CN116595378A - Model training method, course recommendation method, device, equipment and storage medium - Google Patents
Model training method, course recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116595378A CN116595378A CN202310623343.2A CN202310623343A CN116595378A CN 116595378 A CN116595378 A CN 116595378A CN 202310623343 A CN202310623343 A CN 202310623343A CN 116595378 A CN116595378 A CN 116595378A
- Authority
- CN
- China
- Prior art keywords
- target
- learning
- course
- determining
- learner
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 247
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000012216 screening Methods 0.000 claims abstract description 17
- 230000000694 effects Effects 0.000 abstract description 10
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006698 induction Effects 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
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application provides a model training method, a course recommendation method, a device, equipment and a storage medium. The method comprises the following steps: acquiring an initial training sample, wherein the initial training sample comprises a student, a student attribute, a learning time and a learning course; determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in learning courses; determining learning time information and click rate information of a target course according to a training sample to be optimized; determining course quality of a target course according to the learning time information and the click quantity information; screening the initial training sample according to course quality to obtain a target training sample; and training the model to be trained by taking the student attributes in the target training sample as input items and taking the learning courses in the target training sample as labels to obtain a target training model. The method improves the training effect of the model to be trained.
Description
Technical Field
The present application relates to the field of course recommendation technologies, and in particular, to a model training method, a course recommendation method, a device, equipment, and a storage medium.
Background
The courses which are interested by the students are recommended through the learning platform, so that the students can find the courses which are required to learn more efficiently, information overload is reduced, and the method is a common method in the current society of information burst.
At present, when a learning platform in the prior art carries out course recommendation on a learner, the course recommendation is generally carried out on the learner by collecting information of the learner through a course recommendation model which is internally arranged.
However, the existing recommendation model has the problem that the accuracy of recommended courses is low due to poor model training effect.
Disclosure of Invention
The application provides a model training method, a course recommending method, a device, equipment and a storage medium, which are used for solving the problem of low accuracy of recommended courses due to poor model training effect.
In a first aspect, the present application provides a model training method, including:
acquiring an initial training sample, wherein the initial training sample comprises a learner, a learner attribute, a learning time and a learning course, the learning course is a course learned by the learner, and the learning time is the time of the learner to learn the learning course;
Determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in learning courses;
determining learning time information and click rate information of a target course according to a training sample to be optimized;
determining course quality of a target course according to the learning time information and the click quantity information;
screening the initial training sample according to course quality to obtain a target training sample;
and training the model to be trained by taking the student attributes in the target training sample as input items and taking the learning courses in the target training sample as labels to obtain a target training model.
In the application, obtaining an initial training sample comprises:
acquiring historical data information;
according to the historical data information, determining a historical learning course, a historical student attribute and a historical learning time;
determining availability of a history learning course;
determining a learner, a learner attribute, a learning time and a learning course from the historical learning course according to the availability of the historical learning course;
and obtaining an initial training sample according to the trainees, the trainee attributes, the learning time and the learning courses.
In the present application, determining course quality of a target course according to learning time information and click amount information, includes:
determining the effective clicked quantity, the total learning duration and the target learning time of the target course according to the learning time information and the click quantity information;
determining the learned quantity according to the effective clicked quantity and the total learning duration;
determining the learned time according to the target learning time;
and determining the course quality according to the learned quantity and the learned time.
In the application, according to the effective clicked quantity and the total learning duration, the method for determining the learned quantity comprises the following steps:
obtaining the effective clicked rate of the learning course according to the effective clicked amount;
and determining the learned quantity according to the relation between the effective clicked rate and a preset effective click rate threshold value and the relation between the total learning duration and a preset total learning duration threshold value.
In the application, according to the effective clicked quantity, the effective clicked rate of the learning course is obtained, which comprises the following steps:
determining an invalid clicked quantity according to the valid clicked quantity;
and determining the effective clicked rate according to the effective clicked amount and the ineffective clicked amount.
In the present application, determining the learned time period according to the target learning time includes:
Determining the time length of the target learning time and the current time according to the target learning time;
and determining the learned time according to the relation between the time length and the preset time length threshold value.
In the present application, determining course quality of a target course according to learning time information and click amount information, includes:
determining the learning amount information of all target students who learn the target course and the target course in the target time period, wherein the learning amount information comprises the learning amount of each student in all target students to the target course;
determining target students in the whole target students according to learning amount information of the whole target students on the target courses in a target time period, wherein the target time period is obtained according to learning time information;
according to the learning time information and the click quantity information, acquiring the learning time length, the learning times and the course completion rate of a target course by a target student;
determining the preference degree of a target learner for a target course according to the learning duration, the learning times and the course completion rate;
and determining the course quality of the target courses, which is characterized by the target students, according to the preference degree.
In the present application, determining a target learner from among the overall target students based on learning amount information of the overall target learner for the target course in the target time period, includes:
Segmenting the time of the learning target course according to the learning time information and the current time to obtain a target time period;
according to the learning amount information of the whole target students on the target courses in the target time period, determining the learning amount of each student in the whole target students on the target courses and the average learning amount of the whole target students on the target courses;
and determining target students in the whole target students according to the relation between the learning amount and the average learning amount.
In the application, according to the learning time length, the learning times and the course completion rate, determining the preference degree of the target learner for the target course comprises the following steps:
obtaining the average learning duration, the average learning times and the average course completion rate of a target learner on a target learning course, wherein the target learning course is the learning course learned by the target learner;
and determining the preference degree of the target learner for the target course according to the relation between the learning duration and the average learning duration, the relation between the learning times and the average learning times and the relation between the course completion rate and the course average completion rate.
In a second aspect, the present application provides a course recommendation method, including:
obtaining the student attribute of a platform login student;
Inputting the student attributes into a target training model to obtain a target recommended course;
and pushing the target recommended course to the terminal equipment of the platform login student.
In a third aspect, the present application provides a model training apparatus comprising:
the first acquisition module is used for acquiring an initial training sample, wherein the initial training sample comprises a learner, a learner attribute, a learning time and a learning course, the learning course is a course learned by the learner, and the learning time is the time for the learner to learn the learning course;
the first determining module is used for determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in the learning courses;
the second determining module is used for determining learning time information and click rate information of the target course according to the training sample to be optimized;
the third determining module is used for determining the course quality of the target course according to the learning time information and the click quantity information;
the screening module is used for screening the initial training samples according to the course quality to obtain target training samples;
and the training module is used for training the model to be trained by taking the learner attribute in the target training sample as an input item and taking the learning course in the target training sample as a label to obtain a target training model.
In a fourth aspect, the present application provides a course recommendation apparatus, including:
the second acquisition module is used for acquiring the student attribute of the platform login student;
the obtaining module is used for inputting the student attributes into the target training model to obtain a target recommended course;
and the pushing module is used for pushing the target recommended course to the terminal equipment of the platform login student.
In a fifth aspect, the present application provides an electronic device, comprising: a processor, a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of the present application.
In a sixth aspect, the present application provides a computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of the application.
According to the model training method, the course recommending method, the device, the equipment and the storage medium, an initial training sample is obtained, the initial training sample comprises a learner, a learner attribute, learning time and a learning course, wherein the learning course is a course learned by the learner, and the learning time is the learning course learning time of the learner; determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in learning courses; determining learning time information and click rate information of a target course according to a training sample to be optimized; determining course quality of a target course according to the learning time information and the click quantity information; screening the initial training sample according to course quality to obtain a target training sample; the training method comprises the steps of taking a learner attribute in a target training sample as an input item, taking a learning course in the target training sample as a label, training a model to be trained to obtain a means of the target training model, screening an initial training sample by determining course quality, so that the target training sample meeting the requirement of course quality can be obtained, training the model to be trained by the target training sample, and enabling the use effect of the target training model obtained after training to be better, and the accuracy of course recommendation to be higher.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic flow chart of a model training method according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a course recommendation method according to an embodiment of the present application;
FIG. 3 is a flowchart of another model training method according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a model training device according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a course recommendation device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
In the prior art, when a course recommendation model is used for course recommendation, the learning platform generally inputs the historical data of the learning platform as a training sample to a model to be trained to obtain the course recommendation model, however, when the historical data is input into the model to be trained as the training sample, the historical data is generally subjected to simple de-duplication processing, and the historical data is not specifically cleaned according to the actual condition of course learning by a learner, so that the accuracy of the recommended course of the obtained course recommendation model is lower, and the actual requirement of the learner cannot be met.
In order to solve the problems, the application provides a model training method, which can evaluate the course quality of a target course by acquiring the learning time information and the click amount information of the target course, and clean the data of an initial training sample according to the course quality, thereby improving the quality of the target training sample input into a model to be trained, improving the training effect, and enabling the target training model obtained after training to more accurately recommend the course according to the attribute of a learner.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The execution subject of the recommendation method provided by the embodiment of the application can be a server. The server can be a mobile phone, a tablet, a computer and other devices. The implementation manner of the execution body is not particularly limited in this embodiment, as long as the execution body can obtain an initial training sample, where the initial training sample includes a learner, a learner attribute, a learning time and a learning course, and the learning course is a course learned by the learner, and the learning time is a time for the learner to learn the learning course; determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in learning courses; determining learning time information and click rate information of a target course according to a training sample to be optimized; determining course quality of a target course according to the learning time information and the click quantity information; screening the initial training sample according to course quality to obtain a target training sample; training the model to be trained by taking the student attributes in the target training sample as input items and taking the learning courses in the target training sample as labels to obtain a target training model; the student attribute of a platform login student can be obtained; inputting the student attributes into a target training model to obtain a target recommended course; and pushing the target recommended course to the terminal equipment of the platform login student.
Among them, machine Learning (ML) is a multi-domain interdisciplinary, and involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, and computational complexity theory. Is a multi-field intersection subject, and relates to a plurality of subjects such as probability theory, statistics, approximation theory, convex analysis, calculation complexity theory and the like. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.
Fig. 1 is a schematic flow chart of a model training method according to an embodiment of the present application. The implementation body of the method may be a server or other servers, and the embodiment is not particularly limited herein, as shown in fig. 1, and the method may include:
s101, acquiring an initial training sample, wherein the initial training sample comprises a learner, a learner attribute, a learning time and a learning course, the learning course is a course learned by the learner, and the learning time is the time for the learner to learn the learning course.
The initial training sample can be a sample for model training, can be obtained from historical data information of a learning platform, and can also be obtained according to the setting of staff. In an embodiment of the present application, the initial training samples may include: the trainees, trainee attributes, learning time and learning courses, for example, the initial training sample may be "Zhang san, new employee, communication engineering specialty, 24 years old, master, wireless communication post, 2021, 3 months, 30 # 9:00-10:00, cloud computing technology course ID).
The learner may refer to a learner who performs course learning using the learning platform, and in the embodiment of the present application, the learner in the initial training sample may include an ID (I Dentity, identification number) of the learner
The student attribute may refer to attribute information of a student, and in the embodiment of the present application, the attribute information may include information such as an academic, a post, an job entering situation, and the like.
The learning course may refer to a course that a learner learns within a learning platform. In an embodiment of the present application, the learning course in the initial training sample may include an ID of the learning course.
The learning time may refer to the time for a learner to learn a learning course, and in the embodiment of the present application, the learning time may be "xxxxxx yy month zz day, aa: bb ~ cc: dd ", wherein each learner may have a plurality of learning times for the learning course, and the number of learning times may characterize the amount of clicks the learner has on the learning course.
In an embodiment of the present application, the method for obtaining an initial training sample may include:
acquiring historical data information;
according to the historical data information, determining a historical learning course, a historical student attribute and a historical learning time;
determining availability of a history learning course;
Determining a learner, a learner attribute, a learning time and a learning course from the historical learning course according to the availability of the historical learning course;
and obtaining an initial training sample according to the trainees, the trainee attributes, the learning time and the learning courses.
The historical data information can be records of the students stored in the learning platform during learning.
The history learning course, the history learner who learns the history learning course, the history learner attribute, and the history learning time may refer to a learning history record for all or part of the learner in the history data information.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, displayed data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.
The availability may refer to whether the history learning course can be normally played due to the reasons of taking off the shelf, damage, authority limitation, and the like, and when the history learning course can be normally played, the history learning course has availability.
After determining the availability of the history learning course, the history learning course having no availability, and the history learner, the history learner attribute, and the history learning time corresponding to the history learning course having no availability may be deleted, whereby an initial training sample may be obtained.
S102, determining a training sample to be optimized in an initial training sample, wherein the training sample to be optimized is the initial training sample containing a target course, and the target course is a target course in a learning course;
s103, according to the training sample to be optimized, determining learning time information and click rate information of the target course.
The target course may be a learning course arbitrarily selected from the initial training sample. After the target course is determined, a learner who learns the target course and learning time can be determined, so that a training sample to be optimized can be obtained.
The learning time information may refer to a learning time period and a learning time point of a target course by a learner. The click volume information may refer to the number of clicks a learner has on a target course.
S104, determining the course quality of the target course according to the learning time information and the click quantity information.
Wherein the course quality may characterize the extent to which the target course is worth being recommended.
In the embodiment of the application, the method for determining the course quality of the target course according to the learning time information and the click quantity information can comprise the following steps:
determining the effective clicked quantity, the total learning duration and the target learning time of the target course according to the learning time information and the click quantity information;
determining the learned quantity according to the effective clicked quantity and the total learning duration;
determining the learned time according to the target learning time;
and determining the course quality according to the learned quantity and the learned time.
The effective clicked amount may refer to the number of clicks that the time after the learner clicks on the target course exceeds the preset time.
The total learning duration may refer to the total time that the target course is learned.
The target learning time may refer to the time the target course was last clicked from the current time.
The learned amount may refer to an index that the target course is effectively learned, and the learned amount may be determined by the effective clicked amount and the total learning duration.
The learned timeliness may refer to whether the target course was learned by a point in the last period of time.
In the embodiment of the application, the method for determining the learned quantity according to the effective clicked quantity and the total learning duration can comprise the following steps:
Obtaining the effective clicked rate of the learning course according to the effective clicked amount;
and determining the learned quantity according to the relation between the effective clicked rate and a preset effective click rate threshold value and the relation between the total learning duration and a preset total learning duration threshold value.
Wherein the effective clicked rate can be obtained by the effective click rate of the target course and the total click rate of the target course.
The preset effective click rate threshold may be an effective clicked rate threshold preset by a worker. The preset total learning duration threshold may be a total learning duration threshold preset by a worker.
In the embodiment of the application, if the effective clicked rate exceeds the preset effective clicked rate threshold value and/or the total learning duration exceeds the preset total learning duration threshold value, the learned quantity can be determined to meet the requirement. If the effective clicked rate does not exceed the preset effective click rate threshold value and the total learning duration does not exceed the preset total learning duration threshold value, the learned quantity is determined to be unsatisfactory.
In the embodiment of the present application, the method for obtaining the effective clicked rate of the learning course according to the effective clicked rate may include:
determining an invalid clicked quantity according to the valid clicked quantity;
And determining the effective clicked rate according to the effective clicked amount and the ineffective clicked amount.
The invalid clicked amount refers to the number of clicks that the time after the learner clicks on the target course does not exceed the preset time.
In an embodiment of the present application, the method for determining the learned time according to the target learning time may include:
determining the time length of the target learning time and the current time according to the target learning time;
and determining the learned time according to the relation between the time length and the preset time length threshold value.
The preset time length threshold may be a time length threshold preset by a worker.
In the embodiment of the present application, the following formula may be used:
the amount to be learned is determined.
Where j represents the learner number of the learning target course.
Y j Representing a valid click of a target course by a learner, in an embodiment of the present application:
t k1,j representing the learning duration of a learner on a target course;
t0 represents a preset time after a learner clicks on a target course;
Z j representing invalid clicks of a learner on a target course, in an embodiment of the present application:
TH1 represents a preset effective click rate threshold;
t1 represents a preset total learning duration threshold.
The formula can be used: b=max { t 2-newwt k1 -t3,0}, determining a learned age.
Wherein t2 represents the current time;
newt k1 representing a target learning time;
t3 represents a preset time length threshold.
After the learned amount and the learned time period are obtained, the course quality of the target course can be determined by f1=a+b. In the embodiment of the present application, if f1=0, the learned amount of the characterization target course is low and the timeliness is low, and when executing step 105, the training sample to be optimized with the target course may be deleted from the initial training sample.
In the embodiment of the application, the method for determining the course quality of the target course according to the learning time information and the click quantity information can comprise the following steps:
determining the learning amount information of all target students who learn the target course and the target course in the target time period, wherein the learning amount information comprises the learning amount of each student in all target students to the target course;
determining target students in the whole target students according to learning amount information of the whole target students on the target courses in a target time period, wherein the target time period is obtained according to learning time information;
according to the learning time information and the click quantity information, acquiring the learning time length, the learning times and the course completion rate of a target course by a target student;
Determining the preference degree of a target learner for a target course according to the learning duration, the learning times and the course completion rate;
and determining the course quality of the target courses, which is characterized by the target students, according to the preference degree.
Where the entire target learner may refer to all the students who learn the target course.
The learning amount information may refer to a learning time and a learning duration of the target course by each of the entire target students.
The target trainee may refer to a trainee whose learning amount in the target period is greater than the average learning amount of the target course by the entire target trainee.
The target time period may refer to a time period determined according to the division of the learning time information and the current time, for example, the target time period may be divided in units of months or days, thereby obtaining a plurality of time periods. The target time period may be one of a plurality of time periods.
The course completion rate may refer to a relationship between a length of time the target learner is learning the target course and a length of time of the target course.
The preference degree can represent the learning times and course completion rate of the target course by the target student, and when the learning times and course completion rate of the target course are higher, the preference degree of the target course by the target student is higher.
In the embodiment of the present application, the method for determining the target trainees in the overall target trainees according to the learning amount information of the overall target trainees on the target courses in the target time period may include:
segmenting the time of the learning target course according to the learning time information and the current time to obtain a target time period;
according to the learning amount information of the whole target students on the target courses in the target time period, determining the learning amount of each student in the whole target students on the target courses and the average learning amount of the whole target students on the target courses;
and determining target students in the whole target students according to the relation between the learning amount and the average learning amount.
The learning amount may refer to the number of clicks on the target course by each of the target students in the whole target students in the target time period.
The average learning amount may refer to an average number of clicks on the target course by all of the target trainees in the target time period.
In the embodiment of the application, the method for determining the preference degree of the target learner for the target course according to the learning duration, the learning times and the course completion rate may include:
obtaining the average learning duration, the average learning times and the average course completion rate of a target learner on a target learning course, wherein the target learning course is the learning course learned by the target learner;
And determining the preference degree of the target learner for the target course according to the relation between the learning duration and the average learning duration, the relation between the learning times and the average learning times and the relation between the course completion rate and the course average completion rate.
The target learning course may refer to a learning course learned by the target learner, wherein the target learning course may include the target course. In the embodiment of the application, the target learning course can be obtained according to the initial training sample.
The average learning period may refer to an average period for which the target learner learns the target learning course.
The average number of learning may refer to an average number of clicks of the target learner on the target learning course.
The average course completion rate may refer to an average completion rate of a target learner learning a target learning course.
In the embodiment of the present application, the following formula may be used:a target learner of the population of target students is determined.
Wherein, |M q The i represents the number of courses that learner q learns over a period of time;
n is a preset constant, and in the embodiment of the present application, n may be 3;
q represents the number of overall target trainees.
After determining the target trainee, the formula may be:
and determining the preference degree of the target learner for the target course.
Wherein TS q,r Representing the total duration of learning for the target course r;
M q,r representing the total number of learning for the target course r;
CT r to represent the course duration of the target course r; r represents a target learning course learned by a target person;
the α, β, γ may be constant coefficients set in advance.
In the embodiment of the present application, after determining the preference degree of the target learner for the target course, if f2=0, it may be determined that the preference degree of the target learner for the target course does not meet the requirement, the target course is a low-quality course for the target learner, and when executing step 105, the training sample to be optimized with the target course and the target learner may be deleted from the initial training sample.
S105, screening the initial training samples according to the course quality to obtain target training samples.
The screening process may refer to a process of retaining or deleting the target course according to the course quality of the target course.
In the embodiment of the application, each learning course in the initial training sample can be respectively used as a target course, and step 104 is executed, so that the initial training sample is screened to obtain the target training sample.
S106, training the model to be trained by taking the learner attribute in the target training sample as an input item and taking the learning course in the target training sample as a label to obtain a target training model.
The model to be trained can be a neural network model, and training is carried out on the model to be trained by taking the learner attribute in the target training sample as an input item and taking the learning course as a label, so that the weight of each input item is continuously adjusted by the model to be trained until the output result of the model to be trained meets the expected requirement, and the target training model can be obtained.
In an embodiment of the present application, the target training model may be obtained by training through the data mining software IBM SPSS Statistics by inputting the learner attribute and the learning course into the data mining software IBM SPSS Statistics.
According to the model training method provided by the application, the initial training sample can be screened by determining the course quality, so that the target training sample meeting the requirement of the course quality can be obtained, and the target training sample is used for training the model to be trained, so that the target training model obtained after training has a better use effect, and the accuracy of course recommendation is higher, thereby improving the training effect of the model to be trained.
Fig. 2 is a schematic flow chart of a course recommendation method according to an embodiment of the present application. The implementation body of the method may be a server or other servers, and the embodiment is not particularly limited herein, as shown in fig. 2, and the method may include:
S201, obtaining the student attribute of the platform login student.
S202, inputting the student attributes into a target training model to obtain a target recommended course.
S203, pushing the target recommended course to terminal equipment of the platform login student.
The platform login learner can refer to a learner target recommended course logging in the learning platform. After a learner logs in the platform, the learning platform can obtain the learner attribute of the learner logged in the platform after the authority of the learner, input the learner attribute into the target training model, obtain the target recommended course through the target training model, and push the target recommended course to the terminal equipment of the learner logged in the platform.
Fig. 3 is a flow chart of another model training method provided in the embodiment of the present application, the execution subject of the method may be a computer, and the embodiment is not particularly limited herein, as shown in fig. 3, the method may include:
s301, acquiring historical learning data in a learning platform.
The historical learning data may be data within a preset time range, for example, may be data within two years.
The history learning data may include: r1= { student unique identification ID, learning time, learning course unique identification }, r2= { student unique identification, student attribute 1, student attribute 2, student attribute 3, … }, r3= { course unique identification ID, course attribute 1, course attribute 2, course attribute 3, … }.
S302, obtaining an initial training data set according to the historical learning data.
The initial training data may be r0= { learner ID, learner attribute 1, learner attribute 2, learner attribute 3, …, learning time, learning course ID }.
After R1 and R2 are obtained, R1 and R2 are filled into R0 to obtain initial training data, for example, the initial training data may be { Zhang san, new employee, communication engineering specialty, 24 years old, master, wireless communication post, 2021, 3 months No. 30 9:00-10:00, cloud computing technology course ID }.
In the embodiment of the application, each learning course ID may correspond to a plurality of pieces of initial training data, and the plurality of pieces of initial training data of the plurality of learning course IDs constitute an initial training data set.
After the initial training data set is obtained, the same initial training data in the initial training data set can be subjected to de-duplication processing, and meanwhile, the initial training data with invalid courses can be subjected to deletion processing, so that the processed initial training data set is obtained.
In the embodiment of the application, the invalid courses can comprise courses which cannot be played.
S303, determining course quality of courses in the initial training data set;
and S304, optimizing the initial training data set according to the course quality to obtain a target training set.
The course quality can be determined according to the learning quantity index and the learning preference degree.
In the embodiment of the application, the learning quantity index can comprise a learning quality index and a timeliness index, wherein the learning quality index can represent the duration of learning when a course is opened and the opening times, and can represent that the learning quality of the course does not meet the quality requirement when the opening times of the course are less and the learning time after the course is opened is shorter. Wherein, the learning quality index can be calculated by the formula:
and (5) determining.
Wherein by means ofThe learning times meeting the duration requirement of the course and whether all times of learning the course meet the preset proportion can be determined;
by passing throughIt may be determined whether the learning duration of each learner learning the course meets the preset duration requirement. />
Wherein, when a=0, the learning quality characterizing the learning course is low.
The timeliness index can be calculated by the formula: b=max { t 2-newwt k1 -t3,0 }.
Wherein by max { t 2-newwt ] k1 -t3,0} can determine whether a lesson exists within a time frame of t3, and when the learning record is stored, then characterize that the lesson meets the timeliness index.
When f1=0, the learning preference degree indicates that the learning quantity index does not meet the preset learning quantity index requirement.
In the embodiment of the application, the learning preference degree can be calculated by the following formula:
it is determined whether the learner is a high learning amount learner during the time period. When the learner is a large learning amount learner, the formula may be as follows:
and determining the learning preference degree of the course.
Wherein it can pass throughDetermining the relation between the duration of learning a course and the average duration of learning all courses;
can pass throughThe relation between the times of clicking one course and the average times of clicking all courses can be determined;
can pass throughAnd determining the relation between the times of learning a course and the average times of learning all courses.
When f2=0, the index of the characteristic learning amount does not meet the preset learning preference degree requirement.
In the embodiment of the application, after the learning amount index and the learning preference degree are determined, a course which simultaneously accords with the learning amount index condition and the learning preference degree condition can be selected as a target course according to the learning amount index and the learning preference degree, and a course which accords with the learning amount index condition or the learning preference degree condition can also be selected as a target course.
Thus, a target training set can be selected from the initial training data set.
S305, training the initial model according to the target training set to obtain a course recommendation model.
In the embodiment of the application, the target training set can be input into the model for training, and the course recommendation model is obtained by adjusting the parameters of each variable. After the course recommendation model is obtained, the learning platform can recommend courses to the students according to the student attributes of the students.
According to the model training method provided by the embodiment of the application, the data can be optimized based on the characteristics of the historical learning data and in combination with factors such as the data recording time, the time length and the self-adaptive optimization of a learner, invalid data and low-quality data in the historical learning data are removed, so that the quality of the data for model training is higher, and the model training effect is improved.
Fig. 4 is a schematic structural diagram of a model training device according to an embodiment of the present application. As shown in fig. 4, the model training apparatus 40 includes: a first acquisition module 401, a first determination module 402, a second determination module 403, a third determination module 404, a screening module 405, and a training module 406. Wherein:
the first obtaining module 401 is configured to obtain an initial training sample, where the initial training sample includes a learner, a learner attribute, a learning time, and a learning course, the learning course is a course learned by the learner, and the learning time is a time for the learner to learn the learning course;
A first determining module 402, configured to determine a training sample to be optimized in the initial training samples, where the training sample to be optimized is an initial training sample including a target course, and the target course is a target course in the learning courses;
a second determining module 403, configured to determine learning time information and click rate information of the target course according to the training sample to be optimized;
a third determining module 404, configured to determine a course quality of the target course according to the learning time information and the click quantity information;
the screening module 405 is configured to perform screening processing on the initial training sample according to the course quality, so as to obtain a target training sample;
the training module 406 is configured to train the model to be trained by using the learner attribute in the target training sample as an input item and the learning course in the target training sample as a label, so as to obtain a target training model. In an embodiment of the present application, the first obtaining module 401 may be further specifically configured to:
acquiring historical data information;
according to the historical data information, determining a historical learning course, a historical student attribute and a historical learning time;
determining availability of a history learning course;
determining a learner, a learner attribute, a learning time and a learning course from the historical learning course according to the availability of the historical learning course;
And obtaining an initial training sample according to the trainees, the trainee attributes, the learning time and the learning courses.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
determining the effective clicked quantity, the total learning duration and the target learning time of the target course according to the learning time information and the click quantity information;
determining the learned quantity according to the effective clicked quantity and the total learning duration;
determining the learned time according to the target learning time;
and determining the course quality according to the learned quantity and the learned time.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
obtaining the effective clicked rate of the learning course according to the effective clicked amount;
and determining the learned quantity according to the relation between the effective clicked rate and a preset effective click rate threshold value and the relation between the total learning duration and a preset total learning duration threshold value.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
determining an invalid clicked quantity according to the valid clicked quantity;
and determining the effective clicked rate according to the effective clicked amount and the ineffective clicked amount.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
Determining the time length of the target learning time and the current time according to the target learning time;
and determining the learned time according to the relation between the time length and the preset time length threshold value.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
determining the learning amount information of all target students who learn the target course and the target course in the target time period, wherein the learning amount information comprises the learning amount of each student in all target students to the target course;
determining target students in the whole target students according to learning amount information of the whole target students on the target courses in a target time period, wherein the target time period is obtained according to learning time information;
according to the learning time information and the click quantity information, acquiring the learning time length, the learning times and the course completion rate of a target course by a target student;
determining the preference degree of a target learner for a target course according to the learning duration, the learning times and the course completion rate;
and determining the course quality of the target courses, which is characterized by the target students, according to the preference degree.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
Segmenting the time of the learning target course according to the learning time information and the current time to obtain a target time period;
according to the learning amount information of the whole target students on the target courses in the target time period, determining the learning amount of each student in the whole target students on the target courses and the average learning amount of the whole target students on the target courses;
and determining target students in the whole target students according to the relation between the learning amount and the average learning amount.
In an embodiment of the present application, the third determining module 404 may be further specifically configured to:
obtaining the average learning duration, the average learning times and the average course completion rate of a target learner on a target learning course, wherein the target learning course is the learning course learned by the target learner;
and determining the preference degree of the target learner for the target course according to the relation between the learning duration and the average learning duration, the relation between the learning times and the average learning times and the relation between the course completion rate and the course average completion rate.
As can be seen from the above, the model training device of the present embodiment is configured to obtain, by the first obtaining module 401, an initial training sample, where the initial training sample includes a learner, a learner attribute, a learning time and a learning course, the learning course is a course learned by the learner, and the learning time is a time for the learner to learn the learning course; the first determining module 402 is configured to determine a training sample to be optimized in the initial training samples, where the training sample to be optimized is an initial training sample including a target course, and the target course is a target course in the learning courses; a second determining module 403, configured to determine learning time information and click rate information of the target course according to the training sample to be optimized; a third determining module 404, configured to determine a course quality of the target course according to the learning time information and the click rate information; the screening module 405 is configured to perform screening processing on the initial training sample according to the course quality, so as to obtain a target training sample; the training module 406 is configured to train the model to be trained by using the learner attribute in the target training sample as an input item and the learning course in the target training sample as a label, so as to obtain a target training model. Thereby, the effect of model training is improved.
Fig. 5 is a schematic structural diagram of a course recommendation device according to an embodiment of the present application. As shown in fig. 5, the course recommendation device 50 includes: a second obtaining module 501, an obtaining module 502 and a pushing module 503.
Wherein:
a second obtaining module 501, configured to obtain a learner attribute of a platform login learner;
the obtaining module 502 is configured to input a learner attribute to a target training model to obtain a target recommended course;
and the pushing module 503 is configured to push the target recommended course to the terminal device of the platform login student.
As can be seen from the above, the course recommendation device of the present embodiment is configured to obtain the learner attribute of the platform login learner by using the second obtaining module 501; the obtaining module 502 is configured to input a learner attribute to a target training model to obtain a target recommended course; and the pushing module 503 is used for pushing the target recommended course to the terminal equipment of the platform login student. Therefore, the recommended course is more accurate.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device 60 includes:
the electronic device 60 may include one or more processing cores 'processors 601, one or more computer-readable storage media's memory 602, communication components 603, and the like. The processor 601, the memory 602, and the communication section 603 are connected via a bus 604.
In a specific implementation, at least one processor 601 executes computer-executable instructions stored in memory 602, causing at least one processor 601 to perform the model training method and the course recommendation method as described above.
The specific implementation process of the processor 601 may refer to the above-mentioned method embodiment, and its implementation principle and technical effects are similar, and this embodiment will not be described herein again.
In the embodiment shown in fig. 6, it should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or may be other general purpose processors, digital signal processors (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuits (english: application Specific Integrated Circuit, abbreviated as ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
The Memory may comprise high-speed Memory (Random Access Memory, RAM) or may further comprise Non-volatile Memory (NVM), such as at least one disk Memory.
The bus may be an industry standard architecture (Industry Standard Architecture, ISA) bus, an external device interconnect (Peripheral Component, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, the buses in the drawings of the present application are not limited to only one bus or to one type of bus.
In some embodiments, a computer program product is also presented, comprising a computer program or instructions which, when executed by a processor, implement the steps of any of the model training methods or course recommendation methods described above.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, embodiments of the present application provide a computer readable storage medium having stored therein a plurality of instructions capable of being loaded by a processor to perform steps in any one of the model training methods or the course recommendation methods provided by the embodiments of the present application.
Wherein the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
According to one aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium.
Because the instructions stored in the storage medium can execute steps in any model training method or course recommendation method provided by the embodiment of the present application, the beneficial effects that can be achieved in any model training method or course recommendation method provided by the embodiment of the present application can be achieved, which are detailed in the previous embodiments and are not described herein.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (14)
1. A model training method applied to a learning platform, the method comprising:
acquiring an initial training sample, wherein the initial training sample comprises a learner, a learner attribute, a learning time and a learning course, the learning course is a course learned by the learner, and the learning time is the time for the learner to learn the learning course;
determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in the learning courses;
determining learning time information and click rate information of the target course according to the training sample to be optimized;
determining course quality of the target course according to the learning time information and the click quantity information;
screening the initial training sample according to the course quality to obtain a target training sample;
And training the model to be trained by taking the learner attribute in the target training sample as an input item and taking the learning course in the target training sample as a label to obtain a target training model.
2. The method of claim 1, wherein the obtaining initial training samples comprises:
acquiring historical data information;
according to the historical data information, determining a historical learning course, a historical student attribute and a historical learning time;
determining availability of the historic learning course;
determining the learner, the learner attribute, the learning time, and the learning course from the historical learning course according to the availability of the historical learning course;
and obtaining the initial training sample according to the learner, the learner attribute, the learning time and the learning course.
3. The method of claim 1, wherein said determining a course quality of said target course based on said learning time information and said click volume information comprises:
determining the effective clicked quantity, the total learning duration and the target learning time of the target course according to the learning time information and the click quantity information;
Determining the learned quantity according to the effective clicked quantity and the total learning duration;
determining the learned time according to the target learning time;
and determining the course quality according to the learned quantity and the learned time.
4. A method according to claim 3, wherein said determining a learned volume from said effective clicked volume and said total learning duration comprises:
obtaining the effective clicked rate of the learning course according to the effective clicked amount;
and determining the learned quantity according to the relation between the effective clicked rate and a preset effective click rate threshold value and the relation between the total learning duration and a preset total learning duration threshold value.
5. The method of claim 4, wherein said deriving an effective clickthrough rate for the learning course based on the effective clickthrough amount comprises:
determining an invalid clicked quantity according to the valid clicked quantity;
and determining the effective clicked rate according to the effective clicked quantity and the ineffective clicked quantity.
6. A method according to claim 3, wherein said determining a learned age based on said target learning time comprises:
Determining the time length of the target learning time and the current time according to the target learning time;
and determining the learned time according to the relation between the time length and a preset time length threshold value.
7. The method of claim 1, wherein said determining a course quality of said target course based on said learning time information and said click volume information comprises:
determining the learning amount information of all target students who learn the target course and the target course in a target time period, wherein the learning amount information comprises the learning amount of each student in the all target students to the target course;
determining target students in the whole target students according to learning amount information of the whole target students for the target courses in a target time period, wherein the target time period is obtained according to the learning time information;
acquiring the learning duration, the learning times and the course completion rate of the target course by the target learner according to the learning time information and the click quantity information;
determining the preference degree of the target learner for the target course according to the learning duration, the learning times and the course completion rate;
And determining the course quality of the target course, which is characterized by the target learner, according to the preference degree.
8. The method of claim 7, wherein the determining a target learner of the overall target learner based on learning amount information of the target lesson by the overall target learner for a target period of time comprises:
segmenting the time for learning the target course according to the learning time information and the current time to obtain a target time period;
determining the learning amount of each learner in the whole target lesson and the average learning amount of the whole target learner in the target lesson according to the learning amount information of the whole target learner in the target time period;
and determining target students in the whole target students according to the relation between the learning amount and the average learning amount.
9. The method of claim 7, wherein the determining the target learner's preference for the target lesson based on the learning duration, the learning number, and the lesson completion rate comprises:
obtaining the average learning duration, the average learning times and the average course completion rate of the target learning courses of the target students, wherein the target learning courses are the learning courses learned by the target students;
And determining the preference degree of the target learner for the target course according to the relation between the learning duration and the average learning duration, the relation between the learning times and the average learning times and the relation between the course completion rate and the course average completion rate.
10. A course recommendation method, the method comprising:
obtaining the student attribute of a platform login student;
inputting the student attributes into a target training model trained by the method according to claims 1-9 to obtain a target recommended course;
and pushing the target recommended course to the terminal equipment of the platform login student.
11. A model training device, comprising:
the first acquisition module is used for acquiring an initial training sample, wherein the initial training sample comprises a learner, a learner attribute, a learning time and a learning course, the learning course is a course learned by the learner, and the learning time is the time for the learner to learn the learning course;
the first determining module is used for determining a training sample to be optimized in the initial training samples, wherein the training sample to be optimized is an initial training sample containing target courses, and the target courses are target courses in the learning courses;
The second determining module is used for determining learning time information and click rate information of the target course according to the training sample to be optimized;
the third determining module is used for determining the course quality of the target course according to the learning time information and the click quantity information;
the screening module is used for screening the initial training sample according to the course quality to obtain a target training sample;
and the training module is used for training the model to be trained by taking the student attributes in the target training sample as input items and taking the learning courses in the target training sample as labels to obtain a target training model.
12. A course recommendation device, comprising:
the second acquisition module is used for acquiring the student attribute of the platform login student;
the obtaining module is used for inputting the student attributes into a target training model obtained by training by the method of claims 1-9 to obtain a target recommended course;
and the pushing module is used for pushing the target recommended course to the terminal equipment of the platform login student.
13. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
The memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 10.
14. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310623343.2A CN116595378A (en) | 2023-05-30 | 2023-05-30 | Model training method, course recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310623343.2A CN116595378A (en) | 2023-05-30 | 2023-05-30 | Model training method, course recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116595378A true CN116595378A (en) | 2023-08-15 |
Family
ID=87611492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310623343.2A Pending CN116595378A (en) | 2023-05-30 | 2023-05-30 | Model training method, course recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116595378A (en) |
-
2023
- 2023-05-30 CN CN202310623343.2A patent/CN116595378A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110147456B (en) | Image classification method and device, readable storage medium and terminal equipment | |
| CN109740048B (en) | Course recommendation method and device | |
| CN109783632A (en) | Customer service information-pushing method, device, computer equipment and storage medium | |
| CN110377814A (en) | Topic recommended method, device and medium | |
| US9501580B2 (en) | Method and apparatus for automated selection of interesting content for presentation to first time visitors of a website | |
| CN111177413A (en) | Learning resource recommendation method and device and electronic equipment | |
| RU2680746C2 (en) | Method and device for developing web page quality model | |
| CN110851718B (en) | Movie recommendation method based on long and short term memory network and user comments | |
| CN104834731A (en) | Recommendation method and device for self-media information | |
| Reiter | Using statistics to determine causal relationships | |
| CN116204714A (en) | Recommendation method, recommendation device, electronic equipment and storage medium | |
| CN115841402A (en) | Digital training method, system, medium and equipment for safety production | |
| CN112069329B (en) | Text corpus processing method, device, equipment and storage medium | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN110275779B (en) | Resource acquisition method, device, equipment and storage medium | |
| CN113407831B (en) | Course recommendation method and device | |
| CN116541711A (en) | Model training method, course recommendation method, device, equipment and medium | |
| CN109377103B (en) | Evaluation method and device for course recommendation of learning platform | |
| Gao et al. | Forecasting elections with agent-based modeling: Two live experiments | |
| CN110309411A (en) | A kind of resource recommendation method and device | |
| CN108733784B (en) | Teaching courseware recommendation method, device and equipment | |
| CN116595378A (en) | Model training method, course recommendation method, device, equipment and storage medium | |
| Mosthaf | Low-wage jobs-stepping stones or just bad signals? | |
| CN112734142B (en) | Resource learning path planning method and device based on deep learning | |
| CN112231373B (en) | Knowledge point data processing method, apparatus, device and computer readable 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 |