determining the user tag selected by the first user as a specific user tag, and determining the user group matching the specific user tag as the target group.

[0011] According to an embodiment of the present disclosure, in the method for generating recommendation information provided in the first aspect or in the electronic device provided in the third aspect, determining the target group according to the recommendation request also includes the following steps: when it is detected that the user tag information does not carry the user tag selected by the first user, determining the user group to which the first user belongs as the target group. Wherein, determining the user group to which the first user belongs as the target group includes: based on the first user tag and at least one difference tag of the first user, screening in the user database to obtain a target group that matches the first user tag and at least one difference tag, the difference tag differs from the first user tag in at least one attribute dimension.

[0012] According to an embodiment of the present disclosure, in the method for generating recommendation information provided in the first aspect or in the electronic device provided in the third aspect, the behavior data of the target group is analyzed and processed to obtain information to be recommended, including: analyzing the behavior data of the target group to obtain the number / proportion of users of each interactive behavior under each content that generates interactive behavior in the specific object information. Among them, the user ratio is the ratio of the number of users who have performed the interactive behavior to the total number of people in the target group. According to the preset weights of the interactive behaviors and the number / proportion of users, the attention corresponding to each content that generates the interactive behavior is determined. The contents are sorted according to the level of attention of each content. According to the results of sorting the contents, the information to be recommended is generated.

[0013] In the method for generating recommendation information provided in the first aspect or in the electronic device provided in the third aspect, according to an embodiment of the present disclosure, the attention corresponding to each content that generates the interactive behavior is determined based on the preset weights and the number / ratio of users of the interactive behavior, including: for each content that generates the interactive behavior, the number / ratio of users of each interactive behavior of the current content is weighted and calculated with the corresponding preset weight to obtain the attention corresponding to the current content. Or, according to another embodiment of the present disclosure, the attention corresponding to each content that generates the interactive behavior is determined based on the preset weights and the number / ratio of users of the interactive behavior, including: for each content that generates the interactive behavior, in each interactive behavior of the current content, invalid interactive behaviors with a number / ratio of users less than a preset threshold are eliminated to obtain the remaining valid interactive behaviors; the attention corresponding to the current content is obtained by weighting and calculating the number / ratio of users of the valid interactive behaviors with the corresponding preset weight.

[0014] According to an embodiment of the present disclosure, in the method for generating recommendation information provided in the first aspect or in the electronic device provided in the third aspect, the recommendation request carries the behavior label selection information related to the first user received by the first terminal. Among them, the behavior data of the target group is analyzed and processed to obtain the information to be recommended, including the following steps: determining the target interaction behavior according to the behavior label selection information; analyzing the behavior data of the target group to obtain the target content and the number / proportion of users corresponding to the target interaction behavior in the specific object information. Among them, the user ratio is the ratio of the number of users who have performed the target interaction behavior to the total number of people in the target group. According to the preset weight of the target interaction behavior and the number / proportion of users, the attention of the target content is determined. According to the attention of the target content, the target content is sorted. According to the result of the sorting of the target content, the information to be recommended about the behavior label selection information is generated.

[0015] According to an embodiment of the present disclosure, in the method for generating recommendation information provided in the first aspect or in the electronic device provided in the third aspect, the target interactive behavior is determined based on the behavior tag selection information, including: detecting whether the behavior tag selection information carries the behavior tag selected by the first user. When it is detected that the behavior tag selection information carries the behavior tag selected by the first user, the interactive behavior matching the behavior tag is determined as the target interactive behavior. When it is detected that the behavior tag selection information does not carry the behavior tag selected by the first user, all interactive behaviors occurring in the specific object information are determined as target interactive behaviors.

[0016] According to an embodiment of the present disclosure, in the method for generating recommendation information provided in the first aspect above, before receiving the recommendation request sent by the first terminal, it also includes: counting the user tags and behavior data of the user account. In the electronic device provided in the third aspect above, the executable instructions also enable the processor to perform the following steps: before receiving the recommendation request sent by the first terminal, counting the user tags and behavior data of the user account. Among them, the above-mentioned counting of user tags of the user account includes the following steps: structuring and organizing the user portrait data corresponding to the user account to generate user tags. The above-mentioned counting of the behavior data of the user account includes: counting the behavior data under the user account within a preset time period, and generating a behavior tag based on the above-mentioned behavior data.

[0017] According to an embodiment of the present disclosure, the method for generating recommendation information provided in the first aspect above also includes: performing validity verification on the generated user tags. When the number of users corresponding to the candidate user tags is lower than a preset threshold, the candidate user tags are regarded as invalid tags, and the invalid tags are eliminated. The remaining valid tags are used as user tags for users to select.

[0018] According to an embodiment of the present disclosure, in the electronic device provided in the third aspect, the executable instructions further enable the processor to perform the following steps: verify the validity of the generated user tags, and when the number of users corresponding to the candidate user tags is lower than a preset threshold, regard the candidate user tags as invalid tags, and eliminate the invalid tags, and use the remaining valid tags as user tags for users to select.

[0019] According to an embodiment of the present disclosure, the method for generating recommendation information provided in the first aspect further includes: sending the target information for recommendation to the first terminal. In the electronic device provided in the third aspect, the executable instruction further enables the processor to perform the following steps: sending the target information for recommendation to the first terminal. Among them, the sending of the target information for recommendation to the first terminal includes the following steps: receiving the ratio setting information sent by the first terminal, the ratio setting information being used to characterize the proportion of the information to be recommended relative to the target information for recommendation. When the ratio setting information is less than 100%, generating candidate information based on the historical behavior data under the current user account of the first terminal; combining the information to be recommended and the candidate information according to the ratio setting information to obtain the target information; and sending the target information to the first terminal. When the ratio setting information is 100%, sending the information to be recommended to the first terminal.

[0020] According to an embodiment of the present disclosure, the method for displaying recommendation information provided in the second aspect further includes: receiving behavior tag selection information of the first user selecting a behavior tag. In the electronic device provided in the fourth aspect, the executable instruction further causes the processor to perform the following steps: receiving behavior tag selection information of the first user selecting a behavior tag. The step of generating a recommendation request based on the user tag selection information includes the following steps: generating a recommendation request based on the user tag selection information and the behavior tag selection information.

[0021] According to an embodiment of the present disclosure, in the method for displaying recommended information provided in the second aspect, before receiving the target information sent by the server and displaying it on the user interface, it also includes: receiving the ratio setting information of the first user setting the ratio of the above-mentioned information to be recommended to the above-mentioned target information; and sending the above-mentioned ratio setting information to the server. In the electronic device provided in the fourth aspect, the executable instructions also enable the processor to perform the following steps: before receiving the target information sent by the server and displaying it on the user interface, receiving the ratio setting information of the first user setting the ratio of the above-mentioned information to be recommended to the above-mentioned target information; and sending the above-mentioned ratio setting information to the server. Wherein, in the case where the above-mentioned ratio setting information is less than 100%, the above-mentioned target information is the information obtained by combining the above-mentioned information to be recommended and the candidate information according to the above-mentioned ratio setting information, and the above-mentioned candidate information is the information generated according to the historical behavior data under the current user account.

[0022] In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for generating recommendation information as described above is implemented.

[0023] In a sixth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for displaying recommendation information as described above is implemented.

