CN112632385B - Course recommendation method, course recommendation device, computer equipment and medium - Google Patents
Course recommendation method, course recommendation device, computer equipment and medium Download PDFInfo
- Publication number
- CN112632385B CN112632385B CN202011590904.6A CN202011590904A CN112632385B CN 112632385 B CN112632385 B CN 112632385B CN 202011590904 A CN202011590904 A CN 202011590904A CN 112632385 B CN112632385 B CN 112632385B
- Authority
- CN
- China
- Prior art keywords
- user
- course
- recommended
- target
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000013598 vector Substances 0.000 claims abstract description 117
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000004220 aggregation Methods 0.000 claims abstract description 27
- 230000002776 aggregation Effects 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 230000004931 aggregating effect Effects 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims description 52
- 230000006399 behavior Effects 0.000 claims description 49
- 238000003066 decision tree Methods 0.000 claims description 33
- 238000011156 evaluation Methods 0.000 claims description 14
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000007477 logistic regression Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000002349 favourable effect Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Probability & Statistics with Applications (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 invention discloses a course recommendation method, a device, computer equipment and a medium, belonging to the field of information recommendation, wherein the method comprises the following steps: the method comprises the steps of obtaining basic data of a user to be recommended, preprocessing and aggregating the basic data, carrying out image processing on the user to be recommended according to an obtained aggregation result, obtaining a user image, carrying out feature extraction according to the user image, obtaining a target vector, inputting the target vector into a pre-trained course recommendation model, recommending by adopting the pre-trained course recommendation model, obtaining a course category to be recommended, selecting at least one course recommendation information from the course category to be recommended as a target recommendation course, recommending the target recommendation course to the user to be recommended.
Description
Technical Field
The present invention relates to the field of information recommendation, and in particular, to a course recommendation method, apparatus, computer device, and medium.
Background
With the rapid development of society and the advancement of information technology, users in various industries need to constantly learn to improve the skill of the value, and what skills need to be improved, and how to select courses becomes a focus.
In the existing mode, course recommendation is usually realized by setting rules, such as which positions need to master which skills, but different users have different conditions, and the recommendation mode has weaker pertinence, so that the recommendation efficiency is low. With the rapid development of society and the advancement of information technology, users in various industries need to constantly learn to improve the skill of the value, and what skills need to be improved, and how to select courses becomes a focus.
In the existing mode, course recommendation is usually realized by setting rules, such as which positions need to master which skills, but different users have different conditions, and the recommendation mode has weaker pertinence, so that the recommendation accuracy is not high.
Disclosure of Invention
The embodiment of the application provides a course recommendation method, a course recommendation device, computer equipment and a storage medium, so as to improve accuracy of course recommendation.
In order to solve the above technical problems, an embodiment of the present application provides a course recommendation method, including:
acquiring basic data of a user to be recommended;
performing data preprocessing and aggregation on the basic data, and performing image processing on the user to be recommended according to the obtained aggregation result to obtain a user image;
Extracting features according to the user portrait to obtain a target vector;
inputting the target vector into a pre-trained course recommendation model, and adopting the pre-trained course recommendation model to perform data processing to obtain a class of a course to be recommended;
and selecting at least one course recommendation information from the class of the courses to be recommended as a target recommendation course, and recommending the target recommendation course to the user to be recommended.
Optionally, performing data preprocessing and aggregation on the basic data, and performing image processing on the user to be recommended according to the obtained aggregation result, where obtaining the user image includes:
performing data preprocessing on the basic data to obtain the standard data;
performing word segmentation processing on the standard data, and clustering word segmentation processing results to obtain the association category of the user to be recommended;
and generating a target label and importance ranking of the target label according to the association category to obtain the user portrait.
Optionally, the extracting features according to the user portrait, obtaining a target vector includes:
constructing a basic word vector corresponding to each tag in the user image based on a preset corpus;
Calculating the space distance between the basic word vector and other basic word vectors according to each basic word vector, and selecting the minimum value from the space distances as the minimum space distance of the basic word vector;
taking the basic word vector with the minimum space distance smaller than or equal to a preset space distance threshold value as a label vector;
and classifying the label vector based on a K-Means aggregation algorithm to obtain a target vector.
Optionally, before the target vector is input into a pre-trained course recommendation model and the data processing is performed by adopting the pre-trained course recommendation model, the course recommendation method further includes:
acquiring user portraits of each sample user;
extracting a feature vector of each user portrait;
acquiring a historical behavior data set of each sample user;
determining the association category indicated by the historical behavior data in the historical behavior data set of each sample user;
and for each sample user, taking the characteristic vector of the user portrait of the sample user as input, taking the association category indicated by the historical behavior data in the historical behavior data set of the sample user as output, and training to obtain the pre-trained course recommendation model.
Optionally, the pre-trained course recommendation model is a gradient boost decision tree model, and the training data processing by adopting the pre-trained course recommendation model includes:
taking each dimension of the target vector as a training feature;
inputting the training features into a gradient lifting decision tree model, and training the training features through the gradient lifting decision tree model to obtain n decision trees, wherein n is a positive integer;
taking training features contained in the path of each decision tree as independent variables, and predicting course categories based on a two-class logistic regression model to obtain a prediction score corresponding to each course category;
and taking the class of the course with the predictive value exceeding the preset threshold value as the class of the course to be recommended.
