Construction method of media personalized recommendation feed service system and feed service system

Abstract

The present invention relates to a method for constructing a personalized media recommendation feed service system and a feed service system. The method comprises: obtaining recommendation data from a data layer by accessing a data access service to construct a preliminary recommendation candidate set; dynamically updating the recommendation candidate set by accessing a real-time correction service, and optimizing the storage and access efficiency of recommended content by using a three-level cache mechanism; dynamically adjusting the content weight and display order in the recommendation candidate set according to preset specifications by accessing a recommendation intervention service and an AB testing service; and sorting, filtering, and outputting the optimized recommendation candidate set to the user by accessing a recommendation interface service, providing personalized media recommendation content and outputting it to the application layer. By caching high-frequency candidate set data and optimizing recommendation strategies, the present invention improves the system's response speed and user experience, ensuring the relevance and diversity of media recommendation content, while meeting the user's personalized needs and positive guidance standards.

Description

Technical Field

[0001] The present invention relates to the technical field of personalized media recommendation, and in particular to a method for constructing a personalized media recommendation feed service system and a feed service system. Background Art

[0002] Existing technologies have enabled personalized media recommendation systems to be widely used across various content platforms, such as news, videos, and social media. These systems typically analyze user behavior data (such as browsing history, click history, likes, and comments) and combine it with content features to generate personalized media recommendations. However, existing recommendation systems still have limitations in terms of processing efficiency, real-time performance, and recommendation accuracy.

[0003] First, existing systems face bottlenecks in data processing efficiency. Due to the large volume and complexity of user behavior data, traditional batch processing methods are unable to meet the needs of real-time recommendations, resulting in a poor user experience. Second, media recommendations lack real-time performance. Existing systems often fail to promptly update user preferences and content status, resulting in lagging media recommendations and an inability to accurately reflect users' current interests. Furthermore, the flexibility and accuracy of existing recommendation strategies need to be improved. Many systems lack the ability to dynamically adjust recommendation strategies and are unable to optimize based on real-time data and content specifications, resulting in recommendations that are not personalized and accurate enough.

[0004] In order to overcome the above shortcomings, an efficient, real-time and flexible personalized recommendation system is needed to improve the relevance of media recommendation content and user satisfaction. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for constructing a media personalized recommendation feed service system and a feed service system to solve the problems of low data processing efficiency, insufficient real-time performance and poor user experience in the existing technology.

[0006] To achieve one of the above-mentioned objectives, an embodiment of the present invention provides a method for constructing a media personalized recommendation feed service system, which is characterized by comprising:

[0007] Obtain recommendation data from the data layer by accessing the data access service and construct a preliminary recommendation candidate set;

[0008] Dynamically update the recommendation candidate set by accessing the real-time correction service, and optimize the storage and access efficiency of recommended content by using a three-level cache mechanism;

[0009] By accessing the recommendation intervention service and AB testing service, the content weight and display order in the recommendation candidate set are dynamically adjusted according to preset specifications;

[0010] By accessing the recommendation interface service, the optimized recommendation candidate set is sorted, filtered and output to the user, providing personalized media recommendation content and outputting it to the application layer.

[0011] As a further improvement of an embodiment of the present invention, the method also includes accessing a recommendation cache service, analyzing the data in the recommendation candidate set based on user behavior data, content popularity and user characteristics, and caching the recommendation candidate set data determined to be high-frequency.

[0012] As a further improvement of an embodiment of the present invention, the method further includes archiving the recommendation candidate set by accessing a recommendation archiving service to implement a traceability query function for the recommendation data.

[0013] As a further improvement of an embodiment of the present invention, the method further includes that the three-level cache mechanism includes hierarchical storage through MongoDB, Elasticsearch and Redis;

[0014] The MongoDB is used to store the recommendation data, the Elasticsearch is used to store the recommendation candidate set in a distributed manner; and the Redis is used to store the recommendation candidate set determined to be high-frequency.

[0015] Through scheduled tasks and active user prediction, the recommendation candidate set is preloaded from Elasticsearch to Redis, achieving a balance between efficient query and fast access.

[0016] To achieve one of the above-mentioned objects, an embodiment of the present invention provides a feed service system, which includes a data layer, a data processing layer, an interface service layer, and an application layer;

[0017] Media data and user behavior data are collected through the data layer and stored in a database; when user request parameters are received, a recommendation candidate set is obtained from the database, and the recommendation candidate set is updated through the data processing layer and sent to the interface service layer; the recommendation candidate set is optimized, screened and sorted through the interface service layer, and finally output to the application layer.

[0018] As a further improvement of an embodiment of the present invention, the system further includes: the data processing layer includes a recommended data access service module, a recommended real-time correction service module, a recommended cache service module, and a recommended archiving service module; the interface service layer includes a recommended interface service module, a recommended intervention service module, and a recommended AB testing service module;

[0019] The recommendation data access service module is used to receive and process media data and user behavior data to prepare a recommendation candidate set for subsequent recommendation;

[0020] The recommendation real-time correction service module is used to update the recommendation candidate set in real time, adjust the status of the read content and optimize the real-time performance and accuracy of the candidate set;

[0021] The recommendation cache service module is used to store the recommendation candidate sets of high-frequency users, improve the real-time and efficiency of data access, and regularly update and clean the cache;

[0022] The recommendation archiving service module is used to archive and store recommendation data to ensure the integrity and traceability of historical data for analysis and optimization;

[0023] The recommendation interface service module is used to receive user request parameters, obtain a recommendation candidate set, sort and filter the data, and then output the final media recommendation content;

[0024] The recommendation intervention service module is used to dynamically adjust the weight and display order of media recommendation content according to preset media content specifications to ensure that the media recommendation content meets the personalized and positive guidance standards;

[0025] The recommendation AB testing service module is used to group users and test different recommendation strategies, ensuring that each user uses the same strategy during the test to evaluate the effect.

[0026] As a further improvement of an embodiment of the present invention, the system further includes: the feed service system adopts a linkage three-level cache mechanism, including:

[0027] The recommendation data access service module stores the recommendation data through the MongoDB, the recommendation real-time correction service module stores the recommendation candidate set through the Elasticsearch distributed storage; and the recommendation cache service module stores the recommendation candidate set determined to be high-frequency through the Redis.

[0028] As a further improvement of an embodiment of the present invention, the system further includes: the recommendation cache service module periodically queries active users within a preset time period and stores the recommendation candidate sets of the active users in redis;

[0029] The redis uses the sorted set zset for storage and uses the user's unique identifier as the cache access key;

[0030] The recommendation interface service module obtains a recommendation candidate set through the user unique identifier;

[0031] The media that the user has read and blacklisted is cached in redis through the recommendation cache service module, and a set collection is used to cache according to the user's unique identifier. Before returning the recommendation candidate set to the user, the media that has been read and blacklisted is filtered.

[0032] In order to achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention also provides an electronic device, including a memory and a processor, characterized in that the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the method for constructing the above-mentioned media personalized recommendation feed service system are implemented.

[0033] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention further provides a storage medium, wherein the storage medium stores a computer program, and is characterized in that when the computer program is executed by a processor, the steps in the method for constructing the above-mentioned media personalized recommendation feed service system are implemented.

[0034] Compared to existing technologies, this invention provides a method for constructing a personalized media recommendation feed service system and a feed service system. By receiving and standardizing multiple data sources, updating recommendation candidate sets in real time, grouping users using A / B testing, and dynamically adjusting the weighting and order of media recommendation content, this ensures high-quality, personalized, and real-time media recommendations. By caching high-frequency candidate set data and optimizing recommendation strategies, the system's response speed and user experience are improved, ensuring the relevance and diversity of media recommendations while meeting users' personalized needs and positive guidance standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is an overall flow chart of the method for constructing the media personalized recommendation feed service system of the present invention.

[0036] Figure 2 It is a schematic diagram of the architecture of the feed service system of the present invention.

[0037] Figure 3 It is a data flow diagram between microservices of the feed service system of the present invention. DETAILED DESCRIPTION

[0038] The present invention will be described in detail below with reference to the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by those skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0039] The embodiments of the present invention are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and are not to be construed as limiting the present invention.

[0040] In the first embodiment of the present invention, the present invention provides a method for constructing a media personalized recommendation feed service system, such as Figure 1 As shown, the method includes,

[0041] S1: Obtain recommendation data from the data layer by accessing the data access service and construct a preliminary recommendation candidate set;

[0042] S2: Dynamically updates the recommendation candidate set by accessing the real-time correction service and optimizes the storage and access efficiency of the recommended content by using a three-level cache mechanism;

[0043] S3: By accessing the recommendation intervention service and AB testing service, the content weight and display order in the recommendation candidate set are dynamically adjusted according to preset specifications;

[0044] S4: By accessing the recommendation interface service, the optimized recommendation candidate set is sorted, filtered and output to the user, providing personalized media recommendation content and outputting it to the application layer.

[0045] In a specific embodiment of the present invention, by accessing a recommendation cache service, the data in the recommendation candidate set is analyzed based on user behavior data, content popularity and user characteristics, and the recommendation candidate set data determined to be high-frequency is cached.

[0046] It should be noted that there are three types of external data sources in the data layer accessed through the recommendation data access service. The first type is media data, including published media data and recommendation intervention data. The second type is user behavior data, which is sent to the feed service system through the data collection service. The third type is recommendation data, which is the recommendation data and cold start data calculated by the recommendation engine module through the algorithm.

[0047] In a specific embodiment of the present invention, the recommendation candidate set is archived by accessing a recommendation archiving service, thereby realizing a traceability query function of the recommendation data.

[0048] Furthermore, to ensure query performance, historical recommendation candidate sets need to be regularly archived. To this end, the recommendation archiving service regularly cleans up the recommendation candidate sets in Elasticsearch and the keys in Redis, archiving this historical data to OSS and deleting the data stored in Redis and Elasticsearch.

[0049] In a specific embodiment of the present invention, the three-level cache mechanism includes hierarchical storage through MongoDB, Elasticsearch and Redis;

[0050] The MongoDB is used to store the recommendation data, the Elasticsearch is used to store the recommendation candidate set in a distributed manner; and the Redis is used to store the recommendation candidate set determined to be high-frequency.

[0051] Through scheduled tasks and active user prediction, the recommendation candidate set is preloaded from Elasticsearch to Redis, achieving a balance between efficient query and fast access.

[0052] It should be noted that if Figure 3 As shown, a three-level cache is implemented using Elasticsearch, MongoDB, and Redis. Through scheduled tasks and an active user prediction mechanism, the system predicts which users will frequently access recommended content in the coming period based on their behavior and activity levels. Recommendation candidate sets for these active users are then preloaded from Elasticsearch into Redis. This mechanism ensures that the system can quickly respond when a user accesses content, retrieving the stored candidate set data from Redis, significantly improving query efficiency and reducing access latency. At the same time, Elasticsearch maintains its role as long-term storage, ensuring the persistence and integrity of large-scale data. This approach achieves a balance between efficient queries and fast access, reducing storage costs while ensuring the real-time and accuracy of recommendation services.

[0053] In the second embodiment of the present invention, the present invention provides a feed service system, such as Figure 2 As shown, the system includes: a data layer 100, a data processing layer 200, an interface service layer 300 and an application layer 400;

[0054] Media data and user behavior data are collected through the data layer 100 and stored in a database; when user request parameters are received, a recommendation candidate set is obtained from the database, and the recommendation candidate set is updated through the data processing layer 200 and sent to the interface service layer 300; the recommendation candidate set is content optimized, screened and sorted through the interface service layer 300, and finally output to the application layer 400.

[0055] Specifically, the data processing layer includes a recommended data access service module 201, a recommended real-time correction service module 202, a recommended cache service module 203, and a recommended archiving service module 204; the interface service layer 300 includes a recommended interface service module 301, a recommended intervention service module 302, and a recommended AB testing service module 303;

[0056] The recommendation data access service module 201 is used to receive and process media data and user behavior data to prepare a recommendation candidate set for subsequent recommendation;

[0057] The recommendation real-time correction service module 202 is used to update the recommendation candidate set in real time, adjust the status of the read content and optimize the real-time performance and accuracy of the candidate set;

[0058] The recommendation cache service module 203 is used to store the recommendation candidate sets of high-frequency users, improve the real-time performance and efficiency of data access, and regularly update and clean the cache;

[0059] The recommendation archiving service module 204 is used to archive and store recommendation data to ensure the integrity and traceability of historical data for analysis and optimization;

[0060] The recommendation interface service module 301 is used to receive user request parameters, obtain a recommendation candidate set, sort and filter the data, and then output the final media recommendation content;

[0061] The recommendation intervention service module 302 is used to dynamically adjust the weight and display order of media recommendation content according to preset media content specifications to ensure that the media recommendation content meets the personalized and positive guidance standards;

[0062] The recommendation AB testing service module 303 is used to group users and test different recommendation strategies, ensuring that each user uses the same strategy during the test to evaluate the effect.

[0063] It should be noted that if Figure 2 As shown, the feed service system architecture is mainly divided into four layers:

[0064] The first layer is the data layer 100, which receives external data including media data, user data, behavior data, and recommendation candidate sets from the recommendation engine. These four types of data are transmitted to the recommendation feed service according to the data format defined by the recommendation feed service;

[0065] The second layer is the data processing layer 200, which includes the recommendation data access service module 201, which distributes and stores different data pushed to the interface and performs data isolation storage. The recommendation real-time correction service module 202 corrects the data status of the recommendation candidate set. The recommendation cache service module 203 regularly updates the candidate set data to the cache so that the data accessed by the recommendation interface is the latest cache. The recommendation archiving service module 204 archives and cleans up the data in the cache and distributed index to prevent the elasticsearch data from being too large, which will cause the interface service query to be slow.

[0066] The third layer is the interface service layer 300, which includes the following three services: the recommendation interface service module 301 is mainly for various recommendation channels, provides the final recommendation result data, and receives real-time parameter information from users. For example, it can obtain the latest candidate set data sorting based on user hashId, geographic location, preferences, etc. The recommendation intervention service module 302 processes the candidate set data to be recommended to ensure that the recommended data is in line with positive energy and improve the client's end phase. The recommendation AB test service module 303 is mainly used to verify the effects of different recommendation strategies online and facilitate online parameter adjustment of the recommendation strategy;

[0067] The fourth layer is the application layer 400, which can be applied to different types of article type recommendations for different APPs, and can also adapt to recommendations for different channels. As long as the data is passed in according to the specifications defined by the recommendation feed service, the recommendation interface service provided by the recommendation feed service can be obtained.

[0068] It should be noted that the recommendation interface service module 301 provides a recommendation interface data service, and returns the recommendation data of the corresponding channel according to the corresponding requested user hashId and channel Id. At the same time, the recommendation interface service module 301 needs to use the data pre-processed by the other 6 microservices as mentioned above to select the strategy.

[0069] It should be noted that in order to make the recommended content more consistent with the characteristics of the media, the recommendation intervention service module 302 is required to intervene in the recommendation process data before, during, and after the recommendation process. Beforehand, the corresponding column data can be controlled to determine which articles are allowed to be recommended and which are not. During the process, the recommendation weight of certain articles can be specified to increase or decrease the recommendation chance. Afterward, the recommendation interface layer can be used to pin or block recommendations, making the recommendation results more controllable and ensuring the security of media recommended content.

[0070] It should be noted that the AB testing recommendation service module 303 switches between AB plans for different users, adjusting the corresponding algorithm processing in real time based on online user performance. The AB service sets the access ratio for each plan and then buckets the data based on the user's hashId. When a user is assigned to Plan A, they will continue to access Plan A until the AB plan experiment is cleared. This service also supports importing user-specified plans.

[0071] It should be noted that if Figure 3 As shown, the feed service system has scheduling distribution, recommendation engine and data collection services for data access, and mobile phone interface services and OSS object storage for data output.

[0072] It should be noted that by splitting the recommendation feed service into multiple microservices and using Kubernetes for container orchestration, the microservices can run independently. By using Redis cache, NoSQL database and distributed index database, the business code and storage status are completely separated. When encountering business peaks, the recommendation feed service can be quickly and elastically expanded to cope with user access during peak periods.

[0073] In a specific embodiment of the present invention, the feed service system adopts a linkage three-level cache mechanism, including:

[0074] The recommendation data access service module 201 stores the recommendation data through the MongoDB, the recommendation real-time correction service module 202 stores the recommendation candidate sets in a distributed manner through the Elasticsearch, and the recommendation cache service module 203 stores the recommendation candidate sets determined to be high-frequency through the Redis.

[0075] It should be noted that MongoDB is used to store detailed information about recommendation data, including user behavior data, media content metadata, and historical recommendation records. As a NoSQL database, MongoDB offers a flexible data model and efficient query performance, making it suitable for storing complex and frequently changing data. Elasticsearch is used for distributed storage of recommendation candidate sets. Leveraging its powerful full-text search and distributed query capabilities, Elasticsearch can quickly retrieve and index recommendation candidate sets, ensuring efficient access to massive amounts of data. Recommendation candidate set metadata, content popularity metrics, user characteristics, and other information are all stored in Elasticsearch, facilitating fast search and dynamic updates. Redis is used to store frequently recommended candidate sets, particularly content recommended for currently active users. With its high-performance in-memory storage and fast data access capabilities, Redis is suitable for data access scenarios requiring low latency and high throughput. Redis uses its zset (ordered set) data structure to sort and store candidate sets, supporting fast access by priority or time order, ensuring that the recommendation system can deliver the best recommendations in response to user requests instantly.

[0076] In a specific embodiment of the present invention, the recommendation cache service module 203 periodically queries active users within a preset time, and stores the recommendation candidate sets of the active users in redis; the redis uses the sorted set zset for storage, and uses the user's unique identifier as the cache access key;

[0077] The recommendation interface service module 301 obtains a recommendation candidate set through the user unique identifier;

[0078] The recommendation cache service module 203 caches the media that the user has read and blacklisted into redis, and uses a set collection to cache according to the user's unique identifier. Before returning the recommendation candidate set to the user, the media that has been read and blacklisted is filtered.

[0079] It should be noted that, through the recommendation cache service module 203, the system regularly queries active users within a preset timeframe, pre-storing their recommendation candidate sets in the Redis cache. To efficiently manage and store this data, the system uses Redis sorted sets (zsets) for storage, using each user's unique hashId as the cache access key. This allows the interface service to quickly retrieve a user's candidate set simply by using their hashId, improving data access efficiency and real-time performance.

[0080] Furthermore, content that users have read and blacklisted articles are cached in Redis. For ease of management, this data is cached per user using Redis's set structure. Before returning recommendations to users, the system filters based on this cached data to ensure accuracy and relevance. This approach not only optimizes cache resource usage but also significantly improves the performance of the recommendation system and user experience.

[0081] In a third embodiment of the present invention, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the method for constructing the above-mentioned media personalized recommendation feed service system are implemented.

[0082] In a fourth embodiment of the present invention, the present invention provides a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps in the method for constructing the above-mentioned media personalized recommendation feed service system.

[0083] In summary, the present invention provides a method for constructing a personalized media recommendation feed service system and a feed service system. By receiving and standardizing multiple data sources, updating recommendation candidate sets in real time, grouping users using A / B testing, and dynamically adjusting the weighting and order of media recommendation content, this ensures high-quality, personalized, and real-time media recommendations. By caching high-frequency candidate data and optimizing recommendation strategies, the system's response speed and user experience are improved, ensuring the relevance and diversity of media recommendations while meeting users' personalized needs and positive guidance standards.

[0084] It should be understood that although this specification is described in terms of implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation method can also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

[0085] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the modules described above can refer to the corresponding process in the aforementioned method implementation, and will not be repeated here.

[0086] Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of these modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0087] In addition, the functional modules in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into a single module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0088] The above-mentioned integrated modules implemented in the form of software functional modules can be stored in a computer-readable storage medium. The above-mentioned software functional modules are stored in a storage medium and include a number of instructions for causing a computer system (which may be a personal computer, server, or network system, etc.) or a processor to execute some of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