[0024] One or more technical solutions in the above embodiments have at least some or all of the following advantages:

[0025] By determining the target group based on the recommendation request, the target group has different preferences from the current user of the first terminal that initiates the request. The behavioral data of the above target group can reflect the overall preferences of the target group. Therefore, by analyzing and processing the behavioral data of the above target group, the information to be recommended is related to the overall preferences of the target group, thereby breaking the limitations of the current user's own preferences and preventing the user from being trapped in an information cocoon. Based on the above information to be recommended, differentiated information that is different from the user's own preferences can be recommended to the user, helping the user to broaden his horizons. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 The system architecture of the method for generating recommendation information and the method for displaying recommendation information applicable to the embodiment of the present disclosure is schematically shown;

[0029] Figure 2 The flowchart of the method for generating recommendation information according to an embodiment of the present disclosure is schematically shown;

[0030] Figure 3 The following schematically shows a flow chart of a method for generating recommendation information according to another embodiment of the present disclosure;

[0031] Figure 4 The detailed implementation flow chart of step S204 according to the embodiment of the present disclosure is schematically shown;

[0032] Figure 5A A detailed implementation flow chart of determining a user group to which a first user belongs as a target group according to an embodiment of the present disclosure is schematically shown;

[0033] Figure 5B A detailed implementation flow chart of determining a user group to which a first user belongs as a target group according to another embodiment of the present disclosure is schematically shown;

[0034] Fig. 6A The detailed implementation flow chart of step S206 according to an embodiment of the present disclosure is schematically shown;

[0035] Figure 6B The detailed implementation flow chart of step S206 according to another embodiment of the present disclosure is schematically shown;

[0036] Figure 7 The detailed implementation flow chart of sending the target information for recommendation to the first terminal according to the embodiment of the present disclosure is schematically shown;

[0037] Figure 8 The flowchart of the method for displaying recommendation information according to an embodiment of the present disclosure is schematically shown;

[0038] Fig. 9 The flowchart of the method for displaying recommendation information according to another embodiment of the present disclosure is schematically shown;

[0039] Fig.10 A flowchart schematically illustrates a method for displaying recommendation information according to another embodiment of the present disclosure; and

[0040] Fig.11 The structural block diagram of the electronic device provided by the embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0041] Embodiments of the present disclosure provide a method, electronic device, and storage medium for generating and displaying recommendation information. The above method for generating recommendation information includes: receiving a recommendation request sent by a first terminal; determining a target group based on the above recommendation request; and analyzing and processing the behavior data of the above target group to obtain information to be recommended. The above method for displaying recommendation information includes: receiving user tag selection information of a first user selecting a user tag; generating a recommendation request based on the above user tag selection information, and sending the above recommendation request to a server; receiving target information sent by the server and displaying it on a user interface; wherein the above target information includes: information to be recommended for the target group, and the above target group is obtained based on the above user tag selection information.

[0042] The method for generating recommendation information and the method for displaying recommendation information provided by the embodiments of the present disclosure can be applied to content recommendation in various scenarios. For example, the content information used for recommendation can include, but is not limited to: book information, movie information, short video information, news information, takeaway information, amusement park information, tourist attraction information, etc. An exemplary application scenario may be: obtaining the information to be recommended based on the behavior data of the target group, so that a book or a specific chapter of a book in the book information can be recommended based on the information to be recommended; or, a movie in the movie information, a specific plot / segment in a movie can be recommended; or, a short video of a certain type in the short video information, a short video corresponding to a certain content, or a part of a short video under a certain content can be recommended; and so on.

[0043] Based on the method for generating recommendation information and the method for displaying recommendation information provided by the embodiments of the present disclosure, the obtained information to be recommended may be book lists, movies, short videos, news, takeout, amusement parks, tourist attractions and other information corresponding to content related to the preferences of the target group, thereby breaking the limitations of the current user's own preferences and preventing the user from being trapped in an information cocoon. Based on the above information to be recommended, differentiated information that is different from the user's own preferences can be recommended to the user, helping the user to broaden his horizons.

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0045] Figure 1 The system architecture of the method for generating recommendation information and the method for displaying recommendation information applicable to the embodiments of the present disclosure is schematically shown.

[0046] Reference Figure 1 As shown, the system architecture 100 applicable to the method for generating recommendation information and the method for displaying recommendation information according to the embodiment of the present disclosure includes: terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0047] The user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as: e-book reading software / applications (APP), shopping applications, short video applications, web browser applications, search applications, news client applications, instant messaging tools, food delivery applications, social platform software, etc. (only as examples).

[0048] The terminal devices 101, 102, and 103 may be electronic devices with a display screen and supporting at least one of text, picture, and video playback, or the terminal devices 101, 102, and 103 may also be electronic devices with a display screen and supporting web browsing. For example, the electronic devices may include, but are not limited to: smart phones, tablet computers, laptop computers, desktop computers, smart watches, etc.

[0049] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides service support for the application interface or web page browsed by the user using the terminal devices 101, 102, 103. The background management server may analyze and process the received recommendation request, and feed back the result to be recommended (e.g., target information containing information to be recommended generated according to the user's recommendation request) obtained after data processing to the terminal device.

[0050] It should be noted that the method for generating recommendation information provided in the embodiment of the present disclosure can generally be executed by the server 105. The method for generating recommendation information provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. The method for displaying recommendation information provided in the embodiment of the present disclosure can generally be executed by the terminal devices 101, 102, 103.

[0051] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0052] In an exemplary implementation scenario, a user reads books, comics, etc. through an e-book reading software on a terminal device (for example, the e-book reading software is: an e-book reading app, or a browser that supports web-based e-books), and the server provides data support for the e-book reading software. After a user (hereinafter described as the first user) opens the e-book reading software or web-based e-book on a terminal device (the terminal device used by the first user is described as the first terminal), the first user can initiate a recommendation / search request by operating the e-book reading app or web-based e-book on the first terminal. Accordingly, the method for displaying recommended information provided by the embodiment of the present disclosure is executed on the first terminal (see the second embodiment to be described later); the server executes the method for generating recommended information provided by the embodiment of the present disclosure (see the first embodiment to be described later). The server can obtain the target information for recommendation to the terminal device based on the information to be recommended and send it to the terminal device. The terminal device displays the target information on the user interface to recommend it to the first user (current user) corresponding to the current user account.

[0053] Although the above scenario takes content information recommendation in an e-book reading scenario as an example, it can be understood that the application scenario of the technical solution provided by the embodiment of the present disclosure is not limited to the e-book reading scenario, and can be extended to any scenario where content information recommendation is required.

[0054] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0055] A first exemplary embodiment of the present disclosure provides a method of generating recommendation information.

[0056] Figure 2 The flowchart of the method for generating recommendation information according to an embodiment of the present disclosure is schematically shown.

[0057] Reference Figure 2 As shown, the method for generating recommendation information provided by the embodiment of the present disclosure includes the following steps: S202, S204 and S206. The above steps S202 to S206 can be executed by a server that provides data service support for application software (such as e-book reading software) installed on the terminal device.

[0058] In step S202, a recommendation request sent by a first terminal is received.

[0059] In the above step S202, the first terminal refers to a terminal device used by the user to whom the recommended information is given. The number of the above first terminals may be one or more, and the user (user) of the first terminal may be one or more. For example, one user uses multiple terminal devices, or multiple users use one terminal device, or multiple users use their own terminal devices. The above user refers to a user who has registered an account in the application software and uses the above application software with his or her own user account.

[0060] In other scenarios, if the current user uses someone else's account, the actual process of recommending information is to recommend information based on the current account. The server responds to the recommendation request of the current user (actual user) corresponding to the current account. The current user and the current user account may correspond or may not correspond. For example, in one implementation scenario, user A uses user account C. A After logging in, a recommendation request is initiated. The server executes steps S202 to S206, and the generated information about the target group to be recommended is sent to the current user account C. A In another implementation scenario, user A uses user account C B After logging in, a recommendation request is initiated. The server executes steps S202 to S206, and the generated information about the target group to be recommended is sent to the current user account C. B The current user A.

[0061] To simplify the description, the process of recommending information to a certain user is taken as an example here. It can be understood that the process of recommending information to scenarios such as a user using multiple terminal devices, or multiple users using one terminal device, or multiple users using their respective terminal devices can all refer to the process of recommending information to a single user (the actual user corresponding to the current account).

[0062] Exemplarily, the first user initiates a recommendation request on a first terminal installed with e-book reading software (as an example of application software). Upon receiving the recommendation request, the first terminal sends the recommendation request to the server. On the server side, when the server is in operation, it will continue to wait for the recommendation request from the first terminal. After the first terminal sends the recommendation request to the server, the server side receives the first request sent by the first terminal. For the server, the first user here refers to the current user corresponding to the current user account of the first terminal. The behavior data in the subsequent step S206 is based on the user account.

[0063] Although the above embodiment uses e-book reading software as an example of application software, it is understandable that the above application software can also be other application software in addition to recommending book information, such as application software for recommending movie information, short video information, news information, takeaway information, amusement park information, tourist attraction information, etc.

[0064] In step S204, the target group is determined according to the above recommendation request.

[0065] The target group is a group associated with the information carried in the recommendation request. In one embodiment, the recommendation request carries user tag selection information related to the first user received by the first terminal, and the target group is a group associated with the user tag selection information.

[0066] In one embodiment, this relevance may be reflected in: taking the group corresponding to the user tag selected by the first user (which may be the user tag corresponding to the group that the first user is interested in) as the target group. In another embodiment, this relevance may be reflected in that the features of the first user and the target group partially overlap, and the features of the target group also have differences compared to the features of the first user.