Optionally, after selecting at least one course recommendation information from the class of courses to be recommended as a target recommendation course and recommending the target recommendation course to the user to be recommended, the course recommendation method further includes:
receiving learning evaluation data of the user to be recommended aiming at the target recommended course;
Based on the learning evaluation data, carrying out secondary portrait on the user to be recommended to obtain an updated portrait;
and updating the target recommended course based on the updated portrait.
In order to solve the above technical problem, an embodiment of the present application further provides a course recommendation device, including:
the acquisition module is used for acquiring basic data of a user to be recommended;
the portrait module is used for carrying out data preprocessing and aggregation on the basic data, and carrying out portrait processing on the user to be recommended according to the obtained aggregation result to obtain a user portrait;
the extraction module is used for extracting the characteristics according to the user portrait to obtain a target vector;
the training module is used for inputting the target vector into a pre-trained course recommendation model, and adopting the pre-trained course recommendation model to perform data processing to obtain a class of a course to be recommended;
and the recommending module is used for selecting at least one course recommending information from the class of the courses to be recommended as a target recommending course and recommending the target recommending course to the user to be recommended.
Optionally, the portrait module includes:
the preprocessing unit is used for preprocessing the basic data to obtain the standard data;
The clustering unit is used for carrying out word segmentation on the standard data and clustering word segmentation results to obtain the association category of the user to be recommended;
and the portrait generating unit is used for generating a target label and the importance sequence of the target label according to the association category to obtain the portrait of the user.
Optionally, the extracting module includes:
the basic word vector construction unit is used for constructing basic word vectors corresponding to each tag in the user image based on a preset corpus;
the space distance calculation unit is used for calculating the space distance between the basic word vector and other basic word vectors according to each basic word vector, and selecting the minimum value from the space distances as the minimum space distance of the basic word vector;
the word vector screening unit is used for taking a basic word vector with the minimum space distance smaller than or equal to a preset space distance threshold value as a label vector;
and the classification unit is used for classifying the label vector based on a K-Means aggregation algorithm to obtain a target vector.
Optionally, the course recommendation device further includes:
the portrait acquisition module is used for acquiring a user portrait of each sample user;
The feature extraction module is used for extracting the feature vector of each user portrait;
the historical data acquisition module is used for acquiring a historical behavior data set of each sample user;
the association construction module is used for determining association categories indicated by the historical behavior data in the historical behavior data set of each sample user;
and the model training module is used for taking the characteristic vector of the user portrait of the sample user as input, taking the association category indicated by the historical behavior data in the historical behavior data set of the sample user as output and training to obtain the pre-trained course recommendation model for each sample user.
Optionally, the training module includes:
a training feature determining unit, configured to take each dimension of the target vector as a training feature;
the decision tree generating unit is used for inputting the training features into a gradient lifting decision tree model, and training the training features through the gradient lifting decision tree model to obtain n decision trees, wherein n is a positive integer;
the prediction unit is used for predicting course categories based on a two-class logistic regression model by taking training features contained in the path of each decision tree as independent variables to obtain a prediction value corresponding to each course category;
And the recommendation type determining unit is used for taking the course type with the predictive value exceeding a preset threshold value as the course type to be recommended.
Optionally, the course recommendation device further includes:
the receiving module is used for receiving learning evaluation data of the user to be recommended aiming at the target recommended course;
the portrait updating module is used for carrying out secondary portrait on the user to be recommended based on the learning evaluation data to obtain an updated portrait;
and the recommended course updating module is used for updating the target recommended course based on the updated portrait.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the steps of the course recommendation method when executing the computer program.
To solve the above technical problem, embodiments of the present application further provide a computer readable storage medium storing a computer program, which when executed by a processor, implements the steps of the course recommendation method described above.
According to the course recommendation method, device, computer equipment and storage medium, basic data of users to be recommended are obtained, data preprocessing and aggregation are carried out on the basic data, image processing is carried out on the users to be recommended according to the obtained aggregation result, user images are obtained, accurate positioning is achieved on each user to be recommended, personalized recommendation is carried out on the users through the user images in the follow-up process, the pertinence and the accuracy of the follow-up recommendation are improved, meanwhile, feature extraction is carried out according to the user images, target vectors are obtained, the target vectors are input into a pre-trained course recommendation model, data processing is carried out by adopting the pre-trained course recommendation model, at least one course recommendation information is selected from the classes of the courses to be recommended as target recommendation courses, the target recommendation courses are recommended to the users to be recommended, personalized recommendation is carried out on each user to be recommended according to the image characteristics of the user to be recommended, and the accuracy of course recommendation is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a course recommendation method of the present application;
FIG. 3 is a schematic diagram illustrating one embodiment of a course recommendation device in accordance with the present application;
FIG. 4 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, as shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture E interface display perts Group Audio Layer III, moving Picture expert compression standard audio layer 3), MP4 players (Moving Picture E interface display perts Group Audio Layer IV, moving Picture expert compression standard audio layer 4), laptop and desktop computers, and so on.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the course recommendation method provided by the embodiment of the present application is executed by a server, and accordingly, the course recommendation device is set in the server.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. Any number of terminal devices, networks and servers may be provided according to implementation requirements, and the terminal devices 101, 102, 103 in the embodiment of the present application may specifically correspond to application systems in actual production.
