Content recommendation method, device and electronic device

Through the real-time application program interface (RTA API), the user request data is transmitted and the interface data of the received content provider is used to determine the recommended content using user characteristic information, which solves the problem of low efficiency in cross-enterprise content recommendation and achieves more accurate and efficient content recommend.

CN113961608BActive Publication Date: 2024-11-15VIVO MOBILE COMM CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111219365.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-10-19
Publication Date
2024-11-15
Estimated Expiration
2041-10-19

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively obtain more comprehensive user characteristics and data in cross-enterprise content recommendations, resulting in low recommendation efficiency, especially offline transmission has delays and high cost, high federated learning technology threshold, and low penetration rate.

Method used

Transfer user's content request data through real-time application program interface (RTA API), receive the interface data of the content provider, including user characteristic information, and determine the recommended content in the candidate set of content to be recommended, avoid data delays and improve recommendations accuracy.

Benefits of technology

Real-time data transmission is realized, recommendation delay is reduced, content recommendation is improved, data transmission is solved among multiple enterprises, and feature data of multiple users is obtained.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113961608B_ABST
    Figure CN113961608B_ABST
Patent Text Reader

Abstract

The present application discloses a content recommendation method, device and electronic device. The invention belongs to the field of data processing, and the recommendation method comprises: receiving content request data of a user; sending the received content request data to a content provider; receiving interface data returned by the content provider through a real-time application program interface, wherein the interface data comprises user feature information; and determining recommended content in a candidate set of content to be recommended according to the user feature information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of data processing, and specifically relates to a content recommendation method, device and electronic device. Background Art

[0002] With the continuous development of content-related products, both enterprises and individual users are involved in content production, production and dissemination. As content becomes more and more diverse, how to recommend the most interesting and valuable content to users has always been the core capability direction of the content industry. How to obtain more comprehensive characteristics and data of users is an important technical point in the content recommendation industry.

[0003] Currently, the complete link of user behavior occurs in different enterprise products, which results in the behavior data being stored in different enterprise databases. However, due to issues such as enterprise privacy protection, it is difficult to transfer data between enterprises, so that data can be fully applied to recommendation technology. Existing solutions include: after encryption and desensitization, user behavior data is transmitted offline to the other party in the form of data packets for cross-enterprise content recommendation; or, user behavior data is used for cross-enterprise content recommendation through methods such as federated learning.

[0004] However, the offline transmission method will cause a delay between offline data and real-time user behavior, and the cost is high, and the effect is not ideal. The federated learning method has a high technical threshold and requires users to have relevant talents and resource bases, and the popularity rate is very low.

[0005] From this, we can see that how to obtain more comprehensive user characteristics and data across enterprises to improve the accuracy of content recommendations is a technical problem that needs to be solved urgently.

[0006] Application Contents

[0007] The purpose of the embodiments of the present application is to provide a content recommendation method, device and electronic device, which can solve the problem of low efficiency of existing cross-enterprise content recommendation.

[0008] In order to solve the above technical problems, this application is implemented as follows:

[0009] In a first aspect, an embodiment of the present application provides a content recommendation method, the method comprising: receiving content request data of a user; sending the received content request data to a content provider; receiving interface data returned by the content provider through a real-time application program interface, the interface data comprising user feature information; and determining recommended content from a candidate set of content to be recommended based on the user feature information.

[0010] In a second aspect, an embodiment of the present application provides a content recommendation device, comprising: a first receiving module for receiving content request data of a user; a sending module for sending the received content request data to a content provider; a second receiving module for receiving interface data returned by the content provider through a real-time application program interface, wherein the interface data includes user feature information; and a data processing module for determining recommended content from a candidate set of content to be recommended based on the user feature information.

