CN116644233A - Course recommendation method, device, equipment and storage medium of online learning platform - Google Patents

Course recommendation method, device, equipment and storage medium of online learning platform Download PDF

Info

Publication number
CN116644233A
CN116644233A CN202310621273.7A CN202310621273A CN116644233A CN 116644233 A CN116644233 A CN 116644233A CN 202310621273 A CN202310621273 A CN 202310621273A CN 116644233 A CN116644233 A CN 116644233A
Authority
CN
China
Prior art keywords
user
role
attribute information
information
target user
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
Application number
CN202310621273.7A
Other languages
Chinese (zh)
Inventor
李素粉
赵健东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN202310621273.7A priority Critical patent/CN116644233A/en
Publication of CN116644233A publication Critical patent/CN116644233A/en
Pending legal-status Critical Current

Links

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
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155—Bayesian classification
    • 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
    • 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)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Educational Technology (AREA)
  • Educational Administration (AREA)
  • Evolutionary Computation (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides a course recommendation method, device and equipment of an online learning platform and a storage medium. The method comprises the following steps: acquiring a user attribute information set and a role class set from an online learning platform database, extracting attributes related to user role class information from the user attribute information set, generating a user role related attribute information set, acquiring the role class information when the role class information of a target user is not missing, acquiring the target user attribute information when the role class is missing, determining the target user role class information according to the target user attribute information, the user role class set and the user role related attribute information set through a Bayesian classification method, screening candidate course data according to the target user role class information, and recommending candidate course data to the target user. The method improves accuracy and efficiency of course recommendation.

