CN112836122A - Method for constructing recommendation system based on application data - Google Patents
Method for constructing recommendation system based on application data Download PDFInfo
- Publication number
- CN112836122A CN112836122A CN202110147615.7A CN202110147615A CN112836122A CN 112836122 A CN112836122 A CN 112836122A CN 202110147615 A CN202110147615 A CN 202110147615A CN 112836122 A CN112836122 A CN 112836122A
- Authority
- CN
- China
- Prior art keywords
- data
- layer
- recommendation system
- recommendation
- topic
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 230000006399 behavior Effects 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012731 temporal analysis Methods 0.000 claims description 6
- 238000000700 time series analysis Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 230000002349 favourable effect Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
Images
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of recommendation systems, in particular to a method for constructing a recommendation system based on application data, which comprises a user characteristic model, a question recommendation engine, a structured data source and a model strategy, wherein the question recommendation engine consists of a business application layer, a recommendation system layer, a core data layer, an offline calculation layer, a recommendation system background and a scheduling/coordinating server, and through carrying out layered processing on data, proper exercise questions are recommended according to student learning conditions, learning progress and learning preference according to different teaching progress and student learning conditions, and the learning efficiency of students is improved. According to the teaching progress, the student learning condition and the teacher preference, a proper question is recommended for the teacher paper, and the reliability and the effectiveness of the test paper are improved.
Description
Technical Field
The invention relates to the technical field of recommendation systems, in particular to a method for constructing a recommendation system based on application data.
Background
It is particularly difficult to select proper questions from a large question bank. Therefore, there is an increasing demand for a method of constructing a recommendation system based on application data.
The selection of proper questions in a mass question bank existing in the market at present is particularly difficult, different teaching progresses and student learning situations are difficult to distinguish, and the key for improving the learning efficiency of students becomes the user experience is how to recommend proper exercise questions to students with different learning situations, learning progresses and learning preferences. In addition, how to recommend proper questions for the teacher paper according to the teaching progress, the student learning condition and the teacher preference and improve the reliability and the effectiveness of the test paper are also the problem of concern, so a method for constructing a recommendation system based on application data is provided for the problems.
Disclosure of Invention
The present invention aims to provide a method for constructing a recommendation system based on application data, so as to solve the problems proposed in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for building a recommendation system based on application data comprises a user characteristic model, a topic recommendation engine, a structured data source and a model strategy, wherein the topic recommendation engine comprises a service application layer, a recommendation system layer, a core data layer, an off-line calculation layer, a recommendation system background and a scheduling/coordinating server.
Preferably, the business application layer comprises questions, a group paper center and examination/practice, the recommendation system layer comprises a sorting algorithm, a filtering algorithm, an AB distribution algorithm and a log collection algorithm, the core data layer comprises category correlation data, question label data, high-quality question bank data, teacher preference data, student learning condition data and log collection data, the off-line calculation layer comprises application data and basic data, the application data comprises user portrait, student learning condition, a similarity matrix and a high-quality question bank, the basic data comprises teacher basic data, student basic data, question basic data and log basic data, the recommendation system background comprises a scene configuration module, an AB configuration module, a report presentation module and a data maintenance module, the scene configuration module and the AB configuration module in the recommendation system background are configured aiming at the related strategies of the recommendation system layer, the report display module and the data maintenance module in the background of the recommendation system are used for displaying and maintaining relevant data of a recommendation system layer and a core data layer, the recommendation system layer, the core data layer and an off-line calculation layer are deployed through different servers, resources are uniformly distributed by a scheduling/coordinating server, the core data layer is used for pulling data from the off-line calculation layer, the recommendation system layer calls the core data layer through an intelligent routing algorithm, and the business application layer calls the recommendation system layer through a json service.
Preferably, the user characteristic model is composed of a common device characteristic, a demographic characteristic, an access time characteristic, an access frequency characteristic, an attention topic characteristic and other behavior characteristics, the common device characteristic can distinguish whether the user device is a PC, a Phone or a Pad, the demographic characteristic is used for judging the gender and the age of the user, the access time characteristic is the last login time and the distribution of the access time of one day, the access frequency characteristic includes information such as the number of accesses of one day, the number of accesses of one week, the number of recommended clicks of one week and the like, the attention topic characteristic includes the popularity of the attention topic and the type of the attention topic, and the other behavior characteristics include search records and collected contents.
Preferably, the topic feature model is composed of topic content features, topic labels, topic affiliated clusters, topic popularity, timeliness, topic social features and topic value evaluation.
