Intelligent curriculum recommendation method based on implicit vector space

Abstract

The invention discloses an intelligent curriculum recommendation method based on implicit vector space, and relates to an artificial intelligence technology. Comprising the steps of 1, carrying out data collection and preprocessing, 2, constructing implicit vectors of users and courses, 3, calculating similarity and generating recommendation information: establishing a recommendation model, calculating the similarity or correlation between the users and the courses based on the implicit vectors by utilizing the recommendation model, carrying out sorting according to the similarity, generating a personalized course recommendation list for the users, and carrying out recommendation on the courses according to the personalized course recommendation list. And 4, optimization and feedback circulation: continuously optimizing the recommendation model through a machine learning algorithm, establishing a user feedback mechanism, and collecting satisfaction evaluation of a user on a recommendation result for improving the recommendation model.

Description

Technical Field

[0001] The invention discloses a course intelligent recommendation method based on latent vector space, which relates to artificial intelligence technology. Background Art

[0002] With the rapid development of the online education industry, users are faced with an increasingly rich range of course resources. How to effectively match user interests and needs and provide personalized course recommendations has become the key to improving user experience and learning outcomes. Existing recommendation methods have problems such as high computational complexity and difficulty in capturing user potential interests when processing large-scale data. Summary of the invention

[0003] In view of the problems in the prior art, the present invention provides an intelligent course recommendation method based on latent vector space, which efficiently represents user and course features through low-dimensional latent vectors to achieve accurate recommendation.

[0004] The specific scheme proposed by the present invention is:

[0005] The present invention provides a course intelligent recommendation method based on latent vector space, comprising:

[0006] Step 1: Data collection and preprocessing: Collect user behavior data and basic course information on the platform, clean, denoise and standardize the collected data.

[0007] Step 2: Construct user and course latent vectors: Use matrix decomposition or deep learning methods to form user and course interaction data based on the processed data, and map the interaction data into a low-dimensional latent vector space.

[0008] Each user and each course is represented by a point in a high-dimensional space. The point in the high-dimensional space is a latent vector. The latent vector captures the potential characteristics of users and courses.

[0009] Step 3: Calculate similarity and generate recommendation information: Use graph neural network to build a recommendation model, use the recommendation model to calculate the similarity or correlation between users and courses based on latent vectors, sort by similarity, and generate a personalized course recommendation list for users.

[0010] Step 4: Optimization and feedback loop: Continuously optimize the recommendation model through machine learning algorithms. At the same time, establish a user feedback mechanism to collect user satisfaction evaluations on recommendation results for improving the recommendation model.

[0011] Furthermore, in step 1 of the method for intelligent course recommendation based on latent vector space, the user's behavior data on the platform and basic information of the course are collected. The behavior data includes browsing history, click behavior, learning time, and course evaluation; the basic information of the course includes title, description, tag, and category.

[0012] Furthermore, in step 3 of the method for intelligent course recommendation based on latent vector space, the recommendation model is used to calculate the similarity or correlation between the user and the course based on the latent vector by using the cosine similarity calculation method or the Euclidean distance measurement method.

[0013] Furthermore, in step 4 of the method for intelligent course recommendation based on latent vector space, the recommendation results are evaluated according to the actual behavior of the user after obtaining the course recommendation list, and the recommendation model is continuously optimized through a machine learning algorithm based on the evaluation results.

[0014] The present invention also provides a course intelligent recommendation device based on latent vector space, including a collection and preprocessing module, a latent vector management module, an analysis and calculation module and a feedback optimization module.

[0015] The collection and preprocessing module performs data collection and preprocessing: collects user behavior data on the platform and basic information about courses, and cleans, denoises, and standardizes the collected data.

[0016] The latent vector management module constructs the latent vectors of users and courses: it uses matrix decomposition or deep learning methods to form the interaction data between users and courses based on the processed data, and maps the interaction data into a low-dimensional latent vector space.

[0017] Each user and each course is represented by a point in a high-dimensional space. The point in the high-dimensional space is a latent vector. The latent vector captures the potential characteristics of users and courses.

[0018] The analysis and calculation module calculates similarity and generates recommendation information: a recommendation model is established using graph neural networks, and the recommendation model is used to calculate the similarity or correlation between users and courses based on latent vectors, and sorts them according to similarity to generate a personalized course recommendation list for users.