1. A method for constructing a personalized media recommendation feed service system, characterized by: include, Obtain recommendation data from the data layer by accessing the data access service and construct a preliminary recommendation candidate set; Dynamically update the recommendation candidate set by accessing the real-time correction service, and optimize the storage and access efficiency of the recommended content by using a three-level cache mechanism, including: Through the preset real-time recommendation correction steps, the status of read content and the weight of recommendation candidate sets are adjusted according to user behavior data, and the recommendation candidate sets are dynamically updated to optimize real-time performance and accuracy; Through the preset recommendation caching steps, based on user behavior data, content popularity and user feature analysis, the high-frequency recommendation candidate set is determined and stored in the cache. The cache is regularly updated and cleared to improve the real-time performance and efficiency of data access. The three-level cache mechanism includes hierarchical storage through MongoDB, Elasticsearch, and Redis; MongoDB is used to store the recommendation data, Elasticsearch is used to distribute the recommendation candidate sets, and Redis is used to store the recommendation candidate sets determined to be high-frequency. Through scheduled tasks and active user prediction, the recommendation candidate sets are pre-loaded from Elasticsearch to Redis to achieve a balance between efficient query and fast access. By accessing the recommendation intervention service and AB testing service, the content weight and display order in the recommendation candidate set are dynamically adjusted according to the preset specifications, including: Through preset recommendation intervention steps, the content weight and display order of the recommendation candidate set are dynamically adjusted according to the preset media content specifications to ensure that the recommended content meets the personalized and positive guidance standards; Through the preset recommendation AB testing steps, users are grouped to test different recommendation strategies, ensuring that each user uses the same recommendation strategy during the test to evaluate the recommendation effect; By accessing the recommendation interface service, the optimized recommendation candidate set is sorted, filtered, and output to the user, providing personalized media recommendation content and outputting it to the application layer; Through the preset recommendation caching step, active users within a preset time are regularly queried, and the recommendation candidate sets of the active users are stored in the redis; In the Redis, the recommended candidate set is stored using the sorted set zset, and the user's unique identifier is used as the cache access key; Obtain the recommendation candidate set from Redis using the user's unique identifier through the recommendation interface service; Cache the media that the user has read and blacklisted in Redis, using a set collection to cache based on the user's unique identifier; Before returning the recommendation candidate set through the recommendation interface service, the media that has been read and added to the blacklist is filtered out.

2. The method for constructing a personalized media recommendation feed service system according to claim 1, characterized in that: Also includes, The recommendation candidate set is archived by accessing the recommendation archiving service to realize the traceability query function of the recommendation data.

3. A feed service system constructed using the method for constructing a personalized media recommendation feed service system according to claim 1, characterized in that: include, Data source layer, data processing layer, interface service layer and application layer; Collect media data and user behavior data through the data source layer and store them in a database; When receiving the user request parameters, obtaining the recommendation candidate set from the database, updating the recommendation candidate set through the data processing layer, and sending it to the interface service layer; The recommendation candidate set is optimized, screened and sorted through the interface service layer, and finally output to the application layer.

4. The feed service system according to claim 3, characterized in that: The data processing layer includes a recommended data access service module, a recommended real-time correction service module, a recommended cache service module, and a recommended archiving service module; the interface service layer includes a recommended interface service module, a recommended intervention service module, and a recommended AB testing service module; The recommendation data access service module is used to receive and process media data and user behavior data to prepare a recommendation candidate set for subsequent recommendation; The recommendation real-time correction service module is used to update the recommendation candidate set in real time, adjust the status of the read content and optimize the real-time performance and accuracy of the candidate set; The recommendation cache service module is used to store the recommendation candidate sets of high-frequency users, improve the real-time and efficiency of data access, and regularly update and clean the cache; The recommendation archiving service module is used to archive and store recommendation data to ensure the integrity and traceability of historical data for analysis and optimization; The recommendation interface service module is used to receive user request parameters, obtain a recommendation candidate set, sort and filter the data, and then output the final media recommendation content; The recommendation intervention service module is used to dynamically adjust the weight and display order of media recommendation content according to preset media content specifications to ensure that the media recommendation content meets the personalized and positive guidance standards; The recommendation AB testing service module is used to group users and test different recommendation strategies, ensuring that each user uses the same strategy during the test to evaluate the effect.

5. The feed service system according to claim 4, characterized in that: The feed service system adopts a linkage three-level cache mechanism, including: The recommendation data access service module stores the recommendation data through MongoDB, the recommendation real-time correction service module stores the recommendation candidate set through Elasticsearch in a distributed manner; and the recommendation cache service module stores the recommendation candidate set determined to be high-frequency through Redis.

6. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the method for constructing a media personalized recommendation feed service system as described in any one of claims 1-2 are implemented.

7. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps in the method for constructing a media personalized recommendation feed service system as described in any one of claims 1 to 2 are implemented.

Images