Description

Course recommendation method, device, equipment and storage medium of online learning platform
Technical Field
The present application relates to the field of network technologies, and in particular, to a course recommendation method, apparatus, device, and storage medium for an online learning platform.
Background
In the process that the online network learning platform provides training learning service for users, accurate learning recommendation is one main content of platform operation. In order to accurately push course content meeting learning requirements to users, natural attribute information of the users and historical learning information are very important reference data.
In order to recommend proper courses to a target user, the prior art adopts a mode of carrying out target course estimation according to natural attribute information and historical learning information of the user to recommend courses to the target user.
However, the accuracy of course recommendation is reduced due to the problems that the natural attribute information input by the user during login is not complete, or the history learning information is not available for the newly logged-in user.
Disclosure of Invention
The application provides a course recommendation method, device and equipment of an online learning platform and a storage medium, which are used for solving the problems of low efficiency and low accuracy of user post determination.
In a first aspect, the present application provides a course recommendation method for an online learning platform, including:
acquiring a user attribute information set and a role class set from an online learning platform database, wherein the user attribute information set comprises a plurality of attribute information classes, the user role class set comprises a plurality of role class information, and the attribute information comprises: removing natural attribute information and history learning information of the character class information;
Extracting attributes related to user role category information from the attribute information set of the user, and generating a role related attribute information set of the user;
when the role category information of the target user is not lost, acquiring the role category information of the target user, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user;
when the role category of the target user is missing, acquiring attribute information of the target user, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, the role category set of the user and the related attribute information set of the user role, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
In a second aspect, the present application provides a post determining device for an online learning platform user, including:
the acquisition module is used for acquiring a user attribute information set and a role class set from the online learning platform database, wherein the attribute information class comprises a plurality of pieces of sub-attribute information, and the role class set of the user comprises a plurality of pieces of role class information. The attribute information includes: removing natural attribute information and history learning information of the character class information;
The generation module is used for extracting attributes related to the user role category information from the attribute information set of the user and generating a role related attribute information set of the user;
and the recommendation module is used for acquiring the role category information of the target user when the role category information of the target user is not lost, screening candidate course data from the online learning platform database according to the role category information of the target user, recommending the candidate course data to the target user, acquiring the attribute information of the target user when the role category of the target user is lost, determining the role category information of the target user according to the attribute information of the target user, the role category set of the user and the related attribute information set of the user role by a Bayesian classification method, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
In a third aspect, the present application provides an on-line learning platform user position determining apparatus, including:
a processor, a memory, a communication interface;
The memory is used for storing executable instructions of the processor;
wherein the processor is configured to perform the course recommendation method of the online learning platform as described in the first aspect above via execution of the executable instructions.
In a fourth aspect, the present application provides a readable storage medium comprising: a computer program stored thereon, which when executed by a processor, implements a course recommendation method of executing the online learning platform as described in the first aspect above.
According to the course recommendation method, device, equipment and storage medium of the online learning platform, the attribute information set and the role class set of the user are obtained from the online learning platform database, the attribute information set of the user comprises a plurality of attribute information classes, and the role class set of the user comprises a plurality of role class information. The attribute information includes: removing natural attribute information and history learning information of character class information, extracting attributes related to the character class information of the user from the attribute information set of the user, generating a character related attribute information set of the user, acquiring the character class information of the target user when the character class information of the target user is not missing, screening candidate course data from an online learning platform database according to the character class information of the target user, and recommending the candidate course data to the target user; when the role category of the target user is missing, acquiring attribute information of the target user, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, a role category set of the user and a related attribute information set of the user role, screening candidate course data from an online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user. The user role category information is user basic attribute information which plays a representative role in platform course selection of the user, the course is recommended to the target user through the role category information of the user with the role type not being missing, accuracy of course recommendation is improved, the role category information of the user with the role type missing is determined through a Bayesian classification method, courses are recommended to the target user further, and accuracy and efficiency of course recommendation are improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flowchart illustrating a course recommendation method of an online learning platform according to an embodiment of the present application;
fig. 2 is a schematic flow chart of extracting attributes related to user role category information from the attribute information set of the user to generate a user role related attribute information set according to an embodiment of the present application;
fig. 3 is a schematic flow chart of determining character class information of the target user according to the attribute information of the target user, the character class set of the user and the related attribute information set of the user according to a bayesian classification method provided by the embodiment of the application;
FIG. 4 is a schematic structural diagram of a course recommendation device of an online learning platform according to an embodiment of the present application;
FIG. 5 is a schematic diagram of another course recommendation device of an online learning platform according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a course recommendation device of an online learning platform according to an embodiment of the present application.
Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
In the prior art, a mode of estimating a target course according to natural attribute information and historical learning information of a user is adopted to recommend the course to the target user. However, the accuracy of course recommendation is reduced due to the problems that the natural attribute information input by the user during login is not complete, or the history learning information is not available for the newly logged-in user.