Referring to fig. 2, fig. 2 shows a course recommendation method provided by an embodiment of the present application, and the method is applied to the server in fig. 1 for illustration, and is described in detail as follows:
s201: and acquiring basic data of the user to be recommended.
Specifically, when receiving a course recommendation request of a user to be recommended, a server acquires a user identification of the user to be recommended, which is contained in the course recommendation request, and further acquires basic data of the user to be recommended according to the user identification, so that accurate portrayal is performed on the user to be recommended according to the acquired basic data, and a user portrayal of the user to be recommended, which contains a plurality of dimension labels, is obtained.
The basic data refer to historical behavior data of a user, specifically, the historical behavior data can be crawled from each system in a distributed big data mode and then stored in the distributed data, the data content specifically contained in the historical behavior data can be set according to actual service requirements, for example, in the field of service promotion, the historical behavior data specifically can be various index progress, project participation data, success rate and the like.
S202: and carrying out data preprocessing and aggregation on the basic data, and carrying out portrait processing on the user to be recommended according to the obtained aggregation result to obtain a user portrait.
For a specific implementation process of data preprocessing and aggregation for the basic data, reference may be made to the description of the subsequent embodiments, and for avoiding repetition, a description is omitted here.
The concept of User portrayal (User Persona) was originally proposed by the parent Alan Cooper of the interactive design, and was a target User model built on top of a series of attribute data. Typically, the product design and operators abstract from the user group, and are essentially a tool for describing the needs of the user. In this embodiment, the accurate representation is performed by analyzing historical behavior data of the user to obtain labels of the user in each dimension, so as to form a multi-dimensional user representation.
Wherein the historical behavior data includes, but is not limited to: history searches, history clicks, history browses, etc. Historical search records include, but are not limited to: user information, search time, and search keywords. The user information includes basic information of the user, such as name, gender, age, etc., the search time refers to a specific time when a search operation is detected, and the search keyword refers to a keyword which is input and inquired at the search time.
It should be noted that, in this embodiment, through analysis of historical behavior data, the skill mastery degree of the user to be recommended in each dimension is extracted in the process of processing the service, so as to generate the user label of each dimension, and obtain the user portrait, which is favorable for realizing accurate course recommendation through accurate portrait.
S203: and extracting the characteristics according to the user portrait to obtain a target vector.
Specifically, in step S202, after accurate representation is performed on the user, a user representation with multiple dimension labels is obtained, in this embodiment, vectorization and clustering are performed on each dimension label, so as to implement datamation of text labels, and then, training can be performed by inputting digitized target vectors into a pre-trained course recommendation model, so that recommended course information is obtained, which is beneficial to improving accuracy of course recommendation.
S204: inputting the target vector into a pre-trained course recommendation model, and adopting the pre-trained course recommendation model to conduct data processing to obtain the class of the course to be recommended.
Specifically, after the target vector is obtained, the target vector is input into a pre-trained course recommendation model, training is carried out by adopting the model, and the class of the course to be recommended is output.
In this embodiment, by using user figures of a plurality of sample users and recommended course categories corresponding to the sample users as initial data, training is performed on a neural network model or a machine learning model by using the initial data, and a pre-trained course recommended model is obtained.
S205: and selecting at least one course recommendation information from the class of the courses to be recommended as a target recommendation course, and recommending the target recommendation course to the user to be recommended.
Specifically, at least one course is selected from the classes of courses to be recommended and is used as the course to be recommended, course recommendation information is generated and sent to the user to be recommended.
The course recommendation information may be generated by displaying a list to the user to be recommended and generating recommendation information according to the received user selection information, or may be combined with historical data of the user to be recommended to perform relevance ranking on the courses to be recommended, and a preset number of courses before ranking and examination are selected to generate course recommendation information, which is not particularly limited herein.
In this embodiment, basic data of users to be recommended are acquired, data preprocessing and aggregation are performed on the basic data, image processing is performed on the users to be recommended according to the obtained aggregation result, user images are obtained, accurate positioning is achieved on each user to be recommended, personalized recommendation is performed on the users through user images in the follow-up process, the pertinence and the accuracy of follow-up recommendation are improved, meanwhile, feature extraction is performed according to the user images, target vectors are obtained, the target vectors are input into a pre-trained course recommendation model, data processing is performed by adopting the pre-trained course recommendation model, a class of courses to be recommended is obtained, at least one course recommendation information is selected from the class of courses to be recommended as a target recommendation course, and target recommendation courses are recommended to the users to be recommended, so that personalized recommendation is performed on each user to be recommended according to the characteristics of the user images, and the accuracy of course recommendation is improved.
In some optional implementations of this embodiment, in step S202, performing data preprocessing and aggregation on the basic data, and performing image processing on the user to be recommended according to the obtained aggregation result, where obtaining the user image includes:
Performing data preprocessing on the basic data to obtain standard data;
performing word segmentation on the standard data, and clustering word segmentation results to obtain the association category of the user to be recommended;
and generating the target labels and the importance sequences of the target labels according to the association categories to obtain the user portrait.
