CN114048377A - Topic recommendation method and device, electronic equipment and storage medium - Google Patents

Topic recommendation method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114048377A
CN114048377A CN202111323672.2A CN202111323672A CN114048377A CN 114048377 A CN114048377 A CN 114048377A CN 202111323672 A CN202111323672 A CN 202111323672A CN 114048377 A CN114048377 A CN 114048377A
Authority
CN
China
Prior art keywords
learning
target user
value
curve
target
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.)
Granted
Application number
CN202111323672.2A
Other languages
Chinese (zh)
Other versions
CN114048377B (en
Inventor
李程
李翌昕
张维晨
林辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Netease Youdao Information Technology Beijing Co Ltd
Original Assignee
Netease Youdao Information Technology Beijing Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Netease Youdao Information Technology Beijing Co Ltd filed Critical Netease Youdao Information Technology Beijing Co Ltd
Priority to CN202111323672.2A priority Critical patent/CN114048377B/en
Publication of CN114048377A publication Critical patent/CN114048377A/en
Application granted granted Critical
Publication of CN114048377B publication Critical patent/CN114048377B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • 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)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides a topic recommendation method, a topic recommendation device, electronic equipment and a storage medium. The method comprises the following steps: determining the current learning capacity value of the target user; determining the difficulty of the question matched with the target user according to the learning ability value; acquiring a learning target of the target user in a preset time period, and generating a learning path curve for representing the change trend of the learning capacity value of the target user along with time in the preset time period according to the learning target; determining the number of questions matched with the target user according to the learning path curve; and recommending titles to the target users according to the difficulty and the number. The scheme of the application can effectively realize personalized question recommendation, is high in accuracy, and can practically improve learning efficiency and learning effect.