Preferably, the model strategy comprises Association Rules, Classify, Cluster, Dimension reduction and Time series analysis, wherein the Association Rules are used for judging whether the user equipment is a PC, a Phone or a Pad, the Classify is used for predicting the gender and the age of the user, the Cluster is used for topic clustering and user grouping, the Dimension reduction is used for calculating similar users, and the Time series analysis is used for calculating user interest model transfer.
Preferably, the focus of the topic feature model optimization is the difference between personalized recommendation ranking and search ranking, the difference between behavior-based recommendation and content-based recommendation, time-sharing recommendation, scene-based recommendation, recommendation algorithm A/B test, manual data review and learning from base.
Preferably, the structured data source includes a relationship between topics, a relationship between keywords and topics, a relationship between categories and topics, a relationship between clusters and topics, a relationship between users and topics, and a relationship between users and users.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, through the layered processing of the data, aiming at different teaching progresses and student learning conditions, proper exercise questions are recommended according to the student learning conditions, the learning progress and the learning preference, so that the learning efficiency of students is improved. According to the teaching progress, the student learning condition and the teacher preference, a proper question is recommended for the teacher paper, and the reliability and the effectiveness of the test paper are improved.
Drawings
FIG. 1 is a schematic diagram of a topic recommendation engine according to the present invention.
In the figure: 1-service application layer, 2-recommendation system layer, 3-core data layer, 4-off-line calculation layer, 5-recommendation system background and 6-scheduling/coordinating server.
Detailed Description
Referring to fig. 1, the present invention provides a technical solution:
a method for building a recommendation system based on application data comprises a user characteristic model, a topic recommendation engine, a structured data source and a model strategy, wherein the topic recommendation engine is composed of a service application layer 1, a recommendation system layer 2, a core data layer 3, an offline calculation layer 4, a recommendation system background 5 and a scheduling/coordinating server 6.
Business application layer 1 includes the title, organizes the paper center and examination/exercise, recommendation system layer 2 comprises sequencing algorithm, filtering algorithm, AB reposition of redundant personnel algorithm and log collection algorithm, core data layer 3 includes category correlation data, title label data, high-quality question bank data, teacher preference data, student's situation data and log collection data, off-line calculation layer 4 includes application data and basic data, application data is by user portrait, student's situation, similar matrix and high-quality question bank, basic data comprises teacher basic data, student's basic data, title basic data and log basic data, recommendation system backstage 5 comprises scene configuration module, AB configuration module, report presentation module and data dimension module, scene configuration module and AB configuration module in recommendation system backstage 5 are to making the relevant tactics of recommendation system layer 2 and are joined in marriage The device comprises a report display module and a data maintenance module in a recommendation system background 5, wherein the report display module and the data maintenance module are used for displaying and maintaining relevant data of a recommendation system layer 2 and a core data layer 3, the recommendation system layer 2, the core data layer 3 and an offline calculation layer 4 are all deployed through different servers, resources are uniformly distributed by a scheduling/coordinating server 6, the core data layer 3 is used for pulling data from the offline calculation layer 4, the recommendation system layer 2 calls the core data layer 3 through an intelligent routing algorithm, a business application layer 1 calls the recommendation system layer 2 through json service, the arrangement is favorable for carrying out layered processing on the data, and suitable exercise questions are recommended according to different teaching progresses and student situations according to the student situations, learning progresses and learning preference, so that the learning efficiency of students is improved, and a user characteristic model is formed by common equipment characteristic models, The user equipment comprises demographic characteristics, access time characteristics, access frequency characteristics, concerned topic characteristics and other behavior characteristics, the common equipment characteristics can distinguish whether the user equipment is a PC, a Phone or a Pad, the demographic characteristics are used for judging the gender and the age of the user, the access time characteristics are the last login time and the distribution of one-day access time, the access frequency characteristics comprise information such as one-day access times, one-week click recommendation times and the like, the concerned topic characteristics comprise the heat degree of the concerned topic and the type of the concerned topic, the other behavior characteristics comprise search records and collection contents, the setting is favorable for fully knowing the habits of the user, the topic characteristic model of the topic is composed of topic content characteristics, topic labels, cluster to which the topic belongs, the popularity, the timeliness, the social characteristics of the topic and the value evaluation of the topic, and the setting is favorable for the topic characteristic data processing, the model strategy comprises Association Rules, Classify, Cluster, Dimension reduction and Time series analysis, the Association Rules are used for judging whether the user equipment is a PC, a Phone or a Pad, the Classify is used for predicting the gender and the age of the user, the Cluster is used for topic clustering and user grouping, the Dimension reduction is used for calculating similar users, the Time series analysis is used for calculating user interest model transfer, the arrangement is favorable for intelligently predicting the user interest and improving the user experience, the topic feature model optimization is focused on the difference between personalized recommendation sequencing and search sequencing, the difference between behavior-based recommendation and content-based recommendation, Time-sharing recommendation, scene-based recommendation, recommendation algorithm A/B test, manual data review and learning from a bad base, and the arrangement is favorable for fitting a topic continuous experience optimization model of the user, and the structured data source comprises the relationship between the structured data source and the topic, The data source is structured and convenient to call by the aid of the setting of the relation between the keywords and the titles, the relation between the categories and the titles, the relation between the clusters and the titles, the relation between the users and the titles and the relation between the users.
