CN116257694B - Intelligent search recommendation method and system based on online learning courses - Google Patents
Intelligent search recommendation method and system based on online learning courses Download PDFInfo
- Publication number
- CN116257694B CN116257694B CN202310551179.9A CN202310551179A CN116257694B CN 116257694 B CN116257694 B CN 116257694B CN 202310551179 A CN202310551179 A CN 202310551179A CN 116257694 B CN116257694 B CN 116257694B
- Authority
- CN
- China
- Prior art keywords
- user
- learning
- recommendation
- search
- course
- 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.)
- Active
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
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- 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
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the technical field of computers, in particular to an intelligent search recommendation method and system based on online learning courses. The method comprises the steps of collecting learning browsing data of a user, preprocessing and generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in a loaded course catalog; acquiring an online learning course log of a current stage of a user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching; obtaining search results in response to the search instruction; dividing recommendation levels for the obtained search results according to the keywords in the search instruction and the feature vectors of the courses, and recommending to a user side for display according to recommendation priorities of the recommendation levels. According to the method and the device, the learning model is continuously optimized according to feedback of the user, and the recommendation effect is improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to an intelligent search recommendation method and system based on online learning courses.
Background
With the continuous development and popularization of internet technology, more and more people select online learning courses to promote their skills and knowledge level. The online learning platform provides rich course resources, but also has the problems of uneven course quality, repeated course content and the like, and brings certain trouble to students' learning. Therefore, how to quickly and accurately find out high-quality courses meeting the demands of students becomes an important problem for students.
Traditional search engines can only search according to keyword matching, and personalized recommendation can not be performed according to learning requirements and interests of users. The recommendation system based on machine learning can conduct personalized recommendation on the user according to the historical behavior and the interest characteristics of the user, and user satisfaction and learning effects are improved. Therefore, the intelligent search recommendation method and system based on the online learning course have important research and application values.
Disclosure of Invention
The application provides an intelligent search recommendation method and system based on online learning courses, aiming at solving the problem of recommending courses by the existing online learning platform and improving the learning effect and satisfaction of users.
In order to achieve the above object, the embodiment of the present application provides the following technical solutions:
in a first aspect, in one embodiment provided by the present application, an intelligent search recommendation method based on online learning courses is provided, including the following steps:
collecting learning browsing data of a user, preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in a loaded course catalog;
acquiring an online learning course log of a current stage of a user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching;
responding to a search instruction to obtain a search result, wherein the search instruction at least comprises a search term input by a user, and a paragraph or chapter content is selected;
dividing recommendation levels for the obtained search results according to the keywords in the search instruction and the feature vectors of the courses, and recommending to a user side for display according to recommendation priorities of the recommendation levels.
As a further scheme of the application, collecting learning browsing data of the user comprises collecting learning history data and learning behavior data of the user, wherein the learning history data and the learning behavior data comprise learning targets, learning time, learning courses, learning progress and evaluation information of the user.
As a further scheme of the application, classifying and labeling the current online learning course based on a learning model of a user, and establishing a feature vector of the online learning course based on chapter matching, comprising the following steps:
classifying online learning courses in the online learning platform according to the subject field, the difficulty level and the course type of the online learning courses;
labeling the online learning courses in the online learning platform, and labeling according to the topics, the contents and the knowledge points of the online learning courses;
according to the classification and the label of the online learning course, establishing a characteristic vector of the online learning course based on chapter matching, converting the classification and the label of the online learning course into a vector form, and establishing a course characteristic vector.
As a further scheme of the application, the intelligent search recommendation method based on the online learning course further comprises the steps of establishing a recommendation model between a user and the online learning course based on a learning model of the user and a feature vector of the online learning course, and comprises the following steps:
constructing a training data set based on a learning model of a user and feature vectors of an online learning course;
establishing a recommendation model between a user and an online learning course, training and optimizing the model through the constructed training data set,
and updating the recommendation model in real time according to the search behavior and the history record of the user.
As a further scheme of the application, the method further comprises the steps of carrying out chapter information matching according to the loaded course catalog according to the online learning course log of the registered user, and constructing a similarity matrix of the chapter information;
according to the online learning course log of the current user, performing user similarity matrix screening on the current online learning course, and screening out log results with previous similarity sequences from high to low as reference results;
and according to the query information of the user and the context information corresponding to the query information, a personalized recommendation result is given.