Specifically, after basic data of a user are collected, dirty data cleaning, data integrity checking, regularized conversion and other treatments are required to be carried out on the data, data quality is ensured, standard data is obtained, the accuracy of obtaining user portraits is improved, meanwhile, word segmentation and clustering are carried out by utilizing the standard data, the association category of the user is determined according to a clustering result, and then the ordering of target labels and target labels is determined according to the corresponding association category, so that the user portraits are obtained.
It should be noted that, the basic data of each user to be recommended includes multiple pieces of data with multiple dimensions, and the distribution field of the main data of the user to be recommended is determined through clustering, so as to determine the association category corresponding to the user to be recommended. And then determining the target label of the user according to the data falling into the association category.
The importance of the target label can be determined according to the correlation between the target label and the association category, and the closer the target label is to the association category, the greater the importance is.
In the embodiment, the association type of the user to be recommended is determined by carrying out data analysis on the basic data of the user to be recommended, and then the user portrait is generated according to the association type, so that the precision of the user portrait is improved.
In some optional implementations of this embodiment, in step S203, performing feature extraction according to the user portrait, obtaining the target vector includes:
constructing a basic word vector corresponding to each label in the user image based on a preset corpus;
for each basic word vector, calculating the space distance between the basic word vector and other basic word vectors, and selecting the minimum value from the space distances as the minimum space distance of the basic word vector;
taking a basic word vector with the minimum space distance smaller than or equal to a preset space distance threshold value as a label vector;
and classifying the label vector based on a K-Means aggregation algorithm to obtain a target vector.
In artificial intelligence, language representation refers primarily to formalized or mathematical descriptions of language to represent the language in a computer and enable the computer program to automatically process. The word vector in the embodiment of the invention is expressed as a label in the form of a vector.
The preset corpus can be specifically obtained by collecting corpora associated with the business according to actual business requirements.
Specifically, training each label in a user image by using a word vector mode, mapping the labels into a vector according to a preset corpus, linking the vectors together to form a word vector space, obtaining a basic word vector meeting the preset requirement by each vector corresponding to a point in the space, screening the basic word vector to obtain a label vector with higher attention, and clustering the label vector to obtain a target vector.
For example, in one embodiment, the preset spatial distance threshold is 0.8, the base word vectors include H1 (0.9,0.1,0), H2 (0.8,0.1,0.1), and H3 (0,0.1,0.9), the minimum spatial distance of H1 is 0.4243, the minimum spatial distance to H2 is 0.4243, the minimum spatial distance to H3 is 1.1314, and the minimum spatial distances of H1 and H2 are less than the preset spatial distance threshold of 0.8, thus H1 and H2 are used as the tag vectors.
It is understood that by filtering the basic word vectors which do not meet the requirement of the spatial distance threshold, the situation that labels with low attention are also put into user labels is avoided, and therefore the deviation and the positioning of the business in the user portrait can be determined more accurately.
It will be appreciated that the value of each dimension of the base word vector represents a feature that has some semantic and grammatical interpretability, and that each dimension of the base word vector may be referred to as a tag feature.
The K-means algorithm is a distance-based clustering algorithm, and the distance is used as an evaluation index of similarity, namely the closer the distance between two objects is, the greater the similarity is. The algorithm considers that the clusters are composed of objects close to each other, so that the obtained compact and independent clusters are used as final targets, and the clustering algorithm refines the tag vectors with more numbers, so that the efficiency of subsequent model training recommendation is improved.
The preset spatial distance threshold may be set according to actual requirements, which is not limited herein.
In this embodiment, a basic word vector corresponding to each label of the user portrait is constructed, and then clustering is performed to determine the category of the user portrait, so as to obtain a target vector, which is beneficial to the follow-up training of models through the target vector and quickly obtain the category of the recommended course.
In some optional implementations of this embodiment, before step S204, the course recommendation method further includes:
acquiring user portraits of each sample user;
Extracting a feature vector of each user portrait;
acquiring a historical behavior data set of each sample user;
determining an association category indicated by the historical behavior data in the historical behavior data set of each sample user;
for each sample user, taking the feature vector of the user portrait of the sample user as input, taking the association category indicated by the historical behavior data in the historical behavior data set of the sample user as output, and training to obtain a pre-trained course recommendation model.
The historical behavior data set is a data set related to the historical behavior of the sample user, which is obtained by collecting and analyzing the historical behavior data of the sample user, and according to the data set, the association type corresponding to the sample user is determined, and then the feature vector corresponding to the user image is taken as input, the association type is taken as output, and the initial course recommendation model is subjected to supervised learning training, so that the pre-trained course recommendation model is obtained.
Wherein the historical behavior data includes, but is not limited to: history searches, history clicks, history browses, etc. Historical search records include, but are not limited to: user information, search time, and search keywords. The user information includes basic information of the user, such as name, gender, age, etc., the search time refers to a specific time when a search operation is detected, and the search keyword refers to a keyword which is input and inquired at the search time.
In this embodiment, based on the feature vectors of the user portraits of the plurality of sample users extracted in the above steps and the determined association categories indicated by the historical behavior data in the historical behavior data sets of the plurality of sample users, the server may train out a course recommendation model capable of characterizing the correspondence between the feature vectors and the association categories, with the feature vectors of the user portraits of the plurality of sample users as input and the association categories indicated by the historical behavior data in the historical behavior data sets of the plurality of sample users as output.
The association category refers to a class recommendation category corresponding to historical behavior data, for example, a certain historical behavior is captured to be an operation PPT table, the data is evaluated, the evaluation result is that the skill proficiency is a middle level, and then the recommended association category is determined to be a middle level or a high level PPT class.
In this embodiment, the course recommendation model may be various types of artificial neural networks or a model obtained by combining a plurality of types of artificial neural networks. The human brain nerve cell network is abstracted from the information processing perspective, a certain simple model is built, and different networks are formed according to different connection modes. Typically consisting of a large number of interconnections between nodes (or neurons), each node representing a particular output function, called the stimulus function. The connection between each two nodes represents a weight, called a weight, for the signal passing through the connection, and the output of the network varies according to the connection mode, the weight and the excitation function of the network. Here, the server may train an initialization course recommendation model, which may be an untrained course recommendation model or an untrained course recommendation model, where the initialization course recommendation model may be set with initial parameters, and the parameters may be continuously adjusted during the training of the course recommendation model until a course recommendation model capable of characterizing a correspondence between feature vectors and recommendation course categories is trained.
In this embodiment, the server may take all the association categories indicated by the historical behavior data in the historical behavior data set of the sample user as recommended course categories, and take the recommended course categories as output; the method comprises the steps of selecting a part of categories from the associated categories indicated by the historical behavior data in the historical behavior data set of the sample user as recommended course categories, and outputting the recommended course categories; and selecting a part of categories from the associated categories indicated by the historical behavior data in the historical behavior data set of the sample user as recommended course categories, selecting another part of categories as non-recommended course categories, and outputting the recommended course categories and the non-recommended course categories, wherein the recommended course categories can be categories of interest to the sample user (categories closely associated with the historical behavior data of the user), and the non-recommended course categories can be categories of non-interest to the sample user.
In this embodiment, the pre-trained course recommendation model is obtained by training the course recommendation model in advance, and the target vector of the user to be recommended is directly trained by adopting the pre-trained course recommendation model when in subsequent use, which is favorable for improving the efficiency of model training, and simultaneously, the recommendation accuracy of the pre-trained course recommendation model is also favorable for improving by adopting a plurality of real data of the same scene as training data.
In some optional implementations of the present embodiment, optionally, in step S205, the pre-trained course recommendation model is a gradient boost decision tree model, and performing data processing by using the pre-trained course recommendation model to obtain a class of the course to be recommended includes:
taking each dimension of the target vector as a training feature;
inputting training features into a gradient lifting decision tree model, and training the training features through the gradient lifting decision tree model to obtain n decision trees, wherein n is a positive integer;
taking training features contained in the path of each decision tree as independent variables, and predicting course categories based on a two-class logistic regression model to obtain a prediction score corresponding to each course category;
and taking the class with the predictive value exceeding the preset threshold as the class of the class to be recommended.
The gradient boosting decision tree (Gradient Boosting Decision Tree, GBDT) algorithm is an iterative decision tree algorithm consisting of a plurality of decision trees, and the conclusions of all trees are accumulated as the final prediction result.
The decision tree in the gradient lifting decision tree belongs to a regression tree, each node of the tree can obtain a predicted value of the classification characteristic corresponding to the node, and for the classification characteristic of which a specific value is not determined, an average value of the classification characteristic is used as the predicted value of the classification characteristic.
After a decision tree model is generated, feature values of features contained in different paths are subjected to feature combination aiming at each decision tree to obtain combined features, the values of the same combined features of different trees are accumulated, the final accumulated value is used as the feature value of the combined features, the feature value is used as an independent variable in a two-class logistic regression (Logistic Regression, LR) model to calculate a probability value, a predictive value of a target vector corresponding to the combined features is determined according to the probability value, and then the class to be recommended is determined according to the predictive value, so that the accuracy of class recommendation of the class to be recommended is improved.
In some optional implementations of this embodiment, after step S205, the course recommendation method further includes:
receiving learning evaluation data of a user to be recommended aiming at a target recommendation course;
based on the learning evaluation data, carrying out secondary portrayal on the user to be recommended to obtain an updated portrayal;
and updating the target recommended course based on the updated portrait.
Specifically, after the user to be recommended learns the vast recommended course for a period of time, by receiving the evaluation data (test data) of the user to be recommended after learning, the user to be recommended is subjected to secondary portrait, and the specific process can refer to the above embodiment, so as to realize timely update of the portrait of the user, and further judge whether to update the target recommended course according to the actual requirement.
In this embodiment, by performing secondary image evaluation after learning the target recommended course, it is determined whether the target recommended course needs to be updated according to the learning result, so as to further improve the accuracy of course recommendation.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
Fig. 3 is a schematic block diagram of a course recommendation apparatus according to the one-to-one correspondence to the course recommendation method of the above embodiment. As shown in FIG. 3, the course recommending device comprises an acquisition module 31, a portrait module 32, an extraction module 33, a training module 34 and a recommending module 35. The functional modules are described in detail as follows:
the acquisition module 31 is used for acquiring basic data of a user to be recommended;
the portrait module 32 is used for preprocessing and aggregating the basic data, and carrying out portrait processing on the user to be recommended according to the obtained aggregation result to obtain a user portrait;
the extracting module 33 is used for extracting features according to the user portrait to obtain a target vector;
the training module 34 is configured to input the target vector into a pre-trained course recommendation model, and perform data processing by using the pre-trained course recommendation model to obtain a class of the course to be recommended;
The recommending module 35 is configured to select at least one course recommending information from the class of courses to be recommended, as a target recommended course, and recommend the target recommended course to the user to be recommended.
Optionally, the portrait module 32 includes:
the preprocessing unit is used for preprocessing the basic data to obtain standard data;
the clustering unit is used for carrying out word segmentation on the standard data and clustering word segmentation results to obtain the association category of the user to be recommended;
and the portrait generating unit is used for generating the target labels and the importance ranks of the target labels according to the association types to obtain the user portrait.
Optionally, the extraction module 33 includes:
the basic word vector construction unit is used for constructing basic word vectors corresponding to each tag in the user image based on a preset corpus;
the space distance calculation unit is used for calculating the space distance between each basic word vector and other basic word vectors, and selecting the minimum value from the space distances as the minimum space distance of the basic word vector;
the word vector screening unit is used for taking a basic word vector with the minimum space distance smaller than or equal to a preset space distance threshold value as a label vector;
The classification unit is used for classifying the label vector based on the K-Means aggregation algorithm to obtain a target vector.
Optionally, the course recommendation device further includes:
the portrait acquisition module is used for acquiring a user portrait of each sample user;
the feature extraction module is used for extracting the feature vector of each user portrait;
the historical data acquisition module is used for acquiring a historical behavior data set of each sample user;
the association construction module is used for determining association categories indicated by the historical behavior data in the historical behavior data set of each sample user;
the model training module is used for taking the characteristic vector of the user portrait of the sample user as input, taking the association category indicated by the historical behavior data in the historical behavior data set of the sample user as output and training to obtain a pre-trained course recommendation model for each sample user.
Optionally, the training module includes:
a training feature determining unit, configured to take each dimension of the target vector as a training feature;
the decision tree generating unit is used for inputting training features into the gradient lifting decision tree model, and training the training features through the gradient lifting decision tree model to obtain n decision trees, wherein n is a positive integer;
The prediction unit is used for predicting course categories based on a two-class logistic regression model by taking training features contained in the path of each decision tree as independent variables to obtain a prediction value corresponding to each course category;
and the recommendation type determining unit is used for taking the course type with the predictive value exceeding the preset threshold value as the course type to be recommended.
Optionally, the course recommendation device further includes:
the receiving module is used for receiving learning evaluation data of the user to be recommended aiming at the target recommended course;
the portrait updating module is used for carrying out secondary portrait on the user to be recommended based on the learning evaluation data to obtain an updated portrait;
and the recommended course updating module is used for updating the target recommended course based on the updated portrait.
For specific limitations of the course recommendation device, reference may be made to the above limitation of the course recommendation method, and no further description is given here. The modules in the course recommendation apparatus may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 4, fig. 4 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It is noted that only a computer device 4 having a component connection memory 41, a processor 42, a network interface 43 is shown in the figures, but it is understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or D interface display memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used for storing an operating system and various application software installed on the computer device 4, such as program codes for controlling electronic files, etc. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute a program code stored in the memory 41 or process data, such as a program code for executing control of an electronic file.
The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.
The present application also provides another embodiment, namely, a computer-readable storage medium storing an interface display program executable by at least one processor to cause the at least one processor to perform the steps of the course recommendation method as described above.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (7)
1. A course recommendation method, comprising:
acquiring basic data of a user to be recommended;
performing data preprocessing and aggregation on the basic data, and performing image processing on the user to be recommended according to the obtained aggregation result to obtain a user image;
extracting features according to the user portrait to obtain a target vector;
Inputting the target vector into a pre-trained course recommendation model, and adopting the pre-trained course recommendation model to perform data processing to obtain a class of a course to be recommended;
selecting at least one course recommendation information from the class of the courses to be recommended as a target recommendation course, and recommending the target recommendation course to the user to be recommended;
the step of preprocessing and aggregating the basic data, and carrying out portrait processing on the user to be recommended according to the obtained aggregation result, wherein the step of obtaining the user portrait comprises the following steps:
performing data preprocessing on the basic data to obtain standard data; performing word segmentation processing on the standard data, and clustering word segmentation processing results to obtain the association category of the user to be recommended; generating a target label and importance ranking of the target label according to the association category to obtain the user portrait;
the step of extracting the characteristics according to the user portrait, and the step of obtaining the target vector comprises the following steps:
constructing a basic word vector corresponding to each tag in the user image based on a preset corpus; calculating the space distance between the basic word vector and other basic word vectors according to each basic word vector, and selecting the minimum value from the space distances as the minimum space distance of the basic word vector; taking the basic word vector with the minimum space distance smaller than or equal to a preset space distance threshold value as a label vector; classifying the label vector based on a K-Means aggregation algorithm to obtain a target vector;
The pre-trained course recommendation model is a gradient lifting decision tree model, and the data processing by adopting the pre-trained course recommendation model comprises the steps of:
taking each dimension of the target vector as a training feature; inputting the training features into a gradient lifting decision tree model, and training the training features through the gradient lifting decision tree model to obtain n decision trees, wherein n is a positive integer; taking training features contained in the path of each decision tree as independent variables, and predicting course categories based on a two-class logistic regression model to obtain a prediction score corresponding to each course category; and taking the class of the course with the predictive value exceeding the preset threshold value as the class of the course to be recommended.