[0011] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0012] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0013] In the embodiment of the present application, the user's content request data is transmitted through a real-time application program interface, and the interface data of the content provider is received, and the recommended content is determined in the candidate set of the content to be recommended according to the user feature information in the interface data. Data delay caused by offline transmission can be avoided, and the recommended content obtained is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flow chart of a content recommendation method provided by this embodiment;

[0015] Figure 2 is a structural diagram of a content recommendation device provided by this embodiment;

[0016] Figure 3 is a structural schematic diagram of an electronic device provided by this embodiment;

[0017] Figure 4 It is a schematic diagram of the hardware structure of an electronic device provided in this embodiment. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0020] In conjunction with the accompanying drawings, a content recommendation method, device and electronic device provided by the embodiments of the present application are described in detail through specific embodiments and application scenarios.

[0021] refer to Figure 1 This embodiment provides a content recommendation method, which includes the following steps:

[0022] S1100: Receive content request data from a user.

[0023] In this embodiment, the user's content request data can be sent through a user terminal, such as a smart terminal, a tablet, etc., and the requested content is input through a search engine. In this embodiment, the content request data includes a requested content keyword and the user's attribute information. The requested content keyword can be a keyword in the content input by the user through the search engine. For example, the user searches for "funny video" on a content recommendation application APP. Then the requested content keyword is "funny". The user's attribute information may include user ID, mobile phone brand and model, IP address, etc.

[0024] The recommended content in this embodiment may refer to the pictures, texts, videos, H5 and other content recommended in the current mainstream information flow products.

[0025] S1200: Send the received content request data to the content provider.

[0026] It should be noted that the present embodiment is equipped with a real-time application programming interface (Real Time Application Programming Interface, Real Time API) service, namely, RTA service. The user sends content request data to the server through the RTA interface, and the server processes the content data and sends it to the content provider. When sending the content request data to the provider, the sending fields include: field name, required attributes, data type, and encryption method, etc. For example, the sending fields can be as shown in Table 1, wherein sensitive fields involving user privacy are encrypted, such as user ID.

[0027]

[0028] Table 1

[0029] As can be seen from Table 1, the content request data sent to the content provider is field information after data processing, and the fields include request_id, which is used to represent the unique identifier of each request; did, which is used to represent the user ID, such as the international mobile equipment identity code IMEI or the anonymous device identifier OAI; position_id, which is used to represent the content delivery location ID; model, which is used to represent the mobile phone brand and model; location, which is used to represent the latitude and longitude coordinates; user_label, which is used to represent the user label, such as age and gender; ip, which is used to represent the IP address; ua, which is used to represent the user agent.

[0030] In this embodiment, after receiving the data in Table 1, the content provider can match these fields with the users in its own database, and then decide whether to participate in this content recommendation, and return feedback information indicating whether to participate in this content recommendation to the server. For example, the user label in user_label indicates that the user is a 20-year-old female, then the content provider matches the user in its own database according to the user label in user_label, and searches for content with the corresponding features of the label. If not, it will not participate in the delivery of this content recommendation. If so, it can send feedback information indicating that it participates in the delivery of this content recommendation. In this embodiment, the content provider can return interface data through the real-time application program interface.

[0031] S1300: Receive interface data transmitted by a content provider through a real-time application programming interface.

[0032] In this embodiment, the interface data includes user feature information, and the interface data also includes the interface protocol, the data processing volume of the content provider, the connection status code, the feedback time information, the exception handling information, and the cache configuration information. Among them, the interface protocol includes: the communication protocol adopts HTTPS, the POST method is used to send, and the serialization protocol uses protobuf3. HTTPS request header context-type: application / octet-stream; the connection status code includes the HTTPS status code, 200 represents success, and the others are all exceptions; the feedback time information can be 60ms. If the waiting time for feedback exceeds 60ms, it indicates that the feedback of the content provider has timed out; the exception handling information includes: return timeout, or, the HTTPS status code is not equal to 200, or the data format is wrong, cannot be parsed, or the required field is missing, etc.; the cache configuration information includes: whether to cache, the cache mode is priority cache or priority real-time, and the cache duration.

[0033] It can be seen that the content recommender will send the response field to the server. That is, the content recommender sends interface data to the server through the RealTime API interface, and the response fields included in the interface data are shown in Table 2.