As a further aspect of the present application, when obtaining a search result in response to a search instruction, analyzing and processing the search instruction of the user includes the steps of:
word segmentation and key information extraction are carried out on the search instruction so as to obtain the search intention of the user;
obtaining a matched course feature vector according to the search intention and the learning model of the user;
calculating a recommendation score for each course based on a recommendation model between the user and the online learning course;
and sequencing online learning courses according to the recommendation scores, returning to a most relevant course list of the user, and updating and optimizing a recommendation model according to feedback and behavior data of the user.
As a further aspect of the present application, a search recommendation is generated based on a user's search instruction and a recommendation model in response to a search instruction, wherein the method comprises the steps of:
extracting keywords from a search instruction of a user, performing semantic analysis, extracting the keywords from the search instruction, and performing semantic analysis on the search instruction by taking the keywords as input of a recommendation model;
generating a candidate course list based on a search instruction and a recommendation model of a user, and scoring and sorting candidate courses through the recommendation model to obtain personalized search recommendation results;
and presenting the recommendation result to the user, displaying and feeding back the search recommendation result, and continuously optimizing the recommendation model and the search recommendation result according to the feedback and the behavior of the user.
In a second aspect, in another embodiment provided by the present application, an intelligent search recommendation system based on online learning courses is provided, where the system includes a data acquisition module, a data processing module, a feature extraction module, a search recommendation module, and a user interface module.
The data acquisition module is used for acquiring learning browsing data of a user;
the data processing module is used for preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in the loaded course catalog;
the feature extraction module is used for acquiring an online learning course log of the current stage of the user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching;
the search recommendation module is used for responding to the search instruction to obtain search results, dividing recommendation levels for the obtained search results according to keywords in the search instruction and feature vectors of courses, and recommending according to recommendation priorities of the recommendation levels;
and the user interface module is used for displaying the recommendation result and collecting feedback of the user.
As a further scheme of the application, the intelligent search recommendation system based on the online learning course comprises the following modules:
and the optimization module is used for optimizing the learning model according to the feedback of the user.
As a further scheme of the application, the intelligent search recommendation system based on the online learning course comprises the following modules:
the recommendation model building module is used for building a recommendation model between the user and the online learning course based on the learning model of the user and the feature vector of the online learning course, and updating the recommendation model in real time according to the search behavior and the history record of the user.
In a third aspect, in yet another embodiment provided by the present application, a computer device is provided, including a memory storing a computer program and a processor implementing steps of an intelligent search recommendation method based on online learning courses when the computer program is loaded and executed.
In a fourth aspect, in yet another embodiment provided by the present application, a storage medium is provided storing a computer program which, when loaded and executed by a processor, implements the steps of the intelligent search recommendation method based on online learning courses.
Compared with the prior art, the technical scheme provided by the application has the following beneficial effects:
according to the intelligent search recommendation method and system based on the online learning courses, the system is used for matching the keyword sequence of learning browsing data of the user with chapters in the loaded course catalog by collecting learning behavior data of the user, and then intelligent recommendation is carried out on learning resources by combining interests and hobbies of the user and learning targets. In the recommending process, the system considers factors such as difficulty, duration, type and the like of learning resources, learning history and evaluation and the like of users, so that the accuracy and individuation degree of recommendation are improved. Meanwhile, the system can continuously optimize the learning model according to feedback of the user, and improves the recommendation effect. The system has the advantages of friendly user interface, easy operation and capability of meeting the personalized requirements of users.
The application also has the following advantages:
1. the user searching efficiency is improved: the system can intelligently recommend related search results according to the search history and the learning courses of the user, so that the search efficiency of the user is improved.
2. Improving the learning effect of the user: the system can intelligently recommend related learning resources according to the learning course of the user, so that the learning effect of the user is improved.
3. User satisfaction is improved: the system can intelligently recommend related search results and learning resources according to the preference and search history of the user, so that the satisfaction degree of the user is improved.
4. The user searching cost is reduced: the system can intelligently recommend related search results and learning resources according to the search history and learning courses of the user, so that the search cost of the user is reduced.
5. Improving user viscosity of the system: the system can intelligently recommend related search results and learning resources according to the preference and search history of the user, so that the user viscosity of the system is improved.
These and other aspects of the application will be more readily apparent from the following description of the embodiments. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present application. In the drawings:
FIG. 1 is a flowchart of an intelligent search recommendation method based on online learning courses according to an embodiment of the application.
Fig. 2 is a flowchart of establishing feature vectors of an online learning course based on chapter matching in an intelligent search recommendation method based on the online learning course according to an embodiment of the present application.
FIG. 3 is a flowchart of a recommendation model established in an intelligent search recommendation method based on online learning courses according to an embodiment of the application.
Fig. 4 is a flowchart of analysis and processing profiles of search instructions in an intelligent search recommendation method based on online learning courses according to an embodiment of the present application.