According to the application, the attribute information set and the role class set of the user are acquired from the online learning platform database, wherein the attribute information set of the user comprises a plurality of attribute information classes, and the role class set of the user comprises a plurality of role class information. The attribute information includes: removing natural attribute information and history learning information of character class information, extracting attributes related to the character class information of the user from the attribute information set of the user, generating a character related attribute information set of the user, acquiring the character class information of the target user when the character class information of the target user is not missing, screening candidate course data from an online learning platform database according to the character class information of the target user, and recommending the candidate course data to the target user; when the role category of the target user is missing, acquiring attribute information of the target user, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, a role category set of the user and a related attribute information set of the user role, screening candidate course data from an online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user. The user role category information is user basic attribute information which plays a representative role in platform course selection of the user, the course is recommended to the target user through the role category information of the user with the role type not being missing, accuracy of course recommendation is improved, the role category information of the user with the role type missing is determined through a Bayesian classification method, courses are recommended to the target user further, and accuracy and efficiency of course recommendation are improved.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a flowchart of a course recommendation method of an online learning platform according to a first embodiment of the present application.
As shown in fig. 1, the course recommendation method of the online learning platform of the present embodiment may include the following steps:
step S101, acquiring a user attribute information set and a role class set from an online learning platform database, wherein the user attribute information set comprises a plurality of attribute information classes, and the user role class set comprises a plurality of role class information. The attribute information includes: and removing natural attribute information and history learning information of the character class information.
Specifically, the online learning platform database stores natural attribute information input by a platform user when logging in the platform and historical learning information stored by the platform user in the historical use process of the platform. Specifically, the natural attribute information refers to basic attribute information of the user, for example, for an enterprise learning platform user, the natural attribute information of the user, that is, the basic attribute information may include: user ID, user age, user gender, department in which the user is located, user post, user graduation, etc. Specifically, the history learning information refers to history course learning information of the user in the use process of the history platform, for example, for an enterprise learning platform user, the history learning information of the user may include: the learning times of the user, the learning time of the user, the learning course of the user and the like. For a user who logs in the online learning platform and does not start learning, only natural attribute information of the user is stored in the online learning platform database.
Among the respective attribute information of the user, there is user character class information, which refers to user basic attribute information that plays a representative role in platform course selection of the user, for example: for the enterprise learning platform user, the role category information can be user post information.
Specifically, natural attribute information and history learning information of the user may be obtained from the learning platform, and an online learning platform user, that is, an attribute information set B and a role class set C of the user may be generated, where the attribute information includes: the attribute information set of the user includes a plurality of attribute information categories, such as: for the above-described enterprise learning platform, the attribute information set of the user includes a plurality of attribute information categories, for example: a category such as a user age category, a user gender category, and the like, wherein a character category set of the user includes a plurality of character category information, for example: for the enterprise learning platform, the user's character class set includes a plurality of character class information, for example: the operation and maintenance post, personnel post and the like.
Step S102, extracting attributes related to the user role category information from the attribute information set of the user, and generating a role related attribute information set of the user.
The user role category information refers to user basic attribute information that plays a representative role in platform course selection of the user, and specifically, an attribute related to the user role category information may be extracted from the attribute information set B of the user acquired in step S101, so as to generate a role related attribute information set a of the user, as described in step S101.
Wherein the elements in the character related attribute information set A of the user are attribute information set elements of the user associated with the character class information. Specifically, in the process of screening the elements in the attribute information set B of the user and generating the role related attribute information set a of the user, various modes can be selected. For example: in the attribute information set B of the user, for an element that can directly determine that there is a great correlation with the user character class information of the user, for example: in the enterprise learning platform, the learning course of the user in the attribute information set B of the user has great relevance with the character type information of the user, and the learning course can be directly processed and then set as the element of the character related attribute information set A of the user. For example: in the attribute information set B of the user, for an element for which the association with the character class information class cannot be directly judged, for example, there can be employed: and judging whether the element can be set as the element of the character related attribute information set A of the user according to parameters such as item set confidence and the like.
Specifically, the elements of the character-related attribute information set a determined in the above description may be combined together to constitute the character-related attribute information set a of the user.
And step S103, when the role category information of the target user is not lost, acquiring the role category information of the target user, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
Specifically, as described in step S101, the user role category information refers to user basic attribute information that plays a representative role in selecting a platform course for a user, so that the course recommendation method of the online learning platform provided in this embodiment may screen candidate course data from the online learning platform database according to the role category information of the target user, so as to improve accuracy of platform course recommendation.
The target user refers to a user who is currently logged in to the learning platform (including a history learner and a first logged in learner) and needs to recommend courses according to user characteristics of the learning platform, wherein the target user may include: the users with the missing character category information and the users with the missing character category information refer to the users without the character category information when the users fill in the natural attribute information.
Specifically, when the character class information of the target user is not missing, the character class information of the target user can be obtained, candidate course data is screened from the online learning platform database according to the character class information of the target user, and the candidate course data is recommended to the target user.
Step S104, when the role category of the target user is missing, acquiring attribute information of the target user, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, the role category set of the user and the related attribute information set of the user role, screening candidate course data from an online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
Specifically, when the role category of the target user is missing, attribute information of the target user may be obtained, the role category information of the target user is determined by a bayesian classification method according to the attribute information of the target user, the role category set of the user obtained in step S101 and the related attribute information set of the user role generated in step S103, candidate course data is screened from the online learning platform database according to the role category information of the target user, and the candidate course data is recommended to the target user.
Wherein, as described in step S101, the attribute information includes: removing natural attribute information of character class information and history learning information, specifically, a target user whose character class is missing may include: a user with a course learning history and a user without a course learning history, the user without a course learning history including: the first-time logged-in college and the users who have historic logged-in but have not learned courses. Specifically, for a user having a course learning history, the attribute information of the target user may include: removing natural attribute information and history learning information of a target user of character class information; for users without course learning history, the attribute information of the target user may include: and removing the natural attribute information of the target user of the character class information.
