CN112926901A - Structural ability model construction method for learning analysis and evaluation - Google Patents
Structural ability model construction method for learning analysis and evaluation Download PDFInfo
- Publication number
- CN112926901A CN112926901A CN202110400435.5A CN202110400435A CN112926901A CN 112926901 A CN112926901 A CN 112926901A CN 202110400435 A CN202110400435 A CN 202110400435A CN 112926901 A CN112926901 A CN 112926901A
- Authority
- CN
- China
- Prior art keywords
- kwa
- capability
- data
- learning
- ability
- 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
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 40
- 238000004458 analytical method Methods 0.000 title claims abstract description 28
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 238000011158 quantitative evaluation Methods 0.000 abstract description 4
- 238000007670 refining Methods 0.000 abstract 1
- 239000000306 component Substances 0.000 description 6
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000059 patterning Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a structured ability model construction method for learning analysis and evaluation, which is used for acquiring N defined ability dimension data A1,A2,…,ANAnd a unique capability dimension ID corresponding to each type of capability dimension data; refining to obtain M keyword data KW1,KW2,…,KWMAnd a unique keyword ID corresponding to each keyword data; according to a combination setting instruction, combining and pairing the capability dimension data and the keyword data to form L learning target data KWA of the domain knowledge or course content D1,KWA2,…,KWALAnd sets a unique learning target ID identification for each KWA. The invention provides a capability model construction method which can describe the capability learning targets of the field or course in a structured manner and present the relevance and importance of each capability target. Further, a capability model is usedThe test questions are labeled, and the student test data are obtained for analysis, so that quantitative evaluation of each ability dimension of the student can be obtained.
Description
Technical Field
The invention belongs to the field of education measurement, learning analysis and evaluation and self-adaptive learning systems, and particularly relates to a learning analysis and evaluation oriented structural ability model construction method.
Background
In recent years, with the rapid development of big data technology and online education, education data mining, learning analysis and evaluation, adaptive learning systems and the like have become emerging research fields.
The adaptive learning system is an educational technology or product for providing adaptive learning content according to the characteristics or learning conditions of students, can meet the individual requirements of the students, and is considered to be an effective way for improving the learning quality. An adaptive learning system generally includes three core components, a domain model, a student model, and an adaptive model. The domain model is a structured description of course or domain knowledge, and generally represents contents such as concepts, knowledge units and the like and relations thereof by adopting a concept map, a knowledge graph and the like. The student model is used for describing individual characteristics of students, including basic information, learning style, knowledge level and the like, and needs to be obtained based on the field model and learning analysis and evaluation.
On the other hand, the educational industry is actively advancing the teaching transformation from knowledge-oriented to ability-oriented, and existing domain models, such as knowledge maps, and the like, are knowledge-oriented and lack a definition or description method for student ability output. The invention provides a structured ability model construction method, which can describe learning or teaching targets of knowledge in the field based on ability and is beneficial to quantitative evaluation of student ability.
Disclosure of Invention
The invention firstly relates to a structured ability model construction method facing to learning analysis and evaluation, which comprises the following steps:
aiming at a specific field knowledge or course content D, acquiring N defined ability dimension data A1,A2,…,ANAnd a unique capability dimension ID corresponding to each type of capability dimension data;
extracting and acquiring M key word data KW aiming at the domain knowledge or course content D1,KW2,…,KWMAnd a unique keyword ID corresponding to each keyword data;
according to the combination setting instruction, combining and pairing the capability dimension data and the keyword data to form L learning target data KWA of domain knowledge or course content D1,KWA2,…,KWALSetting a unique learning target ID for each KWA;
the importance degree of each KWA is set in the above domain knowledge, and the importance degree is assigned by methods including but not limited to assessment frequency calculation or domain expert experience.
And setting the mutual relation identifications of all the KWAs, wherein the setting method of the mutual relation comprises but is not limited to a sequential relation or a correlation relation.
Another aspect of the invention relates to a method for imaging using any of the models of the invention, comprising the steps of:
acquiring all KWA icons corresponding to the KWA data;
acquiring sequence relation identifications or correlation relation identifications of all KWA data;
and connecting all the KWA icons according to the mutual relation determined by the sequence relation identifier or the correlation relation identifier and displaying the connected KWA icons on a graph.
The invention also relates to a learning-oriented analysis and evaluation method based on any one of the structured ability models, which comprises the following steps,
acquiring KWA labeling information of the test questions based on the structured capability model;
acquiring answering condition information of the test questions;
the evaluation value of the student at each KWA is obtained based on at least one analysis and evaluation method, wherein the analysis and evaluation method comprises but is not limited to an evaluation method such as project reaction theory.
The invention also relates to a learning-oriented analysis and evaluation device based on any of the models of the invention, said device comprising at least one processor and a memory storing instructions which, when executed by the at least one processor, carry out the steps of any of the methods of the invention.
The invention has the beneficial effects that the capability model construction method is provided, the capability learning targets of the field or course can be described in a structuralized mode, and the relevance and the importance of each capability target are presented. The invention also provides a graphical representation method of student capability output, which is convenient for realizing capability evaluation and visual presentation of students by adopting a computer technology. Furthermore, the ability model is adopted to label the test questions, and student test data is obtained to analyze, so that quantitative evaluation of student ability can be obtained.
Drawings
FIG. 1 is a diagram of a capability model architecture of an embodiment of the present invention;
FIG. 2 is a KWA sequence diagram of an embodiment of the present invention;
fig. 3 is a diagram of the relationship between KWA and KWA in the embodiment of the present invention.
Detailed Description
The following embodiments are capable of showing more technical details of the present invention, but should not be construed as specifically limiting the scope of the present invention.
Some embodiments related to the invention are a structural ability model construction method facing learning analysis and evaluation, which comprises the following steps,
aiming at a specific field knowledge or course content D, acquiring N defined ability dimension data A1,A2,…,ANAnd a unique capability dimension ID corresponding to each type of capability dimension data;
extracting and acquiring M key word data KW aiming at the domain knowledge or course content D1,KW2,…,KWMAnd unique corresponding to each keyword dataA keyword ID identification;
according to the combination setting instruction, combining and pairing the capability dimension data and the keyword data to form L learning target data KWA of domain knowledge or course content D1,KWA2,…,KWALSetting a unique learning target ID for each KWA;
and setting the importance degree of each KWA, wherein the importance degree is assigned by using a method including but not limited to checking frequency calculation or field expert experience. Specifically, the importance level of each KWA is set, and may be set based on, for example, evaluation frequency calculation or experience of a domain expert. For example, referring to fig. 1, the importance levels may be classified into a very low (0.2), a low (0.4), a medium (0.6), a high (0.8), and a very high (1.0) five-level, a questionnaire is issued to a plurality of (three or more) experts or teachers to preliminarily assign the importance levels to each KWA, and a value or an average value with the largest number of times is taken as a final importance level of the KWA.
In some embodiments, the method for constructing a structural ability model for learning analysis and evaluation further includes the following steps:
an interrelationship between KWAs is defined, including but not limited to a sequential or a relational relationship. For example, a sequential relationship may be defined: considering KWA1 and KWA2, if they are adjacent and a student needs to reach the learning goal of KWA2 in advance to reach the learning goal of KWA1, they are said to have a sequential relationship, where KWA1 is said to be the front node and KWA2 is said to be the back node. The term "adjacent" refers to content or content with close connotations implied by different KWAs, which may be set by domain experts or teachers generally, and may not be unique. For example, considering the mathematical calculation capability of KWA1 being addition within 10, the concept recognition capability of KWA2 being number within 20, and the mathematical calculation capability of KWA3 being addition within 20, it is obvious that to a student, it is necessary to have KWA3 first having KWA1 and KWA2, and KWA1, KWA2 being very close to what KWA3 contains, KWA1 to KWA3, KWA2 to KWA3 may form a sequential relationship. The sequential relationship between KWAs may be set by a domain expert or teacher. The description of the correlation between the KWAs is helpful for setting a reasonable learning path and realizing accurate resource or test question recommendation.
In some embodiments, the method for defining the sequential relationship comprises the following steps:
the node structure is defined for each KWA according to equation 1:
KWA={KDf, B, I } formula 1
Wherein, KD={KWA1,KWA2,…,KWALF is the set of the domain knowledge or course content D and the learning target data thereof, F belongs to KDIs a set formed by the previous nodes of the KWA, B ∈ KDIs a set of nodes following the KWA, and I represents the degree of importance.
When F is an empty set, the KWA is KDThe learning objective that needs to be reached first; when B is empty, the KWA is KDThe middle terminal needs to reach the learning goal.
The importance level I is a measure of the magnitude of the importance of the KWA in domain knowledge. The model structure describes the required and required relation between each learning target and the adjacent learning targets, realizes the systematic description of the whole course, and has certain guiding significance for teacher teaching and student learning.
For example, consider a system having 4 learning objectives KWA1,KWA2,KWA3,KWA4Domain knowledge of D, then KD=KWA1∪KWA2∪KWA3∪KWA4The order relationship can be described as:
KWA2={KD,KWA1,{KWA3,KWA4},I2},
KWA3={KD,KWA2,KWA4,I3},
in this example, KWA1F is an empty setThen the KWA1Is KDThe learning objective that needs to be reached first; KWA4When B is an empty setThen the KWA4Is KDThe middle terminal needs to reach the learning goal.
In some embodiments, the method for defining the correlation relationship comprises the following steps:
defining a node structure by assigning a correlation parameter to each KWA, wherein the correlation parameter is a correlation coefficient characterized by a conditional probability, namely, the correlation parameter reaches the KWA1Under the condition of KWA2Probability of (KWA) P (KWA)2|KWA1) To describe.
Specifically, in some embodiments of the present invention, the following correlation relationships may be defined. As shown in table 1.1, the correlation coefficient between certain KWAs is preferred, and the correlation parameter is a correlation coefficient characterized by conditional probability, i.e. reaching KWA1Under the condition of KWA2Probability of (KWA) P (KWA)2|KWA1) To describe that the number of rows all represent the number of rows in achieving KWAyUnder the condition of KWAxThe probability value can be obtained by statistics and calculation according to the learning data of the student.
TABLE 1.1 KWA correlation coefficient Table
The invention also relates to some embodiments of a method for patterning a model using any of the preceding embodiments, comprising the steps of:
acquiring all KWA icons corresponding to the KWA data;
acquiring sequence relation identifications or correlation relation identifications of all KWA data;
connecting all KWA icons according to the mutual relation determined by the sequence relation identifier or the correlation relation identifier and displaying the connected KWA icons on a graph;
in some specific embodiments, when the obtained sequential relationship identification is a one-way connection using a one-way arrow, the direction of the arrow points from the front node KWA to the rear node KWA, according to the sequential relationship mentioned above, as shown in fig. 2.
In some specific embodiments, when the obtained correlation relationship identifier is obtained, the connection is a bidirectional connection using a connection coefficient provided on the connection line, according to the correlation relationship table mentioned above, as shown in fig. 3.
In a further embodiment of the graphical method of the present invention, importance assignments of all the KWA data are obtained, and the display area of the KWA icon can be proportionally adjusted according to the importance assignments.
The invention also relates to an embodiment of a learning-oriented analysis and evaluation method based on the structured capability model of any one of the embodiments, which comprises the following steps,
acquiring KWA labeling information of the test questions based on the structured capability model;
acquiring student answering condition information of test questions;
and obtaining the evaluation value of the student at each KWA based on at least one analysis and evaluation method, wherein the analysis and evaluation method comprises an evaluation method utilizing project reaction theory.
It should be noted that, although the project reaction theory described above can only evaluate the measured KWA when evaluating the capacity, based on the structured capacity model constructed by the present invention, other unmeasured KWAs can be updated according to the sequence relationship or the correlation relationship, and the algorithm based on the update is within the protection scope of the present invention.
In the embodiment of the learning analysis and evaluation oriented method, the step of comprehensively evaluating a certain ability dimension of the whole field knowledge or course content comprises the following steps:
acquiring all n KWAs including a certain capability dimension A;
obtaining the capability values q of the n KWAs1,q2,...,qnAnd degree of importance i1,i2,...,in(ii) a For the ability dimension a, the arithmetic mean of all the above KWA ability values can be used as the comprehensive evaluation value of the ability dimension; it is also possible to calculate the weight w of each KWA by its importance degree and calculate the comprehensive evaluation value Q as the capability dimension of the item according to equation 2,
Q=q1*w1+q2*w2+......+qn-1*wn-1+qn*wnformula 2
the term "structured ability model" refers to the structural description or presentation of learning or teaching objectives from the perspective of ability, which helps to accomplish the quantitative evaluation of student ability.
The term "defined" means, for example, that the ability dimension can be designed directly from the general teaching theory, such as the cognitive ability dimension in the bloom education goal taxonomy: the memory, understanding, application, analysis, evaluation and creation can also be defined by self based on related theories and according to specific domain knowledge or course content, such as the ability of memorization and reproduction, the ability of concept recognition, the ability of (concept) association and analysis, the ability of interpretation and understanding, the ability of diagram analysis, the ability of diagram drawing, the ability of mathematical computation, the ability of direct application, the ability of comprehensive application, the ability of comparative analysis, the ability of integration and construction, the ability of checking and judging, the ability of reasonable assumption and so on.
The term "refinement" includes the selection of keywords, for example, the selection of keywords may be defined after being divided into different categories, such as a fact or term category, a concept category, a principle category, an algorithm or method category, a criterion category, and the like, and may also be set individually according to subject experts or teachers.
The term "combinatorial pairing" refers to all teaching or learning objectives that can be set by a disciplinary expert or teacher for the combination of keywords and capability dimensions to preserve, for example, in a computer device, the knowledge in the field.
The invention will now be further illustrated by means of a specific example.
By using the above structural capability model, taking the second chapter of "automatic control principle" of the core course of the automation profession as an example, the graphical description of the course capability target can be obtained. The method comprises the following steps:
s1, starting from the ability guide, defining the ability dimension of the learning objective of knowledge in the field, as shown in table 1:
TABLE 1 capability dimension
And S2, extracting a keyword KW of the domain knowledge, and giving a unique ID (identity) of the keyword as shown in the following table 2.
TABLE 2 keywords
Serial number | Keyword | KW mark |
1 | System model | KW1 |
2 | Transfer function | KW2 |
3 | Dynamic structure chart | KW3 |
4 | Equivalent transformation method | KW4 |
5 | Typical link | KW5 |
6 | Meisen formula | KW6 |
7 | Signal flow diagram | KW7 |
S3, combining the extracted keywords and the defined ability dimension according to the teaching target of the domain knowledge to form the ability output description of the subject knowledge, which is marked by a unique ID and is KWA1,KWA2,…,KWA11As shown in Table 3, then KD={KWA1,KWA2,…,KWA11}
TABLE 3 KWA List
Serial number | KWA name | KWA identification |
1 | Correlation resolution capability of system model | KWA1 |
2 | Concept recognition capability of transfer function | KWA2 |
3 | Mathematical calculation capability of transfer function | KWA3 |
4 | Concept recognition capability of dynamic structure chart | KWA4 |
5 | Graph resolution capability for dynamic structure graphs | KWA5 |
6 | Concept recognition capability of typical links | KWA6 |
7 | Correlation resolution capability of typical links | KWA7 |
8 | Concept recognition capability for signal flow graphs | KWA8 |
9 | Graph resolution capability for signal flow graphs | KWA9 |
10 | Interpretation comprehension of the Meisen equation | KWA10 |
11 | Mathematical calculation capability of the Meisen equation | KWA11 |
S4 shows the importance of each KWA based on the experience of the domain expert as shown in table 4.
TABLE 4 degree of importance of KWA
Serial number | KWA List | Degree of importance |
1 | KWA1 | 0.6 |
2 | KWA2 | 1 |
3 | KWA3 | 0.6 |
4 | KWA4 | 0.2 |
5 | KWA5 | 0.8 |
6 | KWA6 | 0.4 |
7 | KWA7 | 0.6 |
8 | KWA8 | 0.4 |
9 | KWA9 | 0.8 |
10 | KWA10 | 0.4 |
11 | KWA11 | 0.8 |
S5, constructing a sequential relationship between KWAs based on the above KWAs:
KWA2={KD,KWA1,{KWA3,KWA4,KWA6},1},
KWA4={KD,KWA2,{KWA3,KWA5,},0.2}。
KWA6={KD,KWA2,KWA7,0.4},,
KWA8={KD,KWA4,KWA9,0.4}。
KWA9={KD,KWA8,KWA10,0.8},
KWA10={KD,KWA9,KWA11,0.4},
s6, according to the order relationship and importance degree between KWAs, the above structured ability model can be converted into a graphical representation, as shown in fig. 1.
S7, the structured ability model of the invention can be applied to test question marking, and further each KWA can be evaluated. Considering the foregoing capability model, the capability check points of the test questions can be labeled, for example, the questions:
[ problem of judgment ]
A typical link is a system or element that is physically simpler in construction, and may be defined and selected based on the physical characteristics of the system itself under study and interest to simplify and facilitate system analysis.
Since the assessment points of the judgment questions are the concept recognition ability of the typical links, they are labeled as KWA6. Furthermore, according to the response condition of the student to a plurality of test questions and the KWA marking information thereof, the evaluation value of the student in each KWA can be obtained by using a method such as an item reaction theory and the like.
S8, further, using the structural description of the ability by KWA, the ability of the whole domain knowledge or the course content can be comprehensively evaluated. For example KWA in example 15And KWA9Both belong to the graph analysis capability, if the capability values of two KWAs are obtained, the capability values are respectively q5And q is9Then (q) can be taken5+q9) [ 2 ] graph resolution capability A as in domain knowledge4The KWA may be determined from the importance of the evaluation value5And KWA9Account for the whole A4Weight w of50.5 and w9When the table resolution is 0.5, the table resolution of the whole second chapter is calculated by the following formula:
Q4=q5*w5+q9*w9。
here, the ability evaluation is an ability evaluation for the present knowledge field
Implementations and functional operations of the subject matter described in this specification can be implemented in: digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware, including the structures disclosed in this specification and their structural equivalents, or combinations of more than one of the foregoing. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on one or more tangible, non-transitory program carriers, for execution by, or to control the operation of, data processing apparatus.
A computer program (which may also be referred to or described as a program, software application, module, software module, script, or code) can be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data, e.g., one or more scripts stored in: in a markup language document; in a single file dedicated to the relevant program; or in multiple coordinated files, such as files that store one or more modules, sub programs, or portions of code. A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
Implementations of the subject matter described in this specification can be implemented in a computing system that includes a back-end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front-end component, e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the subject matter described in this specification, or any combination of one or more such back-end, middleware, or front-end components. The components in the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network ("LAN") and a wide area network ("WAN"), e.g., the Internet. The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any inventions or of what may be claimed, but rather as descriptions of features that may embody particular implementations of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in combination and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Claims (10)
1. A structural ability model construction method for learning analysis and evaluation is characterized by comprising the following steps: comprises the following steps of (a) carrying out,
acquiring N defined ability dimension data A aiming at any specific field knowledge or course content D1,A2,…,ANAnd a unique capability dimension ID corresponding to each type of capability dimension data;
extracting and acquiring M key word data KW aiming at the domain knowledge or course content D1,KW2,…,KWMAnd a unique keyword ID corresponding to each keyword data;
according to the combination setting instruction, the ability dimension data and the keyword data are combined and paired to form the field knowledge or course content DL learning target data KWA1,KWA2,…,KWALSetting a unique learning target ID for each KWA;
and setting the importance degree of each KWA in the domain knowledge or course, wherein the importance degree is assigned by using a method including but not limited to assessment frequency calculation or domain expert experience.
2. The method of claim 1, wherein: also comprises the following steps:
for each KWA, a correlation is defined between it and other KWAs, including but not limited to a sequential or a correlation.
3. The method of claim 2, wherein: the definition method of the sequence relation comprises the following steps:
the node structure is defined for each KWA according to equation 1:
KWA={KDf, B, I } formula 1
Wherein, KD={KWA1,KWA2,…,KWALF is the set of the domain knowledge or course content D and the learning target data thereof, F belongs to KDIs a set of adjacent front nodes of the KWA, and B belongs to KDIs a set of nodes following the KWA, and I represents the degree of importance.
4. The method of claim 1, wherein: both of said F and B comprise an empty set,
when F is an empty set, the KWA is KDThe learning objective that needs to be reached first;
when B is empty, the KWA is KDThe middle terminal needs to reach the learning goal.
5. The method of claim 2, wherein: the definition method of the correlation relationship comprises the following steps:
defining a node structure by assigning a dependency parameter to each KWAThe correlation parameter is a correlation coefficient characterized by conditional probability, namely KWA1Under the condition of KWA2Probability of (KWA) P (KWA)2|KWA1) To describe.
6. A graphical method based on the model of any of the preceding claims,
acquiring all KWA icons corresponding to the KWA data;
acquiring at least one group of sequential relation identifications or correlation relation identifications of all KWA data;
connecting all KWA icons according to the mutual relation determined by the sequence relation identifier or the correlation relation identifier and displaying the connected KWA icons on a graph;
when the obtained sequence relation identification is obtained, the connection is a one-way connection adopting a one-way arrow;
and when the obtained correlation relationship mark is obtained, the connection is bidirectional connection with a connection coefficient arranged on a connection line.
7. The method of claim 6, wherein: and obtaining importance assignments of all the KWA data, and proportionally adjusting the display area of the KWA icon according to the importance assignments.
8. A learning-oriented analysis and evaluation method based on the structured capability model of any of the preceding claims, characterized in that: comprises the following steps of (a) carrying out,
acquiring KWA labeling information of the test questions based on the structured capability model;
acquiring student answering condition information of test questions;
the student's evaluation value at each KWA is obtained based on at least one analysis and evaluation method including, but not limited to, a project reaction theory evaluation method.
9. The method of claim 8, wherein: the comprehensive evaluation step of a certain ability dimension of the knowledge or course content in the whole field comprises the following steps:
acquiring all n KWAs including a certain capability dimension A;
obtaining capability values q of the n KWAs1,q2,...,qnAnd degree of importance i1,i2,...,in;
For the ability dimension a, the arithmetic mean of all the above KWA ability values can be used as the comprehensive evaluation value of the ability dimension; it is also possible to calculate the weight w of each KWA by its importance degree, and calculate the comprehensive evaluation value Q as the capability dimension of the item according to equation 2,
Q=q1*w1+q2*w2+......+qn-1*wn-1+qn*wnformula 2
10. a learning-oriented analysis and evaluation device based on a structured capability model according to any of the preceding claims, characterized in that the system comprises at least one processor and a memory storing instructions which, when executed by the at least one processor, carry out the method according to any of the claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110400435.5A CN112926901B (en) | 2021-04-14 | 2021-04-14 | Structured capacity model construction method for learning analysis and evaluation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110400435.5A CN112926901B (en) | 2021-04-14 | 2021-04-14 | Structured capacity model construction method for learning analysis and evaluation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112926901A true CN112926901A (en) | 2021-06-08 |
CN112926901B CN112926901B (en) | 2023-10-24 |
Family
ID=76174392
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110400435.5A Active CN112926901B (en) | 2021-04-14 | 2021-04-14 | Structured capacity model construction method for learning analysis and evaluation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112926901B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113468892A (en) * | 2021-06-21 | 2021-10-01 | 北京搜狗科技发展有限公司 | Model testing method and device for model testing |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7480640B1 (en) * | 2003-12-16 | 2009-01-20 | Quantum Leap Research, Inc. | Automated method and system for generating models from data |
US20120315616A1 (en) * | 2011-06-13 | 2012-12-13 | The Learning Contagion, Llc. | E-learning method and system |
CN103106188A (en) * | 2013-02-21 | 2013-05-15 | 用友软件股份有限公司 | Imaging analysis system and imaging analysis method of data model |
CN104504228A (en) * | 2014-09-04 | 2015-04-08 | 北京德塔普博软件有限公司 | Knowledge network display method and system based on target view |
US20160364115A1 (en) * | 2015-06-12 | 2016-12-15 | Scapeflow, Inc. | Method, system, and media for collaborative learning |
CN107463691A (en) * | 2017-08-11 | 2017-12-12 | 北京点易通科技有限公司 | A kind of learning state collects the method and system with identification |
CN109033362A (en) * | 2018-07-26 | 2018-12-18 | 北京仿真中心 | Graphical relation query method and system, computer equipment and readable storage medium storing program for executing |
CN111241243A (en) * | 2020-01-13 | 2020-06-05 | 华中师范大学 | Knowledge measurement-oriented test question, knowledge and capability tensor construction and labeling method |
-
2021
- 2021-04-14 CN CN202110400435.5A patent/CN112926901B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7480640B1 (en) * | 2003-12-16 | 2009-01-20 | Quantum Leap Research, Inc. | Automated method and system for generating models from data |
US20120315616A1 (en) * | 2011-06-13 | 2012-12-13 | The Learning Contagion, Llc. | E-learning method and system |
CN103106188A (en) * | 2013-02-21 | 2013-05-15 | 用友软件股份有限公司 | Imaging analysis system and imaging analysis method of data model |
CN104504228A (en) * | 2014-09-04 | 2015-04-08 | 北京德塔普博软件有限公司 | Knowledge network display method and system based on target view |
US20160364115A1 (en) * | 2015-06-12 | 2016-12-15 | Scapeflow, Inc. | Method, system, and media for collaborative learning |
CN107463691A (en) * | 2017-08-11 | 2017-12-12 | 北京点易通科技有限公司 | A kind of learning state collects the method and system with identification |
CN109033362A (en) * | 2018-07-26 | 2018-12-18 | 北京仿真中心 | Graphical relation query method and system, computer equipment and readable storage medium storing program for executing |
CN111241243A (en) * | 2020-01-13 | 2020-06-05 | 华中师范大学 | Knowledge measurement-oriented test question, knowledge and capability tensor construction and labeling method |
Non-Patent Citations (2)
Title |
---|
傅圆圆 等: "概念图教学法在护理专业中的研究进展", 《中华护理教育》, vol. 9, no. 08, pages 381 - 383 * |
张慧;姚琴芬;: "基于知识可视化的物理实验课程导学教学设计研究", 物理与工程, no. 02 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113468892A (en) * | 2021-06-21 | 2021-10-01 | 北京搜狗科技发展有限公司 | Model testing method and device for model testing |
Also Published As
Publication number | Publication date |
---|---|
CN112926901B (en) | 2023-10-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Asselman et al. | Enhancing the prediction of student performance based on the machine learning XGBoost algorithm | |
Chang et al. | Modeling Exercise Relationships in E-Learning: A Unified Approach. | |
KR102015075B1 (en) | Method, apparatus and computer program for operating a machine learning for providing personalized educational contents based on learning efficiency | |
Cho et al. | Exploring online students’ self-regulated learning with self-reported surveys and log files: a data mining approach | |
Kotsiantis | Use of machine learning techniques for educational proposes: a decision support system for forecasting students’ grades | |
CA2872860C (en) | Method, system, and computer-readable recording medium for providing education service based on knowledge units | |
CN111274411A (en) | Course recommendation method and device, electronic equipment and readable storage medium | |
CN112184500A (en) | Extraclass learning tutoring system based on deep learning and knowledge graph and implementation method | |
CN111159419B (en) | Knowledge tracking data processing method, system and storage medium based on graph convolution | |
Pelánek | The details matter: methodological nuances in the evaluation of student models | |
de Gelder et al. | Safety assessment of automated vehicles: how to determine whether we have collected enough field data? | |
US20160171902A1 (en) | Mathematical Language Processing: Automatic Grading and Feedback for Open Response Mathematical Questions | |
Chanaa et al. | Predicting learners need for recommendation using dynamic graph-based knowledge tracing | |
Gutiérrez et al. | Using the Belbin method and models for predicting the academic performance of engineering students | |
Jove et al. | Attempts prediction by missing data imputation in engineering degree | |
KR102075936B1 (en) | Method, apparatus and computer program for operating a machine learning for providing personalized educational contents based on learning efficiency | |
CN117252047A (en) | Teaching information processing method and system based on digital twinning | |
KR101836206B1 (en) | Method, apparatus and computer program for providing personalized educational contents | |
Meng et al. | CS-BKT: introducing item relationship to the Bayesian knowledge tracing model | |
CN112926901B (en) | Structured capacity model construction method for learning analysis and evaluation | |
Sutoyo et al. | Sentiment analysis of student evaluations of teaching using deep learning approach | |
Ballman | Greater emphasis on variation in an introductory statistics course | |
Nadimpalli et al. | Towards personalized learning paths in adaptive learning management systems: bayesian modelling of psychological theories | |
Hernández et al. | Data-driven Construction of a Student Model using Bayesian networks in an Electrical Domain | |
CN116228361A (en) | Course recommendation method, device, equipment and storage medium based on feature matching |
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 |