FIG. 5 is a flowchart of generating personalized search recommendation results in an intelligent search recommendation method based on online learning courses according to an embodiment of the application.
FIG. 6 is a system block diagram of an intelligent search recommendation system based on online learning courses according to an embodiment of the application.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In some of the flows described in the specification and claims of the present application and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.
Technical solutions in exemplary embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in exemplary embodiments of the present application, and it is apparent that the described exemplary embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Because the traditional search engine can only search according to keyword matching, personalized recommendation can not be performed according to learning requirements and interests of users. The recommendation system based on machine learning can conduct personalized recommendation on the user according to the historical behavior and the interest characteristics of the user, and user satisfaction and learning effects are improved. Therefore, the intelligent search recommendation method and system based on the online learning course have important research and application values.
Aiming at the problems, the intelligent search recommendation method and system based on the online learning courses, provided by the application, utilize the learning history data and behavior data of the user to match the keyword sequence of the learning browsing data of the user with chapters in the loaded course catalog, and classify and label the courses of the online learning platform according to the learning model of the user. When a user performs a search operation, the method recommends courses matching the learning interests and the learning capabilities of the user according to the search keywords, the learning model and the search recommendation model of the user. Meanwhile, the method can also screen the result search result pool according to the feature vector of the current online learning course and the interactive relation between the historical online learning course and the result search result so as to improve the search recommendation accuracy.
In particular, embodiments of the present application are further described below with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of the present application provides an intelligent search recommendation method based on an online learning course, which specifically includes the following steps:
s1, acquiring learning browsing data of a user, preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in a loaded course catalog;
s2, acquiring an online learning course log of the current stage of the user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a characteristic vector of the online learning course based on chapter matching;
s3, obtaining a search result in response to a search instruction, wherein the search instruction at least comprises a search term input by a user and a paragraph or chapter content selected;
and S4, dividing a recommendation level for the obtained search result according to the keywords in the search instruction and the feature vector of the course, and recommending to a user side for display according to the recommendation priority of the recommendation level.
In this embodiment, collecting learning browsing data of the user includes collecting learning history data and learning behavior data of the user, including learning objectives, learning time, learning courses, learning progress, and evaluation information of the user. After learning browsing data of the user are collected, matching keyword sequences of the learning browsing data of the user with chapters in the loaded course catalog according to the collected data, wherein the keyword sequences comprise learning interests, learning preferences, learning capacity and the like of the user, classifying and labeling courses of an online learning platform based on a learning model of the user, establishing characteristic vectors of the courses, training the learning model of the user and the characteristic vectors of the courses by using a machine learning algorithm, and establishing a searching recommendation model. When the user performs a search operation, courses matching the user's learning interests and capabilities are recommended according to the user's search keywords, learning models, and search recommendation models. According to the application, through collecting learning behavior data of the user, the keyword sequence of the learning browsing data of the user is matched with chapters in the loaded course catalog, and then the learning resources are intelligently recommended by combining the interests and the learning targets of the user. In the recommending process, the method considers factors such as difficulty, duration, type and the like of learning resources, learning history and evaluation and the like of users, so that the accuracy and individuation degree of recommendation are improved. Meanwhile, the method can continuously optimize the learning model according to the feedback of the user, and improves the recommendation effect. The method has the advantages of friendly user interface, easy operation and capability of meeting the personalized requirements of users.
Illustratively, in the present embodiment, when learning behavior data of the user is collected, the collecting learning behavior data of the user includes, but is not limited to, the following steps:
1. personal information of the user such as name, age, gender, academy, etc.;
2. the learning history record of the user comprises learned courses, learning duration, learning progress and the like;
3. the evaluation behavior data of the user comprises scoring of courses, evaluation contents and the like;
4. search behavior data of the user, including keywords of the search, the number of times of the search, the result of the search, and the like;
5. user interaction behavior data including click, view, notes, discussions, etc.;
6. social behavior data of the user, including interests, praise, comments, and the like.
In this embodiment, the collected learning behavior data is processed and analyzed, including but not limited to, information such as course history, score, notes, collection, discussion, etc. of the user.
For example, the collected learning behavior data may include the steps of:
1. a user's browsing record including accessed courses, chapters, videos, documents, etc.;
2. learning behavior of a user, including watching video, doing questions, submitting jobs, etc.;
3. scoring and commenting of users, including assessment of courses, chapters, videos, lectures, etc.;
4. the notes and collections of the user, including labeling and collecting courses, chapters, videos, documents, and the like;
5. discussion and communication of users, including discussion and answers to courses, chapters, questions, and the like.