[0019] The feedback optimization module performs optimization and feedback loops: the recommendation model is continuously optimized through machine learning algorithms. At the same time, a user feedback mechanism is established to collect user satisfaction evaluations on recommendation results for improving the recommendation model.

[0020] Furthermore, the collection and preprocessing module of the course intelligent recommendation device based on latent vector space collects user behavior data and basic information of courses on the platform. The behavior data includes browsing history, click behavior, learning time, and course evaluation; the basic information of courses includes title, description, tag, and category.

[0021] Furthermore, the analysis and calculation module of the course intelligent recommendation device based on latent vector space uses the recommendation model to adopt the cosine similarity calculation method or the Euclidean distance measurement method to calculate the similarity or correlation between the user and the course based on the latent vector.

[0022] Furthermore, the feedback optimization module of the course intelligent recommendation device based on latent vector space evaluates the recommendation results according to the actual behavior of the user after obtaining the course recommendation list, and continuously optimizes the recommendation model through a machine learning algorithm according to the evaluation results.

[0023] The benefits of the present invention are:

[0024] By capturing the potential characteristics of users and courses through latent vector space technology, more accurate personalized recommendations can be achieved; reducing users' search time in massive course resources, improving learning efficiency and satisfaction; and enhancing user stickiness and market competitiveness of online education platforms by providing personalized course recommendation services. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic flow chart of the method of the present invention.

[0026] Figure 2 It is a schematic diagram of the application framework of the device of the present invention. DETAILED DESCRIPTION

[0027] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0028] Example 1

[0029] The present invention provides a course intelligent recommendation method based on latent vector space, comprising:

[0030] Step 1: Data collection and preprocessing: Collect user behavior data and basic course information on the platform, and clean, denoise and standardize the collected data. The behavior data and basic course information on the platform are collected. The behavior data may include browsing history, click behavior, learning time, course evaluation, etc.; the basic course information may include title, description, tag, category, etc.

[0031] Step 2: Construct user and course latent vectors: Use matrix decomposition or deep learning methods to form user and course interaction data based on the processed data, and map the interaction data into a low-dimensional latent vector space.

[0032] Each user and each course is represented by a point in a high-dimensional space. The point in the high-dimensional space is a latent vector. The latent vector captures the potential characteristics of users and courses.

[0033] Step 3: Calculate similarity and generate recommendation information: Establish a recommendation model, use the recommendation model to calculate the similarity or correlation between the user and the course based on the latent vector, sort by similarity, and generate a personalized course recommendation list for the user. The recommendation model uses the cosine similarity calculation method or the Euclidean distance measurement method to calculate the similarity or correlation between the user and the course based on the latent vector.

[0034] Step 4: Optimization and feedback loop: Continuously optimize the recommendation model through machine learning algorithms. At the same time, establish a user feedback mechanism to collect user satisfaction evaluations on recommendation results for improving the recommendation model.

[0035] The recommendation results are evaluated based on the actual behavior of users after obtaining the course recommendation list, and the recommendation model is continuously optimized through machine learning algorithms based on the evaluation results.

[0036] Example 2

[0037] The present invention also provides a course intelligent recommendation device based on latent vector space, including a collection and preprocessing module, a latent vector management module, an analysis and calculation module and a feedback optimization module.

[0038] The collection and preprocessing module performs data collection and preprocessing: collects user behavior data on the platform and basic information about courses, and cleans, denoises, and standardizes the collected data.

[0039] The latent vector management module constructs the latent vectors of users and courses: it uses matrix decomposition or deep learning methods to form the interaction data between users and courses based on the processed data, and maps the interaction data into a low-dimensional latent vector space.

[0040] Each user and each course is represented by a point in a high-dimensional space. The point in the high-dimensional space is a latent vector. The latent vector captures the potential characteristics of users and courses.

[0041] The analysis and calculation module calculates similarity and generates recommendation information: establishes a recommendation model, uses the recommendation model to calculate the similarity or correlation between users and courses based on latent vectors, sorts them according to similarity, and generates a personalized course recommendation list for users.

[0042] The feedback optimization module performs optimization and feedback loops: the recommendation model is continuously optimized through machine learning algorithms. At the same time, a user feedback mechanism is established to collect user satisfaction evaluations on recommendation results for improving the recommendation model.