According to the course recommendation method of the online learning platform, the attribute information set and the role class set of the user are obtained from the online learning platform database, the attribute information set of the user comprises a plurality of attribute information classes, and the role class set of the user comprises a plurality of role class information. The attribute information includes: removing natural attribute information and history learning information of character class information, extracting attributes related to the character class information of the user from the attribute information set of the user, generating a character related attribute information set of the user, acquiring the character class information of the target user when the character class information of the target user is not missing, screening candidate course data from an online learning platform database according to the character class information of the target user, and recommending the candidate course data to the target user; when the role category of the target user is missing, acquiring attribute information of the target user, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, a role category set of the user and a related attribute information set of the user role, screening candidate course data from an online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user. The user role category information is user basic attribute information which plays a representative role in platform course selection of the user, the course is recommended to the target user through the role category information of the user with the role type not being missing, accuracy of course recommendation is improved, the role category information of the user with the role type missing is determined through a Bayesian classification method, courses are recommended to the target user further, and accuracy and efficiency of course recommendation are improved.
Fig. 2 is a flow chart of extracting attributes related to user role category information from a user's attribute information set to generate a user role related attribute information set according to a second embodiment of the present application. On the basis of the embodiment shown in fig. 1, this embodiment describes a process of extracting attributes related to user character class information from a user's attribute information set and generating a user character related attribute information set.
As shown in fig. 2, the extracting, from the attribute information set of the user, the attribute related to the user character class information, and generating the attribute information set related to the user character may include the steps of:
step S201, directly extracting a first attribute element group of the user role related attribute information set from the attribute information set of the user.
Specifically, as described in step S102, the elements in the user' S character-related attribute information set a are attribute information set elements of the user associated with the character class information. In the attribute information set B of the user, for the element which can directly judge that the association with the user role category information is great, the element can be directly extracted, and is set as the element of the role related attribute information set a of the user after processing.
Specifically, the judgment can be directly performed on the elements in the attribute information set B of the user, when the elements in the attribute information set B of the user are elements with great relevance to the role category, for example: in the enterprise learning platform, the user learning course in the attribute information set B of the user has great relevance to the role category, and the element of the attribute information set of the user, namely, the user learning course, can be directly set as the element of the role related attribute information set a of the user. Such elements are first attribute elements of the user's role-related attribute information set a, specifically, the first attribute elements of the user's role-related attribute information set may be determined according to the user's attribute information set, and all the first attribute elements of the user's role-related attribute information set a may be combined together to form a first attribute element group of the user's role-related attribute information set a for forming the user's role-related attribute information set a.
Step S202, acquiring natural attribute information and history learning information of a plurality of users, and extracting a second attribute element group of the user role related attribute information set from the attribute information set of the users according to the natural attribute information of the plurality of users, the history learning information of the plurality of users, the attribute set of the users and the role class set of the users.
Specifically, as described in step S103, the elements in the character-related attribute information set a of the user are the user natural attributes associated with the character class information. In the attribute information set B of the user, for an element for which the association with the character class information cannot be directly determined, for example, the following can be applied: and judging whether the element can be set as the element of the character related attribute information set A of the user according to parameters such as item set confidence and the like.
Specifically, the natural attribute information and the history learning information of the plurality of users may be acquired from the online learning platform database, and the second attribute element group of the user role-related attribute information set may be extracted from the attribute information set of the users according to the natural attribute information of the plurality of users, the history learning information of the plurality of users, the attribute information set of the users and the role class set of the users acquired in step S101
The transaction set can be constructed according to the natural attribute information of the plurality of users and the history learning information of the plurality of users, and is a set of all information of the plurality of users.
Specifically, natural attribute information and character class information of a plurality of users whose character class information is not missing can be screened from the online learning platform database. Wherein, each piece of information of the character class information and the natural attribute information of the user which is not missing in the plurality of pieces of character class information can be called a transaction, and a set formed by all the transactions is a transaction set T.
Wherein, a plurality of items can be constructed according to the attribute information set of the user, and different items are used for marking different sub-attribute information under the same attribute information category.
Specifically, the attribute information category includes a plurality of sub-attribute information, for example: the user gender category includes: male and female child attribute information.
Specifically, all items of the attribute information set of the user may be constructed according to the attribute information set of the user acquired in step S101, and different items are used to mark different sub-attribute information under the same attribute information category. For example: an element, namely attribute information category B, can be selected from the attribute information set of the user n -a learning period of the user; determining attribute information category B n I.e. attribute values, for example: morning (8:00-12:00), afternoon (12:00-18:00), evening (18:00-22:00), etc. periods; the attribute information may be classified into category B n As attribute information class B, attribute values n Item(s) of (1), noted Y j Wherein Y is 1 ＝8:00-12:00，Y 2 =12:00-18:00 … …, j=1, 2 … … J, J being attribute information category B n The number of items, and the genusSex information category B n Corresponds to the number of sub-attribute information. Specifically, according to the above method, items of all elements in the attribute information set of the user, that is, attribute categories, can be constructed.
Wherein, a plurality of item sets can be constructed according to the user's character class set and the plurality of items.
Specifically, all items of the character class set may be constructed according to all items of the attribute information set of the user constructed as described above and the user character class set acquired in step S101. For example: for the enterprise learning platform, one element, namely the role class C, can be selected from the role class set m -an operation post; the items of the attribute category constructed above can be combined with the character category C m Respectively correspond to and construct role class C m For example: role class C m And attribute category B n Item Y of (2) 1 The constructed item set is { operation and maintenance post, learning period-am }, character class C m And attribute category B n Item Y of (2) 2 The constructed item set is { fortune and maintenance post, learning period-afternoon }. Specifically, according to the above method, a set of items of all elements in the character class set, namely, the character class, can be constructed.