The principles and embodiments of the present invention are explained herein using specific examples, which are presented only to assist in understanding the method and its core concepts of the present invention. The foregoing is only a preferred embodiment of the present invention, and it should be noted that there are objectively infinite specific structures due to the limited character expressions, and it will be apparent to those skilled in the art that a plurality of modifications, decorations or changes may be made without departing from the principle of the present invention, and the technical features described above may be combined in a suitable manner; such modifications, variations, combinations, or adaptations of the invention using its spirit and scope, as defined by the claims, may be directed to other uses and embodiments.
Claims (7)
1. A method for constructing a recommendation system based on application data comprises a user characteristic model, a topic recommendation engine, a structured data source and a model strategy, and is characterized in that: the topic recommendation engine is composed of a business application layer (1), a recommendation system layer (2), a core data layer (3), an offline calculation layer (4), a recommendation system background (5) and a scheduling/coordinating server (6).
2. The method of claim 1, wherein the recommendation system is constructed based on application data, and the method comprises: the business application layer (1) comprises questions, a group paper center and examination/practice, the recommendation system layer (2) is composed of a sequencing algorithm, a filtering algorithm, an AB shunt algorithm and a log collection algorithm, the core data layer (3) comprises category correlation data, question label data, high-quality question bank data, teacher preference data, student learning condition data and log collection data, the off-line calculation layer (4) comprises application data and basic data, the application data comprises user portrait, student learning condition, a similar matrix and a high-quality question bank, the basic data comprises teacher basic data, student basic data, question basic data and log, the recommendation system (5) comprises a scene configuration module, an AB configuration module, a report display module and a data maintenance module, the method comprises the steps that a scene configuration module and an AB configuration module in a recommendation system background (5) are configured aiming at a recommendation system layer (2) relevant strategy, a report display module and a data maintenance module in the recommendation system background (5) are configured aiming at the recommendation system layer (2) and core data layer (3) relevant data, the recommendation system layer (2), the core data layer (3) and an offline calculation layer (4) are deployed through different servers, resources are uniformly distributed through a scheduling/coordinating server (6), the core data layer (3) pulls data from the offline calculation layer (4), the recommendation system layer (2) calls the core data layer (3) through an intelligent routing algorithm, and a business application layer (1) calls the recommendation system layer (2) through a json service.
3. The method of claim 1, wherein the recommendation system is constructed based on application data, and the method comprises: the user feature model is composed of common device features, demographic features, access time features, access frequency features, attention topic features and other behavior features, the common device features can distinguish whether the user device is a PC, Phone or Pad, the demographic features are used for judging the gender and age of the user, the access time features are distribution of last login time and one-day access time, the access frequency features comprise information such as one-day access times, one-week access times and one-week click recommendation times, the attention topic features comprise heat of the attention topic and types of the attention topic, and the other behavior features comprise search records and collection contents.
4. The method of claim 1, wherein the recommendation system is constructed based on application data, and the method comprises: the topic feature model is composed of topic content features, topic labels, topic affiliated clusters, topic popularity, timeliness, topic social features and topic value evaluation.
5. The method of claim 1, wherein the recommendation system is constructed based on application data, and the method comprises: the model strategy comprises Association Rules, Classify, Cluster, Dimension reduction and Time series analysis, wherein the Association Rules are used for judging whether user equipment is a PC, a Phone or a Pad, the Classify is used for predicting the gender and the age of a user, the Cluster is used for topic clustering and user grouping, the Dimension reduction is used for calculating similar users, and the Time series analysis is used for calculating user interest model transfer.
6. The method of claim 1, wherein the recommendation system is constructed based on application data, and the method comprises: the focus of the topic feature model optimization is the difference between personalized recommendation sequencing and search sequencing, the difference between behavior-based recommendation and content-based recommendation, time-sharing recommendation, scene-based recommendation, recommendation algorithm A/B test, manual data review and learning from base.