[0067] In step S206, the behavior data of the target group is analyzed and processed to obtain information to be recommended.

[0068] The behavior data of the target group may be directly obtained by the server from a database; or the server may obtain user data from a database and then filter the user data to obtain the behavior data of the target group.

[0069] By analyzing and processing the behavioral data of the target group, the corresponding recommended information can reflect the overall preferences of the target group, thereby breaking the limitations of the current user's own preferences and preventing users from falling into information cocoons.

[0070] Based on the above steps S202 to S206, the target group is determined according to the recommendation request. The target group has preferences different from the current user of the first terminal that initiates the request. The behavior data of the above target group can reflect the overall preference of the target group. Therefore, by analyzing and processing the behavior data of the above target group, the information to be recommended is related to the overall preference of the target group, thereby breaking the limitations of the current user's own preferences and preventing the user from being trapped in an information cocoon. Based on the above information to be recommended, differentiated information that is different from the user's own preferences can be recommended to the user, helping the user to broaden his horizons.

[0071] Figure 3 The flowchart of a method for generating recommendation information according to another embodiment of the present disclosure is schematically shown.

[0072] According to an embodiment of the present disclosure, the method for generating recommendation information includes, in addition to the above steps S202 to S206, a further step S301: counting user tags and behavior data of user accounts.

[0073] This step S301 is executed before the above step S202, and for multiple recommendation requests initiated by one or more users, the statistical results generated by the above step S301 can be directly called, that is, there is no need to execute step S301 of counting user tags and behavior data every time a recommendation request is received.

[0074] The statistical step can be executed after the server is started, and the statistical cycle can be set to a preset time period, such as this week, this month, the previous three months, etc. In addition, the statistical results will be updated in real time as time goes by. For example, the statistical results on May 20 will be updated to the statistical results on June 1 when used on June 1. For example, the update frequency can be set, such as updating the statistical results every three days (the specific value can be changed), so that the statistical results have good reference value and timeliness.

[0075] According to an embodiment of the present disclosure, counting user tags of user accounts includes: structuring user portrait data corresponding to the user accounts to generate user tags. The user tags can represent the characteristics of the users.

[0076] For example, the server records the user data of e-book reading software (an example of application software) and extracts user portrait data from it, including but not limited to: age, gender, occupational identity (student, white-collar worker, carpenter, entrepreneur, civil servant, police), monthly income, region (Beijing, Shanghai), educational background (study abroad, English major, computer major), hobbies, consumption index, etc., and can generate user tags after structuring the above user portrait data. For example, the generated user tags include: age, gender, student, white-collar worker, carpenter, entrepreneur, civil servant, police, monthly income of more than 5k, monthly income of 10k to 15k, monthly income of more than 20k, Beijing, Shanghai, study abroad, English major, computer major, literature major, like reading books, like watching movies, like outdoor sports, etc., average monthly consumption of 3k, moonlight clan, etc.

[0077] According to an embodiment of the present disclosure, counting the behavior data of a user account includes: counting the behavior data of the user account within a preset time period, and generating a behavior tag based on the behavior data.

[0078] The above preset time period can be set according to statistical requirements. In the recommendation scenario, the preset time period should try to meet the timeliness, such as within the past week, within the past month, etc. Behavior data includes but is not limited to: like, follow, annotate, forward, comment, share, underline, comment, favorite, etc. Behavior tags correspond to the statistical behavior content, such as: like, comment, underline, forward, favorite, etc.

[0079] In an embodiment of the present disclosure, the user tag generated by the server can be directly used as a user tag displayed / shown on various terminal devices (eg, including the first terminal and other terminal devices with application programs installed) for selection by the user.

[0080] In another embodiment of the present disclosure, after generating user tags, it may also include: performing validity verification on the generated user tags, and when the number of users corresponding to the candidate user tags is lower than a preset threshold, the above candidate user tags are regarded as invalid tags, and the invalid tags are eliminated, and the remaining valid tags are used as user tags for users to select.

[0081] In this embodiment, in the scenario of big data, invalid user tags are screened out based on the number of users, so that the tags presented to users for selection are all valid tags, ensuring the reliability of user tags. In addition, the target group determined by the server based on the user tag selection information is representative, and the recommended information obtained based on the behavior data of the target group can reflect the overall preferences of the target group.

[0082] Figure 4 The detailed implementation flow chart of step S204 according to the embodiment of the present disclosure is schematically shown.

[0083] According to an embodiment of the present disclosure, the recommendation request carries the user tag selection information related to the first user received by the first terminal.

[0084] In an exemplary implementation scenario, the user interface of the terminal device will display options for user tags for the user to select. These user tags are obtained by the server by pre-implementing the user tags of the user account in the above step S301. On the first terminal side, the user tag selection information of the first user selecting the user tag is received; according to the user tag selection information, a recommendation request is generated, and the recommendation request is sent to the server. Then, on the server side, the received recommendation request carries the user tag selection information related to the first user received by the first terminal.

[0085] Reference Figure 4As shown, in the above step S204, according to the above recommendation request, determining the target group includes the following steps: S401, and one of S402a and S402b. In one recommendation request, only one of S402a and S402b is executed, and in multiple recommendation requests, at least one of S402a and S402b may be executed.

[0086] In step S401, it is detected whether the user tag selection information carries the user tag selected by the first user.

[0087] In an actual scenario, the user may select the user tag or not, for example, select the skip option. By determining whether the user tag selection information carries the user tag selected by the first user, it can be determined whether to execute step S402a or step S402b.

[0088] In step S402a, when it is detected that the user tag information carries the user tag selected by the first user, the user tag selected by the first user is determined as a specific user tag, and the user group matching the specific user tag is determined as a target group.

[0089] The label selection information may include: a user label, or a combination of multiple user labels. For example, the label selection information is a combination of the following three labels selected by the first user from a label selection list including "general undergraduate colleges, 211 / 985 colleges, literature department, physics department, physical education department, ..., professor, lecturer, student, ..., principal": "211 / 985 colleges", "literature department", "professor".

[0090] In the above step S402a, the group of people matching the three label combinations of "211 / 985 colleges", "Department of Literature" and "Professor" is the target group.

[0091] By screening in the user database, the behavioral data of the above-mentioned target groups can be obtained.

[0092] In step S402b, when it is detected that the user tag information does not carry the user tag selected by the first user, the user group to which the first user belongs is determined as the target group.

[0093] In the above step S402b, the application scenario corresponding to the failure to receive the above tag selection information may be: the user does not select in the tag selection list of the terminal device (here, the first terminal), or does not click in the selection box after a specific tag. For example, the user interface of the above application software (such as e-book reading software) also provides a skip option or a default option for the tag selection list. When the user chooses to skip or selects the default option, step S402b is correspondingly implemented on the server side.

[0094] In this embodiment, a user selection mode is provided. In the user selection mode, tag options are provided to the user. The first user (the current user who needs recommended information) can freely select and combine tags according to his own interests, so as to obtain a customized target group on the server side. If the user does not select a tag option, the default mode is entered to determine the target group, and the information to be recommended is generated according to the behavior data of the target group.

[0095] Figure 5A A detailed implementation flow chart of determining the user group to which the first user belongs as the target group according to an embodiment of the present disclosure is schematically shown.

[0096] According to an embodiment of the present disclosure, determining the user group to which the first user belongs as the target group includes step S511, such as Figure 5A shown.

[0097] In step S511, according to the first user tag of the first user, a first user group including the first user tag is screened in a user database, and the first user group is used as a target group.

[0098] In this embodiment, the first user group including the first user tag is used as the target group. The first user group including the first user tag here may only include the first user tag, or in addition to the first user tag, also include at least one other tag. The first user tag of the first user mentioned above refers to some or all tags under the user account corresponding to the current user (for example, the first user account). The user tag data is relative to the user account. The current user is identified based on the user account. The actual user of the current user account (the current user) may not be the nominal user of the current account (for example, user A in the aforementioned example uses user account C). B Initiate a recommendation request after logging in), in this scenario, the data corresponding to the current user account is used as the basis, that is, the first user tag of the first user refers to the user account C B All or part of the user tags under .