[0043] As the information interaction and execution process between the modules of the above-mentioned device are based on the same concept as the embodiment of the method of the present invention, the specific contents can be found in the description of the embodiment of the method of the present invention and will not be repeated here.

[0044] Similarly, the device of the present invention captures the potential characteristics of users and courses through latent vector space technology to achieve more accurate personalized recommendations; reduces the user's search time in massive course resources, improves learning efficiency and satisfaction; and enhances the user stickiness and market competitiveness of the online education platform by providing personalized course recommendation services.

[0045] It should be noted that not all steps and modules in the above-mentioned processes and device structures are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.

[0046] The above-described embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art based on the present invention are within the protection scope of the present invention. The protection scope of the present invention shall be subject to the claims.

Claims

1. The intelligent course recommendation method based on latent vector space is characterized by include: Step 1: Data collection and preprocessing: Collect user behavior data and basic course information on the platform, clean, denoise and standardize the collected data. Step 2: Construct user and course latent vectors: Use matrix decomposition or deep learning methods to form user and course interaction data based on the processed data, and map the interaction data into a low-dimensional latent vector space. Each user and each course is represented by a point in a high-dimensional space. The point in the high-dimensional space is a latent vector. The latent vector captures the potential characteristics of users and courses. Step 3: Calculate similarity and generate recommendation information: Use graph neural network to build a recommendation model, use the recommendation model to calculate the similarity or correlation between users and courses based on latent vectors, sort by similarity, and generate a personalized course recommendation list for users. Step 4: Optimization and feedback loop: Continuously optimize the recommendation model through machine learning algorithms. At the same time, establish a user feedback mechanism to collect user satisfaction evaluations on recommendation results for improving the recommendation model.

2. The course intelligent recommendation method based on latent vector space according to claim 1 is characterized by: In step 1, the user's behavior data on the platform and basic information of the course are collected. The behavior data includes browsing history, click behavior, learning time, and course evaluation; the basic information of the course includes title, description, tag, and category.

3. The course intelligent recommendation method based on latent vector space according to claim 1 is characterized by: In step 3, the recommendation model is used to calculate the similarity or correlation between the user and the course based on the latent vector using the cosine similarity calculation method or the Euclidean distance measurement method.

4. The course intelligent recommendation method based on latent vector space according to claim 1 is characterized by: In step 4, the recommendation results are evaluated based on the actual behavior of the user after obtaining the course recommendation list, and the recommendation model is continuously optimized through the machine learning algorithm based on the evaluation results.

5. The course intelligent recommendation device based on latent vector space is characterized by It includes collection and preprocessing module, latent vector management module, analysis and calculation module and feedback optimization module. The collection and preprocessing module performs data collection and preprocessing: collects user behavior data on the platform and basic information about courses, and cleans, denoises, and standardizes the collected data. The latent vector management module constructs the latent vectors of users and courses: it uses matrix decomposition or deep learning methods to form the interaction data between users and courses based on the processed data, and maps the interaction data into a low-dimensional latent vector space. Each user and each course is represented by a point in a high-dimensional space. The point in the high-dimensional space is a latent vector. The latent vector captures the potential characteristics of users and courses. The analysis and calculation module calculates similarity and generates recommendation information: a recommendation model is established using graph neural networks, and the recommendation model is used to calculate the similarity or correlation between users and courses based on latent vectors, and sorts them according to similarity to generate a personalized course recommendation list for users. The feedback optimization module performs optimization and feedback loops: the recommendation model is continuously optimized through machine learning algorithms. At the same time, a user feedback mechanism is established to collect user satisfaction evaluations on recommendation results for improving the recommendation model.

6. The course intelligent recommendation device based on latent vector space according to claim 5 is characterized by: The collection and preprocessing module collects users' behavioral data on the platform and basic information about courses. The behavioral data includes browsing history, click behavior, learning time, and course evaluation; the basic information about courses includes title, description, tag, and category.

7. The course intelligent recommendation device based on latent vector space according to claim 5 is characterized by: The analysis and calculation module uses the recommendation model to adopt the cosine similarity calculation method or the Euclidean distance measurement method to calculate the similarity or correlation between users and courses based on latent vectors.

8. The course intelligent recommendation device based on latent vector space according to claim 5 is characterized by: The feedback optimization module evaluates the recommendation results based on the actual behavior of users after obtaining the course recommendation list, and continuously optimizes the recommendation model through machine learning algorithms based on the evaluation results.

Images