[0034] As shown in Table 2, the interface data includes code, which represents the unique identifier of each request, which is consistent with request_id in Table 1; Is_putin, which indicates whether to participate in this estimated delivery; type, which represents the type of user returned this time; mass_fraction, which represents the quality score of the behavior type (1-10); cache_time, which represents the cache time (0 <k≤1440)。

[0035]

[0036] Table 2

[0037] It should be noted that type is the user type corresponding to the user corresponding to the unique identifier of each request by the content recommender, and the corresponding user type in the database of the content recommender, and the user type is an agreement between the content recommender and the content recommendation platform, representing the meaning of user behavior, that is, the user type is a preset user type, which corresponds to the needs of the current requesting user, and the user type is the target user type of the content recommender.

[0038] In one example, if content is to be recommended to a user, content recall is required, that is, a process of roughly selecting a batch of content to be recommended from a large amount of information for the user based on the user's historical behavior data, and selecting a candidate set. Therefore, after receiving the user's content request data, this embodiment also includes: obtaining the user's attribute information and determining the user's historical browsing content; obtaining the content to be recommended in the content database based on the content keywords and the user's historical browsing content, and determining the candidate set of the content to be recommended.

[0039] In one example, the server locks the user's historical browsing records within a period of time based on the user's attribute information contained in the content request data. The historical browsing records can represent the user's content preferences at the current time, and then obtains the content to be recommended from the content database based on the content keywords and historical browsing records in the content request data. That is, the server combines the user's historical preferences and current search keywords to estimate the content that the user is interested in, and forms a candidate set based on all the content to be recommended.

[0040] In one example, a massive amount of content information is stored in a content database. For example, the content database may be a video library set up in the cloud and storing a number of video data. The video data stored in the video library may include all video data uploaded by users through a certain video application.

[0041] In one example, when the content provider connects with the server, based on the content of the above interface data, the content provider needs to provide the interface URL and the recommended content delivered in the Real Time API. In addition, the content provider needs to evaluate its own server and confirm the maximum acceptable number of requests, so that the content recommendation platform can send the corresponding number of content request data based on the maximum acceptable number of requests of the content provider.

[0042] In one example, when a content provider connects to a server, if the content provider cannot return a request within 60ms, it can also access the cache service, but it needs to tell the platform the cache duration and whether to prioritize cache, that is, send cache configuration information to the content recommendation platform.

[0043] In one example, the content provider may perform encryption and desensitization on the user features output by the feature model.

[0044] In this embodiment, after the interface data is transmitted through the real-time application program interface, the method further includes: detecting whether the user characteristic information in the interface data meets the preset rules; if the user characteristic information meets the preset rules, determining the recommended content according to the user characteristic information; if the user characteristic information does not meet the preset rules, prohibiting the use of the user characteristic information. The preset rules can be jointly negotiated by the content recommender and the content recommendation platform. For example, the preset rules can be that the user characteristic information must be desensitized data, the user characteristic information must be legal, etc.

[0045] For example, when the user characteristic information in the interface data is not desensitized and involves a situation where user information may be leaked, if it is determined that the user characteristic information does not meet the preset rules, it is prohibited to use the user characteristic information to determine the recommended content. If the user characteristic information meets the preset rules, the recommended content is determined based on the user characteristic information.

[0046] S1400: Determine recommended content in a candidate set of content to be recommended based on user feature information.

[0047] In this embodiment, the user characteristic information can be analyzed by deep learning to obtain the first user characteristic information. For example, the user ID, age characteristics, gender characteristics, and behavior characteristics on the content recommendation platform in the user characteristic information are obtained. The first user characteristic information obtained after analysis can accurately reflect the user's preferences, thereby achieving the effect of accurately recommending content.

[0048] In this embodiment, customized second user characteristic information is also obtained. The customized second user characteristic information can be user characteristic information supplemented by the content recommender based on the performance of the same user ID in its own database, or it can be supplementary characteristic information obtained by the content recommendation platform based on the historical data of the user ID in the content recommendation platform.

[0049] Each item of content to be recommended in the candidate set of content to be recommended is scored according to the first user characteristic information and the second user characteristic information to obtain a scoring result, and the recommended content is determined according to the scoring result.

[0050] In this embodiment, since the content to be recommended in the candidate set is obtained only based on the user feature information in the interface data sent by the content recommender, further screening is required. Therefore, this step further screens the content to be recommended in combination with the second user feature, and determines the content to be recommended that satisfies both the first user feature and the second user feature as the recommended content. Specifically, the predicted score of the content to be recommended that satisfies both the first user feature and the second user feature can be calculated based on the deep learning algorithm, and the predicted score and the actual score are compared for the mean square error. The smaller the error, the more accurate the recommended content. Thus, content can be recommended to users more accurately.

[0051] It is understandable that in this embodiment, the user sends content request data, and the content recommendation platform sends the content request data to the content recommender in real time, thereby avoiding errors caused by offline data. And the data recommender can be multiple parties, which can not only solve the data transmission problem between multiple enterprises, but also obtain user feature data of multiple parties.

[0052] It should be noted that the content recommendation method provided in the embodiment of the present application can be executed by a content recommendation device, or by a control module in the content recommendation device for executing the method for loading content recommendation. In the embodiment of the present application, the content recommendation method provided in the embodiment of the present application is described by taking the content recommendation device executing the method for loading content recommendation as an example.

[0053] This embodiment provides a content recommendation device 200, referring to Figure 2 , the device comprises:

[0054] The first receiving module 201 is used to receive content request data from a user;

[0055] The sending module 202 is used to send the received content request data to the content provider;

[0056] The second receiving module 203 is used to receive interface data returned by the content provider through the real-time application program interface, wherein the interface data includes user feature information;

[0057] The data processing module 204 is used to determine the recommended content in the candidate set of content to be recommended according to the user characteristic information.

[0058] In one example, the content recommendation device also includes a candidate data processing module, which is used to: after receiving the user's content request data, obtain the user's attribute information and determine the user's historical browsing content; wherein the content request data includes the requested content keyword and the user's attribute information; based on the content keyword and the user's historical browsing content, obtain the content to be recommended in the content database and determine the candidate set of the content to be recommended.

[0059] In one example, the data processing module is used to: after receiving interface data returned by the content provider through a real-time application program interface, determine whether the user characteristic information in the interface data complies with preset rules; if the user characteristic information complies with the preset rules, determine recommended content based on the user characteristic information; if the user characteristic information does not comply with the preset rules, prohibit the use of the user characteristic information.

[0060] In one example, the data processing module is used to: perform feature analysis on the user feature information to obtain first user feature information; obtain customized second user feature information; score each item of content to be recommended in the candidate set of content to be recommended based on the first user feature information and the second user feature information to obtain a scoring result, and determine the recommended content based on the scoring result.

[0061] The content recommendation device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0062] The content recommendation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0063] The content recommendation device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the content recommendation device in the method embodiment are not described here.

[0064] Optionally, the present application embodiment further provides an electronic device 300, referring to Figure 3 , including a processor 301, a memory 302, a program or instruction stored in the memory 302 and executable on the processor 301, wherein the program or instruction, when executed by the processor 301, implements each process of the above-mentioned content recommendation method embodiment and can achieve the same technical effect, and will not be described again here to avoid repetition.

[0065] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0066] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0067] The electronic device 1000 includes but is not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010 and other components.

[0068] Those skilled in the art will appreciate that the electronic device 1000 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1010 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0069] Among them, the processor 1010 is used to receive content request data from a user; in response to the content request data, send the received content request data to a content provider; receive interface data returned by the content provider through a real-time application program interface, wherein the interface data includes user feature information; and determine recommended content in a candidate set of content to be recommended based on the user feature information.

[0070] Optionally, the processor 1010 is further used to obtain attribute information of the user and determine the historical browsing content of the user after receiving the content request data of the user; obtain the content to be recommended in the content database according to the content keywords and the historical browsing content of the user, and determine a candidate set of the content to be recommended.