Description

Topic recommendation method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a topic recommendation method and apparatus, an electronic device, and a storage medium.
Background
With the continuous popularization of computer technology and the rapid development of information technology, the way of acquiring knowledge has changed fundamentally, and the way of education based on network has been gradually known and accepted. An online learning question recommendation system, an online examination system and the like are used as an education auxiliary platform, and a large number of students and teacher users are won by using a convenient and practical learning method with massive question resources.
In the existing online learning question recommendation scheme, when a user is recommended questions, a fixed recommendation strategy is often used for recommendation, so that the learning requirements of different users cannot be effectively matched, and the problems of insufficient accuracy, low learning efficiency and poor learning effect of the existing question recommendation scheme are caused.
Disclosure of Invention
In view of the above technical problems, there is a need for an improved scheme, which can effectively improve the problem recommendation accuracy and correspondingly improve the learning efficiency and learning effect when performing problem recommendation in an online learning process.
Based on the above purpose, the present application provides a title recommendation method, including:
determining the current learning capacity value of the target user;
determining the difficulty of the question matched with the target user according to the learning ability value;
acquiring a learning target of the target user in a preset time period, and generating a learning path curve for representing the change trend of the learning capacity value of the target user along with time in the preset time period according to the learning target;
determining the number of questions matched with the target user according to the learning path curve;
and recommending titles to the target users according to the difficulty and the number.
In some optional embodiments, the determining the current learning ability value of the target user specifically includes: acquiring historical answer data of the target user and a learning capacity value of the target user after answering the question last time; and calculating the current learning ability value of the target user by adopting a question reaction theory algorithm according to the historical answer data and the learning ability value of the target user after the target user answers the question last time.
In some optional embodiments, the determining, according to the learning ability value, a difficulty of a topic matched with the target user specifically includes: and correspondingly taking the learning ability value as the difficulty of the question matched with the target user based on a question reaction theory algorithm.
In some optional embodiments, the determining, according to the learning ability value, a difficulty of a topic matched with the target user specifically includes: acquiring a preset capacity value interval corresponding to the learning capacity value according to the learning capacity value; and calculating the percentile corresponding to the learning ability value in the ability value interval, and taking the percentile correspondence as the difficulty of the question matched with the target user.
In some optional embodiments, the determining, according to the learning path curve, the number of topics matched with the target user specifically includes: determining a capacity value median curve corresponding to the capacity value interval; calculating a first differential value of the learning path curve; calculating a second difference value on the position corresponding to the starting point of the learning path curve on the potential value median curve; and determining the number of the titles matched with the target user according to the first differential value, the second differential value and a preset standard number.
In some optional embodiments, the obtaining of the learning objective of the target user within a predetermined time period further comprises: determining an upper limit curve and a lower limit curve of the capacity value corresponding to the capacity value interval; and in response to determining that the learning objective does not fall within the range defined by the capacity value upper-bound curve and the capacity value lower-bound curve, feeding back prompt information for prompting that the learning objective is unreasonable to the objective user.
In some optional embodiments, the capacity value upper bound curve, the capacity value middle bound curve, and the capacity value lower bound curve are determined by: acquiring a reference learning ability value of a reference user corresponding to the ability value interval within a certain amount of time period; calculating 95% percentile of all the reference learning capacity values corresponding to each moment in the time period; obtaining the upper bound curve of the capacity value according to the 95% percentile corresponding to all the moments in the time period; for each moment in the time period, calculating 50% percentile of all the reference learning capacity values corresponding to the moment; obtaining a capacity value median curve according to the 50% percentiles corresponding to all the moments in the time period; for each moment in the time period, calculating 5% percentile of all the reference learning capacity values corresponding to the moment; and obtaining the lower bound curve of the capacity value according to the 5% percentile corresponding to all the moments in the time period.
Based on the same inventive concept, an exemplary embodiment of the present application further provides a title recommendation device, including:
a first determination module configured to determine a current learning ability value of the target user;
a second determination module configured to determine a difficulty of a question matched with the target user according to the learning ability value;
the generation module is configured to acquire a learning target of the target user in a preset time period and generate a learning path curve for representing the change trend of the learning capacity value of the target user along with time in the preset time period according to the learning target;
a third determination module configured to determine the number of topics matched with the target user according to the learning path curve;
and the recommending module is configured to recommend the titles to the target users according to the difficulty and the number.
Based on the same inventive concept, the exemplary embodiments of this application also provide an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method as described in any one of the above is implemented.
Based on the same inventive concept, the exemplary embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method as described in any one of the above.
From the above, according to the question recommendation method, the device, the electronic device and the storage medium provided by the application, the learning path reflecting the trend that the learning ability of the user changes along with time is determined based on the learning target of the user, the difficulty and the number of the questions to be recommended to the user are respectively determined according to the ability and the learning path of the user, and the question recommendation is performed to the user based on the determined difficulty and the number, so that the recommended questions can be matched with the learning ability and the learning target of the user, the personalized question recommendation is effectively realized, the accuracy is high, and the learning efficiency and the learning effect can be practically improved.
Drawings
In order to more clearly illustrate the technical solutions in the present application or the related art, the drawings needed to be used in the description of the embodiments or the related art will be briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of an application scenario in an exemplary embodiment of the present application;
FIG. 2 is a schematic flow chart of a topic recommendation method according to an exemplary embodiment of the present application;
FIG. 3 is a diagram illustrating an upper bound curve of a capacity value, a middle bound curve of the capacity value, and a lower bound curve of the capacity value in an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating an unreasonable learning objective of an embodiment of the present application;
FIG. 5 is a graph illustrating a learning path in an embodiment of the present application;
FIG. 6 is a graph illustrating an updated learning path curve in an embodiment of the present application;
FIG. 7 is a schematic structural diagram of a topic recommendation apparatus according to an exemplary embodiment of the present application;
fig. 8 is a schematic diagram of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
The principles and spirit of the present application will be described with reference to a number of exemplary embodiments. It should be understood that these embodiments are given solely for the purpose of enabling those skilled in the art to better understand and to practice the present application, and are not intended to limit the scope of the present application in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