2. The course recommendation method of claim 1, wherein before said inputting said target vector into a pre-trained course recommendation model and performing data processing using said pre-trained course recommendation model, said course recommendation method further comprises:
acquiring user portraits of each sample user;
Extracting a feature vector of each user portrait;
acquiring a historical behavior data set of each sample user;
determining the association category indicated by the historical behavior data in the historical behavior data set of each sample user;
and for each sample user, taking the characteristic vector of the user portrait of the sample user as input, taking the association category indicated by the historical behavior data in the historical behavior data set of the sample user as output, and training to obtain the pre-trained course recommendation model.
3. A course recommendation method as claimed in any one of claims 1 to 2, wherein after selecting at least one course recommendation information from the class of courses to be recommended as a target recommended course and recommending the target recommended course to the user to be recommended, the course recommendation method further comprises:
receiving learning evaluation data of the user to be recommended aiming at the target recommended course;
based on the learning evaluation data, carrying out secondary portrait on the user to be recommended to obtain an updated portrait;
and updating the target recommended course based on the updated portrait.
4. A course recommendation device, said course recommendation device being operative to implement a course recommendation method as claimed in any one of claims 1 to 3, said course recommendation device comprising:
the acquisition module is used for acquiring basic data of a user to be recommended;
the portrait module is used for carrying out data preprocessing and aggregation on the basic data, and carrying out portrait processing on the user to be recommended according to the obtained aggregation result to obtain a user portrait;
the extraction module is used for extracting the characteristics according to the user portrait to obtain a target vector;
the training module is used for inputting the target vector into a pre-trained course recommendation model, and adopting the pre-trained course recommendation model to perform data processing to obtain a class of a course to be recommended;
and the recommending module is used for selecting at least one course recommending information from the class of the courses to be recommended as a target recommending course and recommending the target recommending course to the user to be recommended.
5. The curriculum recommending apparatus of claim 4, wherein said portrayal module comprises:
the preprocessing unit is used for carrying out data preprocessing on the basic data to obtain standard data;
The clustering unit is used for carrying out word segmentation on the standard data and clustering word segmentation results to obtain the association category of the user to be recommended;
and the portrait generating unit is used for generating a target label and the importance sequence of the target label according to the association category to obtain the portrait of the user.
6. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the course recommendation method of any one of claims 1 to 3 when the computer program is executed by the processor.
7. A computer readable storage medium storing a computer program, which when executed by a processor implements a course recommendation method as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011590904.6A CN112632385B (en) | 2020-12-29 | 2020-12-29 | Course recommendation method, course recommendation device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011590904.6A CN112632385B (en) | 2020-12-29 | 2020-12-29 | Course recommendation method, course recommendation device, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112632385A CN112632385A (en) | 2021-04-09 |
| CN112632385B true CN112632385B (en) | 2023-09-22 |
Family
ID=75285970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011590904.6A Active CN112632385B (en) | 2020-12-29 | 2020-12-29 | Course recommendation method, course recommendation device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112632385B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113139834A (en) * | 2021-04-29 | 2021-07-20 | 北京沃东天骏信息技术有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN113205135B (en) * | 2021-04-30 | 2023-08-18 | 平安科技（深圳）有限公司 | Course prediction model updating method, course prediction model updating device, computer equipment and storage medium |
| CN113139750B (en) * | 2021-05-14 | 2024-04-09 | 中国平安人寿保险股份有限公司 | Course recommendation method and device, server and storage medium |
| CN113159959A (en) * | 2021-05-20 | 2021-07-23 | 中国银行股份有限公司 | Foreign exchange product recommendation method and device |
| CN113407831B (en) * | 2021-06-16 | 2024-03-01 | 中国联合网络通信集团有限公司 | Course recommendation method and device |
| CN113469786A (en) * | 2021-06-29 | 2021-10-01 | 深圳市点购电子商务控股股份有限公司 | Method and device for recommending articles, computer equipment and storage medium |
| CN113641901B (en) * | 2021-08-05 | 2024-02-02 | 腾讯科技（深圳）有限公司 | Information recommendation method, information recommendation device, computer readable medium and electronic equipment |
| CN114119058B (en) * | 2021-08-10 | 2023-09-26 | 国家电网有限公司 | User portrait model construction method, device and storage medium |
| CN113360780A (en) * | 2021-08-10 | 2021-09-07 | 北京黑马企服科技有限公司 | Big data based information recommendation method and system |