The acquired learning behavior data is processed and analyzed, and the information such as interests, preferences, capability level and the like of the user can be extracted through the technologies such as data mining, machine learning and the like, so that more personalized and accurate courses and resources can be recommended for the user.
In this embodiment, the intelligent search recommendation method based on online learning courses further includes establishing an interest model of the user based on the processed and analyzed learning behavior data. The interest model of the user is built based on the focus of the user: analyzing courses, knowledge points, topics and the like focused by the user according to learning behavior data of the user, and establishing a focused point model of the user; based on the user's preferences: and analyzing which type of courses, learning resources, learning modes and the like the user likes according to the learning behavior data of the user, and establishing a preference model of the user. Based on learning objectives of the user: and analyzing learning targets and demands of the user according to the learning behavior data and the learning history of the user, and establishing a learning target model of the user. Based on the user's capability level: and analyzing the knowledge level, skill level, cognitive level and the like of the user according to the learning behavior data and the learning history of the user, and establishing a capability level model of the user. Based on the learning style of the user: and analyzing the learning styles of the user, such as visual type, auditory type, manual type and the like, according to the learning behavior data and the learning history of the user, and establishing a learning style model of the user.
Based on the analysis results, an interest model of the user can be established for recommending courses conforming to the interests and the targets of the user.
When an interest model of a user is established, learning behavior data of the user needs to be analyzed, and data acquisition and data processing are needed; the data collection is to collect learning behavior data of the user, and the learning behavior data comprises learning history, scoring, notes, collection, discussion and other information. The data processing is to perform cleaning, de-duplication, normalization and the like on the acquired data so as to facilitate subsequent analysis.
In this embodiment, the specific steps for establishing the interest model of the user are as follows:
1. analyzing the attention points and the preference of the user according to the information of the historical course record, scoring, notes, collection, discussion and the like of the user, and knowing the interest field and the learning style of the user;
2. according to the learning target of the user, analyzing the requirement and target of the user, and knowing the learning direction and key point of the user;
3. establishing an interest model of the user according to the information such as the interest field, the learning style and the learning target of the user, wherein the interest model comprises the information such as interest labels, knowledge point association degrees and learning paths of the user;
4. continuously updating and optimizing an interest model of the user, and adjusting information such as interest labels, knowledge point association degrees, learning paths and the like according to new learning behavior data of the user so as to improve recommendation effects;
5. model updating: as the learning behavior of the user changes, the interest model also needs to be updated and optimized continuously to maintain accuracy and practicality.
In the embodiment of the present application, referring to fig. 2, a current online learning course is classified and labeled based on a learning model of a user, and a feature vector of the online learning course based on chapter matching is established, which includes the following steps:
s101, course classification: classifying online learning courses in the online learning platform according to the subject field, the difficulty level and the course type of the online learning courses;
s102, course labeling: labeling the online learning courses in the online learning platform, and labeling according to the topics, the contents and the knowledge points of the online learning courses;
s103, establishing course feature vectors: according to the classification and the label of the online learning course, establishing a characteristic vector of the online learning course based on chapter matching, converting the classification and the label of the online learning course into a vector form, and establishing a course characteristic vector.
The application has the advantages that the machine learning algorithm is utilized to train the learning model of the user and the characteristic vector of the course, the search recommendation model is established, the course matched with the learning interest and the learning ability of the user can be recommended more accurately, and the learning effect and the satisfaction of the user are improved.
In this embodiment, referring to fig. 3, the intelligent search recommendation method based on the online learning course further includes establishing a recommendation model between the user and the online learning course based on the learning model of the user and the feature vector of the online learning course, including the following steps:
s201, constructing a training data set based on a learning model of a user and feature vectors of an online learning course;
s202, establishing a recommendation model between a user and an online learning course, and training and optimizing the model through the constructed training data set;
and S203, updating the recommendation model in real time according to the search behavior and the history record of the user.
And selecting a proper machine learning algorithm, such as collaborative filtering, content-based recommendation, deep learning and the like, establishing a recommendation model between a user and a course, and training and optimizing the model to improve the accuracy and efficiency of recommendation. The recommendation model can be updated in real time according to the search behavior and the history record of the user so as to adapt to the changing interests and requirements of the user. And when online recommendation is performed, according to the query and the context information of the user, a recommendation model is combined to give a personalized recommendation result.
In this embodiment, the method further includes performing chapter information matching according to the loaded course catalog according to the online learning course log of the registered user, and constructing a similarity matrix of the chapter information;
according to the online learning course log of the current user, performing user similarity matrix screening on the current online learning course, and screening out log results with previous similarity sequences from high to low as reference results;
and according to the query information of the user and the context information corresponding to the query information, a personalized recommendation result is given.