According to an embodiment of the application, a topic recommendation method, a topic recommendation device, an electronic device and a storage medium are provided.
In this document, it is to be understood that any number of elements in the figures are provided by way of illustration and not limitation, and any nomenclature is used for differentiation only and not in any limiting sense.
The principles and spirit of the present application are explained in detail below with reference to several representative embodiments of the present application.
Summary of The Invention
In the existing problem recommendation scheme under the online learning scene, when a user is recommended a problem, the specifically recommended problem is often obtained according to a fixed recommendation strategy, however, the respective specific learning requirements of different users based on different learning abilities, learning stages and learning methods are different. By using a fixed recommendation strategy, different specific learning requirements cannot be met, and the problems of insufficient accuracy, low learning efficiency and poor learning effect of the conventional question recommendation scheme are caused. In addition, in the prior art, some personalized item recommendation methods for different users also exist, but the schemes are only simple and singly considering factors such as the learning ability and the learning stage of the user, and cannot sufficiently meet the learning requirement of the user, and the defects and the problems still exist.
In order to solve the above problem, the present application provides a title recommendation method, specifically including: determining the current learning capacity value of the target user; acquiring a learning target of the target user in a preset time period, and generating a learning path curve for representing the change trend of the learning capacity value of the target user along with time in the preset time period according to the learning target; determining the difficulty of the question matched with the target user according to the learning ability value; determining the number of questions matched with the target user according to the learning path curve; and recommending titles to the target users according to the difficulty and the number. Considering that a learning target is set in a certain time period in the learning process of a user, the realization of the learning target usually means that a better learning effect is realized, and the learning stage and the learning method of the user can be reflected to a certain degree through the learning target. Based on the invention concept, the scheme of the embodiment of the application determines the learning path reflecting the change trend of the learning ability of the user along with time based on the learning target of the user, respectively determines the difficulty and the quantity of the questions to be recommended to the user according to the ability and the learning path of the user, and recommends the questions to the user based on the determined difficulty and the quantity, so that the recommended questions can be matched with the learning ability and the learning target of the user, the personalized question recommendation is effectively realized, the accuracy is high, and the learning efficiency and the learning effect can be practically improved.
Application scene overview
Reference is made to fig. 1, which is a schematic view of an application scenario of a topic recommendation method provided in an embodiment of the present application. The application scenario includes a terminal device 101, a server 102, and a data storage system 103. The terminal device 101, the server 102, and the data storage system 103 may be connected through a wired or wireless communication network. The terminal device 101 includes, but is not limited to, a desktop computer, a mobile phone, a mobile computer, a tablet computer, a media player, a smart wearable device, a Personal Digital Assistant (PDA), or other electronic devices capable of implementing the above functions. The server 102 and the data storage system 103 may be independent physical servers, may also be a server cluster or distributed system formed by a plurality of physical servers, and may also be cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and big data and artificial intelligence platforms.
The server 102 is configured to provide an online learning service for a user of the terminal device 101, and a client in communication with the server 102 is installed in the terminal device 101, through which the user can perform online learning, specifically, perform an answering activity. In the above answering activity, the client acquires the answer-related data (such as learning target, answering data, etc.) input by the user by calling the input component (such as keyboard, microphone, etc.) of the terminal device 101 and transmits the data to the server 102. The data storage system 103 provides data storage support for the work operation of the server 102, such as storing topic data, storing learning ability values of users, storing process data or result data in user answers, and the like. The server 102 may determine the learning ability value of the user and determine the learning path curve of the user according to the learning target of the user, then determine the difficulty and the number of the questions recommended to the user, and return the recommended questions to the terminal device 101 according to the determined difficulty and the number, so that the terminal device 101 generates an answer interface through the client, and the user performs an answer activity.
The title recommendation method according to the exemplary embodiment of the present application is described below with reference to an application scenario of fig. 1. It should be noted that the above application scenarios are only presented to facilitate understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. Rather, embodiments of the present application may be applied to any scenario where applicable.
Exemplary method
Referring to fig. 2, an embodiment of the present application provides a title recommendation method, including the following steps:
and step S201, determining the current learning ability value of the target user.
In this step, the learning ability value of the target user is first determined. Wherein, the target user refers to the user who is currently performing answering activities. The target user is in the continuous answering process, and the current learning ability value of the target user is the learning ability value of the target user after the target user finishes answering the latest question.
In specific implementation, the learning ability value may be data that is determined by any existing evaluation method and is used for reflecting the learning ability of the user, and is not specifically limited in this embodiment.
As an alternative embodiment, an Item Response Theory (IRT) algorithm may be used to obtain the current learning ability value of the target user through calculation. In the IRT algorithm, the current learning ability value of the target user can be calculated through a maximum likelihood estimation statistical algorithm according to the historical answer data of the target user and the learning ability value of the target user after the last answer.
Specifically, using the IRT algorithm, the current learning ability value of the target user can be calculated by the following formula:
Figure BDA0003343572060000071
Figure BDA0003343572060000072
Figure BDA0003343572060000073
in the above formula, θt+1The current learning ability value of the target user is obtained; thetatThe learning ability value of the target user after the last answer is given; d is a constant with a default value of 1.7; n is the number of questions the target user has answered; a isiFor the distinction degree of the current topic, the default value is obtained in this embodimentConsidered to be 1; c. CiThe lower limit value of the current question represents the possibility of guessing the question, and the value is defaulted to 0 in the embodiment; u. ofiSetting time u for right and wrong answer of current answer of target useriValue of 1, u when making a mistakeiThe value is 0; piAnd (4) the probability of making a pair for the current answer of the target user.
Wherein, PiCan be calculated by the following formula:
Figure BDA0003343572060000074
in the above formula, biThe difficulty of the current topic is set for each topic under the IRT algorithm and is represented by a numerical value.
By the above calculation method, the current learning ability value of the target user can be calculated according to the historical answer data of the target user and the learning ability value of the target user after answering the question last time.
And S202, determining the difficulty of the question matched with the target user according to the learning ability value.
In this step, the difficulty of the question to be recommended to the target user is determined based on the current learning ability value of the target user determined in step S201. The specific principle is that the difficulty of the questions to be recommended to the target user is matched with the current learning ability value of the target user; that is, it is not suitable to recommend questions to the user that are too difficult to learn about their ability values, so as to prevent their ability limitations from failing to complete effective answers; it is also not desirable to recommend questions to the user that are simple relative to their learning ability values to prevent the answer from losing the purpose of learning or practice.
As an alternative implementation manner, the difficulty of the topic matching with the target user may be determined based on the learning ability value calculated by the IRT algorithm in the embodiment of step S201.
Specifically, in the IRT algorithm, the topic also has a parameter of information amount. When recommending topics based on the IRT algorithm, generally, the topic with the largest information amount is selected for recommendation. The calculation formula of the information amount of the title is as follows:
Figure BDA0003343572060000081
in the above formula, I is the information amount, and the meanings of a, b, c, D, and θ are the same as the meanings of the corresponding terms in the calculation formula regarding the current learning ability value of the target user in step S201.
When the information quantity takes the maximum value, the following holds:
Figure BDA0003343572060000082
the above formula gives the relationship between the learning ability value and the difficulty of the question under the condition of the maximum information amount. In this embodiment, to further simplify the data processing procedure, the relationship is directly simplified to θ ═ b. That is, after the current learning ability value of the target user in step S201 is obtained, the learning ability value can be directly used as the difficulty of the topic matched with the target user. Correspondingly, for all the alternative topics, each topic is marked with a numerical value corresponding to the learning ability value as the difficulty of the topic. For example, based on the IRT algorithm, if the current learning ability value of the target user is obtained through calculation as 80, the topic with the difficulty of 80 may be correspondingly determined as the topic matched with the target user in the to-be-selected topics, so as to be recommended to the target user in the subsequent steps.
In some cases, when the learning ability value of the target user is calculated through the IRT algorithm, there may be a case where there is no or no possibility of acquiring the historical answer data of the target user and the learning ability value after the last answer. For the case that the historical answer data exists but the learning ability value after the last answer cannot be obtained, the learning ability value of the target user can be determined according to the historical answer data through the correctness or the score of the question, for example, if the answer correctness of the target user is 90% or the score is 90 points, the learning ability value of the target user can be determined to be 90. And for the condition that the historical answer data and the learning ability value after the last answer can not be obtained, determining the user portrait of the target user, matching all users through the user portrait, and taking the learning ability value of the matched user as the learning ability value of the target user correspondingly.
As an optional implementation manner, based on the current learning ability value of the target user obtained by the IRT algorithm, the difficulty of the topic to be recommended to the target user may also be determined according to the position of the current learning ability value of the target user in a predetermined ability value interval. When online learning is performed, the questions are often correspondingly distinguished according to users with different learning ability values, that is, the questions with higher difficulty are provided for users with higher learning ability values, and the questions with lower difficulty are provided for users with lower learning ability values, so that the learning requirements of the users with different learning abilities are met. When users with different learning abilities are divided, segmentation can be performed according to the learning ability values of the users. For example, the range of learning ability values is [0-100], and the total range of learning ability values can be divided into several ranges of learning ability values according to a certain range length. For example, 10 is divided into interval lengths, and each 10 intervals of capability values are formed.
In specific implementation, based on the division of the ability value interval, the ability value interval corresponding to the learning ability value can be determined according to the obtained current learning ability value of the target user. After the current learning ability value of the target user and the corresponding ability value interval are determined, the position of the current learning ability value of the target user in the ability value interval can be determined in a percentile calculation mode. The percentile is a statistical concept, which means that a group of data is sorted from small to large, and a corresponding cumulative percentile is calculated, and the value of the data corresponding to a certain percentile is called the percentile of the percentile. Furthermore, according to the quantile of the current learning ability value of the target user in the corresponding ability value interval, the quantile can be used as the difficulty of the theme matched with the target user. Correspondingly, for all the alternative topics, each topic is marked with a numerical value corresponding to the learning ability value as the difficulty of the topic. For example, the current learning ability value of the target user is 53, the corresponding ability value interval is (50, 60), the quantile of the current learning ability value of the target user in the corresponding ability value interval is 0.3, and correspondingly, the topic with the difficulty of 0.3 is determined as the topic matched with the target user, so as to be recommended to the target user in the subsequent steps.
It can be understood that, as the learning process of the target user proceeds, the learning ability value of the target user is correspondingly updated, and in the subsequent learning, the difficulty of the question matched with the target user is determined in real time according to the latest learning ability value.
In the above description, when setting the capacity value sections, the number of the capacity value sections, the section length, and the like may be set according to implementation needs, and specific numerical values in the foregoing embodiments are merely examples.
Step S203, acquiring a learning target of the target user in a preset time period, and generating a learning path curve for representing the trend of the learning ability value of the target user along with time in the preset time period according to the learning target.
In this step, a learning objective of the target user within a predetermined time period is first obtained, and the learning objective may be submitted by the target user. Specifically, the learning objective is a learning ability value of the user, which is increased from an initial learning ability value to a target learning ability value within a predetermined time period. Based on this, in this embodiment, a learning path curve is generated according to the learning target of the target user within the predetermined time period, and the learning path curve is used to represent the trend of the learning ability value of the target user with time within the predetermined time period. Specifically, the learning objectives of the target user are: the current learning ability value is S0, and it is desired to raise the learning ability value to ST within the time T. The learning path curve of the target user can be expressed as:
Figure BDA0003343572060000101
in the above formula, f _ path is a learning path curve, T is a unit time within T in a predetermined time period, and T is greater than or equal to 0 and less than or equal to T.
And S204, determining the number of the questions matched with the target user according to the learning path curve.
In this step, the number of topics matched with the target user is determined according to the obtained learning path curve of the target user. The capacity value interval in which the current learning capacity value of the target user is located needs to be considered.
As described in the foregoing step S202, the learning ability value may be segmented. And aiming at the capacity value interval corresponding to the current learning capacity value of the target user. A certain number of users can be obtained as reference users, and the learning ability value of the reference users is referred to as a reference learning ability value in this embodiment. And in a certain time period (the time period is greater than or equal to a preset time period in the learning target of the target user), constructing a data set of the reference learning ability values corresponding to the ability value interval for the reference learning ability values of all the reference users of which the reference learning ability values are in the ability value interval. For example, the capacity value interval is (50,60], the data time period in the data set is 30 days, and the data set includes, for each reference user, the reference learning capacity value of the reference user for each of the 30 days.
And respectively calculating an upper limit curve of the capacity value, a middle curve of the capacity value and a lower limit curve of the capacity value in the capacity value interval according to the data set corresponding to the capacity value interval. The ability value upper-bound curve is used for reflecting the learning path (the change trend of the reference learning ability value along with the time) of the reference user with a higher reference learning ability value in the reference users corresponding to the ability value interval; the lower limit curve of the ability value is used for reflecting the learning path of the partial reference user with lower reference learning ability value; the capacity value median curve is used for reflecting the learning path of the reference user with the reference learning capacity value at the average level in the capacity value interval.
Specifically, for the capacity value median curve, for each time within the time period, a 95% percentile of all reference learning capacity values corresponding to the time is calculated. For all the reference users corresponding to the capacity value interval, the reference learning capacity value of each reference user is included at each moment, and for the reference learning capacity values, 95% percentiles of the reference learning capacity values are taken; and after the 95% percentile at each moment is obtained, fitting the 95% percentile at each moment to form a curve, and obtaining the capacity value median curve.
Similar to the obtaining of the middle curve of the capacity value, the 95% percentile and the 5% percentile are respectively taken for all the reference learning capacity values corresponding to each moment, and the upper limit curve and the lower limit curve of the capacity value can be respectively obtained. Taking the capacity value interval as (50, 60) and the time period length as 30 days (the unit time length is 1 day) as an example, the obtained capacity value upper bound curve, capacity value middle bound curve and capacity value lower bound curve can be referred to as shown in fig. 3, where f _ upper, f _ mean and f _ lower respectively represent the capacity value upper bound curve, capacity value middle bound curve and capacity value lower bound curve.
In specific implementation, the ability value upper bound curve, the ability value middle bound curve and the ability value lower bound curve can be used for judging whether the learning target of the target user is reasonable in a preset time period. If the learning target of the target user is reasonable, the number of the questions matched with the target user can be further determined according to the learning path curve of the target user; if the learning target of the target user is unreasonable, feedback prompt needs to be given to the target user, so that the target user can modify the learning target in time.
Specifically, since the learning objective is the learning ability value raised from an initial learning ability value to a goal within a predetermined time period, the learning ability value of the objective to be raised can be compared with the range defined by the upper limit curve and the lower limit curve of the ability value, and if the learning objective falls within the range defined by the upper limit curve and the lower limit curve of the ability value, the learning objective is reasonable; if the learning target does not fall within the range defined by the upper limit curve and the lower limit curve of the capacity value, the learning target is unreasonable. For example, referring to fig. 4, the learning objectives of the target user are: an initial learning ability value of 53, with a desire to raise the learning ability value to 73 over a 20 day period; the corresponding ability value interval is (50, 60), it can be seen that the learning ability value 73 of the target to which the target user wants to be improved exceeds the range defined by the corresponding ability value upper-bound curve and the ability value lower-bound curve, which indicates that the learning target is not reasonable relative to the current learning ability of the target user, prompt information can be fed back to the target user, and the prompt information is used for prompting that the learning target submitted by the target user is not reasonable and needs to be modified.
In specific implementation, if the learning target submitted by the target user is reasonable, the number of the topics matched with the target user can be further determined according to the learning path curve of the target user and the capacity value median curve of the capacity value interval corresponding to the current learning capacity value.
Specifically, the number of topics matched with the target user is related to the gradient of the learning path curve, and the number of topics is determined by adjusting based on the average level of the reference user in the capacity value interval. The step of determining the number of topics matched with the target user may be specifically expressed as: determining a capacity value median curve corresponding to the capacity value interval; calculating a first differential value of the learning path curve; calculating a second difference value on the position corresponding to the starting point of the learning path curve on the potential value median curve; and determining the number of the titles matched with the target user according to the first differential value, the second differential value and a preset standard number.
The process of determining the number of topics is described in detail below with reference to an example. Referring to fig. 5, the learning objectives of the target user are: an initial learning ability value of 53, which is expected to increase to 65 in a 20 day period; the corresponding capacity value interval is (50, 60)]. If the learning ability value 65 of the target that the target user wants to promote falls within the range defined by the ability value upper bound curve and the ability value lower bound curve, and the learning target is reasonable, the learning path curve f _ path of the target user is further obtained according to the method described in the embodiment in step S203. Interval of capacity valueIs (50, 60)]The median curve of the capacity value of (c) is f _ mean. A first differential value f' _ path of the learning path curve f _ path is calculated,
Figure BDA0003343572060000121
accordingly, the second differential value f' _ mean at a position on the median curve f _ mean corresponding to the start point of the learning path curve f _ path, i.e., the slope at that position, is calculated. The second difference value f' _ mean may be calculated in a manner of
Figure BDA0003343572060000122
Where f _ mean (Δ t) is a learning ability value at the next moment from the previous position, f _ mean (0) is a learning ability value at the current position, and Δ t is a unit time length (1 day in this example). Referring to the capability value median curve f _ mean in fig. 5, the second difference value f' _ mean is calculated to be 0.3. According to the obtained first difference value f '_ path and the second difference value f' _ media, the number of titles matched with the target user can be determined in the following manner:
Figure BDA0003343572060000123
wherein N is a standard number of topics, is a predetermined value, and can be determined according to an average level of users. According to the specific numerical values set forth above,
Figure BDA0003343572060000124
it indicates that the learning ability value is higher than the average level when the target user starts the learning target, and can be 70% more based on the number of topics of the standard as the number of topics matched with the target user.
It can be understood that, as the learning process of the target user proceeds, the corresponding learning path curve is updated correspondingly, and in the subsequent learning, the number of the topics matched with the target user is determined according to the updated learning path curve. For example, referring to fig. 6, based on the foregoing example, the learning ability value is raised to 60 after the target user has learned for 10 days. If the learning ability values 53 to 60 are the learning ability values of the target user, the learning ability values 65 of the target are terminated, and the updated learning path curve f _ path is generated, starting with the current learning ability value 60. Based on the updated learning path curve f _ path and the capability value median curve f _ mean, the method as the above example is adopted to respectively calculate the first difference value and the second difference value, and then the number of the topics matched with the target user is determined again.
In addition, along with the progress of the learning process of the target user, if the current learning ability value of the target user exceeds the upper limit value of the current corresponding ability value interval, the target user is relegated to the next higher ability value interval, the learning target and the learning path curve are correspondingly renewed, and the number of the questions matched with the target user is determined according to the latest renewed learning path curve. For example, in addition to the above example, if the learning ability value of the target user is increased to 61 after a certain number of days of learning, the ability value section corresponding to the target user may be updated to (60, 70), the learning path curve may be regenerated, the ability value upper limit curve, the ability value middle limit curve, and the ability value lower limit curve of the ability value section (60, 70) may be calculated accordingly, and the processing such as the determination of the reasonableness of the learning target and the determination of the number of topics matching the target user may be performed.
And S205, recommending titles to the target users according to the difficulty and the number.
In this step, based on the difficulty and the number of the topics determined in the previous steps and matched with the target user, corresponding topics are obtained in a data storage system pre-stored with a large number of topics, and the corresponding topics are recommended to the target user based on the determined difficulty and number.
Therefore, the topic recommendation method in the embodiment of the application determines the learning path reflecting the trend of the learning ability of the user changing with time based on the learning target of the user, determines the difficulty and the number of the topics to be recommended to the user according to the ability and the learning path of the user, and recommends the topics to the user based on the determined difficulty and the number, so that the recommended topics can be matched with the learning ability and the learning target of the user, personalized topic recommendation is effectively achieved, the accuracy is high, and the learning efficiency and the learning effect can be improved practically.
It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment, and the multiple devices interact with each other to complete the method.
It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Exemplary device
Based on the same inventive concept, corresponding to any of the above exemplary embodiment methods, the present application also provides a topic recommendation apparatus.
Referring to fig. 7, the title recommending apparatus includes:
a first determining module 701 configured to determine a current learning ability value of a target user;
a second determining module 702 configured to determine a difficulty of a topic matched with the target user according to the learning ability value;
a generating module 703 configured to obtain a learning objective of the target user within a predetermined time period, and generate a learning path curve representing a trend of the learning ability value of the target user with time within the predetermined time period according to the learning objective;
a third determining module 704 configured to determine the number of topics matching the target user according to the learning path curve;
and the recommending module 705 is configured to recommend the titles to the target users according to the difficulty and the number.
In some optional embodiments, the first determining module 701 is specifically configured to obtain historical answer data of the target user and a learning ability value of the target user after last answer; and calculating the current learning ability value of the target user by adopting a question reaction theory algorithm according to the historical answer data and the learning ability value of the target user after the target user answers the question last time.
In some optional embodiments, the second determining module 702 is specifically configured to correspond the learning ability value to a difficulty of the topic matched with the target user based on a topic reaction theory algorithm.
In some optional embodiments, the second determining module 702 is specifically configured to obtain, according to the learning ability value, a predetermined ability value interval corresponding to the learning ability value; and calculating the percentile corresponding to the learning ability value in the ability value interval, and taking the percentile correspondence as the difficulty of the question matched with the target user.
In some optional embodiments, the third determining module 704 is specifically configured to determine a capacity value median curve corresponding to the capacity value interval; calculating a first differential value of the learning path curve; calculating a second difference value on the position corresponding to the starting point of the learning path curve on the potential value median curve; and determining the number of the titles matched with the target user according to the first differential value, the second differential value and a preset standard number.
In some optional embodiments, the third determining module 704 is specifically configured to determine an upper limit curve and a lower limit curve of the capability value corresponding to the capability value interval; and in response to determining that the learning objective does not fall within the range defined by the capacity value upper-bound curve and the capacity value lower-bound curve, feeding back prompt information for prompting that the learning objective is unreasonable to the objective user.
In some optional embodiments, the capacity value upper bound curve, the capacity value middle bound curve, and the capacity value lower bound curve are determined by: acquiring a reference learning ability value of a reference user corresponding to the ability value interval within a certain amount of time period; calculating 95% percentile of all the reference learning capacity values corresponding to each moment in the time period; obtaining the upper bound curve of the capacity value according to the 95% percentile corresponding to all the moments in the time period; for each moment in the time period, calculating 50% percentile of all the reference learning capacity values corresponding to the moment; obtaining a capacity value median curve according to the 50% percentiles corresponding to all the moments in the time period; for each moment in the time period, calculating 5% percentile of all the reference learning capacity values corresponding to the moment; and obtaining the lower bound curve of the capacity value according to the 5% percentile corresponding to all the moments in the time period.
The apparatus of the foregoing embodiment is used to implement the corresponding title recommendation method in any embodiment in the foregoing exemplary method section, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any of the above exemplary method embodiments, the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the title recommendation method according to any of the above exemplary method embodiments.
Fig. 8 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
Bus 1050 includes a path that transfers information between various components of the device, such as processor 1010, memory 1020, input/output interface 1030, and communication interface 1040.
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The electronic device of the above embodiment is used to implement the corresponding title recommendation method in any embodiment in the above exemplary method section, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Exemplary program product
Based on the same inventive concept, corresponding to any of the above exemplary embodiment methods, the present application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the title recommendation method as described in any of the above exemplary method sections.
The non-transitory computer readable storage medium may be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.
The storage medium of the above embodiment stores computer instructions for causing the computer to execute the title recommendation method according to any one of the above exemplary method embodiments, and has the advantages of corresponding method embodiments, which are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be embodied as a system, method or computer program product. Thus, the present application may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.) or a combination of hardware and software, and is referred to herein generally as a "circuit," module "or" system. Furthermore, in some embodiments, the present application may also be embodied in the form of a computer program product in one or more computer-readable media having computer-readable program code embodied therein.
Any combination of one or more computer-readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive example) of the computer readable storage medium may include, for example: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
Further, while the operations of the methods of the present application are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Rather, the steps depicted in the flowcharts may change the order of execution. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
Use of the verbs "comprise", "comprise" and their conjugations in this application does not exclude the presence of elements or steps other than those stated in this application. The article "a" or "an" preceding an element does not exclude the presence of a plurality of such elements.
While the spirit and principles of the application have been described with reference to several particular embodiments, it is to be understood that the application is not limited to the disclosed embodiments, nor is the division of aspects, which is for convenience only as the features in such aspects may not be combined to benefit from the description. The application is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the following claims is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures and functions.