| CN113656679B (en) * | 2021-08-27 | 2024-03-12 | 支付宝(杭州)信息技术有限公司 | User searching method and device |
| CN113656705B (en) * | 2021-08-31 | 2024-02-20 | 中国平安财产保险股份有限公司 | Course recommendation method, device, equipment and storage medium based on artificial intelligence |
| CN113837836A (en) * | 2021-09-18 | 2021-12-24 | 珠海格力电器股份有限公司 | Model recommendation method, device, equipment and storage medium |
| CN115967837A (en) * | 2021-10-11 | 2023-04-14 | 广州视源电子科技股份有限公司 | Method, device, equipment and medium for content interaction based on web course video |
| CN114173200B (en) * | 2021-12-06 | 2022-08-26 | 江苏省广电有线信息网络股份有限公司镇江分公司 | Video management pushing method and device based on private radio and television network |
| 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 |
| CN114840743B (en) * | 2022-03-01 | 2023-02-07 | 深圳市小秤砣科技有限公司 | Model recommendation method and device, electronic equipment and readable storage medium |
| CN114357323B (en) * | 2022-03-19 | 2022-06-03 | 深圳市启程教育科技有限公司 | Foreign trade talent based course recommendation system and method |
| CN114741605A (en) * | 2022-04-26 | 2022-07-12 | 泰康保险集团股份有限公司 | Method and device for recommending annuity products, electronic equipment and readable medium |
| CN115344787B (en) * | 2022-08-23 | 2023-07-04 | 华南师范大学 | Multi-granularity recommendation method, system, device and storage medium |
| CN116342335B (en) * | 2023-02-03 | 2023-11-14 | 武汉博奥鹏程教育科技有限公司 | Course recommendation method and device |
| CN116228484B (en) * | 2023-05-06 | 2023-07-07 | 中诚华隆计算机技术有限公司 | Course combination method and device based on quantum clustering algorithm |
| CN116228483B (en) * | 2023-05-06 | 2023-07-21 | 中诚华隆计算机技术有限公司 | Learning path recommendation method and device based on quantum drive |
| CN117151346B (en) * | 2023-10-30 | 2024-02-09 | 中国民航大学 | Civil aviation specialty teaching training system based on wisdom study |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN109816494A (en) * | 2019-01-31 | 2019-05-28 | 北京卡路里信息技术有限公司 | A kind of course recommended method, device, equipment and storage medium |
| CN111209474A (en) * | 2019-12-27 | 2020-05-29 | 广东德诚科教有限公司 | Online course recommendation method and device, computer equipment and storage medium |
| 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 |
-
2020
- 2020-12-29 CN CN202011590904.6A patent/CN112632385B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544663A (en) * | 2013-06-28 | 2014-01-29 | Tcl集团股份有限公司 | Method and system for recommending network public classes and mobile terminal |
| CN109816494A (en) * | 2019-01-31 | 2019-05-28 | 北京卡路里信息技术有限公司 | A kind of course recommended method, device, equipment and storage medium |
| CN111209474A (en) * | 2019-12-27 | 2020-05-29 | 广东德诚科教有限公司 | Online course recommendation method and device, computer equipment and storage medium |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112632385A (en) | 2021-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112632385B (en) | Course recommendation method, course recommendation device, computer equipment and medium | |
| CN111444428B (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| CN111753060B (en) | Information retrieval method, apparatus, device and computer readable storage medium | |
| CN110825956A (en) | Information flow recommendation method and device, computer equipment and storage medium | |
| CN113722438B (en) | Sentence vector generation method and device based on sentence vector model and computer equipment | |
| CN113010702A (en) | Interactive processing method and device for multimedia information, electronic equipment and storage medium | |
| CN110232128A (en) | Topic file classification method and device | |
| CN108959550B (en) | User focus mining method, device, equipment and computer readable medium | |
| CN111914159A (en) | Information recommendation method and terminal | |
| CN113392179A (en) | Text labeling method and device, electronic equipment and storage medium | |
| CN115659008A (en) | Information pushing system and method for big data information feedback, electronic device and medium | |
| CN112380421A (en) | Resume searching method and device, electronic equipment and computer storage medium | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text | |
| CN113918704A (en) | Question-answering method and device based on machine learning, electronic equipment and medium | |
| CN113569118A (en) | Self-media pushing method and device, computer equipment and storage medium | |
| CN113569018A (en) | Question and answer pair mining method and device | |
| CN112948526A (en) | User portrait generation method and device, electronic equipment and storage medium | |
| CN110929526A (en) | Sample generation method and device and electronic equipment | |
| CN116955591A (en) | Recommendation language generation method, related device and medium for content recommendation | |
| CN116910357A (en) | Data processing method and related device | |
| CN115238077A (en) | Text analysis method, device and equipment based on artificial intelligence and storage medium | |
| CN114817478A (en) | Text-based question and answer method and device, computer equipment and storage medium | |
| CN114707510A (en) | Resource recommendation information pushing method and device, computer equipment and storage medium | |
| CN116484085A (en) | Information delivery method, device, equipment, storage medium and program product | |
| CN113704623A (en) | Data recommendation method, device, equipment and storage medium |
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 |