In this embodiment, referring to fig. 4, when obtaining a search result in response to a search instruction, analyzing and processing the search instruction of the user includes the following steps:
s301, word segmentation and key information extraction are carried out on the search instruction so as to obtain the search intention of a user;
s302, obtaining matched course feature vectors according to the search intention and the learning model of the user;
s303, calculating a recommendation score of each course based on a recommendation model between the user and the online learning course;
s304, ordering online learning courses according to the recommendation scores, returning to a course list most relevant to the user, and updating and optimizing a recommendation model according to feedback and behavior data of the user.
In this embodiment, personalized search recommendation results are generated based on the user's search instructions and recommendation model, including but not limited to recommending relevant courses, lectures, learning resources, and the like. The analysis and processing of the search instruction of the user may include the following steps:
1. keyword extraction: and extracting keywords from the search instruction to be used as input of a recommendation model.
2. Semantic analysis: and carrying out semantic analysis on the search instruction to understand the intention and the requirement of the user, and further generating personalized recommendation results better.
3. Contextual analysis: contextual information of the search instructions, such as time, place, device, etc., is considered to better understand the needs and intent of the user.
4. User feedback: and adjusting and optimizing the search instruction according to the feedback information of the user so as to improve the recommendation effect.
Further, referring to fig. 5, in response to the search instruction, obtaining the search result is based on the search instruction and the recommendation model of the user, and personalized search recommendation results are generated, which includes the following steps:
s401, extracting keywords from a search instruction of a user and performing semantic analysis, wherein the keywords are extracted from the search instruction and used as input of a recommendation model, and the search instruction is subjected to semantic analysis;
s402, generating a candidate course list based on a search instruction and a recommendation model of a user, and scoring and sorting candidate courses through the recommendation model to obtain personalized search recommendation results;
and S403, presenting the recommendation result to the user, displaying and feeding back the search recommendation result, and continuously optimizing the recommendation model and the search recommendation result according to the feedback and the behavior of the user.
In this embodiment, the analysis and processing of the search instruction of the user includes keyword extraction, semantic analysis, and the like, so as to determine the search intention and the demand of the user. Based on the interest model of the user and the characteristic vector of the course, a machine learning algorithm is adopted to establish a recommendation model between the user and the course. And screening a candidate course list from the course library according to the search intention and the requirement of the user. And scoring and sorting the candidate courses through the recommendation model to obtain final personalized search recommendation results, and presenting the recommendation results to the user for selection and learning.
The searching recommendation results are displayed and fed back, and the information comprises course names, course descriptions, scores, learning difficulties and the like, and links of related recommendation courses.
According to the intelligent search recommendation method and system based on the online learning courses, the system is used for matching the keyword sequence of learning browsing data of the user with chapters in the loaded course catalog by collecting learning behavior data of the user, and then intelligent recommendation is carried out on learning resources by combining interests and hobbies of the user and learning targets. In the recommending process, the system considers factors such as difficulty, duration, type and the like of learning resources, learning history and evaluation and the like of users, so that the accuracy and individuation degree of recommendation are improved. Meanwhile, the system can continuously optimize the learning model according to feedback of the user, and improves the recommendation effect. The system has the advantages of friendly user interface, easy operation and capability of meeting the personalized requirements of users.
Referring to fig. 6, an embodiment of the present application further provides an intelligent search recommendation system based on an online learning course, which performs search result recommendation using the intelligent search recommendation method based on an online learning course, and the intelligent search recommendation system based on an online learning course includes a data acquisition module 110, a data processing module 120, a feature extraction module 130, a search recommendation module 140, a user interface module 150, an optimization module 160, and a recommendation model establishment module 170.
The data acquisition module 110 is used for acquiring learning browsing data of a user;
the data processing module 120 is configured to pre-process the learning browsing data, generate a keyword sequence of the learning browsing data, and match the keyword sequence of the learning browsing data of the user with chapters in the loaded course catalog;
the feature extraction module 130 is configured to obtain an online learning course log of a current stage of the user, classify and tag the current online learning course based on a learning model of the user, and establish a feature vector of the online learning course based on chapter matching;
the search recommendation module 140 is configured to obtain a search result in response to a search instruction, divide a recommendation level for the obtained search result according to a keyword in the search instruction and a feature vector of a course, and recommend according to a recommendation priority of the recommendation level;
the user interface module 150 is used for displaying the recommendation result and collecting feedback of the user;
the optimizing module 160 is configured to optimize the learning model according to feedback of a user;
the recommendation model establishing module 170 is configured to establish a recommendation model between the user and the online learning course based on the learning model of the user and the feature vector of the online learning course, and update the recommendation model in real time according to the search behavior and the history of the user.
