CN116467518A - Intelligent content recommendation system - Google Patents
Intelligent content recommendation system Download PDFInfo
- Publication number
- CN116467518A CN116467518A CN202310434730.1A CN202310434730A CN116467518A CN 116467518 A CN116467518 A CN 116467518A CN 202310434730 A CN202310434730 A CN 202310434730A CN 116467518 A CN116467518 A CN 116467518A
- Authority
- CN
- China
- Prior art keywords
- module
- recommendation
- content
- rule
- content pool
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006399 behavior Effects 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
- G06F16/9574—Browsing optimisation, e.g. caching or content distillation of access to content, e.g. by caching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of Internet, and discloses an intelligent content recommendation system, which comprises: the scene module is used for defining scenes to be recommended according to service requirements and user behaviors; a rule module for designing a series of rules for mapping the content pool module of the downstream data source according to the scene requirements in the scene module; a background management module for managing the rule module and the content pool module; the rule engine module is used for processing the recommendation request, the historical behavior and the preference to obtain a recommendation result and returning the recommendation result; and the recommendation service module is used for acquiring data from the corresponding content pool module according to the recommendation result of the rule engine module and returning the data to the user. The invention can provide more accurate and efficient recommendation service for users and more efficient business popularization means for enterprises.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to an intelligent content recommendation system.
Background
Conventional recommendation systems typically employ both offline computing and online recommendation phases.
In the offline computing stage, the system performs offline computing according to the historical behavior data of the user, the characteristics of the articles and other information to obtain a recommendation list of each user, and algorithms such as collaborative filtering, content-based recommendation, matrix decomposition and the like are generally used. The calculated recommendation list may be stored in a database or cache.
In the online recommendation stage, when a user requests a recommendation list, the system can find the recommendation list which is most matched with the user from the stored recommendation list, and performs operations such as sequencing, filtering and the like, and finally recommends a certain number of articles to the user.
The conventional AI algorithm recommended method currently in common use has the following disadvantages: the interpretation of the recommendation result is poor, so that the user is difficult to understand the reason and basis of recommendation; for new users or cold start conditions, accurate personalized recommendation results cannot be provided; the traditional recommendation system usually needs offline calculation, cannot realize real-time recommendation and has low response speed; cold start problem: the conventional recommendation system often needs a large amount of user behavior data to recommend, so that the recommendation accuracy of new users and new articles is low; lack of personalization: recommendation systems based on collaborative filtering, content filtering and other algorithms often lack personalized recommendation and cannot fully meet personalized demands of users; once the model is trained, it is difficult to adjust the recommendation strategy and content, and the model needs to be retrained, which is costly.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide an intelligent content recommendation system which provides more accurate and efficient recommendation service for users and provides more efficient business popularization means for enterprises.
The technical scheme for achieving the purpose is as follows:
an intelligent content recommendation system, comprising:
the scene module is used for defining scenes to be recommended according to service requirements and user behaviors;
rule module for designing a series of rules according to the requirements of the scenes in the scene module
A content pool module for mapping downstream data sources;
a background management module for managing the rule module and the content pool module;
the rule engine module is used for processing the recommendation request, the historical behavior and the preference to obtain a recommendation result and returning the recommendation result;
and the recommendation service module is used for acquiring data from the corresponding content pool module according to the recommendation result of the rule engine module and returning the data to the user.
Preferably, each rule in the rule module corresponds to one content pool in the content pool module.
Preferably, each content pool in the content pool module needs to specify a parameter so that the program can take the parameter to access the specified downstream.
Preferably, the background management module may add, edit and delete scenes in the scene module, rules in the rule module and content pools in the content pool module.
Preferably, the recommendation service module is spliced according to the data combination acquired from the plurality of data sources, fills the data combination into corresponding recommendation positions according to the sequence specified by the rule, generates a final recommendation result, and recommends the final recommendation result to the user.
Preferably, each content pool in the content pool module corresponds to one or more data sources.
Preferably, the user can select the corresponding data source according to the actual requirement and set the parameters of the data source.
Preferably, the execution sequence of the rule can be set with priority according to the service requirement.
The beneficial effects of the invention are as follows:
1) The recommendation logic can be flexibly customized based on the rule engine module, the recommendation logic can be flexibly customized by writing rules, the requirements of different business scenes are met, and the recommendation rules can be customized according to different business scenes by adopting a scene+rule+content pool combination mode.
2) The recommendation system can support a plurality of data sources, so that the range of the data sources can be enlarged, and the recommendation accuracy can be improved.
3) The problem of cold start is solved, through nimble rule configuration, can customize the recommendation to new user and new article, has solved conventional recommendation system's cold start problem, has used the caching technology in addition, can generate the recommendation result in the short time to can respond to the user request fast.
4) Personalized recommendation is realized, personalized recommendation can be performed according to historical behaviors and preferences of users, and recommendation accuracy and user satisfaction are improved.
5) And the expandability can integrate a plurality of data sources as a content pool, and has higher expandability and customizability.
6) Maintainability, scene, rule, modification and maintenance of content pool are easier, only need to modify corresponding code or configuration, and maintenance cost is lower.
The invention can rapidly and flexibly recommend related content for the user through the combination of the rule and the content pool; the system is based on analysis and understanding of multidimensional data, and meets personalized requirements of users by combining priorities of rules and selection of content pools; the system can be widely applied to various recommendation scenes, and provides more accurate and efficient recommendation services for users.
Drawings
FIG. 1 is a block diagram of an intelligent content recommendation system of the present invention;
FIG. 2 is a block diagram of an intelligent content recommendation system of the present invention;
fig. 3 is a business architecture diagram of an intelligent content recommendation system of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying positive importance.
The invention will be further described with reference to the accompanying drawings.
As shown in fig. 1-2, an intelligent content recommendation system, comprising:
the scene module 1 is used for defining scenes such as shopping, reading, entertainment and the like which need to be recommended according to service requirements and user behaviors; each scene corresponds to a set of recommendation rules.
The rule module 2 is used for designing a series of rules according to the requirements of scenes in the scene module, the rules can be managed and regulated in a configuration file and other modes, priority can be set for the execution sequence of the rules according to service requirements, and the new users and the new articles can be customized and recommended through flexible rule configuration, so that the problem of cold start of a conventional recommendation system is solved; wherein a rule corresponds to a content pool.
A content pool module 3 for mapping downstream data sources; each content pool within the content pool module 3 maps downstream data sources, which can be implemented using a variety of different data storage techniques, such as relational databases, noSQL databases, memory databases, distributed caches, etc.; downstream services of some content pool mapping, such as a data center API, an algorithm recommendation API, etc., can also be defined; as shown in fig. 3 below, for each content pool, a parameter needs to be specified so that the program can take the parameter to access the specified downstream, e.g., AI algorithm; each content pool corresponds to a plurality of data sources and also supports a plurality of data sources, wherein the data sources can be traditional data sources such as a memory cache database, a relational database, a data center, and the like, can also be novel data sources such as an artificial intelligence algorithm, and can not only expand the range of the data sources, but also improve the recommendation accuracy; in the configuration process, a user can select a corresponding data source according to actual requirements and set parameters of the data source.
A background management module 4 for managing the rule module 2 and the content pool module 3; the background management module 4 can add, edit and delete scenes in the scene module 1, rules in the rule module 2 and content pools in the content pool module 3; the method can be realized based on the Web application program, is easy to modify and maintain, and only needs to modify corresponding codes or configurations.
The rule engine module 5 is used for processing the recommendation request, historical behaviors and preferences to obtain a recommendation result and returning the recommendation result, which is a core component used for processing the recommendation request, the rule engine module 5 can analyze the request and acquire data from a different content pool by using a specified rule according to the content of the request, and the rule engine module 5 is responsible for specifically executing business codes written by developers in the background and returning a final recommendation result to the recommendation service module 6; the rule engine module 5 may use an existing open source rule engine; the rule engine module 5 can also conduct personalized recommendation according to the historical behaviors and preferences of the user, so that recommendation accuracy and user satisfaction are improved.
The recommendation service module 6 is used for acquiring data from the corresponding content pool module according to the recommendation result of the rule engine module 5 and returning the result to the user; the recommendation service module 6 generates a final recommendation result according to the data combination and splicing obtained from the plurality of data sources, and fills the final recommendation result into corresponding recommendation positions according to the sequence specified by the rule, and recommends the final recommendation result to the user.
Firstly, according to a scene requested by a user, a group of corresponding recommendation rules exist, each recommendation rule corresponds to a content pool, related data are acquired from a data source according to the rules and the content pools, the acquired data are combined and spliced, and then the data are filled in corresponding recommendation positions according to the sequence specified by the rules, so that a final recommendation result is generated and recommended to the user. The recommendation logic is flexibly customized by writing rules, so that the requirements of different business scenes are met, and the recommendation rules can be customized according to the different business scenes by adopting a scene+rule+content pool combination mode.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (8)
1. An intelligent content recommendation system, comprising:
the scene module is used for defining scenes to be recommended according to service requirements and user behaviors;
a rule module for designing a series of rules according to the scene requirements in the scene module;
a content pool module for mapping downstream data sources;
a background management module for managing the rule module and the content pool module;
the rule engine module is used for processing the recommendation request, the historical behavior and the preference to obtain a recommendation result and returning the recommendation result;
and the recommendation service module is used for acquiring data from the corresponding content pool module according to the recommendation result of the rule engine module and returning the data to the user.
2. The intelligent content recommendation system of claim 1 wherein each rule in said rule module corresponds to a content pool in said content pool module.
3. An intelligent content recommendation system according to claim 1 wherein each content pool in said content pool module requires a parameter to be specified so that a program can take the parameter to access the specified downstream.
4. The intelligent content recommendation system of claim 1 wherein said background management module can add, edit and delete scenes in said scene module, rules in said rules module and content pools in said content pool module.
5. The intelligent content recommendation system according to claim 1, wherein the recommendation service module splices according to the data combination acquired from the plurality of data sources, fills the data combination into the corresponding recommendation positions according to the sequence specified by the rule, and generates final recommendation results to recommend to the user.
6. The intelligent content recommendation system of claim 1 wherein each content pool in said content pool module corresponds to one or more data sources.
7. The intelligent content recommendation system according to claim 1, wherein the user can select the corresponding data source according to the actual requirement and set the parameters of the data source.
8. The intelligent content recommendation system according to claim 1, wherein the order of execution of the rules is prioritized according to business needs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310434730.1A CN116467518A (en) | 2023-04-21 | 2023-04-21 | Intelligent content recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310434730.1A CN116467518A (en) | 2023-04-21 | 2023-04-21 | Intelligent content recommendation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116467518A true CN116467518A (en) | 2023-07-21 |
Family
ID=87180346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310434730.1A Pending CN116467518A (en) | 2023-04-21 | 2023-04-21 | Intelligent content recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116467518A (en) |
-
2023
- 2023-04-21 CN CN202310434730.1A patent/CN116467518A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10990646B2 (en) | System for dynamic user interface generation | |
| US20200257543A1 (en) | Aggregate Features For Machine Learning | |
| US11468103B2 (en) | Relational modeler and renderer for non-relational data | |
| US11176154B1 (en) | Collaborative dataset management system for machine learning data | |
| JP4856627B2 (en) | Partial query caching | |
| US10579632B2 (en) | Personalized content authoring driven by recommendations | |
| CN117194609A (en) | Providing command bundle suggestions for automated assistants | |
| US11449553B2 (en) | Systems and methods for generating real-time recommendations | |
| US11119764B2 (en) | Automated editing task modification | |
| US20100161558A1 (en) | Computer-based data processing system and method of processing data objects | |
| US20100023562A1 (en) | Extended system for accessing electronic documents with revision history in non-compatible repositories | |
| US20210312136A1 (en) | Machine Learning System for Optimizing Projects | |
| CN105989056B (en) | A kind of Chinese news recommender system | |
| US20120209859A1 (en) | Methods and systems to profile individuals and organizations, and to evaluate culture fit | |
| Fekete | Progressivis: A toolkit for steerable progressive analytics and visualization | |
| CN112115276B (en) | Intelligent customer service method, device, equipment and storage medium based on knowledge graph | |
| US20210004693A1 (en) | Real-Time On the Fly Generation of Feature-Based Label Embeddings Via Machine Learning | |
| US10762902B2 (en) | Method and apparatus for synthesizing adaptive data visualizations | |
| KR102153259B1 (en) | Data domain recommendation method and method for constructing integrated data repository management system using recommended domain | |
| CN111680087B (en) | Main data model management platform and method | |
| US20150081576A1 (en) | Generating a supplemental description of an entity | |
| CN117035078A (en) | Multi-mode knowledge graph unified representation learning framework | |
| CN116467518A (en) | Intelligent content recommendation system | |
| CN115617338A (en) | Method and device for quickly generating service page and readable storage medium | |
| CN115543428A (en) | Simulated data generation method and device based on strategy template |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |