CN111080025A - Learning feature data processing method and device and electronic equipment - Google Patents
Learning feature data processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN111080025A CN111080025A CN201911358851.2A CN201911358851A CN111080025A CN 111080025 A CN111080025 A CN 111080025A CN 201911358851 A CN201911358851 A CN 201911358851A CN 111080025 A CN111080025 A CN 111080025A
- Authority
- CN
- China
- Prior art keywords
- learning
- attribute
- grouping
- target object
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 73
- 230000001149 cognitive effect Effects 0.000 claims abstract description 40
- 238000003745 diagnosis Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 33
- 230000008569 process Effects 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 19
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 description 11
- 241001649081 Dina Species 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
- G06F16/24554—Unary operations; Data partitioning operations
- G06F16/24556—Aggregation; Duplicate elimination
-
- 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)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Educational Technology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a learning feature data processing method and device and electronic equipment. Wherein, the method comprises the following steps: acquiring initial learning characteristic data of a plurality of target objects in a history learning process, and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute; determining an attribute weight of each target object based on a priority ranking result of the learning feature grouping attributes; matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result; calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result; grouping the target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets; initializing test question parameters of the target objects in each object set, and inputting the test question parameters into the cognitive diagnosis model to estimate learning parameters of each object set.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a learning feature data processing method and device and electronic equipment.
Background
In the related art, when teaching management is performed in a school, learning conditions of students often need to be mastered, but current learning state feedback modes are reflected through examination scores, the mastering conditions of knowledge points of users cannot be determined, if the learning conditions of the students cannot be mastered, the learning conditions of the students cannot be managed, and the mastering conditions of the knowledge points of new courses of the students cannot be estimated. In the related art, a learning education platform adapted to students is developed, and along with the continuous development of an online education platform, education transition and policy response are brought by 'internet + education'. Through the student learning state model in the online education platform, the grasping condition of the student on the knowledge or skill (attribute) related to the problem can be presumed by answering the problem of the student, but the mode has obvious defects and the following problems are not considered: the characteristics of the performance basis, the homework completion condition, the learning data on the learning platform and the like of students in different levels have certain differences, the cognitive levels of the students are different, and finally the cognition of the knowledge point mastering condition of the students is deviated, so that the subsequent teaching quality is influenced.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for processing learning feature data and electronic equipment, and aims to at least solve the technical problems that differences of learning features of students at different levels are not considered in related technologies, so that learning cognitive levels of the students are deviated, and teaching quality is influenced.
According to an aspect of the embodiments of the present invention, there is provided a processing method of learning feature data, including: acquiring initial learning characteristic data of a plurality of target objects in a history learning process, and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute and carry out priority sequencing on the learning characteristic grouping attribute; determining an attribute weight of each target object based on a priority ranking result of the learning feature grouping attributes; matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result; calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result; grouping a plurality of target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets; initializing test question parameters of the target object in each object set, and inputting the test question parameters into a cognitive diagnosis model to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on knowledge points.
Optionally, the learned feature grouping attribute comprises at least one of: the system comprises the following steps of completing the work of a target course, average scores of pre-requisite courses, winning prize of competition, and learning state data of the target object in a target learning system, wherein the pre-requisite courses are used for indicating basic courses relevant to the target course.
Optionally, determining the attribute weight of each target object based on the result of the priority ranking of the learning feature grouping attributes comprises: determining the number of priorities of the learning features; acquiring the priority order of each learning feature grouping attribute, and creating a priority matrix based on the priority order of the learning feature grouping attributes and the priority quantity of the learning features; and calculating the attribute weight of each learning feature grouping attribute based on the priority matrix.
Optionally, the step of calculating an attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result includes: determining the number of target objects to obtain the total number of the target objects; calculating the attribute score of the learning feature grouping attribute of each target object based on the total number of the target objects, the learning feature grouping attribute of each target object and the attribute weight of the learning feature grouping attribute.
Optionally, the step of grouping a plurality of target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets includes: determining the total number of the target object groups; clustering and grouping all target objects based on the total number of the target object groups to obtain a plurality of object sets, wherein each group of the object sets comprises at least one target object; after obtaining the plurality of object sets, the processing method further includes: determining an attribute score of the learning feature grouping attribute of each target object in an object set to obtain a set attribute score corresponding to each object set; and calculating the score mean value of the set attribute scores in each object set, and sequencing the score mean values to obtain a grouping and sequencing matrix.
Optionally, the step of initializing test question parameters of the target object in each object set, and inputting the test question parameters into the cognitive diagnosis model to estimate learning parameters of each object set includes: determining the test question error rate and the test question guessing rate of the target object in each object set to obtain test question parameters; calculating test question parameters of each object set according to the set hierarchy of the object set where the target object is located; inputting the test question parameters of each target object in each object set into a cognitive diagnosis model so as to estimate the learning parameters of each object set.
Optionally, the estimated learning parameters include at least one of: test question guessing rate, test question coarse heart rate and course score.
According to another aspect of the embodiments of the present invention, there is also provided a processing apparatus for learning feature data, including: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring initial learning characteristic data of a plurality of target objects in the history learning process and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute; the determining unit is used for determining the attribute weight of each target object based on the priority ranking result of the learning feature grouping attributes; the matching unit is used for matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result; the calculating unit is used for calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result; the grouping unit is used for grouping a plurality of target objects based on the attribute scores of the learning characteristic grouping attributes to obtain a plurality of object sets; and the estimation unit is used for initializing test question parameters of the target object in each object set and inputting the test question parameters into the cognitive diagnosis model so as to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on the knowledge points.
Optionally, the learned feature grouping attribute comprises at least one of: the system comprises the following steps of completing the work of a target course, average scores of pre-requisite courses, winning prize of competition, and learning state data of the target object in a target learning system, wherein the pre-requisite courses are used for indicating basic courses relevant to the target course.
Optionally, the determining unit includes: the first determining module is used for determining the priority number of the learning features; the learning feature grouping attribute acquisition module is used for acquiring the priority order of each learning feature grouping attribute and creating a priority matrix based on the priority order of the learning feature grouping attributes and the priority number of the learning features, wherein the priority matrix indicates the priority ordering result of the learning feature grouping attributes; and the first calculation module is used for calculating the attribute weight of each learning feature grouping attribute based on the priority matrix.
Optionally, the computing unit further comprises: the second determining module is used for determining the number of the target objects to obtain the total number of the target objects; and the second calculation module is used for calculating the attribute score of the learning feature grouping attribute of each target object based on the total number of the target objects, the learning feature grouping attribute of each target object and the attribute weight of the learning feature grouping attribute.
Optionally, the grouping unit includes: the third determining module is used for determining the total number of the target object groups; clustering and grouping all target objects based on the total number of the target object groups to obtain a plurality of object sets, wherein each group of the object sets comprises at least one target object; the processing apparatus of learning feature data further includes: the fourth determination module is used for determining the attribute score of the learning feature grouping attribute of each target object in the object set after a plurality of object sets are obtained, and obtaining a set attribute score corresponding to each object set; and the third calculation module is used for calculating the score mean value of the set attribute scores in each object set and sequencing the score mean values to obtain a grouping and sequencing matrix.
Optionally, the pre-estimating unit includes: the fifth determining module is used for determining the test question error rate and the test question guessing rate of the target object in each object set to obtain test question parameters; the fourth calculation module is used for calculating the test question parameters of each object set according to the set hierarchy of the object set where the target object is located; and the estimation module is used for inputting the test question parameters of each target object in each object set into the cognitive diagnosis model so as to estimate the learning parameters of each object set.
Optionally, the estimated learning parameters include at least one of: test question guessing rate, test question coarse heart rate and course score.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the processing method of learning feature data of any one of the above items via execution of the executable instructions.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein when the program runs, a device on which the storage medium is located is controlled to execute the processing method of learning feature data described in any one of the above.
In the embodiment of the invention, initial learning characteristic data of a plurality of target objects in the history learning process is acquired, the learning characteristic grouping attributes are obtained and sorted based on the characteristic grades of the initial learning characteristic data, the attribute weight of each target object is determined based on the priority sorting result of the learning characteristic grouping attributes, then the initial learning characteristic data of each target object is matched with the learning characteristic grouping attributes to obtain the matching result, the attribute score of the learning characteristic grouping attributes of each target object is calculated based on the attribute weight of the target object and the matching result, then the plurality of target objects are grouped based on the attribute score of the learning characteristic grouping attributes to obtain a plurality of object sets, finally the test question parameters of the target objects in each object set can be initialized, and the test question parameters are input into the cognitive diagnosis model, and estimating the learning parameters of each object set, wherein the learning parameters are used for analyzing the mastery condition of the target object on the knowledge points. In this embodiment, by combining the personalized cognitive diagnosis method of the object (taking students as an example) learning feature grouping, learning features of different levels are considered, so that each object can be grouped by combining each learning feature grouping attribute (such as student score basis, job completion condition, competition award winning condition, learning data on a learning platform), more accurate knowledge mastering conditions of different object sets belonging to different learning degree gradients can be obtained respectively, and the teaching quality is improved, thereby solving the technical problem that the learning cognitive level of the students is biased and the teaching quality is influenced because differences of the learning features of the students of different levels are not considered in the related technology.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow diagram of an alternative method of processing learned feature data according to an embodiment of the invention;
fig. 2 is a schematic diagram of an alternative processing apparatus for learning feature data according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
To facilitate understanding of the invention by those skilled in the art, some terms or nouns referred to in the embodiments of the invention are explained below:
DINA, a discrete input noise And gate model, is a discrete cognitive diagnosis model, which describes student objects as multidimensional knowledge point grasping vectors And starts diagnosis from the actual answer results of students. In embodiments of the present invention, a cognitive diagnostic model may be used, the cognitive diagnostic model including: continuous and discrete, continuous cognitive diagnostic models include, but are not limited to: the IRT (project reflection model) is used for deducing test question parameters and potential abilities of students by jointly modeling test questions and the students according to the answering conditions of the students, and the DINA model is a discrete cognitive diagnosis model. The traditional DINA cognitive diagnosis model does not carefully consider the difference of learning abilities of students at different levels. Because the initial knowledge level and the learning ability of each student are different, the learning tracks cannot be completely overlapped, and the cognitive diagnosis results of individuals at different levels are different. Therefore, in the cognitive diagnosis process combined with student learning feature grouping completed according to the embodiment of the present invention, grouping can be performed according to different learning data of students, and DINA parameters are initialized in a targeted manner, so that diagnosis of knowledge point mastering level can be performed for the students more accurately, and high-quality learning service can be provided for the students more individually.
The objects related to the following embodiments of the present invention may be understood as students at school for learning, online users for learning on a platform, users for self-education, etc., and are schematically illustrated as students in the embodiments of the present invention.
According to the embodiment of the invention, the DINA model can be improved by means of the learning characteristic data of the individual differences of different students, so that the diagnosis result of the knowledge point mastering level is more accurate. The individual difference learning characteristics of different students are closely combined, the initial performance basis (such as the basic course performance, the mastering condition of knowledge points of associated courses and the completion condition of basic course items), the past competition performance, the learning ability level and the learning data on the platform are included, and the DINA parameter model is improved, so that the result accuracy and the interpretability of the cognitive diagnosis model are improved.
Meanwhile, the method and the device can be matched with scenes of an online education platform, have good adaptability, effectively utilize a large amount of learning data brought by the online education platform, include platform learning behavior data such as course videos, clicking of course pages, browsing records, completion conditions of homework and the like, and serve as grouping basis of the learning capability characteristics of students. Effectively utilizes trace data resources left by the platform, realizes different operations for different students, improves the service level of the online education platform, is beneficial to reducing the student loss of the online education platform, accords with the development trend of 'internet + education', and has wide development prospect.
The embodiment of the invention can be used for the personalized learning possibility of the education according to the factors in the online education. Students in different levels can clearly analyze and determine own learning location by means of powerful big data technology, possibility is provided for the students to realize accurate and personalized autonomous learning by means of convenience of an online education system and a large number of high-quality learning resources, and learning efficiency is improved. The invention is illustrated below with reference to various examples.
Example one
In accordance with an embodiment of the present invention, there is provided an embodiment of a processing method for learning feature data, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of an alternative processing method for learning feature data according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
step S102, acquiring initial learning characteristic data of a plurality of target objects in a history learning process, and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute; meanwhile, the learning characteristic grouping attributes can be subjected to priority sequencing;
step S104, determining the attribute weight of each target object based on the priority ranking result of the learning feature grouping attributes;
step S106, matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result;
step S108, calculating the attribute score of the learning characteristic grouping attribute of each target object based on the attribute weight of the target object and the matching result;
step S110, grouping a plurality of target objects based on the attribute scores of the learning characteristic grouping attributes to obtain a plurality of object sets;
step S112, initializing test question parameters of the target object in each object set, and inputting the test question parameters into the cognitive diagnosis model to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on the knowledge points.
Through the steps, initial learning characteristic data of a plurality of target objects in the history learning process can be obtained firstly, grouping is carried out based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute, the attribute weight of each target object is determined based on the priority ranking result of the learning characteristic grouping attribute, then the initial learning characteristic data of each target object is matched with the learning characteristic grouping attribute to obtain a matching result, the attribute score of the learning characteristic grouping attribute of each target object is calculated based on the attribute weight of the target object and the matching result, then the plurality of target objects can be grouped based on the attribute score of the learning characteristic grouping attribute to obtain a plurality of object sets, finally the test question parameters of the target objects in each object set can be initialized, and the test question parameters are input into the cognitive diagnosis model, and estimating the learning parameters of each object set, wherein the learning parameters are used for analyzing the mastery condition of the target object on the knowledge points. In this embodiment, by combining the personalized cognitive diagnosis method of the object (taking students as an example) learning feature grouping, learning features of different levels are considered, so that each object can be grouped by combining each learning feature grouping attribute (such as student score basis, job completion condition, competition award winning condition, learning data on a learning platform), more accurate knowledge mastering conditions of different object sets belonging to different learning degree gradients can be obtained respectively, and the teaching quality is improved, thereby solving the technical problem that the learning cognitive level of the students is biased and the teaching quality is influenced because differences of the learning features of the students of different levels are not considered in the related technology.
The embodiment of the invention can be applied to various environments such as learning platforms, teaching data management systems and the like.
The present invention will be described below with reference to the respective steps.
Step S102, acquiring initial learning characteristic data of a plurality of target objects in the history learning process, and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute.
The initial learning features in embodiments of the present invention include, but are not limited to: the class characteristics of the target course (i.e., the course to be learned by the student, such as the high-number class), the class characteristics of the precedent course (the basic course associated with the target course), the winning of the competition, the network learning, and the like.
Grouping attributes of different levels based on initial learning feature data of the student.
As an alternative embodiment of the present invention, the learned feature grouping attribute includes at least one of: the target learning system comprises the work completion data of the target course, the average score of the pre-course, the competition winning data and the learning state data of the target object in the target learning system, wherein the pre-course is used for indicating the basic course related to the target course.
And step S104, determining the attribute weight of each target object based on the priority ranking result of the learning feature grouping attributes.
In the embodiment of the present invention, determining the attribute weight of each target object based on the priority ranking result of the learning feature grouping attribute includes: determining the number of priorities of the learning features; acquiring the priority order of each learning characteristic grouping attribute, and creating a priority matrix based on the priority order of the learning characteristic grouping attributes and the priority quantity of the learning characteristics; and calculating the attribute weight of each learning feature grouping attribute based on the priority matrix.
As for the priority order, for example, the priority order in which the above-described learning feature grouping attributes are determined is: the target course learning system comprises the work completion data of the target course, the average score of the precedent course, the competition winning data and the learning state data of the target object in the target learning system. That is, the priority of the job completion data of the target course is higher than the priority of the average score of the precedent course, the priority of the average score of the precedent course is higher than the priority of the competition winning data, and the priority of the competition winning data is higher than the priority of the learning state data of the target object in the target learning system.
In the present application, the job completion data of the target course includes: accuracy of job completion of target course, using M4Represents; average performance of prerequisite courses may use M3Show that the progress of the pre-requisite course and the pre-requisite can be passedCalculating the average score of the precedent course according to the relevance of the course and the target course; contest winning data may use M2The expression can be calculated by the winning type and the winning grade; the learning state data of the target object in the target learning system can be obtained by M1And (4) showing.
Optionally, setting the number of feature priorities to num, the number of precedent courses to N, and the number of competition levels to T (e.g., 9); obtaining a priority order for each learned feature grouping attribute and creating a priority matrix M ═ M1,M2,...,Mi,...,MnumIn which M isiA priority representing an ith learned feature group attribute; num;
wherein M is4Accuracy of job completion for target course, M3As an average score of a pre-requisite course (pre-requisite course)1First-hand course2.nRespectively correspond to { score1,score2,...,scoreNThe relevance of the n door precedent courses and the target courses is { relation respectively1,relation2,...relationN)，M2The winning number matrix of the first, second and third prizes of school, province and state is N9＝{N1,N2,...,Ni,...,N9Class corresponds to 1,2, 9), respectively, where N isiIndicating the number of times of winning prize of the i-th level of competition; m1For network learning data such as related learning task completion conditions, related teaching video browsing records and the like on a learning platform (such as a mu course net), task can be used for representing the sum of the number of completed related learning tasks and the number of browsing related teaching videos;
setting gradient k between grouping attribute weights of different priority orders by a user, thereby calculating the attribute weight of each learning characteristic grouping attribute, wherein the formula for calculating the attribute weight is as follows:
wherein i is 1,2, 3, 4, WiRepresents the ith learning feature grouping attribute (M)i) The weight of (2).
Step S106, matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result;
for example, after learning characteristic grouping attributes (such as student score basis, job completion condition, competition prize winning condition, and learning data on a learning platform) are obtained, priority ranking is performed on the grouping attributes, and if the subject job completion condition- > generates performance basis (pre-determined course score) - > competition prize winning condition- > learning data on the learning platform, the attribute weight of each target object is determined according to the ranking, and the weights are sequentially reduced; and then matching is carried out to obtain a matching result.
After the attribute weight and the matching result of the learning feature grouping attribute are obtained, the attribute score of the learning feature grouping attribute can be calculated.
And step S106, calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result.
As an optional embodiment of the present invention, the step of calculating an attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result includes: determining the number of target objects to obtain the total number of the target objects; and calculating the attribute score of the learning feature grouping attribute of each target object based on the total number of the target objects, the learning feature grouping attribute of each target object and the attribute weight of the learning feature grouping attribute.
For example, when calculating the learning feature grouping attribute score of each student, the method comprises the following steps: setting the number of students as I; calculating a learning feature grouping attribute score, R ═ { R, for I students1,R2,...,Ri,...,RIIn which R isiThe learning feature group attribute score of the ith student is represented. Calculating an attribute score by the following formula:
And step S106, grouping the target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets.
As an optional embodiment of the present invention, the step of grouping the plurality of target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets includes: determining the total number of the target object groups; and clustering and grouping all the target objects based on the total number of the target object groups to obtain a plurality of object sets, wherein each group of object sets comprises at least one target object.
After obtaining the plurality of object sets, the processing method further includes: determining the attribute score of the learning characteristic grouping attribute of each target object in the object set to obtain a set attribute score corresponding to each object set; and calculating the score mean value of the set attribute scores in each object set, and sequencing the score mean values to obtain a grouping and sequencing matrix.
For example, when grouping, the following steps may be performed: setting the total number of the groups as X; students were grouped using a clustering algorithm. Reordering according to the mean value of the learning feature grouping attribute scores R of the X groups of students (for example, sorting can be carried out from small to large), and obtaining a grouping sorting matrix Z ═ Z1,Z2,...,ZXAre respectively corresponding to the hierarchy YX1,2, X; where Yx denotes that the number of layers of the x-th group set is x.
After the object set is obtained by grouping, test question parameters (test question error rate and guess rate) of each group of students can be initialized according to the grouping condition of the students. For example, setting the test question error rate S of X groups of students0＝{S0 1,S0 2,...,S0 XTest question guess rate g0＝{g0 1,g0 2,...,g0 X}; according to the pointThe hierarchy of the group set, the failure rate and guess rate of each group is calculated by the following formulas:
step S110, initializing test question parameters of the target object in each object set, and inputting the test question parameters into the cognitive diagnosis model to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on the knowledge points.
In the embodiment of the invention, the step of initializing the test question parameters of the target object in each object set and inputting the test question parameters into the cognitive diagnosis model to estimate the learning parameters of each object set comprises the following steps: determining the test question error rate and test question guessing rate of the target object in each object set to obtain test question parameters; calculating test question parameters of each object set according to the set hierarchy of the object set where the target object is located; and inputting the test question parameters of each target object in each object set into the cognitive diagnosis model to estimate the learning parameters of each object set.
Optionally, the estimated learning parameter includes at least one of: the method comprises the steps of test question guessing rate (the test question guessing rate can be the probability that a predicted student can correctly answer a certain question after learning the target course), test question coarse heart rate (the test question coarse heart rate can be the probability that the predicted student wrongly answers the question after learning the target course) and course score.
The invention is illustrated by using DINA as a cognitive diagnostic model, and the S of each group of students0、g0And substituting the initial values into the cognitive diagnosis model respectively to obtain the guess rate g and the careless rate s of each group of student sets. The learning parameters may also include a likelihood function, wherein the likelihood function is obtained
The time can be obtained by calculating the guessing rate and the careless rate. The likelihood function can predict the total points of the courses of the students, and a learning platform and a teaching system can master the knowledge points of the students conveniently.
Wherein, in the calculation of DINA, the considered contents include: the method comprises the following steps of student, questions, knowledge points, a score matrix, the score condition of the student on a certain question, a potential capability matrix, the mastering condition of the student on a certain knowledge point, a potential answer matrix, the potential answer condition of the student on a certain question, a question knowledge point association matrix, the investigation condition of a certain question on a knowledge point, a question guessing rate and a question coarse heart rate. The scoring condition of the student on a certain subject can be finally obtained through the data, the total curriculum score of the student can be predicted, and the learning platform and the teaching system can conveniently master the knowledge point mastering condition of the student.
Because the initial knowledge level and the learning ability of each student are different, the learning tracks cannot be completely overlapped, and the cognitive diagnosis results of different individuals are different. The embodiment of the invention can carry out grouping according to different learning data of students and specifically initialize the DINA parameter s0、g0Therefore, the diagnosis of the knowledge point mastering level can be accurately carried out for the student, and high-quality learning service can be provided for the student more individually.
Example two
Fig. 2 is a schematic diagram of an alternative processing apparatus for learning feature data according to an embodiment of the present invention, as shown in fig. 2, the processing apparatus includes: an acquisition unit 21, a determination unit 22, a matching unit 23, a calculation unit 24, a grouping unit 25, a prediction unit 26, wherein,
the acquiring unit 21 is configured to acquire initial learning feature data of a plurality of target objects in a history learning process, and perform grouping based on feature levels of the initial learning feature data to obtain a learning feature grouping attribute;
a determining unit 22, configured to determine an attribute weight of each target object based on a priority ranking result of the learning feature grouping attributes;
the matching unit 23 is configured to match the initial learning feature data of each target object with the learning feature grouping attribute to obtain a matching result;
a calculating unit 24, configured to calculate an attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result;
a grouping unit 25, configured to group the multiple target objects based on the attribute scores of the learning feature grouping attributes to obtain multiple object sets;
and the estimating unit 26 is used for initializing test question parameters of the target object in each object set and inputting the test question parameters into the cognitive diagnosis model to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastery condition of the target object on the knowledge points.
The processing device of learning feature data can acquire initial learning feature data of a plurality of target objects in a history learning process through the acquisition unit 21, and perform grouping based on the feature level of the initial learning feature data to obtain the learning feature grouping attribute, then determine the attribute weight of each target object through the determination unit 22 based on the priority ranking result of the learning feature grouping attribute, then match the initial learning feature data of each target object with the learning feature grouping attribute through the matching unit 23 to obtain the matching result, and calculate the attribute score of the learning feature grouping attribute of each target object through the calculation unit 24 based on the attribute weight of the target object and the matching result, and then group the plurality of target objects through the grouping unit 25 based on the attribute score of the learning feature grouping attribute, a plurality of object sets are obtained, and finally, the test question parameters of the target object in each object set can be initialized through the estimation unit 26, and the test question parameters are input into the cognitive diagnosis model to estimate the learning parameters of each object set, wherein the learning parameters are used for analyzing the mastery condition of the target object on the knowledge points. In this embodiment, by combining the personalized cognitive diagnosis method of the object (taking students as an example) learning feature grouping, learning features of different levels are considered, so that each object can be grouped by combining each learning feature grouping attribute (such as student score basis, job completion condition, competition award winning condition, learning data on a learning platform), more accurate knowledge mastering conditions of different object sets belonging to different learning degree gradients can be obtained respectively, and the teaching quality is improved, thereby solving the technical problem that the learning cognitive level of the students is biased and the teaching quality is influenced because differences of the learning features of the students of different levels are not considered in the related technology.
Optionally, the learning feature grouping attribute includes at least one of: the target learning system comprises the work completion data of the target course, the average score of the pre-course, the competition winning data and the learning state data of the target object in the target learning system, wherein the pre-course is used for indicating the basic course related to the target course.
In an embodiment of the present invention, the determining unit includes: the first determining module is used for determining the priority number of the learning features; the first acquisition module is used for acquiring the priority order of each learning feature grouping attribute and creating a priority matrix based on the priority order of the learning feature grouping attributes and the priority quantity of the learning features; and the first calculation module is used for calculating the attribute weight of each learning feature grouping attribute based on the priority matrix.
Optionally, the computing unit further includes: the second determining module is used for determining the number of the target objects to obtain the total number of the target objects; and the second calculation module is used for calculating the attribute score of the learning feature grouping attribute of each target object based on the total number of the target objects, the learning feature grouping attribute of each target object and the attribute weight of the learning feature grouping attribute.
As an alternative embodiment of the present invention, the grouping unit includes: the third determining module is used for determining the total number of the target object groups; clustering and grouping all target objects based on the total number of the grouped target objects to obtain a plurality of object sets, wherein each group of object sets comprises at least one target object; the processing apparatus for learning feature data further includes: the fourth determination module is used for determining the attribute score of the learning feature grouping attribute of each target object in the object set after the plurality of object sets are obtained, and obtaining a set attribute score corresponding to each object set; and the third calculation module is used for calculating the score mean value of the set attribute scores in each object set and sequencing the score mean values to obtain a grouping and sequencing matrix.