Wherein the confidence of the plurality of item sets may be calculated from the transaction set and the plurality of item sets.
Specifically, the confidence c of each item set, that is, the item set corresponding to the item of the attribute category for each role category, may be calculated according to the transaction set and all item sets of the role category set constructed in the above process. For example: role class C m And attribute category B n Item Y of (2) j The expression of the corresponding item set confidence c is:
specifically, c=p (Y j |C m ) For role class C m And attribute category B n Item Y of (2) j The confidence of the corresponding item set indicates that the transaction set T contains sub-attribute information Y j The transaction also contains rolesClass C m S=p (C m ∪Y j ) For role class C m And attribute category B n Item Y of (2) j Corresponding support degree, representing sub-attribute information Y j And character class C m The percentage of both in the transaction set T, P (C m ) Representing character class C m Percentage in transaction set T.
Specifically, all item set confidence levels of all character categories corresponding to the items of all attribute categories may be calculated according to the above method.
Wherein the second set of attribute elements of the user role related attribute information set may be extracted from the user's attribute information set based on the confidence levels of the plurality of item sets.
Specifically, the second attribute element group of the user character-related attribute information set may be extracted from the attribute information set of the user according to the above-calculated all item set confidence degrees that all character categories correspond to the items of all attribute categories.
Specifically, the confidence thresholds for multiple sets of items may be set according to the user's set of attributes.
Specifically, all item sets of the role class set can be constructed according to the above process, and the item set confidence threshold c corresponding to each attribute class can be set 0 . For example: attribute category B n Corresponding item set confidence threshold c 0 The expression of (2) is:
specifically, J is attribute type B n For example: when attribute class B n -j=4 when the learning period of the user is 4, oc is an adjustment coefficient, and can be adjusted according to the platform requirement, oc is less than or equal to J, for example: when ≡ = 3, this indicates an average probability that the confidence level needs to be tripled.
Specifically, when the confidence coefficient of the item set is greater than the confidence coefficient threshold value of the item set corresponding to the confidence coefficient of the item set, setting the attribute information category corresponding to the confidence coefficient of the item set in the user attribute set as the second attribute element of the user role related attribute information set.
Specifically, the item set confidence threshold c corresponding to the attribute category can be calculated according to 0 And judging whether a strong association relationship exists between the character category and the attribute category, namely whether the element of the attribute set of the user can be set as the second attribute element of the character related attribute information set of the user or not. Wherein, the item set confidence coefficient c corresponding to any item of the post category and the attribute category is larger than the item set confidence coefficient threshold c corresponding to the attribute category 0 A strong association may be considered between the role category and the attribute category, i.e. the element of the user attribute set, may be set to the second attribute element value of the user's role-related attribute information set. For example: judging character class C m And attribute category B n Whether there is strong association relation between them, can compare role class C m And attribute category B n Item Y of (2) j Confidence level c of corresponding item set, and attribute category B n Corresponding item set confidence threshold c 0 The relation between the two is that for j=1, 2, …, J, if any set confidence is greater than the threshold, i.e. P (Y j |C m )>c 0 Consider the role class C m And attribute category B n There is a strong association between them. Then attribute class B n As a second attribute element of the user's role-related attribute information set a.
Specifically, the second attribute elements of all the user role related attribute information sets may be combined to form the second attribute element group of the user role related attribute information set.
Step S203, the first attribute element group and the second attribute element group are combined to generate a user role related attribute information set.
Specifically, the first attribute element group configured in step S201 and the second attribute element group configured in step S202 may be combined to generate the character-related attribute information set a of the user.
According to the method, the device and the system for generating the attribute information set, the attribute related to the user role category information is extracted from the attribute information set of the user, the first attribute element group of the attribute information set related to the user role is directly extracted from the attribute information set of the user, the natural attribute information and the history learning information of a plurality of users are obtained, the second attribute element group of the attribute information set related to the user role is extracted from the attribute information set of the user according to the natural attribute information of the plurality of users, the history learning information of the plurality of users, the attribute set of the user and the role category set of the user, the first attribute element group and the second attribute element group are combined, the confirmation of each element in the first attribute element group and the second attribute element group is carried out in different modes, and the accuracy of the attribute information set related to the role of the user is improved.
Fig. 3 is a schematic flow chart of determining character class information of a target user according to attribute information of the target user, a character class set of the user, and a user character related attribute information set according to a third embodiment of the present application. On the basis of the embodiment shown in fig. 1, the present embodiment describes a process of determining character class information of a target user by a bayesian classification method according to attribute information of the target user, a character class set of the user, and a user character related attribute information set.
As shown in fig. 3, determining the role category information of the target user according to the attribute information of the target user, the role category set of the user, and the user role related attribute information set by bayesian classification according to the present embodiment may include the following steps:
step S301, determining a role related attribute information tuple of the target user according to the user role related attribute information set and the attribute information of the target user.
Specifically, the role-related attribute information tuple X of the target user may be confirmed according to the role-related attribute information set a of the user confirmed in step S102 and the attribute information of the target user acquired in step S104.
The role related attribute information tuple X of the target user refers to a set formed by natural attribute information of the target user corresponding to the role related attribute information set a of the user. Specifically, the natural attribute information of the target user may be filtered according to the elements of the character-related attribute information set a of the user. For example: when the element of the role related attribute information set a of the user confirmed in step S103 includes the element of the department where the user is located, the department information of the user where the user is located of the target user may be selected from the natural attribute information of the target user obtained in step S104, and may be used as the element of the role related attribute information tuple X of the target user.
Optionally, the natural attribute information of the target user may have incomplete filling or/and selection, so that the number of elements is less than the number of elements of the character-related attribute information set of the user according to the selected natural attribute information of the target user and the character-related attribute information tuple of the target user determined by the character-related attribute information set of the user, where the number of elements does not affect the determination of the character class information of the target user.
Step S302, according to the role class set of the user and the role related attribute information tuple of the target user, the role class of the target user is analyzed through a Bayesian classification method, and the role class information of the target user is determined.