[0099] Exemplarily, the first user (the current user corresponding to the current account) is an Internet product manager who has worked for 5 years, and the corresponding user tags include: "Working for 5 years" and "Internet product manager", and the above-mentioned first user tag may include at least one of the following tags "Working for 5 years" and "Internet product manager". Correspondingly, the first user group including the first user tag may be one of the following examples: "Teacher who has worked for 5 years", "Literary worker who has worked for 5 years", ..., "Programmer who has worked for 5 years" (corresponding to the first user tag of "Working for 5 years"); "Internet product manager with a monthly salary of more than 50,000", ..., "Internet product manager who works in Beijing and has a monthly salary of more than 50,000" (corresponding to the first user tag of "Internet product manager"); "Internet product manager who has worked for 5 years and has a monthly salary of more than 50,000", ..., "Internet product manager who has worked in Beijing for 5 years and has a monthly salary of more than 50,000" (corresponding to the first user tags of "Working for 5 years" and "Internet product manager").

[0100] Figure 5B A detailed implementation flowchart of determining a user group to which a first user belongs as a target group according to another embodiment of the present disclosure is schematically shown.

[0101] According to another embodiment of the present disclosure, determining the user group to which the first user belongs as the target group includes step S521, such as Figure 5B shown.

[0102] In step S521, based on the first user tag and at least one difference tag of the first user, a user database is screened to obtain a second user group that matches the first user tag and at least one difference tag, and the second user group is used as a target group. The difference tag is different from the first user tag in at least one attribute dimension.

[0103] In this embodiment, a second user group including a first user tag and at least one difference tag (in order to be described differently from the aforementioned first target group) is used as the target group.

[0104] The above-mentioned difference label is different from the above-mentioned first user label in at least one attribute dimension. For example, the first user label is "Internet product manager with 5 years of work experience", which has two attribute dimensions: years of work experience and professional identity. The difference label can have a difference in the number of attributes or attribute types with the first user label, or a difference in attribute content. For example, the difference label is one of the following examples: "Data analyst with 5 years of work experience", "Literary worker with 10 years of work experience", "Internet product manager working in Beijing with an annual income of more than 500,000", "Students from 211 / 985 colleges", etc.

[0105] Similar to the above embodiment, the first user tag of the first user is part of or all of the tags under the current user account. Correspondingly, the second user group including the first user tag and at least one difference tag is also clear, and no further examples are given here.

[0106] In the embodiments of the present disclosure, two modes, a default mode and a user selection mode, are provided to generate information to be recommended. Fig. 6A and Figure 6B To describe the process of how to generate the information to be recommended.

[0107] Fig. 6A The detailed implementation flow chart of step S206 according to an embodiment of the present disclosure is schematically shown.

[0108] According to the embodiments of the present disclosure, referring to Fig. 6A As shown, in the above step S206, the behavior data of the above target group is analyzed and processed to obtain the information to be recommended, which includes the following steps: S611, S612, S613 and S614.

[0109] In step S611, the behavior data of the target group is analyzed to obtain the number / ratio of users of each interactive behavior under each content that generates interactive behavior in the specific object information.

[0110] Among them, the user ratio is the ratio of the number of users who have performed interactive behaviors to the total number of people in the target group.

[0111] The above-mentioned specific object information may include but is not limited to: book information, movie information, short video information, news information, takeaway information, amusement park information, tourist attraction information, etc. The above-mentioned specific object information is set by the server according to the information recommendation requirements of the application software provided by the service. For example, for the scenario where the application software is about e-book reading, the above-mentioned specific object information is book information; for the scenario where the application software is about short video recommendation, the above-mentioned specific object information is short video information. In the behavior data of the target group, for each content that generates interactive behavior in the specific object information, the statistical results of the number / proportion of users of each interactive behavior can be described as the interactive behavior statistics.

[0112] Exemplarily, taking the e-book reading scenario as an example, the above-mentioned specific object information is book information, and the target group is, for example: Internet product managers. The different contents of book information are reflected in different books / short videos, or in different paragraphs, different lines, different chapters, etc. of the same book. For example, "First Principles" and "Behind the Scenes Products" are different contents in book information; different paragraphs / chapter / text lines in "Behind the Scenes Products" also belong to different contents of book information. The above-mentioned interactive behaviors include one or more of the following behaviors: which paragraphs / chapter / lines in which books are underlined and annotated, which books are read (it may also further include reading time information, reading page turning speed, reading stay time, etc.), collection, forwarding, commenting, etc. Correspondingly, the interactive behavior statistics are the behavioral statistics obtained by statistically analyzing the interactive behaviors actually generated by Internet product managers (target groups) during the reading process. Exemplarily, there are 10,000 Internet product managers in total, and the above interactive behavior statistics include: 30% (3,000 people) of the Internet product managers have read the book "Behind the Scenes Product"; 10% (1,000 people) of the Internet product managers have forwarded the book "Behind the Scenes Product", and 2% (200 people) of the Internet product managers have commented on the book "Behind the Scenes Product"; 15% (1,500 people) of the Internet product managers have read the book "The Age of Big Data", and 10% (1,000 people) of the Internet product managers have underlined the ×× paragraph in the book "The Age of Big Data", etc.

[0113] It is understandable that the above-mentioned e-book reading scenario is only used as an example. In other application scenarios, the above-mentioned explanation and description of the statistical results of interactive behaviors in the e-book reading scenario can be adaptively referred to.

[0114] In step S612, the attention level corresponding to each content generating the interactive behavior is determined according to the preset weight of the interactive behavior and the number / ratio of users. In the embodiment of the present disclosure, the " / " in "A / B" means: or.

[0115] The above preset weights are set according to the relative importance of the interactive behaviors. For example, there are five types of interactive behaviors, namely forwarding, reading, underlining, collecting, and commenting. The preset weight of forwarding is 0.3 points, the preset weight of reading is 0.2, the preset weight of underlining is 0.1, the preset weight of collecting is 0.2, and the preset weight of commenting is 0.2.

[0116] In step S613, the above contents are sorted according to the degree of attention of each content.

[0117] For example, the contents generating interactive behaviors in the above-mentioned specific object information may be ranked in order of attention from high to low.

[0118] In step S614, information to be recommended is generated according to the results of sorting the above contents.

[0119] The above step S614 can be implemented in various ways, as long as it is a recommendation method related to the ranking results of each content that generates interactive behaviors, it can be used as a method for generating information to be recommended. For example, a preset number of contents (such as the top 3) ranked at the top of the above content ranking results are used as information to be recommended; or, based on the content ranking results, similar content is recommended; or, based on the content ranking results, content with the same author is recommended; or, based on the content ranking results, content with the same category is recommended, etc.

[0120] For example, recommend similar content: In the ranking results of the target group, the first book is "Behind the Scenes Product", and the generated information to be recommended is: "Product Methodology". Recommend content by the same author: In the ranking results of the target group, the top three books are "Behind the Scenes Product", "Big Data Era" and "Big Data Foundation and Application" by the same author X, so another book by the same author X is recommended: "Big Data Analysis: Turning Numbers into Gold".

[0121] In this embodiment, in the default mode, no choice is provided to the user, and the default logic of the application system / application software (for example, reading / movie recommendations / short videos / news applications / takeout / travel and other application systems) is: content is sorted according to the level of attention paid to the interactive behavior, and then the information to be recommended is generated based on the results of the above content sorting.

[0122] Figure 6B The detailed implementation flow chart of step S206 according to another embodiment of the present disclosure is schematically shown.

[0123] In this embodiment, a user selection mode is provided, in which the user is provided with the option of behavior tags, and the user can select the behavior that the user is interested in for the target group. If the user does not select the behavior corresponding to the behavior tag, the information to be recommended is generated in the same manner as in the above embodiment (default mode).

[0124] According to an embodiment of the present disclosure, the recommendation request carries the behavior tag selection information related to the first user received by the first terminal.

[0125] In an exemplary implementation scenario, in addition to displaying options for user tags for users to select, the user interface of the terminal device also displays options for behavior tags for users to select. These behavior tags are obtained by the server by pre-implementing the above step S301 to collect behavioral data of user accounts.

[0126] Reference Figure 6BAs shown, in the above step S206, the behavior data of the above target group is analyzed and processed to obtain the information to be recommended, including the following steps: S621, S622, S623, S624 and S625.

[0127] In step S621, the target interactive behavior is determined according to the above behavior tag selection information.

[0128] In the implementation scenario of step S621, a behavior tag selection list is provided on the user interface of the application software (e.g., e-book reading application software), and each behavior tag in the behavior tag selection list is a user behavior option obtained by counting the actual behavior of the user, such as but not limited to one or more of the behaviors represented by the following behavior tags: collection, underline, reading, forwarding, like, comment, follow, etc.

[0129] By selecting (for example, the first user selects on the first terminal) behavior tags corresponding to one or more behaviors that the target group is interested in from the behavior tag selection list of the terminal device, the server side can obtain the information to be recommended by implementing the above steps S621 to S625.