7. The method of claim 1, wherein the recommendation system is constructed based on application data, and the method comprises: the structured data source comprises a relation between topics, a relation between keywords and topics, a relation between categories and topics, a relation between clusters and topics, a relation between users and topics, and a relation between users and users.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110147615.7A CN112836122A (en) | 2021-02-03 | 2021-02-03 | Method for constructing recommendation system based on application data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110147615.7A CN112836122A (en) | 2021-02-03 | 2021-02-03 | Method for constructing recommendation system based on application data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112836122A true CN112836122A (en) | 2021-05-25 |
Family
ID=75931672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110147615.7A Withdrawn CN112836122A (en) | 2021-02-03 | 2021-02-03 | Method for constructing recommendation system based on application data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112836122A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407831A (en) * | 2021-06-16 | 2021-09-17 | 中国联合网络通信集团有限公司 | Course recommendation method and equipment |
| CN113779396A (en) * | 2021-09-10 | 2021-12-10 | 平安科技（深圳）有限公司 | Topic recommendation method and device, electronic equipment and storage medium |
| CN116738371A (en) * | 2023-08-14 | 2023-09-12 | 广东信聚丰科技股份有限公司 | User learning portrait construction method and system based on artificial intelligence |
-
2021
- 2021-02-03 CN CN202110147615.7A patent/CN112836122A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113407831A (en) * | 2021-06-16 | 2021-09-17 | 中国联合网络通信集团有限公司 | Course recommendation method and equipment |
| CN113407831B (en) * | 2021-06-16 | 2024-03-01 | 中国联合网络通信集团有限公司 | Course recommendation method and device |
| CN113779396A (en) * | 2021-09-10 | 2021-12-10 | 平安科技（深圳）有限公司 | Topic recommendation method and device, electronic equipment and storage medium |
| CN113779396B (en) * | 2021-09-10 | 2023-09-01 | 平安科技（深圳）有限公司 | Question recommending method and device, electronic equipment and storage medium |
| CN116738371A (en) * | 2023-08-14 | 2023-09-12 | 广东信聚丰科技股份有限公司 | User learning portrait construction method and system based on artificial intelligence |
| CN116738371B (en) * | 2023-08-14 | 2023-10-24 | 广东信聚丰科技股份有限公司 | User learning portrait construction method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112836122A (en) | Method for constructing recommendation system based on application data | |
| Wang et al. | Using collaborative filtering to support college students’ use of online forum for English learning | |
| CN103198086A (en) | Information processing device, information processing method, and program | |
| Gao et al. | Optimization analysis and implementation of online wisdom teaching mode in cloud classroom based on data mining and processing | |
| CN108563749B (en) | Online education system resource recommendation method based on multi-dimensional information and knowledge network | |
| Witkin | An Analysis of Needs Assessment Techniques for Educational Planning at State, Intermediate, and District Levels. | |
| CN109637233A (en) | A kind of method and system of intelligent tutoring | |
| JP3883795B2 (en) | Attendance class selection device, attendance class selection method, and storage medium | |
| RU2581009C2 (en) | System and method for accumulating accreditation | |
| CN113052737A (en) | Learning method and system based on forced supervision and intelligent recommendation | |
| EP3834056A1 (en) | Live bi-directional video/audio feed generation between a consumer and a service provider | |
| CN106844511A (en) | Syndication search method and system | |
| CN112465677A (en) | Teaching platform for online education | |
| US20130309645A1 (en) | Systems and Methods for Educational Social Networking | |
| Katan et al. | The readiness of e-publishing among Malaysian book publishers | |
| US20150006253A1 (en) | Polling questions served with supplemental information | |
| KR20230112397A (en) | Marketing process-based marketing strategy planning online system of training and practice functions | |
| Shen et al. | An open framework for smart and personalized distance learning | |
| KR101245824B1 (en) | Method, system and computer-readable recording medium for providing study information | |
| Li et al. | Design of Intelligent Push System for Teaching Resources Based on User Profile | |
| Duan et al. | Analysis of college art teaching system under the background of video big data technology | |
| Jia et al. | A mental health education strategy based on online videos | |
| CN112307346B (en) | Courseware management system based on big data | |
| Shang | Development of College English Personalized Learning Support System Based on Data Mining Technology | |
| Xiao | Research on Information Demand of College Students in Emergency Environment based on Virtual Q&A Community-Take" Zhihu" as an Example |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210525 |
|
| WW01 | Invention patent application withdrawn after publication |