Claims (10)

1. A title recommendation method, comprising:
determining the current learning capacity value of the target user;
determining the difficulty of the question matched with the target user according to the learning ability value;
acquiring a learning target of the target user in a preset time period, and generating a learning path curve for representing the change trend of the learning capacity value of the target user along with time in the preset time period according to the learning target;
determining the number of questions matched with the target user according to the learning path curve;
and recommending titles to the target users according to the difficulty and the number.
2. The method according to claim 1, wherein the determining the current learning ability value of the target user specifically comprises:
acquiring historical answer data of the target user and a learning capacity value of the target user after answering the question last time;
and calculating the current learning ability value of the target user by adopting a question reaction theory algorithm according to the historical answer data and the learning ability value of the target user after the target user answers the question last time.
3. The method according to claim 2, wherein the determining the difficulty of the topic matched with the target user according to the learning ability value specifically includes:
and correspondingly taking the learning ability value as the difficulty of the question matched with the target user based on a question reaction theory algorithm.
4. The method according to claim 1, wherein the determining the difficulty of the topic matched with the target user according to the learning ability value specifically includes:
acquiring a preset capacity value interval corresponding to the learning capacity value according to the learning capacity value;
and calculating the percentile corresponding to the learning ability value in the ability value interval, and taking the percentile correspondence as the difficulty of the question matched with the target user.
5. The method according to claim 4, wherein the determining the number of topics matched with the target user according to the learning path curve specifically includes:
determining a capacity value median curve corresponding to the capacity value interval;
calculating a first differential value of the learning path curve;
calculating a second difference value on the position corresponding to the starting point of the learning path curve on the potential value median curve;
and determining the number of the titles matched with the target user according to the first differential value, the second differential value and a preset standard number.
6. The method of claim 4, wherein obtaining the learning objective of the target user within a predetermined time period further comprises:
determining an upper limit curve and a lower limit curve of the capacity value corresponding to the capacity value interval;
and in response to determining that the learning objective does not fall within the range defined by the capacity value upper-bound curve and the capacity value lower-bound curve, feeding back prompt information for prompting that the learning objective is unreasonable to the objective user.
7. The method of claim 6, wherein the capacity value upper bound curve, the capacity value median curve, and the capacity value lower bound curve are determined by:
acquiring a reference learning ability value of a reference user corresponding to the ability value interval within a certain amount of time period;
calculating 95% percentile of all the reference learning capacity values corresponding to each moment in the time period; obtaining the upper bound curve of the capacity value according to the 95% percentile corresponding to all the moments in the time period;
for each moment in the time period, calculating 50% percentile of all the reference learning capacity values corresponding to the moment; obtaining a capacity value median curve according to the 50% percentiles corresponding to all the moments in the time period;
for each moment in the time period, calculating 5% percentile of all the reference learning capacity values corresponding to the moment; and obtaining the lower bound curve of the capacity value according to the 5% percentile corresponding to all the moments in the time period.
8. A title recommendation device, comprising:
a first determination module configured to determine a current learning ability value of the target user;
a second determination module configured to determine a difficulty of a question matched with the target user according to the learning ability value;
the generation module is configured to acquire a learning target of the target user in a preset time period and generate a learning path curve for representing the change trend of the learning capacity value of the target user along with time in the preset time period according to the learning target;
a third determination module configured to determine the number of topics matched with the target user according to the learning path curve;
and the recommending module is configured to recommend the titles to the target users according to the difficulty and the number.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
CN202111323672.2A 2021-11-08 2021-11-08 Question recommending method and device, electronic equipment and storage medium Active CN114048377B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111323672.2A CN114048377B (en) 2021-11-08 2021-11-08 Question recommending method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111323672.2A CN114048377B (en) 2021-11-08 2021-11-08 Question recommending method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114048377A true CN114048377A (en) 2022-02-15
CN114048377B CN114048377B (en) 2024-05-03

Family

ID=80207929

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111323672.2A Active CN114048377B (en) 2021-11-08 2021-11-08 Question recommending method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114048377B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160009155A (en) * 2014-07-15 2016-01-26 한양대학교 산학협력단 Method and System for Smart Personalized Learning Tutoring to Provide Service of Effective Study Encouragement and Tutoring and Learning Strategy Establishment
CN107391503A (en) * 2016-05-16 2017-11-24 刘洪波 Personalized recommendation method with interest guiding function
US20180374371A1 (en) * 2017-06-27 2018-12-27 International Business Machines Corporation Recommending learning activities
CN110413728A (en) * 2019-06-20 2019-11-05 平安科技（深圳）有限公司 Exercise recommended method, device, equipment and storage medium
KR20200012431A (en) * 2018-07-27 2020-02-05 (주)웅진씽크빅 Method for providing an information of a question analysis using big data
CN111813921A (en) * 2020-08-20 2020-10-23 浙江学海教育科技有限公司 Topic recommendation method, electronic device and computer-readable storage medium
CN112149994A (en) * 2020-09-22 2020-12-29 黄秋英 English personal ability tracking learning system based on statistical analysis
CN112860756A (en) * 2021-04-23 2021-05-28 平安科技（深圳）有限公司 Exercise test-based learning resource recommendation method and device and computer equipment
CN113094495A (en) * 2021-04-21 2021-07-09 上海松鼠课堂人工智能科技有限公司 Learning path demonstration method, device, equipment and medium for deep reinforcement learning

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20160009155A (en) * 2014-07-15 2016-01-26 한양대학교 산학협력단 Method and System for Smart Personalized Learning Tutoring to Provide Service of Effective Study Encouragement and Tutoring and Learning Strategy Establishment
CN107391503A (en) * 2016-05-16 2017-11-24 刘洪波 Personalized recommendation method with interest guiding function
US20180374371A1 (en) * 2017-06-27 2018-12-27 International Business Machines Corporation Recommending learning activities
KR20200012431A (en) * 2018-07-27 2020-02-05 (주)웅진씽크빅 Method for providing an information of a question analysis using big data
CN110413728A (en) * 2019-06-20 2019-11-05 平安科技（深圳）有限公司 Exercise recommended method, device, equipment and storage medium
CN111813921A (en) * 2020-08-20 2020-10-23 浙江学海教育科技有限公司 Topic recommendation method, electronic device and computer-readable storage medium
CN112149994A (en) * 2020-09-22 2020-12-29 黄秋英 English personal ability tracking learning system based on statistical analysis
CN113094495A (en) * 2021-04-21 2021-07-09 上海松鼠课堂人工智能科技有限公司 Learning path demonstration method, device, equipment and medium for deep reinforcement learning
CN112860756A (en) * 2021-04-23 2021-05-28 平安科技（深圳）有限公司 Exercise test-based learning resource recommendation method and device and computer equipment

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
AMIR HOSSEIN NABIZADEH等: "Learning path personalization and recommendation methods: A survey of the state-of-the-art", EXPERT SYSTEMS WITH APPLICATIONS, 30 May 2020 (2020-05-30) *
林卓力: "物理习题进阶设计模型的建构与应用", 中国优秀硕士学位论文全文数据库社会科学Ⅱ辑, 15 January 2021 (2021-01-15) *

Also Published As

Publication number Publication date
CN114048377B (en) 2024-05-03

Similar Documents

Publication Publication Date Title
KR102331049B1 (en) Leveraging user signals for initiating communications
US20170250930A1 (en) Interactive content recommendation personalization assistant
US20190217206A1 (en) Method and system for training a chatbot
US8832117B2 (en) Apparatus, systems and methods for interactive dissemination of knowledge
CN111914176B (en) Question recommendation method and device
US20160132601A1 (en) Hybrid Explanations In Collaborative Filter Based Recommendation System
US11048875B2 (en) Skimming data sequences using recurrent neural networks
US10218770B2 (en) Method and system for sharing speech recognition program profiles for an application
CN109726390B (en) Document processing method, device, electronic equipment and storage medium
CN109960650B (en) Big data-based application program evaluation method, device, medium and electronic equipment
US20190361720A1 (en) Contextual insight generation and surfacing on behalf of a user
KR20160113685A (en) Method, apparatus and system for content recommendation
CN103488669A (en) Information processing apparatus, information processing method and program
CN112698895A (en) Display method, device, equipment and medium of electronic equipment
CN110377827B (en) Course training scene pushing method and device, medium and electronic equipment
CN116204714A (en) Recommendation method, recommendation device, electronic equipment and storage medium
CN114662676A (en) Model optimization method and device, electronic equipment and computer-readable storage medium
CN114021029A (en) Test question recommendation method and device
CN113383329A (en) Comprehension-based identification of educational content in multiple content types
CN113836388B (en) Information recommendation method, device, server and storage medium
CN114048377B (en) Question recommending method and device, electronic equipment and storage medium
CN111459542A (en) Method, device and system for determining recommended configuration index, storage medium and equipment
US20230017951A1 (en) Artificial intelligence-based multi-goal-aware device sampling
WO2022141142A1 (en) Method and system for determining target audio and video
CN110879865B (en) Recommendation method and device for nuclear products

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