[0130] According to an embodiment of the present disclosure, the target interactive behavior is determined based on the above-mentioned behavior label selection information, including: detecting whether the above-mentioned behavior label selection information carries the behavior label selected by the above-mentioned first user; when it is detected that the above-mentioned behavior label selection information carries the behavior label selected by the above-mentioned first user, the interactive behavior matching the above-mentioned behavior label is determined as the target interactive behavior; when it is detected that the above-mentioned behavior label selection information does not carry the behavior label selected by the above-mentioned first user, all interactive behaviors occurring in the specific object information are determined as target interactive behaviors.

[0131] Based on the above, it can be known that when the first user selects a behavior tag, the interactive behavior matching the behavior tag selected by the first user is determined as the target interactive behavior, so as to achieve information recommendation related to the user's selected behavior (such as like behavior, collection behavior, etc.). When the first user does not select any behavior tag (such as selecting the skip option), all interactive behaviors occurring in the specific object information to be recommended by the current application are determined as target interactive behaviors, for example, all interactive behaviors occurring in the book information to be recommended by the e-book reading software are determined as target interactive behaviors; in this case, the implementation process in steps S622 to S625 is substantially the same as the process corresponding to the aforementioned steps S611 to S614.

[0132] In step S622, the behavior data of the target group is analyzed to obtain the target content and the number / proportion of users corresponding to the target interactive behavior in the specific object information.

[0133] Among them, the user ratio is the ratio of the number of users who have performed the target interactive behavior to the total number of people in the target group.

[0134] In an exemplary embodiment, the first terminal receives the first user-related behavior tag selection information: for the target group "Internet product managers with 5 years of work", the behavior tag "collection behavior" is selected. In step S622, the behavior data of the target group "Internet product managers with 5 years of work" is analyzed to obtain the target content and user quantity / proportion corresponding to the target interaction behavior of "collection behavior" in the book information, including: among the Internet product managers with 5 years of work, 30% of users have collected the book "Behind the Scenes Products", 20% of users have collected "Probability Theory", 10% of users have collected "Big Data Era", 5% of users have collected "Big Data Foundation and Application", and so on.

[0135] In another exemplary embodiment, the behavior tag selection information related to the first user received by the first terminal is: the first user has not selected any behavior tag. In this case, the default mode is entered and the target interaction behavior is determined as: all interaction behaviors occurring in the specific object information to be recommended by the current application.

[0136] In step S623, the attention level of the target content is determined according to the preset weight of the target interactive behavior and the number / proportion of users.

[0137] Exemplarily, when the target interactive behavior is collecting behavior, the preset weight of collecting is 0.2. Then, based on the preset weight of 0.2 of the target interactive behavior of collecting and the user ratio, the target contents corresponding to the target interactive behavior can be determined: the attention levels of "Behind the Scenes Products", "Probability Theory", "Big Data Era", and "Big Data Foundations and Applications" are respectively: 0.2×30%=0.06, 0.2×20%=0.04, 0.2×10%=0.02, and 0.2×5%=0.01.

[0138] In step S624, the target contents are sorted according to the degree of attention of the target contents.

[0139] Exemplarily, according to the level of attention paid to the above target contents, the target contents are sorted, and the following sorting results are obtained in order from first to last: "Behind-the-scenes Products", "Probability Theory", "Big Data Era", and "Big Data Foundations and Applications".

[0140] In step S625, based on the result of sorting the target content, information to be recommended regarding the behavior tag selection information is generated.

[0141] The implementation method of generating the information to be recommended according to the target content ranking results in step S625 can be various implementation methods, as long as it is a recommendation method related to the ranking results of each target content, it can be used as a method for generating the information to be recommended. Specific examples can be found in the description of step S614, which will not be repeated here.

[0142] In the above-mentioned embodiment, in step S612, according to the preset weight of the above-mentioned interactive behavior and the above-mentioned number / proportion of users, determining the attention level corresponding to each content generating the interactive behavior has the following implementation mode.

[0143] According to an embodiment of the present disclosure, the degree of attention corresponding to each content that generates interactive behavior is determined based on the preset weights of the above-mentioned interactive behaviors and the above-mentioned number / proportion of users, including: for each content that generates interactive behavior, the number / proportion of users of each interactive behavior of the current content is weighted and calculated with the corresponding preset weight to obtain the degree of attention corresponding to the current content.

[0144] In an exemplary embodiment, the various interactive behaviors are: forwarding, reading, underlining, collecting, and commenting, among which the preset weight of forwarding is 0.3 points, the preset weight of reading is 0.2, the preset weight of underlining is 0.1, the preset weight of collecting is 0.2, and the preset weight of commenting is 0.2. In the statistical results of the interactive behaviors of the target group of professors of literature departments in 211 / 985 institutions, 50% of users commented on and forwarded "Border Town", 30% of users read "One Hundred Years of Solitude"; 20% of users collected "The Scream", 10% of users commented on "Ordinary World", 6% of users collected "A Brief History of Time", and 9% of users forwarded "A Brief History of Time".

[0145] In this embodiment, the attention degree can be obtained by calculating the weighted sum. Based on the logic of determining the attention degree in this embodiment, the calculation expression of the attention degree of "Border Town" is, for example, 50%×(0.2+0.3)=0.25; the calculation expression of the attention degree of "One Hundred Years of Solitude" is, for example, 30%×0.2=0.06; the calculation expression of the attention degree of "The Scream" is, for example, 20%×0.2=0.04; the calculation expression of the attention degree of "Ordinary World" is, for example, 10%×0.2=0.02; the calculation expression of the attention degree of "A Brief History of Time" is, for example, 6%×0.2+9%×0.3=0.039.

[0146] In this embodiment, the idea of ​​calculating the attention degree is: considering all behaviors generated by users of the target group under each content, and obtaining the attention degree according to the relative importance (preset weight) of each behavior and the statistical distribution of the number of users. The attention degree obtained by this calculation method can reflect all user interaction data of each content, and more comprehensively reflect the attention degree of the target group to each content.

[0147] According to another embodiment of the present disclosure, the attention level corresponding to each content that generates the interaction behavior is determined based on the preset weight of the above-mentioned interaction behavior and the above-mentioned number / ratio of users, including: for each content that generates the interaction behavior, in each interaction behavior of the current content, invalid interaction behaviors whose number / ratio of users is less than a preset threshold are eliminated to obtain the remaining valid interaction behaviors. The attention level corresponding to the current content is obtained by weighted sum calculation based on the number / ratio of users of the above-mentioned valid interaction behaviors and the corresponding preset weight.

[0148] In this embodiment, invalid interactive behaviors in each content are first eliminated, and then the remaining valid interactive behaviors are weighted and calculated with their respective preset weights to obtain the attention of the current content. The following still takes the interactive behavior statistics of the target group of professors of the Department of Literature of 211 / 985 colleges in the above embodiment as an example, where the preset thresholds corresponding to forwarding, reading, underlining, collection, and commenting are: 20%, 20%, 10%, 5%, and 10%, respectively. For "Border Town", the proportion of users who comment and forward are greater than the preset threshold, so both commenting and forwarding are valid interactive behaviors. Similarly, for "One Hundred Years of Solitude", reading is an effective interactive behavior. For "The Scream", collection is an effective interactive behavior. For "Ordinary World", the proportion of users who comment is equal to the preset threshold, which is an effective interactive behavior. For "A Brief History of Time", collection is an effective interactive behavior; the proportion of users who forward behavior is 9%, which is less than the preset threshold of 20%, which is an invalid interactive behavior. Therefore, the invalid interaction behavior of 9% of users forwarding "A Brief History of Time" is first eliminated, and the attention of each content is calculated by weighted sum for the remaining valid interactions. The calculation expression of the attention of "Border Town" is, for example, 50%×(0.2+0.3)=0.25; the calculation expression of the attention of "One Hundred Years of Solitude" is, for example, 30%×0.2=0.06; the calculation expression of the attention of "The Scream" is, for example, 20%×0.2=0.04; the calculation expression of the attention of "Ordinary World" is, for example, 10%×0.2=0.02; the calculation expression of the attention of "A Brief History of Time" is, for example, 6%×0.2=0.012.

[0149] In this embodiment, the idea of ​​calculating the attention degree is: for different user behaviors generated by the target group, only when the number / proportion of users corresponding to the behavior is greater than or equal to the preset threshold, the user behavior of the target group will be considered valid, and then the attention degree is calculated based on the valid data. The attention degree obtained under this calculation method can ensure that the overall distribution of attention degree is closer to the overall preference trend of the target group by eliminating invalid behavior data.