Specifically, the role category information of the target user may be determined by analyzing the role category of the target user through a bayesian classification method according to the role category set C determined in step S101 and the role related attribute information tuple X of the target user determined in step S301.
The Bayesian classification algorithm is a classification method of statistics, and is an algorithm for classifying by using probability statistical knowledge. In many occasions, the Bayesian classification algorithm can be compared with decision trees and neural network classification algorithms, and the Bayesian classification algorithm can be applied to a large database, and has the advantages of simple method, high classification accuracy and high speed. Bayesian classification can predict the probability of class membership, such as the probability that a given tuple belongs to a particular class.
Specifically, the probability that the role related attribute information tuple X of the target user belongs to different user role categories, that is, the probability that the role related attribute information tuple X of the target user corresponds to each user role category in the role category set, may be calculated according to the bayesian classification algorithm, and the position of the target user is confirmed according to the probability value of each user role category.
Specifically, the posterior probability of each role category can be calculated by a bayesian classification method according to the role category set of the user and the role related attribute information tuple of the target user.
Specifically, the posterior probability of each user role, that is, the probability that the role related attribute information tuple X of the target user belongs to different user role categories may be calculated by the bayesian classification method described in step S301 according to the role class set C determined in step S101 and the target user role related attribute information tuple X determined in step S301.
For example: for a certain target user, the role-related attribute information tuple X of the target user can be determined according to step S301 i ，X i ＝{x 1 ,x 2 ,…,x N I=1, 2, …, N. Wherein, user role class C m Posterior probability of (a), i.e. character-related attribute information tuple X of target user i Belonging to user role class C m The probability of (a) is expressed as:
specifically, P (C m |X i ) The value of (c) may be calculated from the data set D constructed from the transaction set T described in step S202. Wherein P (X) i ) Constant for all user role categories; p (C) m )＝|C m,D I/I D I, wherein I C m,D I is C in D m The training tuple number of the class, |D| is the training tuple number of D;
wherein the user's role-related attribute information set A generally has a plurality of attributes, namely the target user's role-related attribute information tuple X i Is typically of multiple elements, so P (X i |C m ) Is very costly. To reduce the computation P (X i |C m ) Can assume that there is no dependency between attributes, the attribute values are conditionally independent of each other, i.e. P (X i |C m ) The expression of (2) is:
wherein x is n Representing tuple Xi at attribute A n Is a value of (2). P (x) n |C m ) Is attribute A in D n Has a value of x n C of (2) m Tuple number of class divided by C in D m Tuple number of class |C m,D |。
Specifically, the posterior probability of each user role category information of the target user, namely the role related attribute information tuple X of the target user, can be calculated according to the algorithm i Probabilities of belonging to different user role categories.
Specifically, the character class information of the target user may be determined according to the posterior probability of each character class.
Specifically, the posterior probability of each user role category information of the target user, that is, the probability that the role related attribute information tuple X of the target user belongs to different user role categories, which is obtained by calculation is compared, wherein the user role category information corresponding to the maximum posterior probability is the role category information of the target user.
According to the attribute information of the target user, the role class set of the user and the attribute information set related to the role of the user, the role related attribute information tuple of the target user is determined according to the role related attribute information set of the user and the attribute information of the target user, the role class of the target user is analyzed according to the role class set of the user and the role related attribute information tuple of the target user through a Bayesian classification method, and the role class information of the target user is determined, wherein the posterior probability of each user post is calculated through the Bayesian classification method, so that the accuracy and the efficiency of post determination of the target user are improved.
Fig. 4 is a schematic structural diagram of a course recommendation device of an online learning platform according to a fourth embodiment of the present application.
As shown in fig. 4, the course recommendation device 40 of the online learning platform of the present embodiment includes an acquisition module 41, a generation module 42, and a recommendation module 43.
The obtaining module 41 is configured to obtain, from the online learning platform database, a set of attribute information of a user and a set of role categories, where the set of attribute information of the user includes a plurality of attribute information categories, the attribute information categories include a plurality of sub-attribute information, and the set of role categories of the user includes a plurality of role category information. The attribute information includes: and removing natural attribute information and history learning information of the character class information.
A generating module 42, configured to extract attributes related to the user role category information from the attribute information set of the user, and generate a role related attribute information set of the user.
The recommendation module 43 is configured to obtain character class information of a target user when the character class information of the target user is not missing, screen candidate course data from the online learning platform database according to the character class information of the target user, recommend the candidate course data to the target user, obtain attribute information of the target user when the character class of the target user is missing, determine the character class information of the target user according to the attribute information of the target user, the character class set of the user and the user character related attribute information set through a bayesian classification method, screen candidate course data from the online learning platform database according to the character class information of the target user, and recommend the candidate course data to the target user.
Optionally, the recommendation module 43 includes: the first recommending unit and the second recommending unit.
The first recommending unit 413 is configured to obtain role category information of the target user when the role category information of the target user is not missing, screen candidate course data from the online learning platform database according to the role category information of the target user, and recommend the candidate course data to the target user.
The second recommending unit 423 is configured to obtain attribute information of the target user when the role category of the target user is missing, determine the role category information of the target user according to the attribute information of the target user, the role category set of the user, and the related attribute information set of the user role by using a bayesian classification method, screen candidate course data from the online learning platform database according to the role category information of the target user, and recommend the candidate course data to the target user. Fig. 5 is a schematic structural diagram of another course recommendation device of an online learning platform according to an embodiment of the present application.
The apparatus provided in this embodiment may be used to execute the technical solutions of fig. 1 to 3 in the above method embodiment, and its implementation principle and technical effects are similar, and this embodiment is not repeated here.
Fig. 6 is a schematic structural diagram of a course recommendation device of an online learning platform according to a fifth embodiment of the present application.
As shown in fig. 6, the course recommendation device 60 of the online learning platform of the present embodiment includes: processor 61, memory 62, communication interface 63.
The memory 62 is used to store executable instructions of the processor;
wherein processor 61 is configured to perform the course recommendation method of the online learning platform of any one of fig. 1-3 of the above-described method embodiments via execution of executable instructions.
Embodiments of the present application also provide a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements a course recommendation method for executing the online learning platform of any one of fig. 1 to 3 of the above-described method embodiments.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (10)