[0071] Optionally, the processor 1010 is further used to detect whether the user characteristic information in the interface data complies with preset rules; if the user characteristic information complies with the preset rules, determine the recommended content based on the user characteristic information; if the user characteristic information does not comply with the preset rules, prohibit the use of the user characteristic information.

[0072] Optionally, the processor 1010 is further used to perform feature analysis on the user feature information to obtain first user feature information; obtain customized second user feature information; score each item of content to be recommended in the candidate set of content to be recommended based on the first user feature information and the second user feature information to obtain a scoring result, and determine the recommended content based on the scoring result.

[0073] It should be understood that in the embodiment of the present application, the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1007 includes a touch panel 10071 and other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include two parts: a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, a physical keyboard, a function key (such as a volume control button, a switch button, etc.), a trackball, a mouse, and a joystick, which will not be repeated here. The memory 1009 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor 1010.

[0074] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned content recommendation method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0075] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0076] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes 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 "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0077] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0078] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A content recommendation method, characterized in that: The method comprises: Receiving content request data from a user; Sending the received content request data to the content provider; Receiving interface data returned by the content provider through a real-time application program interface, wherein the interface data includes user feature information; Determining recommended content from a candidate set of content to be recommended based on the user characteristic information; The content request data includes a requested content keyword and attribute information of the user. After receiving the content request data of the user, the method further includes: Acquire attribute information of the user and determine historical browsing content of the user; According to the content keywords and the user's historical browsing content, the content to be recommended is obtained from a content database, and a candidate set of the content to be recommended is determined.

2. The method according to claim 1, characterized in that The interface data also includes: interface protocol, data processing volume of the content provider, connection status code, feedback time information, exception handling information, and cache configuration information.

3. The method according to claim 1, characterized in that After receiving the interface data returned by the content provider through the real-time application program interface, the method further includes: Determining whether the user characteristic information in the interface data complies with a preset rule; When the user characteristic information meets the preset rules, determining the recommended content according to the user characteristic information; If the user characteristic information does not conform to a preset rule, use of the user characteristic information is prohibited.

4. The method according to claim 1, characterized in that: Determining recommended content from a candidate set of content to be recommended based on the user characteristic information includes: Performing feature analysis on the user feature information to obtain first user feature information; Acquire customized second user characteristic information; wherein the first user characteristic information and the second user characteristic information are used to reflect the user's preferences; Each item of content to be recommended in the candidate set of content to be recommended is scored according to the first user characteristic information and the second user characteristic information to obtain a scoring result, and the recommended content is determined according to the scoring result.

5. A content recommendation device, characterized in that: The device comprises: A first receiving module, used for receiving content request data from a user; A sending module, used for sending the received content request data to a content provider; A second receiving module, configured to receive interface data returned by the content provider through a real-time application program interface, wherein the interface data includes user feature information; A data processing module, configured to determine recommended content from a candidate set of content to be recommended based on the user characteristic information; The candidate data processing module is used to obtain the user's attribute information and determine the user's historical browsing content after receiving the user's content request data, wherein the content request data includes the requested content keyword and the user's attribute information; based on the content keyword and the user's historical browsing content, obtain the content to be recommended in the content database and determine the candidate set of the content to be recommended.

6. The device according to claim 5, characterized in that The data processing module is used for: After receiving the interface data returned by the content provider through the real-time application program interface, determining whether the user characteristic information in the interface data conforms to a preset rule; When the user characteristic information meets the preset rules, determining the recommended content according to the user characteristic information; If the user characteristic information does not conform to a preset rule, use of the user characteristic information is prohibited.

7. The device according to claim 5, characterized in that The data processing module is used for: Performing feature analysis on the user feature information to obtain first user feature information; Acquire customized second user characteristic information; wherein the first user characteristic information and the second user characteristic information are used to reflect the user's preferences; Each item of content to be recommended in the candidate set of content to be recommended is scored according to the first user characteristic information and the second user characteristic information to obtain a scoring result, and the recommended content is determined according to the scoring result.

8. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method according to any one of claims 1 to 4.