Optionally, the estimation unit includes: the fifth determining module is used for determining the test question error rate and the test question guessing rate of the target object in each object set to obtain test question parameters; the fourth calculation module is used for calculating the test question parameters of each object set according to the set hierarchy of the object set where the target object is located; and the estimation module is used for inputting the test question parameters of each target object in each object set into the cognitive diagnosis model so as to estimate the learning parameters of each object set.
Optionally, the estimated learning parameter includes at least one of: test question guessing rate, test question coarse heart rate and course score.
The processing device for learning feature data may further include a processor and a memory, where the acquiring unit 21, the determining unit 22, the matching unit 23, the calculating unit 24, the grouping unit 25, the estimating unit 26, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory. The kernel can be set with one or more than one, and the learning parameters of each object set are estimated by adjusting the kernel parameters, wherein the learning parameters are used for analyzing the mastering condition of the target object on the knowledge points.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including: a processor; and a memory for storing executable instructions for the processor; wherein the processor is configured to perform the processing method of the learned feature data of any one of the above items via execution of the executable instructions.
According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein when the program runs, a device on which the storage medium is located is controlled to execute the processing method of learning feature data of any one of the above items.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: acquiring initial learning characteristic data of a plurality of target objects in a history learning process, and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute; determining an attribute weight of each target object based on a priority ranking result of the learning feature grouping attributes; matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result; calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result; grouping the target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets; initializing test question parameters of the target object in each object set, and inputting the test question parameters into the cognitive diagnosis model to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on the knowledge points.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for processing learning feature data, comprising:
acquiring initial learning characteristic data of a plurality of target objects in a history learning process, and grouping based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute;
determining an attribute weight of each target object based on a priority ranking result of the learning feature grouping attributes;
matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result;
calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result;
grouping a plurality of target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets;
initializing test question parameters of the target object in each object set, and inputting the test question parameters into a cognitive diagnosis model to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on knowledge points.
2. The processing method of claim 1, wherein the learned feature grouping attribute comprises at least one of: the system comprises the following steps of completing the work of a target course, average scores of pre-requisite courses, winning prize of competition, and learning state data of the target object in a target learning system, wherein the pre-requisite courses are used for indicating basic courses relevant to the target course.
3. The processing method of claim 2, wherein determining the attribute weight for each target object based on the prioritized results of the learned feature grouping attributes comprises:
determining the number of priorities of the learning features;
acquiring the priority order of each learning feature grouping attribute, and creating a priority matrix based on the priority order of the learning feature grouping attributes and the priority number of the learning features, wherein the priority matrix indicates the priority ordering result of the learning feature grouping attributes;
and calculating the attribute weight of each learning feature grouping attribute based on the priority matrix.
4. The processing method according to claim 3, wherein the step of calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result comprises:
determining the number of target objects to obtain the total number of the target objects;
calculating the attribute score of the learning feature grouping attribute of each target object based on the total number of the target objects, the learning feature grouping attribute of each target object and the attribute weight of the learning feature grouping attribute.
5. The processing method according to claim 1,
grouping a plurality of target objects based on the attribute scores of the learning feature grouping attributes to obtain a plurality of object sets, wherein the step of grouping the target objects comprises the following steps: determining the total number of the target object groups; clustering and grouping all target objects based on the total number of the target object groups to obtain a plurality of object sets, wherein each group of the object sets comprises at least one target object;
after obtaining the plurality of object sets, the processing method further includes: determining an attribute score of the learning feature grouping attribute of each target object in an object set to obtain a set attribute score corresponding to each object set; and calculating the score mean value of the set attribute scores in each object set, and sequencing the score mean values to obtain a grouping and sequencing matrix.
6. The process of claim 1, wherein the step of initializing test question parameters of the target objects in each set of objects and inputting the test question parameters into a cognitive diagnostic model to estimate learning parameters for each set of objects comprises:
determining the test question error rate and the test question guessing rate of the target object in each object set to obtain test question parameters;
calculating test question parameters of each object set according to the set hierarchy of the object set where the target object is located;
inputting the test question parameters of each target object in each object set into a cognitive diagnosis model so as to estimate the learning parameters of each object set.
7. The process of any one of claims 1 to 6, wherein the estimated learning parameters include at least one of: test question guessing rate, test question coarse heart rate and course score.