1. The course recommendation method of the online learning platform is characterized by comprising the following steps of:
acquiring a user attribute information set and a role class set from an online learning platform database, wherein the user attribute information set comprises a plurality of attribute information classes, the user role class set comprises a plurality of role class information, and the attribute information comprises: removing natural attribute information and history learning information of the character class information;
Extracting attributes related to user role category information from the attribute information set of the user, and generating a role related attribute information set of the user;
when the role category information of the target user is not lost, acquiring the role category information of the target user, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user;
when the role category of the target user is missing, acquiring attribute information of the target user, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, the role category set of the user and the related attribute information set of the user role, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
2. The method of claim 1, wherein extracting attributes associated with user role category information from the set of attribute information for the user, generating a set of user role related attribute information, comprises:
Directly extracting a first attribute element group of a user role related attribute information set from the attribute information set of the user;
acquiring natural attribute information and history learning information of a plurality of users, and extracting a second attribute element group of the user role-related attribute information set from the attribute information set of the users according to the natural attribute information of the plurality of users, the history learning information of the plurality of users, the attribute set of the users and the role class set of the users;
and merging the first attribute element group and the second attribute element group to generate the user role related attribute information set.
3. The method according to claim 2, wherein the attribute information category includes a plurality of sub-attribute information, and the extracting the second attribute element group of the user role-related attribute information set from the attribute information set of the user according to the natural attribute information of the plurality of users, the history learning information of the plurality of users, the attribute set of the user, and the role class set of the user includes:
constructing a transaction set according to the natural attribute information of the plurality of users and the history learning information of the plurality of users, wherein the transaction set is a set of all information of the plurality of users;
Constructing a plurality of items according to the attribute set of the user, wherein different items are used for marking different sub-attribute information under the same attribute information category;
constructing a plurality of item sets according to the role class set of the user and a plurality of items;
calculating confidence degrees of a plurality of item sets according to the transaction set and the item sets;
and extracting a second attribute element group of the user role related attribute information set from the attribute information set of the user according to the confidence degrees of the item sets.
4. A method according to claim 3, wherein said extracting a second set of attribute elements of said set of user role related attribute information from said set of user attribute information based on confidence levels of a plurality of said sets of items comprises:
setting confidence thresholds of a plurality of item sets according to the attribute information sets of the users;
when the confidence coefficient of the item set is larger than the confidence coefficient threshold value of the item set corresponding to the confidence coefficient of the item set, setting the attribute information category corresponding to the confidence coefficient of the item set in the user attribute set as a second attribute element of the user role related attribute information set;
and merging all the second attribute elements of the user role related attribute information set to form a second attribute element group of the user role related attribute information set.
5. The method according to claim 1, wherein said determining the role category information of the target user by bayesian classification based on the attribute information of the target user, the role category set of the user, and the user role related attribute information set, comprises:
determining a role related attribute information tuple of the target user according to the user role related attribute information set and the attribute information of the target user;
and analyzing the role category of the target user through a Bayesian classification method according to the role category set of the user and the role related attribute information tuple of the target user, and determining the role category information of the target user.
6. The method of claim 5, wherein the determining the role category information of the target user by analyzing the role category of the target user through a bayesian classification method according to the role category set of the user and the role related attribute information tuple of the target user comprises:
calculating posterior probability of each role category by a Bayesian classification method according to the role category set of the user and the role related attribute information tuple of the target user;
And determining the character category information of the target user according to the posterior probability of each character category.
7. A course recommendation device for an online learning platform, comprising:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a user attribute information set and a role class set from an online learning platform database, the user attribute information set comprises a plurality of attribute information classes, the user role class set comprises a plurality of role class information, and the attribute information comprises: removing natural attribute information and history learning information of the character class information;
the generation module is used for extracting attributes related to the user role category information from the attribute information set of the user and generating a role related attribute information set of the user;
and the recommendation module is used for acquiring the role category information of the target user when the role category information of the target user is not lost, screening candidate course data from the online learning platform database according to the role category information of the target user, recommending the candidate course data to the target user, acquiring the attribute information of the target user when the role category of the target user is lost, determining the role category information of the target user according to the attribute information of the target user, the role category set of the user and the related attribute information set of the user role by a Bayesian classification method, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
8. The apparatus of claim 7, wherein the recommendation module comprises:
the first recommendation unit is used for acquiring the role category information of the target user when the role category information of the target user is not lost, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user;
and the second recommendation unit is used for acquiring attribute information of the target user when the role category of the target user is missing, determining the role category information of the target user through a Bayesian classification method according to the attribute information of the target user, the role category set of the user and the related attribute information set of the user role, screening candidate course data from the online learning platform database according to the role category information of the target user, and recommending the candidate course data to the target user.
9. A course recommendation device for an online learning platform, comprising:
a processor, a memory, a communication interface;
the memory is used for storing executable instructions of the processor;
Wherein the processor is configured to perform the course recommendation method of the online learning platform of any one of claims 1 to 6 via execution of the executable instructions.
10. A readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements a course recommendation method of executing the online learning platform of any one of claims 1 to 6.
CN202310621273.7A 2023-05-29 2023-05-29 Course recommendation method, device, equipment and storage medium of online learning platform Pending CN116644233A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310621273.7A CN116644233A (en) 2023-05-29 2023-05-29 Course recommendation method, device, equipment and storage medium of online learning platform