[0150] Figure 7 The detailed implementation flow chart of sending target information for recommendation to the first terminal according to an embodiment of the present disclosure is schematically shown.

[0151] The method for generating recommendation information provided by the embodiment of the present disclosure may further include the following steps in addition to the above operations S202 to S206: sending target information for recommendation to the first terminal, wherein the target information includes: information to be recommended. The information to be recommended is part of or all of the target information.

[0152] In one embodiment, referring to Figure 7 As shown, sending target information for recommendation to the first terminal includes the following steps: S711 and {S712a, S713a and S714a} or {S712b} in the following group of steps.

[0153] In step S711, ratio setting information sent by the first terminal is received, where the ratio setting information is used to represent the ratio of the information to be recommended to the target information for recommendation.

[0154] The above ratio setting information may be set by the user (first user) corresponding to the current user account on the first terminal.

[0155] When the ratio setting information is less than 100%, steps S712a to S714a are executed.

[0156] In step S712a, candidate information is generated according to the historical behavior data of the current user account of the first terminal.

[0157] In step S713a, the information to be recommended and the candidate information are combined according to the ratio setting information to obtain the target information.

[0158] In step S714a, the target information is sent to the first terminal.

[0159] Based on the above steps S712a to S714a, by combining the information to be recommended and the candidate information according to the proportion setting information, the target information obtained contains both content related to the preferences of the target group and content related to the preferences of the user corresponding to the current user account. The target information can not only ensure a high probability of attracting the interest of the current user, but also expand the information receiving surface of the current user, and can take into account the breadth and accuracy of the recommended information. While avoiding users from falling into information cocoons, it can also provide users with a proportion of information presentation for the target group. For example, applying the above method to the field of e-book reading can help increase the probability of users clicking on book lists and increase reading volume.

[0160] In step S712b, when the ratio setting information is 100%, the information to be recommended is sent to the first terminal.

[0161] When the user chooses to use the information to be recommended generated according to the target group as all the information in the target information for recommendation, the information to be recommended obtained in step S206 is sent to the first terminal for information presentation / display at the first terminal.

[0162] In this embodiment, the user can set the ratio of the information to be recommended in the target information. When the ratio setting information is R, and R is less than 100%, the server generates candidate information based on the historical behavior data of the current user account, and then combines the above information to be recommended according to the ratio R and the candidate information according to the ratio 1-R to obtain the target information. For example, if the number of recommended items set for the target information is 20, and the ratio R of the information to be recommended is 80%, then 16 items are information to be recommended and 4 items are candidate information.

[0163] It can be understood that, when the ratio setting information R=100%, the information to be recommended is the above-mentioned target information.

[0164] In the above embodiment, the user is provided with a selection of the proportion of the information to be recommended generated according to the target group corresponding to the user tag selected by the user to the target information for recommendation. In other embodiments of the present disclosure, a default recommendation logic may also be set, and the user is not provided with a proportion selection. For example, in an embodiment including operations S202 to S206, after operation S206, the following operation is also included: sending the information to be recommended to the current user account of the first terminal. That is, the above information to be recommended is used as all the information in the target information.

[0165] In summary, the method for generating recommendation information provided by the embodiment of the present disclosure proposes a method for recommendation based on the target group. This recommendation method analyzes and processes the behavior data of the target group, and the information to be recommended is related to the overall preference of the target group, so as to break the limitations of the current user's own preferences and avoid the user from falling into the information cocoon. Based on the above information to be recommended, differentiated information that is different from the user's own preferences can be recommended to the user to help the user broaden his horizons. This recommendation method is completely different from the stereotyped recommendation idea of ​​recommending based on each user's own preferences (for example, recommending based on content or user's own attributes). The recommendation method is very novel and can provide users with a recommendation method that is differentiated from their own preferences. For example, a user whose professional identity is a software engineer can obtain the information to be recommended related to the target group by selecting the user label corresponding to the target group of "Professor of Literature Department of 211 / 985 Colleges", thereby broadening the user's horizons and having high social value. In a specific application scenario, such as the scenario of e-book reading, the above recommendation method can take into account the reader's interest preferences and broaden the reader's reading field, which helps to improve the user reading volume and click-through rate of e-book reading software. It is understandable that in scenarios where users select user tags that are related or unrelated to themselves, or in scenarios where users do not select user tags, this target group-based recommendation method can prevent users from falling into an information cocoon.

[0166] The second exemplary embodiment of the present disclosure provides a method for displaying recommended information. Compared with the first embodiment, which is described from the perspective of generating recommended information on the server side, the method for displaying recommended information provided in this embodiment is described from the perspective of the terminal device side. In the overall implementation scenario, the first embodiment and this embodiment can be combined to obtain a complete path of the information flow.

[0167] Figure 8 The flowchart of the method for displaying recommendation information according to an embodiment of the present disclosure is schematically shown.

[0168] Reference Figure 8 As shown, the method for displaying recommendation information provided by the embodiment of the present disclosure includes the following steps: S801, S803 and S805.

[0169] In step S801, user tag selection information of a first user selecting a user tag is received.

[0170] On the terminal device, a user tag selection list is provided on the user interface of the application software (eg, e-book reading software); or all selectable user tags are presented on the user interface, and a selection box for the user to select is provided after each user tag.

[0171] When the current user (e.g., the first user) under a certain user account (e.g., the first user account) logs in to the account in the user interface of the application software of a certain terminal device (e.g., the first terminal), by selecting in the above-mentioned user tag selection list, or clicking the skip option (which can be set to other non-selection forms), or clicking in the selection box after a specific user tag, or confirming the selection of the skip option, the above-mentioned tag selection information related to the first user corresponding to the first user account is received on the corresponding terminal device (the terminal device corresponding to the first embodiment is described as the first terminal).

[0172] In step S803, a recommendation request is generated according to the user tag selection information, and the recommendation request is sent to the server.

[0173] When the first terminal receives the user tag selection information, it generates a recommendation request carrying the tag selection information according to the user tag selection information, and sends the recommendation request to the server.

[0174] After step S803, the server performs the above operations S202, S204 and S206 to obtain the information to be recommended. Afterwards, the server sends the target information for recommendation to the first terminal, wherein the target information includes the above information to be recommended.

[0175] In step S805, the target information sent by the server is received and displayed on the user interface; wherein the target information includes: information to be recommended for a target group, the target group being obtained according to the user tag selection information.

[0176] Based on the above steps S801 to S805, the user selects the user tag corresponding to the group of interest on the user interface of the application software or does not select any user tag. The terminal device generates a recommendation request based on the user tag selection information and forwards it to the server, thereby receiving the recommended target information sent by the server. This target information includes the recommended information generated based on the behavioral data of the target group corresponding to the user tag selection information, and displays information that is differentiated from the user's personal preferences to the user under the current account, thereby preventing the user from falling into an information cocoon.

[0177] It is understandable that step S301 on the server side is to be executed before step S801 on the terminal device, so that based on the user tags obtained in step S301, a selection list or selection box of user tags for the user to select can be generated on the user interface of the terminal device.

[0178] Fig. 9 The flowchart of a method for displaying recommendation information according to another embodiment of the present disclosure is schematically shown.

[0179] The method for displaying recommended information provided by the embodiment of the present disclosure includes, in addition to the above steps S801 to S805, the following steps: S901, receiving the behavior tag selection information of the above first user selecting the behavior tag. For simplicity, refer to Fig. 9 As shown, only S901 and S803a are illustrated.

[0180] The above step S901 can be combined with step S801 and implemented in one step, or they can be implemented one after another, and the user interface provides options of user tags and behavior tags for the user to select. It is understandable that step S301 on the server side is executed before step S901 in this embodiment.

[0181] Accordingly, in the embodiment including step S901, in the above step S803, generating a recommendation request according to the above user tag selection information includes step S803a: generating a recommendation request according to the above user tag selection information and the above behavior tag selection information. The above recommendation request carries the user tag selection information and the behavior tag selection information.

[0182] Correspondingly, on the server side, step S206 is implemented by implementing the following steps S621, S622, S623, S624 and S625.

[0183] Fig.10 The flowchart of a method for displaying recommendation information according to another embodiment of the present disclosure is schematically shown.

[0184] Based on the above embodiments, before the above step S805, the following steps are further included: S1001 and S1002. For simplicity, Fig.10 Only steps S1001, S1002 and S805 are illustrated.