It should be noted that, the intelligent search recommendation system based on the online learning course adopts the steps of the intelligent search recommendation method based on the online learning course, so the operation process of the intelligent search recommendation system based on the online learning course in this embodiment is not described in detail.
In one embodiment, there is also provided in an embodiment of the present application a computer device including at least one processor, and a memory communicatively coupled to the at least one processor, the memory storing instructions executable by the at least one processor to cause the at least one processor to perform the intelligent search recommendation method based on online learning courses, the processor executing instructions to implement the steps of the method embodiments described above.
A computer device provided in an embodiment of the application includes a memory having a computer program stored therein and a processor configured to execute the computer program stored in the memory. The memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the steps in the method embodiments described above:
collecting learning browsing data of a user, preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in a loaded course catalog;
acquiring an online learning course log of a current stage of a user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching;
responding to a search instruction to obtain a search result, wherein the search instruction at least comprises a search term input by a user, and a paragraph or chapter content is selected;
dividing recommendation levels for the obtained search results according to the keywords in the search instruction and the feature vectors of the courses, and recommending to a user side for display according to recommendation priorities of the recommendation levels.
In one embodiment of the present application, there is also provided a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method embodiments described above:
collecting learning browsing data of a user, preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in a loaded course catalog;
acquiring an online learning course log of a current stage of a user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching;
responding to a search instruction to obtain a search result, wherein the search instruction at least comprises a search term input by a user, and a paragraph or chapter content is selected;
dividing recommendation levels for the obtained search results according to the keywords in the search instruction and the feature vectors of the courses, and recommending to a user side for display according to recommendation priorities of the recommendation levels.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory.
In summary, the intelligent search recommendation method and system based on online learning courses provided by the application are used for matching the keyword sequence of the learning browsing data of the user with the chapters in the loaded course catalog by collecting the learning behavior data of the user, and then intelligently recommending the learning resources by combining the interests and the learning targets of the user. In the recommending process, the system considers factors such as difficulty, duration, type and the like of learning resources, learning history and evaluation and the like of users, so that the accuracy and individuation degree of recommendation are improved. Meanwhile, the system can continuously optimize the learning model according to feedback of the user, and improves the recommendation effect. The system has the advantages of friendly user interface, easy operation and capability of meeting the personalized requirements of users.
Training the learning model of the user and the feature vector of the course by using a machine learning algorithm, establishing a search recommendation model, and more accurately recommending the course matched with the learning interest and the learning ability of the user, thereby improving the learning effect and the satisfaction of the user.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the application.
Claims (8)
1. The intelligent search recommendation method based on the online learning course is characterized by comprising the following steps of:
collecting learning browsing data of a user, preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in a loaded course catalog;
acquiring an online learning course log of a current stage of a user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching;
responding to a search instruction to obtain a search result, wherein the search instruction at least comprises a search term input by a user, and a paragraph or chapter content is selected;
the intelligent search recommendation method based on the online learning course divides a recommendation level for the acquired search result according to the keywords in the search instruction and the feature vector of the course, and recommends the acquired search result to a user side for display according to the recommendation priority of the recommendation level;
classifying and labeling the current online learning course based on a learning model of a user, and establishing a feature vector of the online learning course based on chapter matching, wherein the method comprises the following steps:
classifying online learning courses in the online learning platform according to the subject field, the difficulty level and the course type of the online learning courses;
labeling the online learning courses in the online learning platform, and labeling according to the topics, the contents and the knowledge points of the online learning courses;
according to the classification and the label of the online learning course, establishing a characteristic vector of the online learning course based on chapter matching, converting the classification and the label of the online learning course into a vector form, and establishing a course characteristic vector;
the intelligent search recommendation method based on the online learning course further comprises the steps of establishing a recommendation model between the user and the online learning course based on a learning model of the user and a feature vector of the online learning course, and comprises the following steps:
constructing a training data set based on a learning model of a user and feature vectors of an online learning course;
establishing a recommendation model between a user and an online learning course, training and optimizing the model through the constructed training data set,
and updating the recommendation model in real time according to the search behavior and the history record of the user.
2. The intelligent search recommendation method based on online learning courses, as claimed in claim 1, wherein collecting learning browsing data of the user includes collecting learning history data and learning behavior data of the user, including learning objectives, learning time, learning courses, learning progress, and evaluation information of the user.
3. The intelligent search recommendation method based on online learning courses, as claimed in claim 2, wherein the recommendation model further comprises performing chapter information matching according to the loaded course catalogue according to the online learning course log of the registered user and constructing a similarity matrix of the chapter information when performing online recommendation;
according to the online learning course log of the current user, performing user similarity matrix screening on the current online learning course, and screening out log results with previous similarity sequences from high to low as reference results;
and according to the query information of the user and the context information corresponding to the query information, a personalized recommendation result is given.
4. The intelligent search recommendation method based on online learning courses of claim 3 wherein analyzing and processing search instructions of a user when obtaining search results in response to the search instructions includes the steps of:
word segmentation and key information extraction are carried out on the search instruction so as to obtain the search intention of the user;
obtaining a matched course feature vector according to the search intention and the learning model of the user;
calculating a recommendation score for each course based on a recommendation model between the user and the online learning course;
and sequencing online learning courses according to the recommendation scores, returning to a most relevant course list of the user, and updating and optimizing a recommendation model according to feedback and behavior data of the user.
5. The intelligent search recommendation method based on online learning courses of claim 4 wherein obtaining search results in response to search instructions is based on user search instructions and recommendation models, generating personalized search recommendation results, comprising the steps of:
extracting keywords from a search instruction of a user, performing semantic analysis, extracting the keywords from the search instruction, and performing semantic analysis on the search instruction by taking the keywords as input of a recommendation model;
generating a candidate course list based on a search instruction and a recommendation model of a user, and scoring and sorting candidate courses through the recommendation model to obtain personalized search recommendation results;
and presenting the recommendation result to the user, displaying and feeding back the search recommendation result, and continuously optimizing the recommendation model and the search recommendation result according to the feedback and the behavior of the user.
6. An intelligent search recommendation system based on online learning courses, which is characterized in that the intelligent search recommendation system based on online learning courses recommends search results by adopting the intelligent search recommendation method based on online learning courses according to any one of claims 1-5; the intelligent search recommendation system based on the online learning course comprises:
the data acquisition module is used for acquiring learning browsing data of a user;
the data processing module is used for preprocessing the learning browsing data, generating a keyword sequence of the learning browsing data, and matching the keyword sequence of the learning browsing data of the user with chapters in the loaded course catalog;
the feature extraction module is used for acquiring an online learning course log of the current stage of the user, classifying and labeling the current online learning course based on a learning model of the user, and establishing a feature vector of the online learning course based on chapter matching;
the search recommendation module is used for responding to the search instruction to obtain search results, dividing recommendation levels for the obtained search results according to keywords in the search instruction and feature vectors of courses, and recommending according to recommendation priorities of the recommendation levels;
and the user interface module is used for displaying the recommendation result and collecting feedback of the user.
7. The intelligent search recommendation system based on online learning courses of claim 6 further comprising an optimization module for use in determining a user-based search recommendationHouseholdAnd (3) optimizing the learning model.
8. The intelligent search recommendation system based on online learning courses as claimed in claim 7, further comprising a recommendation model building module for building a recommendation model between the user and the online learning courses based on the learning model of the user and the feature vectors of the online learning courses, and updating the recommendation model in real time according to the search behavior and the history of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310551179.9A CN116257694B (en) | 2023-05-16 | 2023-05-16 | Intelligent search recommendation method and system based on online learning courses |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310551179.9A CN116257694B (en) | 2023-05-16 | 2023-05-16 | Intelligent search recommendation method and system based on online learning courses |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116257694A CN116257694A (en) | 2023-06-13 |
| CN116257694B true CN116257694B (en) | 2023-08-22 |
Family
ID=86686577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310551179.9A Active CN116257694B (en) | 2023-05-16 | 2023-05-16 | Intelligent search recommendation method and system based on online learning courses |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116257694B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649319B (en) * | 2023-12-11 | 2024-06-04 | 广州工程技术职业学院 | Intelligent teaching method, device, equipment and medium based on sea dangerous goods classification |
| CN117874339B (en) * | 2024-01-03 | 2024-06-21 | 北京华乐思教育科技有限公司 | Intelligent recommendation system and method for testing and analyzing learning content |
| CN117575745B (en) * | 2024-01-17 | 2024-04-30 | 山东正禾大教育科技有限公司 | Course teaching resource individual recommendation method based on AI big data |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670087A (en) * | 2018-11-28 | 2019-04-23 | 平安科技（深圳）有限公司 | Course intelligent recommendation method, apparatus, computer equipment and storage medium |
| CN109919810A (en) * | 2019-01-22 | 2019-06-21 | 山东科技大学 | Student's modeling and personalized course recommended method in on-line study system |
| CN111475716A (en) * | 2020-03-26 | 2020-07-31 | 威比网络科技(上海)有限公司 | Online course recommendation method, system, equipment and storage medium |
| CN113065060A (en) * | 2021-02-18 | 2021-07-02 | 山东师范大学 | Deep learning-based education platform course recommendation method and system |
| KR20210152182A (en) * | 2020-06-08 | 2021-12-15 | (주)인더스트리미디어 | Learning service server for recommending learning linked on-line education and off-line education and mehtod thereof |
| CN114139056A (en) * | 2021-12-01 | 2022-03-04 | 浪潮云信息技术股份公司 | Intelligent search recommendation method and system based on online learning course |
| CN115146162A (en) * | 2022-06-30 | 2022-10-04 | 武汉美和易思数字科技有限公司 | Online course recommendation method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140186817A1 (en) * | 2012-12-31 | 2014-07-03 | Fujitsu Limited | Ranking and recommendation of open education materials |
| EP3079116A1 (en) * | 2015-04-10 | 2016-10-12 | Tata Consultancy Services Limited | System and method for generating recommendations |
| US20220415200A1 (en) * | 2020-02-20 | 2022-12-29 | Gopalakrishnan Venkatasubramanyam | Smart-learning and learning path |
| CN114519143B (en) * | 2022-02-18 | 2024-05-14 | 北京百度网讯科技有限公司 | Training method of course recommendation model, course recommendation method and device |
-
2023
- 2023-05-16 CN CN202310551179.9A patent/CN116257694B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670087A (en) * | 2018-11-28 | 2019-04-23 | 平安科技（深圳）有限公司 | Course intelligent recommendation method, apparatus, computer equipment and storage medium |
| CN109919810A (en) * | 2019-01-22 | 2019-06-21 | 山东科技大学 | Student's modeling and personalized course recommended method in on-line study system |
| CN111475716A (en) * | 2020-03-26 | 2020-07-31 | 威比网络科技(上海)有限公司 | Online course recommendation method, system, equipment and storage medium |
| KR20210152182A (en) * | 2020-06-08 | 2021-12-15 | (주)인더스트리미디어 | Learning service server for recommending learning linked on-line education and off-line education and mehtod thereof |
| CN113065060A (en) * | 2021-02-18 | 2021-07-02 | 山东师范大学 | Deep learning-based education platform course recommendation method and system |
| CN114139056A (en) * | 2021-12-01 | 2022-03-04 | 浪潮云信息技术股份公司 | Intelligent search recommendation method and system based on online learning course |
| CN115146162A (en) * | 2022-06-30 | 2022-10-04 | 武汉美和易思数字科技有限公司 | Online course recommendation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116257694A (en) | 2023-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116257694B (en) | Intelligent search recommendation method and system based on online learning courses | |
| CN104834729B (en) | Topic recommends method and topic recommendation apparatus | |
| CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
| CN111737495B (en) | Middle-high-end talent intelligent recommendation system and method based on domain self-classification | |
| US10846617B2 (en) | Context-aware recommendation system for analysts | |
| CN104680453B (en) | Course based on student's attribute recommends method and system | |
| CN111475716A (en) | Online course recommendation method, system, equipment and storage medium | |
| CN111859160B (en) | Session sequence recommendation method and system based on graph neural network | |
| US11544135B2 (en) | Systems and methods for the analysis of user experience testing with AI acceleration | |
| US10762150B2 (en) | Searching method and searching apparatus based on neural network and search engine | |
| CN105426550B (en) | Collaborative filtering label recommendation method and system based on user quality model | |
| US11416534B2 (en) | Classification of electronic documents | |
| CN111831924A (en) | Content recommendation method, device, equipment and readable storage medium | |
| CN111400586A (en) | Group display method, terminal, server, system and storage medium | |
| Zhong et al. | Design of a personalized recommendation system for learning resources based on collaborative filtering | |
| CN113656687A (en) | Teacher portrait construction method based on teaching and research data | |
| CN115146161A (en) | Personalized learning resource recommendation method and system based on content recommendation | |
| CN111581435A (en) | Video cover image generation method and device, electronic equipment and storage medium | |
| CN116362426B (en) | Learning behavior prediction management system and method based on artificial intelligence and deep learning | |
| Giannopoulos et al. | Algorithms and criteria for diversification of news article comments | |
| CN113836388A (en) | Information recommendation method and device, server and storage medium | |
| CN116680425A (en) | Processing system and method for generating image based on user text prompt word | |
| CN115115407A (en) | Intelligent recommendation method and system for urban integrated intelligent service platform | |
| CN114090777A (en) | Text data processing method and device | |
| Estivill-Castro et al. | Towards the Ranking of Web-pages for Educational Purposes. |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |