CN111125339A - Test question recommendation method based on formal concept analysis and knowledge graph - Google Patents
Test question recommendation method based on formal concept analysis and knowledge graph Download PDFInfo
- Publication number
- CN111125339A CN111125339A CN201911169910.1A CN201911169910A CN111125339A CN 111125339 A CN111125339 A CN 111125339A CN 201911169910 A CN201911169910 A CN 201911169910A CN 111125339 A CN111125339 A CN 111125339A
- Authority
- CN
- China
- Prior art keywords
- concept
- test
- test question
- knowledge
- similarity
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides a test question recommendation method based on formal concept analysis and a knowledge graph, which comprises the steps of establishing formal concept backgrounds with objects of all students and attributes of all test questions according to question making records of the students; establishing a student-test question concept lattice according to the form concept background; calculating a first similarity between the initial concept and other concepts in the student-test question concept lattice; calculating a second similarity between the set of knowledge points for each test question and the set of knowledge points for each test question in the starting concept; multiplying the first similarity corresponding to each other concept with the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts; recommending the unfinished test questions with larger recommendation degree to the target students according to the recommendation degree of each test question. Compared with the prior art, the method comprehensively considers the common characteristics of students, and realizes efficient and accurate test question recommendation.
Description
Technical Field
The invention relates to the technical field of recommendation algorithms, in particular to a test question recommendation method based on formal concept analysis and a knowledge graph.
Background
With the rapid development of internet technology, numerous network education platforms such as mu class net, net cloud classroom, MOOC China and the like appear at home and abroad. The rise of these education platforms brings a great deal of education data, and how to utilize the data to provide better services for students is a problem to be solved urgently today. The online education test question recommendation is an important exploration direction, and can help students to improve the knowledge ability in a more targeted manner and effectively consolidate error-prone knowledge points.
The existing online education test question recommendation technology can be mainly divided into a collaborative filtering recommendation algorithm, a content-based recommendation algorithm, a mixed recommendation algorithm and the like. The collaborative filtering technology only depends on user historical record data to recommend the user, and the effect is poor under the condition of sparse data. The content-based recommendation algorithm is difficult to realize accurate classification and description in the preprocessing process, and is inefficient in the case of large data. The hybrid recommendation uses a combination of multiple algorithm modes, which results in higher system complexity and greatly increased cost. The recommendation technology can not accurately analyze weak knowledge points of students, and is difficult to achieve high algorithm efficiency and recommend test questions to the students in a targeted manner.
Disclosure of Invention
In order to overcome the problems in the related art, the embodiment of the invention provides a test question recommendation method, device and equipment based on formal concept analysis and a knowledge graph.
According to a first aspect of the embodiments of the present invention, there is provided a form concept analysis and knowledge graph-based test question recommendation method, including the following steps:
establishing a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, wherein the relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a knowledge point set;
establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept;
calculating a first similarity between the initial concept and other concepts except the initial concept in the student-test question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions by the target students;
calculating a second similarity between the set of knowledge points for each test question and the set of knowledge points for each test question in the starting concept;
multiplying the first similarity corresponding to each other concept with the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts;
recommending the unfinished test questions with larger recommendation degree to the target student according to the recommendation degree of each test question; wherein the non-done test questions are test questions except the test questions already done by the target student.
According to a second aspect of the embodiments of the present invention, there is provided a test question recommendation apparatus including:
the first construction unit is used for establishing a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, and the relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a knowledge point set;
the second construction unit is used for establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept;
the first arithmetic unit is used for calculating a first similarity between the initial concept and other concepts except the initial concept in the student-test question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions by the target students;
the second operation unit is used for calculating the maximum second similarity between the knowledge point set of each test question and the knowledge point set of each test question in the starting concept;
the third operation unit is used for multiplying the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts;
the recommending unit is used for recommending the unfinished test questions with larger recommendation degree to the target student according to the recommendation degree of each test question; wherein the non-done test questions are test questions except the test questions already done by the target student.
According to a third aspect of the embodiments of the present invention, there is provided a test question recommendation apparatus, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the formal concept analysis and knowledge graph based test question recommendation method according to the first aspect.
According to a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the formal concept analysis and knowledge graph test question recommendation method according to the first aspect.
In the embodiment of the application, the student-test question concept lattices are constructed by a formal concept analysis method, the commonality characteristics of students in each concept lattice are comprehensively considered when the test questions are recommended, missed questions which are jointly made by the students are extracted, and the analysis of the common weak points of knowledge of the students is facilitated; by calculating the first similarity between other concepts and the initial concept, the possibility that the test questions in other concepts with high similarity to the initial concept are recommended is higher, the recommendation calculation mode not only focuses on the target students to do missed test questions, but also comprehensively considers the commonality problem of the students, and the test question recommendation is more comprehensive and valuable. Moreover, based on the knowledge graph theory, the second similarity between the knowledge point sets is calculated, so that the similarity between the test questions is calculated more accurately; and multiplying the first similarity corresponding to other concepts by the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts, accurately calculating the recommendation degree of each test question, and recommending the non-done test question to the student according to the recommendation degree. The embodiment of the application realizes high efficiency and accuracy, can reflect the common problems of students and has a targeted test question recommendation method.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart illustrating a form concept analysis and knowledge graph-based test question recommendation method according to an exemplary embodiment of the present invention;
FIG. 2 is a diagram illustrating a formal conceptual context according to an exemplary embodiment of the present invention;
FIG. 3 is a schematic diagram of a hash corresponding to a concept lattice shown in an exemplary embodiment;
fig. 4 is a flowchart illustrating S104 in a form concept analysis and knowledge graph-based test question recommendation method according to an exemplary embodiment of the present invention;
fig. 5 is a flowchart illustrating S106 in a form concept analysis and knowledge graph-based test question recommendation method according to an exemplary embodiment of the present invention;
fig. 6 is a schematic structural diagram of a form concept analysis and knowledge graph-based test question recommendation apparatus according to an exemplary embodiment of the present invention;
fig. 7 is a schematic structural diagram of a test question recommendation apparatus based on formal concept analysis and knowledge graph according to an exemplary embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if/if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, fig. 1 is a flowchart illustrating a form concept analysis and knowledge graph-based test question recommendation method according to an exemplary embodiment of the present invention. The method is executed by the test question recommending device and comprises the following steps:
s101: establishing a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, wherein the relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a set of knowledge points.
Formal concept analysis is a method for data analysis and rule extraction, and is commonly used in the fields of machine learning, data mining, knowledge discovery and the like. Formal concept background is the basis for formal concept analysis, which can represent objects, attributes, and binary correspondences between objects and attributes.
In the embodiment of the application, the test question recommendation device obtains the question making records of all students, the question making records of each student record the test questions missed by each student, and the form concept background with the objects of all students and the attributes of all test questions is established according to all students, all test questions and the test questions missed by each student. The binary correspondence in the formal concept background indicates whether each student made a wrong test question.
Specifically, referring to fig. 2, fig. 2 is a schematic diagram illustrating a formal conceptual background according to an exemplary embodiment. In the schematic diagram of the formal concept background shown in fig. 2, the objects are students U0 to U6, the attributes are test questions t0 to t9, and in the binary correspondence between the students and the test questions, 1 indicates that the student does not miss the test questions, and 0 indicates that the student does not miss the test questions.
In the embodiment of the application, each test question is associated with a knowledge point set. The test questions in the embodiment of the present application are all the test questions in the test question bank, and the knowledge points are the knowledge points examined by the test questions in the test question bank, for example: the knowledge points to be investigated behind a test question of certain solid geometry are three-dimensional system establishment, coordinate calculation, vector operation, vertical theorem, parallel theorem, dihedral angle and the like, and a knowledge point set is formed by the investigated knowledge points.
Specifically, a knowledge graph is constructed in advance according to the contents of all the test questions in the test question library, wherein the knowledge graph comprises all knowledge points related to all the test questions, relations among different knowledge points and distances among different knowledge points. Each test question in the test question library is associated with a plurality of knowledge points, and the plurality of knowledge points form a knowledge point set associated with the test question. Under the assistance of the knowledge map, the similarity of knowledge points among the test questions can be analyzed, and the precision of test question recommendation is improved.
S102: establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept.
The generation of concept lattices is a basic task for formal concept analysis, and generation algorithms related to the concept lattices can be divided into two types: batch production algorithms and progressive generation algorithms. The classical algorithm of the batch generation algorithm is a Lattice algorithm, and the concept Lattice is obtained by firstly generating all concept sets and then establishing the relationship between direct predecessor and direct successor among the concept sets. The classical algorithm of the progressive generation algorithm is the Godin algorithm, which is to generate a certain concept set first, and then gradually generate all the concept sets and continuously update the edges to obtain a concept lattice. Compared with a batch generation algorithm, the progressive generation algorithm can effectively avoid repeated generation of the existing concept lattice and improve the efficiency of the algorithm.
In one exemplary embodiment, a student-question concept lattice is built based on the formal concept context and the progressive construction concept lattice algorithm. The student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept.
Referring to fig. 3, fig. 3 is a schematic diagram of hases corresponding to concept lattices shown in an exemplary embodiment. The concept lattice shown in fig. 3 is created based on a schematic diagram of the formal concept background shown in fig. 2. The concept lattice comprises 33 concept sets, and taking the 7 th concept set as an example, the 7 th concept set represents that students U0, U1 and U3 in the current concept set all miss the test questions t1 and t5 in the concept set.
The concepts are generated by constructing the student-test question concept lattice, each concept can extract the test questions missed by the students together, and the common problems of the students in the concepts are reflected on the basis of the missed test questions together, so that in the subsequent test question recommendation process, the similarity between one test question and the target test question missed by the students is not only considered, but also the common characteristics of the test questions missed by the students in each concept are considered, the value of the test questions is comprehensively and diversely considered, and the test question recommendation degree is more comprehensively analyzed. Meanwhile, on the basis of generating the concept lattice, the efficiency of the test question recommendation algorithm is improved, and the frequency of acquiring the student commonality characteristics by the concept background in the circular traversal form is reduced.
S103: calculating a first similarity between the initial concept and other concepts except the initial concept in the student-test question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions for the target students.
In the embodiment of the application, the test question recommendation device obtains the test question record of the target student according to the identification of the target student, and obtains all the test questions missed by the target student. And traversing the concepts in the concept lattice according to all the missed test questions made by the target students to obtain the initial concepts of all the test questions made by the target students, wherein the students in the concepts comprise the target students. The test question recommending device calculates a first similarity between the starting concept and other concepts except the starting concept in the student-test question concept lattice.
Referring to fig. 2 and fig. 3, when the target student is U0, the test question recommendation apparatus obtains all test questions t1, t2, t5, and t9 missed by U0, traverses the concept set in the concept lattice to obtain the concept 20 in which the student includes U0 and the test questions in the concept are t1, t2, t5, and t9, and uses the concept 20 as a starting concept, and the concepts other than the starting concept are other concepts.
In one exemplary embodiment, the test question recommendation apparatus obtains the similarity between each of the other concepts and the starting concept based on the degree of repetition of the test questions in the starting concept with the test questions in the other concepts. The higher the repetition degree of the test questions is, the greater the similarity between the test questions in the other concept sets and the test questions in the initial concept set is.
In another exemplary embodiment, the test question recommending apparatus calculates a first similarity of the starting concept with other concepts except the starting concept in the student-test question concept lattice through a first semantic similarity calculation formula based on formal concept analysis; wherein the first semantic similarity calculation formula is as follows:
|Di|＝|Ei∪Euser|×|Ii∪Iuser|
Cias the ith other concept, CuserTo initiate the concept, comSim (C)i,Cuser) For the similarity between the ith other concept and the starting concept, Ei∪EuserA union of students in the ith other concept and students in the starting concept; i isi∪IobjectA test question union set of the test question in the ith other concept and the test question in the initial concept; i DiL is the product of the number of students in the student union set and the number of test questions in the test question union set; diWhether each student in the student union set carries out the corresponding relation of each test question in the wrong test question union set or not is judged; zero (D) is the number of test questions in the union of student's that have not been missed.
The first semantic similarity calculation formula is a semantic similarity formula based on formal concept analysis and proposed by Firsakoda, and the similarity between other concepts and the initial concept can be calculated more accurately through the formula, so that the possibility that test questions in other concepts with high similarity to the initial concept are recommended is higher. The recommendation calculation mode utilizes the commonality characteristics of the students to the maximum extent, and not only considers the missed test questions made by the target students. So that even if the similarity between the current test question and the test question missed by the target student is not high, the test question is possible to be recommended due to the fact that the first similarity corresponding to other concepts is larger.
S104: calculating a second similarity between the set of knowledge points for each test question and the set of knowledge points for each test question in the starting concept.
In the embodiment of the application, each test question corresponds to one knowledge point set, and the higher the correlation degree of knowledge points included in the two knowledge point sets is, the higher the similarity degree representing the two knowledge point sets is. The test question recommendation apparatus calculates a second similarity between the set of knowledge points for each test question and the set of knowledge points for each test question in the starting concept. For example, the set of knowledge points for the current question is z0The knowledge point set of each test question in the initial concept is z1-znThe test question recommendation devices respectively calculate z0And z1，z0And z2。。。z0And znAnd obtaining the maximum second similarity among the obtained plurality of second similarities.
Further, to calculate the second similarity between the knowledge point sets, in an exemplary embodiment, S104 may further include S1041 to S1042, as shown in fig. 4, where S1041 to S1042 specifically include the following:
s1041: and acquiring a knowledge point set of the non-done test questions except the test questions already done by the target students.
The test question recommending device acquires a knowledge point set of the test questions which are not done except the test questions which have already been done by the target student.
Specifically, before acquiring a knowledge point set of test questions, the test question recommendation device firstly judges whether the current test questions are test questions already done by a target student, and if not, acquires the knowledge point set of the current test questions; if so, no acquisition is performed. And finally obtaining a knowledge point set of each non-test question. By judging whether the current test question is the test question already made by the target student or not, repeated acquisition of a knowledge point set and subsequent repeated calculation of the second similarity are avoided, and the efficiency of test question recommendation is improved.
S1042: and calculating a second similarity between each knowledge point set of the non-made test questions and the knowledge point set of each test question in the starting concept.
The test question recommendation device calculates a second similarity between each set of knowledge points for the non-made test questions and each set of knowledge points for the test questions in the starting concept. The second similarity can be obtained by calculating the repetition rate of knowledge points in the knowledge point set of each test question, or can be obtained by a similarity calculation formula based on a knowledge graph.
In an exemplary embodiment, a second similarity between each set of knowledge points of the non-test question and the set of knowledge points of each test question in the starting concept is calculated through a second semantic similarity calculation formula based on a weight path of the knowledge graph; the second semantic similarity calculation formula is as follows:
IC(Clcs)＝-logProb(Clcs)
freq(Clcs)＝count(entities(Clcs))
BSijset of knowledge points for problem not made, BSuserA set of knowledge points for each test question in the starting concept, m is a set of knowledge points BSijN is the knowledge point set BSuserNumber of knowledge points in, MoKnowledge point set BSijInner knowledge point, NpGathering BS for knowledge pointsuserInner knowledge points, simwpath(Mo,Np) For similarity of any two knowledge points, CS (BS)ij,BSuser) Is BSijAnd BSuserAll possible sets of pairs of knowledge points in the set of knowledge points, length (M)o,Np) Is MoAnd NpThe relative path length in the knowledge graph, IC (Clcs) is the IC value of the minimum common father node of two knowledge points in the knowledge graph, N is the occurrence frequency of the knowledge point corresponding to the minimum common father node Clcs in the knowledge graph, and count () is used for calculating the test question corresponding to the knowledge point in the knowledge graphNumber of occurrences in the spectrum.
The second semantic similarity calculation formula calculates the semantic similarity by using the path lengths of the two concepts in the knowledge-graph and the minimum common parent node. By combining the knowledge map, weak knowledge points of students can be analyzed more fully, and the calculation of the recommendation degree of test questions is more accurate.
In another exemplary embodiment, the test question recommendation device may also directly perform the second similarity calculation for each test question without determining whether the current test question is a test question already made by the target student, and when the test question recommendation is finally performed, obtain an unredone test question with a higher recommendation degree and recommend the unredone test question to the target student by determining whether the recommended test question is a test question already made by the target student.
S105: and multiplying the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts.
In the embodiment of the application, the test question recommendation device multiplies the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts.
In an exemplary embodiment, the test question recommending device multiplies the first similarity corresponding to each of the other concepts by the maximum second similarity corresponding to the knowledge point set of the non-made test questions in the other concepts through a recommendation calculating formula to obtain the recommendation of each non-made test question in the other concepts; wherein, the recommendation degree calculation formula is as follows:
Scoreij＝comSim(Ci,Cuser)*simkm(BSij,BSuser)
Scoreijthe recommendation degree corresponding to the jth non-done test question in the ith other concept, comSim (C)i,Cuser) For similarity between the ith other concept and the starting concept, simkm(BSij,BSuser) For the jth non-done test question in the ith other conceptThe maximum similarity between the set of knowledge points of (a) and the set of knowledge points of each test question in the starting concept.
The relevance of students and test questions is reflected through the first similarity of other concepts and the initial concept, candidate recommended test questions with high quality and generality can be mined, then the test questions matched with weak knowledge points of the students are searched by combining the knowledge graph, the maximum second similarity of each test question which is not made is obtained, and the weight of the test questions similar to the weak knowledge points is increased in a targeted mode. Finally, the recommendation degree of each non-done test question in other concepts is obtained, and the recommendation degree accuracy is improved.
S106: recommending the unfinished test questions with larger recommendation degree to the target student according to the recommendation degree of each test question; wherein the non-done test questions are test questions except the test questions already done by the target student.
In the embodiment of the application, the test question recommending device recommends the unfinished test questions with larger recommendation degree to the target students according to the recommendation degree of each test question; wherein the non-done test questions are test questions except the test questions already done by the target student.
Specifically, the test question recommendation device may rank the test questions according to the recommendation degree of each test question, and based on a ranking result, recommend the non-done test questions with the top-N item recommendation degrees to the target student. The test question recommending device can also select the non-done test questions with the recommendation degree larger than the recommendation degree threshold value to recommend the non-done test questions to the target students according to the recommendation degree threshold value, and the recommendation degree threshold value can be set according to the number of the test questions selected by the target students at this time, and is not limited here.
In an exemplary embodiment, after the recommendation degrees of all the test questions are calculated, the test questions already done by the target student are filtered, and the non-done test questions with higher recommendation degrees are recommended to the target student, so that the students are prevented from repeatedly doing the same test questions.
In another exemplary embodiment, when calculating the second similarity between the knowledge point set of each test question and the knowledge point set of each test question in the starting concept, the knowledge point sets of the test questions other than the test questions already done by the target student are obtained, and then the second similarity between the knowledge point set of each test question and the knowledge point set of each test question in the starting concept is calculated. Therefore, the finally obtained recommendation degrees of the test questions are all recommendation degrees of the test questions which are not made, and the test questions which are already made by the target student do not need to be filtered. The method ensures that students are prevented from repeatedly achieving the same test questions, improves the algorithm efficiency and reduces the calculation amount.
Further, to avoid the same test questions appearing repeatedly in the recommendation process, in an exemplary embodiment, S106 may include S1061 to S1062, as shown in fig. 5, where S1061 to S1062 are specifically as follows:
s1061: and acquiring all recommendation degrees calculated by each of the non-done test questions in different other concepts.
And the test question recommending device acquires all recommendation degrees calculated by each of the non-done test questions in different other concepts. Because the non-done test questions may exist in different other concepts, when the first similarity degrees corresponding to different other concepts are different, the finally obtained recommendation degrees of the non-done test questions in different other concepts are also different.
S1062: recommending the unfinished test questions with larger maximum value of all recommendation degrees calculated by the unfinished test questions in different other concepts to the target students according to the recommendation degrees of the unfinished test questions.
And the test question recommending device recommends the non-done test questions with larger maximum value of all recommendation degrees calculated by the non-done test questions in different other concepts to the target students according to the recommendation degrees of the non-done test questions.
Because the non-done test questions may exist in different other concepts, the recommendation to the target student is carried out according to the maximum value of all recommendation degrees calculated by the non-done test questions in the different other concepts, so that the recommendation is more reasonable, and the accuracy of the test question recommendation is further improved.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a test question recommendation apparatus according to an exemplary embodiment of the present invention. The included units are used for executing steps in the embodiments corresponding to fig. 1 and fig. 4 to fig. 5, and refer to the related descriptions in the embodiments corresponding to fig. 1 and fig. 4 to fig. 5. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 6, the test question recommendation apparatus 2 based on formal concept analysis and knowledge graph includes:
the first construction unit 21 is configured to establish a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, where a relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a knowledge point set;
the second construction unit 22 is used for establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept;
a first arithmetic unit 23 for calculating a first similarity between the initial concept and the concepts other than the initial concept in the student-question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions by the target students;
a second arithmetic unit 24 for calculating a maximum second similarity between the knowledge point set of each test question and the knowledge point set of each test question in the starting concept;
a third operation unit 25, configured to multiply the first similarity corresponding to each of the other concepts by the maximum second similarity corresponding to the knowledge point set of each of the test questions in the other concepts to obtain a recommendation degree of each of the test questions in the other concepts;
and the recommending unit 26 is used for recommending the test questions with larger recommendation degrees to the target students according to the recommendation degrees of all the test questions.
Referring to fig. 7, fig. 7 is a schematic diagram of a test question recommendation device according to an embodiment of the present invention. As shown in fig. 7, the test question recommending apparatus 3 of this embodiment includes: a processor 30, a memory 31 and a computer program 32, such as a test question recommendation program, stored in said memory 31 and executable on said processor 30. The processor 30, when executing the computer program 32, implements the steps in the above-described embodiments of the test question recommendation method, such as the steps S101 to S106 shown in fig. 1. Alternatively, the processor 30, when executing the computer program 32, implements the functions of the modules/units in the above-mentioned device embodiments, such as the functions of the units 21 to 26 shown in fig. 6.
Illustratively, the computer program 32 may be partitioned into one or more modules/units that are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions for describing the execution process of the computer program 32 in the test question recommending apparatus 3. For example, the computer program 32 may be divided into a first construction unit, a second construction unit, a first operation unit, a second operation unit, a third operation unit and a recommendation unit, and each unit has the following specific functions:
the first construction unit is used for establishing a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, and the relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a knowledge point set;
the second construction unit is used for establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept;
the first arithmetic unit is used for calculating a first similarity between the initial concept and other concepts except the initial concept in the student-test question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions by the target students;
the second operation unit is used for calculating the maximum second similarity between the knowledge point set of each test question and the knowledge point set of each test question in the starting concept;
the third operation unit is used for multiplying the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts;
and the recommending unit is used for recommending the test questions with larger recommendation degrees to the target students according to the recommendation degrees of all the test questions.
Further, the first arithmetic unit is specifically configured to:
calculating a first similarity of the initial concept and other concepts except the initial concept in the student-question concept lattice through a first semantic similarity calculation formula based on formal concept analysis; wherein the first semantic similarity calculation formula is as follows:
|Di|＝|Ei∪Euser|×|Ii∪Iuser|
Cias the ith other concept, CuserTo initiate the concept, comSim (C)i,Cuser) For the similarity between the ith other concept and the starting concept, Ei∪EuserA union of students in the ith other concept and students in the starting concept; i isi∪IobjectA test question union set of the test question in the ith other concept and the test question in the initial concept; i DiL is the product of the number of students in the student union set and the number of test questions in the test question union set; diWhether each student in the student union set carries out the corresponding relation of each test question in the wrong test question union set or not is judged; zero (D) is the number of test questions in the union of student's that have not been missed.
Further, the second arithmetic unit includes:
the acquisition unit is used for acquiring a knowledge point set of the test questions which are not done except the test questions which have already been done by the target students;
and the fourth operation unit is used for calculating a second similarity between each knowledge point set of the non-made test questions and the knowledge point set of each test question in the starting concept.
Further, the fourth operation unit is specifically configured to:
calculating a second similarity between each knowledge point set of the non-test questions and the knowledge point set of each test question in the starting concept through a second semantic similarity calculation formula based on a knowledge map weight path; the second semantic similarity calculation formula is as follows:
IC(Clcs)＝-logProb(Clcs)
freq(Clcs)＝count(entities(Clcs))
BSijset of knowledge points for problem not made, BSuserA set of knowledge points for each test question in the starting concept, m is a set of knowledge points BSijN is the knowledge point set BSuserNumber of knowledge points in, MoKnowledge point set BSijInner knowledge point, NpGathering BS for knowledge pointsuserInner knowledge points, simwpath(Mo,Np) For similarity of any two knowledge points, CS (BS)ij,BSuser) Is BSijAnd BSuserAll possible sets of pairs of knowledge points in the set of knowledge points, length (M)o,Np) Is MoAnd NpRelative path length in the knowledge-graph, IC (Clcs) is the distance between two knowledge points in the knowledge-graphIdentifying the IC value of the minimum public father node in the map, wherein N is the occurrence frequency of the knowledge point corresponding to the minimum public father node Clcs in the knowledge map, and count () is used for calculating the occurrence frequency of the test question corresponding to the knowledge point in the knowledge map.
Further, the third arithmetic unit is specifically configured to:
multiplying the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of the non-made test questions in the other concepts through a recommendation calculation formula to obtain the recommendation of each non-made test question in the other concepts; wherein, the recommendation degree calculation formula is as follows:
Scoreij＝comSim(Ci,Cuser)*simkm(BSij,BSuser)
Scoreijthe recommendation degree corresponding to the jth non-done test question in the ith other concept, comSim (C)i,Cuser) For similarity between the ith other concept and the starting concept, simkm(BSij,BSuser) The maximum similarity between the knowledge point set of the jth undone test question in the ith other concept and the knowledge point set of each test question in the starting concept.
Further, the recommending unit is specifically configured to:
acquiring all recommendation degrees calculated by each of the non-done test questions in different other concepts;
recommending the unfinished test questions with larger maximum value of all recommendation degrees calculated by the unfinished test questions in different other concepts to the target students according to the recommendation degrees of the unfinished test questions.
Further, the second building unit is specifically configured to:
and establishing a student-test question concept lattice according to the form concept background and a preset progressive construction concept lattice algorithm.
The test question recommending apparatus 3 may include, but is not limited to, a processor 30 and a memory 31. It will be understood by those skilled in the art that fig. 7 is only an example of the test question recommending apparatus 3, and does not constitute a limitation to the test question recommending apparatus 3, and may include more or less components than those shown, or combine some components, or different components, for example, the test question recommending apparatus 8 may further include an input-output device, a network access device, a bus, etc.
The Processor 30 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 31 may be an internal storage unit of the test question recommending apparatus 3, such as a hard disk or a memory of the test question recommending apparatus 3. The memory 31 may also be an external storage device of the test question recommending apparatus 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the test question recommending apparatus 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the test question recommending apparatus 3. The memory 31 is used for storing the computer program and other programs and data required by the test question recommendation apparatus. The memory 31 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of 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, devices or units, and may be in an electrical, mechanical 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 network 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 modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. . Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice. The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.
Claims (10)
1. A test question recommendation method based on formal concept analysis and knowledge graph is characterized by comprising the following steps:
establishing a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, wherein the relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a knowledge point set;
establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept;
calculating a first similarity between the initial concept and other concepts except the initial concept in the student-test question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions by the target students;
calculating a second similarity between the set of knowledge points for each test question and the set of knowledge points for each test question in the starting concept;
multiplying the first similarity corresponding to each other concept with the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts;
recommending the unfinished test questions with larger recommendation degree to the target student according to the recommendation degree of each test question; wherein the non-done test questions are test questions except the test questions already done by the target student.
2. The method for recommending test questions based on formal concept analysis and knowledge-graph according to claim 1, wherein said calculating a first similarity between the starting concept and other concepts except the starting concept in said student-test question concept lattice comprises the steps of:
calculating a first similarity of the initial concept and other concepts except the initial concept in the student-question concept lattice through a first semantic similarity calculation formula based on formal concept analysis; wherein the first semantic similarity calculation formula is as follows:
|Di|＝|Ei∪Euser|×|Ii∪Iuser|
Cias the ith other concept, CuserTo initiate the concept, comSim (C)i,Cuser) For the similarity between the ith other concept and the starting concept, Ei∪EuserA union of students in the ith other concept and students in the starting concept; i isi∪IobjectA test question union set of the test question in the ith other concept and the test question in the initial concept; i DiL is the product of the number of students in the student union set and the number of test questions in the test question union set; diWhether each student in the student union set carries out the corresponding relation of each test question in the wrong test question union set or not is judged; zero (D) is the number of test questions in the union of student's that have not been missed.
3. The method for recommending test questions based on formal concept analysis and knowledge-graph according to claim 1, wherein said calculating a second similarity between the set of knowledge points of each test question and the set of knowledge points of each test question in said starting concept comprises the steps of:
acquiring a knowledge point set of the non-done test questions except the already done test questions of the target students;
and calculating a second similarity between each knowledge point set of the non-made test questions and the knowledge point set of each test question in the starting concept.
4. The method for recommending test questions based on formal concept analysis and knowledge-graph according to claim 3, wherein said calculating a second similarity between each of said set of knowledge points of non-done test questions and said set of knowledge points of each test question in said starting concept comprises the steps of:
calculating a second similarity between each knowledge point set of the non-test questions and the knowledge point set of each test question in the starting concept through a second semantic similarity calculation formula based on a knowledge map weight path; the second semantic similarity calculation formula is as follows:
IC(Clcs)＝-logProb(Clcs)
freq(Clcs)＝count(entities(Clcs))
BSijset of knowledge points for problem not made, BSuserA set of knowledge points for each test question in the starting concept, m is a set of knowledge points BSijN is the knowledge point set BSuserNumber of knowledge points in, MoKnowledge point set BSijInner knowledge point, NpGathering BS for knowledge pointsuserInner knowledge points, simwpath(Mo,Np) For similarity of any two knowledge points, CS (BS)ij,BSuser) Is BSijAnd BSuserAll possible sets of pairs of knowledge points in the set of knowledge points, length (M)o,Np) Is MoAnd NpRelative Path Length in the knowledge-graph, IC (Clcs) is the minimum of two knowledge points in the knowledge-graphAnd N is the occurrence frequency of the knowledge point corresponding to the minimum public father node Clcs in the knowledge graph, and count () is used for calculating the occurrence frequency of the test question corresponding to the knowledge point in the knowledge graph.
5. The method for recommending test questions based on formal concept analysis and knowledge graph according to claim 3, wherein said step of multiplying the first similarity corresponding to each of said other concepts by the maximum second similarity corresponding to the knowledge point set of each test question in said other concepts to obtain the recommendation degree of each test question in said other concepts comprises the steps of:
multiplying the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of the non-made test questions in the other concepts through a recommendation calculation formula to obtain the recommendation of each non-made test question in the other concepts; wherein, the recommendation degree calculation formula is as follows:
Scoreij＝comSim(Ci,Cuser)*simkm(BSij,BSuser)
Scoreijthe recommendation degree corresponding to the jth non-done test question in the ith other concept, comSim (C)i,Cuser) For similarity between the ith other concept and the starting concept, simkm(BSij,BSuser) The maximum similarity between the knowledge point set of the jth undone test question in the ith other concept and the knowledge point set of each test question in the starting concept.
6. The test question recommendation method based on formal concept analysis and knowledge graph according to claim 3, wherein the method of recommending the non-done test questions with larger recommendation degree to the target students according to the recommendation degree of the test questions comprises the steps of:
acquiring all recommendation degrees calculated by each of the non-done test questions in different other concepts;
recommending the unfinished test questions with larger maximum value of all recommendation degrees calculated by the unfinished test questions in different other concepts to the target students according to the recommendation degrees of the unfinished test questions.
7. The test question recommendation method based on formal concept analysis and knowledge graph according to any one of claims 1 to 6, wherein the establishing of student-test question concept lattice according to the formal concept background comprises the steps of:
and establishing a student-test question concept lattice according to the form concept background and a preset progressive construction concept lattice algorithm.
8. A test question recommendation device based on formal concept analysis and knowledge graph is characterized by comprising:
the first construction unit is used for establishing a formal concept background with objects of all students and attributes of all test questions according to the question making records of the students, and the relationship in the formal concept background indicates whether each student misses each test question; wherein each test question is associated with a knowledge point set;
the second construction unit is used for establishing a student-test question concept lattice according to the form concept background; the student-test question concept lattice comprises a plurality of concepts, and students in each concept miss test questions in the concept;
the first arithmetic unit is used for calculating a first similarity between the initial concept and other concepts except the initial concept in the student-test question concept lattice; wherein students in the starting concept comprise target students, and the test questions in the starting concept are all missed test questions by the target students;
the second operation unit is used for calculating a second similarity between the knowledge point set of each test question and the knowledge point set of each test question in the starting concept;
the third operation unit is used for multiplying the first similarity corresponding to each other concept by the maximum second similarity corresponding to the knowledge point set of each test question in the other concepts to obtain the recommendation degree of each test question in the other concepts;
the recommending unit is used for recommending the unfinished test questions with larger recommendation degree to the target student according to the recommendation degree of each test question; wherein the non-done test questions are test questions except the test questions already done by the target student.
9. A form concept analysis and knowledge-graph based test question recommendation apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911169910.1A CN111125339B (en) | 2019-11-26 | 2019-11-26 | Test question recommendation method based on formal concept analysis and knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911169910.1A CN111125339B (en) | 2019-11-26 | 2019-11-26 | Test question recommendation method based on formal concept analysis and knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111125339A true CN111125339A (en) | 2020-05-08 |
| CN111125339B CN111125339B (en) | 2023-05-09 |
Family
ID=70496701
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911169910.1A Active CN111125339B (en) | 2019-11-26 | 2019-11-26 | Test question recommendation method based on formal concept analysis and knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111125339B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580896A (en) * | 2020-12-31 | 2021-03-30 | 南京谦萃智能科技服务有限公司 | Knowledge point prediction method, knowledge point prediction device, knowledge point prediction equipment and storage medium |
| CN114328633A (en) * | 2021-12-28 | 2022-04-12 | 河南大学 | Wrong question knowledge point strengthening training test question recommendation method based on concept lattice |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273490A (en) * | 2017-06-14 | 2017-10-20 | 北京工业大学 | A kind of combination mistake topic recommendation method of knowledge based collection of illustrative plates |
| CN109359215A (en) * | 2018-12-03 | 2019-02-19 | 江苏曲速教育科技有限公司 | Video intelligent method for pushing and system |
| CN109635100A (en) * | 2018-12-24 | 2019-04-16 | 上海仁静信息技术有限公司 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
| CN110232185A (en) * | 2019-01-07 | 2019-09-13 | 华南理工大学 | Towards financial industry software test knowledge based map semantic similarity calculation method |
-
2019
- 2019-11-26 CN CN201911169910.1A patent/CN111125339B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273490A (en) * | 2017-06-14 | 2017-10-20 | 北京工业大学 | A kind of combination mistake topic recommendation method of knowledge based collection of illustrative plates |
| CN109359215A (en) * | 2018-12-03 | 2019-02-19 | 江苏曲速教育科技有限公司 | Video intelligent method for pushing and system |
| CN109635100A (en) * | 2018-12-24 | 2019-04-16 | 上海仁静信息技术有限公司 | A kind of recommended method, device, electronic equipment and the storage medium of similar topic |
| CN110232185A (en) * | 2019-01-07 | 2019-09-13 | 华南理工大学 | Towards financial industry software test knowledge based map semantic similarity calculation method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580896A (en) * | 2020-12-31 | 2021-03-30 | 南京谦萃智能科技服务有限公司 | Knowledge point prediction method, knowledge point prediction device, knowledge point prediction equipment and storage medium |
| CN114328633A (en) * | 2021-12-28 | 2022-04-12 | 河南大学 | Wrong question knowledge point strengthening training test question recommendation method based on concept lattice |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111125339B (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7343568B2 (en) | Identifying and applying hyperparameters for machine learning | |
| KR20180041200A (en) | Information processing method and apparatus | |
| US9633403B2 (en) | Managing sustainable intellectual property portfolio of an enterprise | |
| US10296837B2 (en) | Comment-comment and comment-document analysis of documents | |
| US8949271B2 (en) | Method for monitoring a number of machines and monitoring system | |
| Demir et al. | Multiobjective evolutionary clustering of web user sessions: a case study in web page recommendation | |
| EP2645309B1 (en) | Automatic combination and mapping of text-mining services | |
| CN103514304A (en) | Project recommendation method and device | |
| CN111651641B (en) | Graph query method, device and storage medium | |
| CN113360711B (en) | Model training and executing method, device, equipment and medium for video understanding task | |
| CN111125339B (en) | Test question recommendation method based on formal concept analysis and knowledge graph | |
| CN109872026A (en) | Evaluation result generation method, device, equipment and computer readable storage medium | |
| US10853332B2 (en) | Discovering schema using anchor attributes | |
| Smith-Miles et al. | Instance space analysis for algorithm testing: Methodology and software tools | |
| Avraham et al. | The discrete and semicontinuous Fréchet distance with shortcuts via approximate distance counting and selection | |
| Riondato et al. | Finding the true frequent itemsets | |
| CN109408643B (en) | Fund similarity calculation method, system, computer equipment and storage medium | |
| CN111427544B (en) | Software requirement document generation method and device, storage medium and electronic equipment | |
| CN111797313A (en) | Self-learning recommendation method and device, computer equipment and storage medium | |
| Feng et al. | On a mallows-type model for (ranked) choices | |
| Dobrean et al. | A Hybrid Approach to MVC Architectural Layers Analysis. | |
| CN116304155A (en) | Three-dimensional member retrieval method, device, equipment and medium based on two-dimensional picture | |
| CN109885651A (en) | A kind of question pushing method and device | |
| Wotzlaw | On Solving the Maximum $ k $-club Problem | |
| Bruss et al. | Graph embeddings at scale |
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 |