[0185] In step S1001, ratio setting information of a first user for setting the ratio of the information to be recommended to the target information is received.

[0186] In step S1002, the above ratio setting information is sent to the server.

[0187] Among them, when the above-mentioned ratio setting information is less than 100%, the above-mentioned target information is information obtained by combining the above-mentioned information to be recommended and candidate information according to the above-mentioned ratio setting information, and the above-mentioned candidate information is information generated according to the historical behavior data under the current user account.

[0188] In some embodiments, the above step S1001 can be executed after step S801, or combined with step S801 to be executed in one step. When combined with step S801 to be executed in one step, step S1002 can be combined with step S803 to be executed, and the generated recommendation request also carries: ratio setting information. Alternatively, in some other embodiments, the above steps S1001 and S1002 are executed after step S803, and correspondingly, the server side sends the target information for recommendation to the first terminal, including the following steps: S711 and {S712a, S713a and S714a} or {S712b} in the following step group. The above execution order is only an example, and the execution order can be adaptively adjusted as long as it does not affect the overall technical effect.

[0189] The above-mentioned various technical solutions provided by the embodiments of the present disclosure can be implemented in hardware in all or part of the steps, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the electronic device according to the embodiments of the present disclosure. The embodiments of the present disclosure can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. The program implementing the embodiments of the present disclosure can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0190] A third exemplary embodiment of the present disclosure provides an electronic device.

[0191] Fig.11 The structural block diagram of the electronic device provided by the embodiment of the present disclosure is schematically shown.

[0192] Reference Fig.11 As shown, the electronic device 1100 provided by the embodiment of the present disclosure includes a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104, wherein the processor 1101, the communication interface 1102 and the memory 1103 communicate with each other via the communication bus 1104; the memory 1103 is used to store at least one executable instruction; the processor 1101 is used to implement the method for generating recommendation information or the method for displaying recommendation information as described above when executing the executable instruction stored in the memory.

[0193] Specifically, when implementing the above method for generating recommendation information, the above executable instructions enable the above processor to perform the following steps: receiving a recommendation request sent by the first terminal; determining a target group according to the above recommendation request; and analyzing and processing the behavior data of the above target group to obtain the information to be recommended. The detailed implementation process of each of the above steps and the steps further included in the above method for generating recommendation information can refer to the description of the first embodiment and will not be repeated here. The electronic device of this embodiment can be: a server that provides data services for terminal devices installed with application software.

[0194] When implementing the above method for displaying recommended information, the above executable instructions enable the above processor to perform the following steps: receiving user tag selection information of the first user selecting a user tag; generating a recommendation request based on the above user tag selection information, and sending the above recommendation request to the server; receiving the target information sent by the server and displaying it on the user interface; wherein the above target information includes: information to be recommended for the target group, and the above target group is obtained based on the above user tag selection information. The detailed implementation process of each of the above steps and the steps further included in the above method for recommending information can refer to the description of the second embodiment, which will not be repeated here. The electronic device of this embodiment can be a terminal device with application software installed.

[0195] The above-mentioned application software can be one or more of the following software: e-book reading software (such as e-book reading app or browser), short video software, search software, food delivery software, etc.

[0196] The above-mentioned memory 1103 can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory 1103 has a storage space for program codes for executing any method step in the above-mentioned method. For example, the storage space for program codes may include various program codes for implementing the various steps in the above method respectively. These program codes can be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. Such computer program products are usually portable or fixed storage units. The storage unit may have a storage segment or storage space arranged similarly to the memory 1103 in the above-mentioned electronic device. The program code can be compressed, for example, in an appropriate form. Generally, the storage unit includes a program for executing the method steps according to an embodiment of the present disclosure, that is, a code that can be read by a processor such as 1101, which, when run by an electronic device, causes the electronic device to execute the various steps in the method described above.

[0197] The fourth exemplary embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for generating recommendation information or the method for displaying recommendation information as described above is implemented.

[0198] The computer-readable storage medium may be included in the device / apparatus described in the above embodiment; or it may exist independently without being assembled into the device / apparatus. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0199] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0200] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or step from another entity or step, and do not necessarily require or imply any such actual relationship or order between these entities or steps. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0201] The foregoing is merely a specific embodiment of the present disclosure, which enables those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. A method for generating recommendation information, characterized in that: include: receiving a recommendation request sent by the first terminal; The recommendation request carries user tag selection information related to the first user received by the first terminal; wherein the user tag selection information is generated by operating in options of user tags for the user to select, and the options include user tags that are different from the preferences of the first user; Determine a target group according to the recommendation request; the target group has preference differences with the first user; wherein, determining the target group according to the recommendation request includes: when it is detected that the user tag selection information does not carry the user tag selected by the first user, screening in a user database according to the first user tag and at least one difference tag of the first user, to obtain a target group matching the first user tag and the at least one difference tag, wherein the difference tag is different from the first user tag in at least one attribute dimension; The behavior data of the target group is analyzed and processed to obtain the information to be recommended.

2. The method according to claim 1, It is characterized in that Wherein, determining the target group according to the recommendation request includes: Detecting whether the user tag selection information carries a user tag selected by the first user; When it is detected that the user tag selected by the first user is carried in the user tag selection information, the user tag selected by the first user is determined as a specific user tag, and a user group matching the specific user tag is determined as a target group.

3. The method according to claim 1, characterized in that The analyzing and processing of the behavior data of the target group to obtain the information to be recommended includes: Analyze the behavior data of the target group to obtain the number / proportion of users who have each interactive behavior under each content that generates interactive behavior in the specific object information, wherein the user ratio is the ratio of the number of users who have performed the interactive behavior to the total number of users in the target group; Determining the attention level corresponding to each content generating the interactive behavior according to the preset weight of the interactive behavior and the number / ratio of users; sorting the contents according to the level of interest of each content; and According to the results of sorting the contents, information to be recommended is generated.

4. The method according to claim 3, characterized in that The step of determining the attention level corresponding to each content generating the interactive behavior according to the preset weight of the interactive behavior and the number / proportion of users includes: For each content that generates interactive behavior, the number / proportion of users of each interactive behavior of the current content is weighted and calculated with the corresponding preset weight to obtain the corresponding attention degree of the current content; or, For each content that generates interactive behavior, invalid interactive behaviors whose number / proportion of users is less than a preset threshold are eliminated from the various interactive behaviors of the current content to obtain the remaining valid interactive behaviors; weighted and calculated according to the number / proportion of users of the valid interactive behaviors and the corresponding preset weights to obtain the attention corresponding to the current content.

5. The method according to claim 1, characterized in that The recommendation request carries the behavior tag selection information related to the first user received by the first terminal; The analyzing and processing of the behavior data of the target group to obtain the information to be recommended includes: Selecting information based on the behavior tag to determine a target interactive behavior; Analyze the behavior data of the target group to obtain the target content and the number / proportion of users corresponding to the target interactive behavior in the specific object information; wherein the user ratio is the ratio of the number of users who have performed the target interactive behavior to the total number of users in the target group; Determining the attention level of the target content according to the preset weight of the target interactive behavior and the number / proportion of users; sorting the target content according to the level of attention paid to the target content; and According to the result of sorting the target content, information to be recommended regarding the behavior tag selection information is generated.

6. The method according to claim 5, characterized in that The step of selecting information according to the behavior tag and determining the target interaction behavior includes: Detecting whether the behavior tag selection information carries the behavior tag selected by the first user; When it is detected that the behavior tag selected by the first user is carried in the behavior tag selection information, determining the interaction behavior matching the behavior tag as the target interaction behavior; When it is detected that the behavior tag selection information does not carry the behavior tag selected by the first user, all interaction behaviors occurring in the specific object information are determined as target interaction behaviors.

7. The method according to any one of claims 1 to 6, characterized in that Before receiving the recommendation request sent by the first terminal, the method further includes: counting user tags and behavior data of the user account; The user tags of the statistical user accounts include: Structuralize the user portrait data corresponding to the user account and generate user tags; The statistical user account behavior data includes: Collect behavioral data of user accounts within a preset time period and generate behavioral tags based on the behavioral data.

8. The method according to claim 7, characterized in that Also includes: The generated user tags are checked for validity. When the number of users corresponding to the candidate user tags is lower than a preset threshold, the candidate user tags are regarded as invalid tags and the invalid tags are removed. The remaining valid tags are used as user tags for user selection.