8. A processing apparatus for learning feature data, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring initial learning characteristic data of a plurality of target objects in the history learning process and grouping the initial learning characteristic data based on the characteristic grade of the initial learning characteristic data to obtain a learning characteristic grouping attribute;
the determining unit is used for determining the attribute weight of each target object based on the priority ranking result of the learning feature grouping attributes;
the matching unit is used for matching the initial learning characteristic data of each target object with the learning characteristic grouping attributes to obtain a matching result;
the calculating unit is used for calculating the attribute score of the learning feature grouping attribute of each target object based on the attribute weight of the target object and the matching result;
the grouping unit is used for grouping a plurality of target objects based on the attribute scores of the learning characteristic grouping attributes to obtain a plurality of object sets;
and the estimation unit is used for initializing test question parameters of the target object in each object set and inputting the test question parameters into the cognitive diagnosis model so as to estimate learning parameters of each object set, wherein the learning parameters are used for analyzing the mastering condition of the target object on the knowledge points.
9. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the processing method of learned feature data of any one of claims 1 to 7 via execution of the executable instructions.
10. A storage medium characterized by comprising a stored program, wherein a device in which the storage medium is located is controlled to execute the processing method of learning feature data according to any one of claims 1 to 7 when the program runs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911358851.2A CN111080025A (en) | 2019-12-25 | 2019-12-25 | Learning feature data processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911358851.2A CN111080025A (en) | 2019-12-25 | 2019-12-25 | Learning feature data processing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080025A true CN111080025A (en) | 2020-04-28 |
Family
ID=70317767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911358851.2A Pending CN111080025A (en) | 2019-12-25 | 2019-12-25 | Learning feature data processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080025A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112837574A (en) * | 2021-01-15 | 2021-05-25 | 中科远见(重庆)科技有限公司 | Interactive classroom system and method thereof |
| CN113129185A (en) * | 2021-03-29 | 2021-07-16 | 深圳数联天下智能科技有限公司 | Seat table generation method, electronic device and storage medium |
-
2019
- 2019-12-25 CN CN201911358851.2A patent/CN111080025A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112837574A (en) * | 2021-01-15 | 2021-05-25 | 中科远见(重庆)科技有限公司 | Interactive classroom system and method thereof |
| CN112837574B (en) * | 2021-01-15 | 2023-04-07 | 中科远见(重庆)科技有限公司 | Interactive classroom system and method thereof |
| CN113129185A (en) * | 2021-03-29 | 2021-07-16 | 深圳数联天下智能科技有限公司 | Seat table generation method, electronic device and storage medium |
| CN113129185B (en) * | 2021-03-29 | 2024-04-26 | 深圳数联天下智能科技有限公司 | Seat table generation method, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704732B (en) | Cognitive diagnosis based time-sequence problem recommendation method and device | |
| CN109740048B (en) | Course recommendation method and device | |
| CN108921221A (en) | Generation method, device, equipment and the storage medium of user characteristics | |
| CN110991645A (en) | Self-adaptive learning method, system and storage medium based on knowledge model | |
| CN112800097A (en) | Special topic recommendation method and device based on deep interest network | |
| CN110659311B (en) | Topic pushing method and device, electronic equipment and storage medium | |
| CN111651676A (en) | Method, device, equipment and medium for performing occupation recommendation based on capability model | |
| CN111680216B (en) | Test question recommendation method, system, medium and equipment | |
| CN116028602A (en) | Question recommending method and device, computer equipment and storage medium | |
| CN113409174A (en) | Knowledge point evaluation method and device | |
| CN111080025A (en) | Learning feature data processing method and device and electronic equipment | |
| CN110489455A (en) | Education resource recommended method, device, electronic equipment and storage medium | |
| CN114429212A (en) | Intelligent learning knowledge ability tracking method, electronic device and storage medium | |
| US20240177624A1 (en) | Learning management systems and methods therefor | |
| Juran et al. | Using worker personality and demographic information to improve system performance prediction | |
| CN109785197A (en) | A kind of Learning behavior analyzing method and device | |
| CN116433082B (en) | Evaluation report generation method and device, electronic equipment and storage medium | |
| CN108509959A (en) | Pornographic application and identification method, device, computer readable storage medium and server | |
| CN116992140A (en) | Teaching course online recommendation method and system applied to rehabilitation medicine department | |
| CN111062449A (en) | Prediction model training method, interestingness prediction device and storage medium | |
| CN116228475A (en) | Career planning practice method and device based on big data and electronic equipment | |
| CN108417266A (en) | The determination method and system of student's cognitive state | |
| Lee et al. | Prescribing deep attentive score prediction attracts improved student engagement | |
| TWI598843B (en) | Use of expert information to help analyze systems and methods | |
| CN112131427A (en) | Exercise set question acquisition method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200428 |
|
| RJ01 | Rejection of invention patent application after publication |