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310621273.7A CN116644233A (en) 2023-05-29 2023-05-29 Course recommendation method, device, equipment and storage medium of online learning platform

Publications (1)

Publication Number Publication Date
CN116644233A true CN116644233A (en) 2023-08-25

Family

ID=87622542

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310621273.7A Pending CN116644233A (en) 2023-05-29 2023-05-29 Course recommendation method, device, equipment and storage medium of online learning platform

Country Status (1)

Country Link
CN (1) CN116644233A (en)

Similar Documents

Publication Publication Date Title
US9721221B2 (en) Skill estimation method in machine-human hybrid crowdsourcing
CN112199608B (en) Social media rumor detection method based on network information propagation graph modeling
US11562262B2 (en) Model variable candidate generation device and method
CN109635010B (en) User characteristic and characteristic factor extraction and query method and system
CN110287292B (en) Judgment criminal measuring deviation degree prediction method and device
CN110866832A (en) Risk control method, system, storage medium and computing device
CN113256383B (en) Recommendation method and device for insurance products, electronic equipment and storage medium
CN110634060A (en) User credit risk assessment method, system, device and storage medium
CN112529750A (en) Learning event recommendation method and system based on graph neural network model
CN111062486A (en) Method and device for evaluating feature distribution and confidence coefficient of data
CN112836750A (en) System resource allocation method, device and equipment
CN112365007A (en) Model parameter determination method, device, equipment and storage medium
CN117271905B (en) Crowd image-based lateral demand analysis method and system
CN111259167A (en) User request risk identification method and device
CN114493686A (en) Operation content generation and pushing method and device
US11551317B2 (en) Property valuation model and visualization
CN117540336A (en) Time sequence prediction method and device and electronic equipment
CN111221915B (en) Online learning resource quality analysis method based on CWK-means
CN117093849A (en) Digital matrix feature analysis method based on automatic generation model
CN116644233A (en) Course recommendation method, device, equipment and storage medium of online learning platform
CN112463964B (en) Text classification and model training method, device, equipment and storage medium
CN113627997A (en) Data processing method and device, electronic equipment and storage medium
CN114186646A (en) Block chain abnormal transaction identification method and device, storage medium and electronic equipment
CN113689114A (en) Method, device and equipment for determining credit degree
CN115033763B (en) Big data based storage method and system thereof

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