9. The method according to any one of claims 1 to 6, characterized in that: Also includes: Sending target information for recommendation to the first terminal; The sending of the target information for recommendation to the first terminal includes: receiving ratio setting information sent by the first terminal, where the ratio setting information is used to represent a ratio of the information to be recommended to the target information for recommendation; In the case where the ratio setting information is less than 100%, generating candidate information according to the historical behavior data under the current user account of the first terminal; combining the information to be recommended and the candidate information according to the ratio setting information to obtain the target information; and sending the target information to the first terminal; When the ratio setting information is 100%, the information to be recommended is sent to the first terminal.

10. A method for displaying recommended information, characterized in that: include: Receiving user tag selection information of a first user selecting a user tag; The user tag selection information is generated by operating in options of user tags for the user to select, wherein the options include user tags that are different from the preferences of the first user; Generate a recommendation request according to the user tag selection information, and send the recommendation request to a server; Receive target information sent by a server and display it on a user interface; wherein the target information includes: information to be recommended for a target group; wherein the target group is obtained according to the user tag selection information, and the target group and the first user have preference differences; wherein, when the user tag selection information does not carry the user tag selected by the first user, a user database is screened according to the first user tag and at least one difference tag of the first user to obtain a target group matching the first user tag and at least one difference tag, and the difference tag differs from the first user tag in at least one attribute dimension.

11. The method according to claim 10, characterized in that Also includes: Receiving behavior tag selection information of the first user selecting a behavior tag; The step of generating a recommendation request according to the user tag selection information includes: A recommendation request is generated according to the user tag selection information and the behavior tag selection information.

12. The method according to claim 10, characterized in that Before receiving the target information sent by the server and displaying it on the user interface, it also includes: Receiving ratio setting information of the first user setting the ratio of the information to be recommended to the target information; Sending the ratio setting information to a server; Among them, when the ratio setting information is less than 100%, the target information is the information obtained by combining the information to be recommended and the candidate information according to the ratio setting information, and the candidate information is the information generated according to the historical behavior data under the current user account.

13. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following steps: Receiving a recommendation request sent by a first terminal; the recommendation request carries user tag selection information related to a first user received by the first terminal; wherein the user tag selection information is generated by operating in options of user tags for the user to select, and the options include user tags that are different from the preferences of the first user; Determine a target group according to the recommendation request; the target group has preference differences with the first user; wherein, determining the target group according to the recommendation request includes: when it is detected that the user tag selection information does not carry the user tag selected by the first user, screening in a user database according to the first user tag and at least one difference tag of the first user, to obtain a target group matching the first user tag and the at least one difference tag, wherein the difference tag is different from the first user tag in at least one attribute dimension; The behavior data of the target group is analyzed and processed to obtain the information to be recommended.

14. The electronic device according to claim 13, characterized in that: Determining the target group according to the recommendation request includes the following steps: Detecting whether the user tag selection information carries a user tag selected by the first user; When it is detected that the user tag selected by the first user is carried in the user tag selection information, the user tag selected by the first user is determined as a specific user tag, and a user group matching the specific user tag is determined as a target group.

15. The electronic device according to claim 13, characterized in that: The step of analyzing and processing the behavior data of the target group to obtain the information to be recommended includes the following steps: Analyze the behavior data of the target group to obtain the number / proportion of users who have each interactive behavior under each content that generates interactive behavior in the specific object information, wherein the user ratio is the ratio of the number of users who have performed the interactive behavior to the total number of users in the target group; Determining the attention level corresponding to each content generating the interactive behavior according to the preset weight of the interactive behavior and the number / ratio of users; sorting the contents according to the level of interest of each content; and According to the results of sorting the contents, information to be recommended is generated.

16. The electronic device according to claim 15, characterized in that: The step of determining the attention level corresponding to each content generating the interactive behavior according to the preset weight of the interactive behavior and the number / proportion of users comprises the following steps: For each content that generates interactive behavior, the number / proportion of users of each interactive behavior of the current content is weighted and calculated with the corresponding preset weight to obtain the corresponding attention degree of the current content; or, For each content that generates interactive behavior, invalid interactive behaviors whose number / proportion of users is less than a preset threshold are eliminated from the various interactive behaviors of the current content to obtain the remaining valid interactive behaviors; weighted and calculated according to the number / proportion of users of the valid interactive behaviors and the corresponding preset weights to obtain the attention corresponding to the current content.

17. The electronic device according to claim 13, characterized in that: The recommendation request carries the behavior tag selection information related to the first user received by the first terminal; The step of analyzing and processing the behavior data of the target group to obtain the information to be recommended includes the following steps: Selecting information based on the behavior tag to determine a target interactive behavior; Analyze the behavior data of the target group to obtain the target content and the number / proportion of users corresponding to the target interactive behavior in the specific object information; wherein the user ratio is the ratio of the number of users who have performed the target interactive behavior to the total number of users in the target group; Determining the attention level of the target content according to the preset weight of the target interactive behavior and the number / proportion of users; sorting the target content according to the level of attention paid to the target content; and According to the result of sorting the target content, information to be recommended regarding the behavior tag selection information is generated.

18. The electronic device according to claim 17, characterized in that: The step of selecting information according to the behavior tag and determining the target interaction behavior comprises the following steps: Detecting whether the behavior tag selection information carries the behavior tag selected by the first user; When it is detected that the behavior tag selected by the first user is carried in the behavior tag selection information, determining the interaction behavior matching the behavior tag as the target interaction behavior; When it is detected that the behavior tag selection information does not carry the behavior tag selected by the first user, all interaction behaviors occurring in the specific object information are determined as target interaction behaviors.

19. The electronic device according to any one of claims 13 to 18, characterized in that: The executable instructions further cause the processor to perform the following steps: Before receiving the recommendation request sent by the first terminal, counting user tags and behavior data of the user account; The step of counting user tags of user accounts includes the following steps: Structuralize the user portrait data corresponding to the user account and generate user tags; The statistical user account behavior data includes: Collect behavioral data of user accounts within a preset time period and generate behavioral tags based on the behavioral data.

20. The electronic device according to claim 19, characterized in that: The executable instructions further cause the processor to perform the following steps: The generated user tags are checked for validity. When the number of users corresponding to the candidate user tags is lower than a preset threshold, the candidate user tags are regarded as invalid tags and the invalid tags are removed. The remaining valid tags are used as user tags for user selection.

21. The electronic device according to any one of claims 13 to 18, characterized in that: The executable instructions further cause the processor to perform the following steps: Sending target information for recommendation to the first terminal; The sending of the target information for recommendation to the first terminal includes the following steps: receiving ratio setting information sent by the first terminal, where the ratio setting information is used to represent a ratio of the information to be recommended to the target information for recommendation; In the case where the ratio setting information is less than 100%, generating candidate information according to the historical behavior data under the current user account of the first terminal; combining the information to be recommended and the candidate information according to the ratio setting information to obtain the target information; and sending the target information to the first terminal; When the ratio setting information is 100%, the information to be recommended is sent to the first terminal.

22. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the following steps: Receiving user tag selection information of a first user selecting a user tag; the user tag selection information is generated by operating in options of user tags for the user to select, wherein the options include user tags that are different from the preferences of the first user; Generate a recommendation request according to the user tag selection information, and send the recommendation request to a server; Receive target information sent by a server and display it on a user interface; wherein the target information includes: information to be recommended for a target group; wherein the target group is obtained according to the user tag selection information, and the target group and the first user have preference differences; wherein, when the user tag selection information does not carry the user tag selected by the first user, a user database is screened according to the first user tag and at least one difference tag of the first user to obtain a target group matching the first user tag and at least one difference tag, and the difference tag differs from the first user tag in at least one attribute dimension.

23. The electronic device according to claim 22, characterized in that: The executable instructions further cause the processor to perform the following steps: Receiving behavior tag selection information of the first user selecting a behavior tag; The step of generating a recommendation request according to the user tag selection information comprises the following steps: A recommendation request is generated according to the user tag selection information and the behavior tag selection information.

24. The electronic device according to claim 22, characterized in that: The executable instructions further cause the processor to perform the following steps: Before receiving the target information sent by the server and displaying it on the user interface, receiving ratio setting information set by the first user for the ratio of the information to be recommended to the target information; Sending the ratio setting information to a server; Among them, when the ratio setting information is less than 100%, the target information is the information obtained by combining the information to be recommended and the candidate information according to the ratio setting information, and the candidate information is the information generated according to the historical behavior data under the current user account.

25. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

26. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 10 to 12 is implemented.

Images