CN112733035A - Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device - Google Patents
Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device Download PDFInfo
- Publication number
- CN112733035A CN112733035A CN202110084853.8A CN202110084853A CN112733035A CN 112733035 A CN112733035 A CN 112733035A CN 202110084853 A CN202110084853 A CN 202110084853A CN 112733035 A CN112733035 A CN 112733035A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- knowledge point
- learned
- points
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/381—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using identifiers, e.g. barcodes, RFIDs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Library & Information Science (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a knowledge point recommendation method and device based on a knowledge graph, a storage medium and an electronic device. The knowledge point recommendation method comprises the following steps: generating a knowledge graph according to the constructed subject level model and the mapping relation of the knowledge points; and determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user through a knowledge connectivity algorithm based on the knowledge map. The method and the device solve the technical problems that the recommendation precision is low and the requirements of the user on the knowledge points cannot be well met due to the fact that knowledge point recommendation cannot be carried out based on knowledge connectivity.
Description
Technical Field
The application relates to the field of learning resource recommendation, in particular to a knowledge point recommendation method and device based on a knowledge graph, a storage medium and an electronic device.
Background
The inventor finds that learning resources are recommended to a learner, only the interest degree of the learner is considered, the learning sequence of objective existence of different knowledge points is not considered, the structure and the characteristics of subject knowledge are not considered, and knowledge point recommendation based on knowledge connectivity cannot be performed; the recommendation precision is low, and the requirements of the user on the knowledge points cannot be well met.
Aiming at the problems that the recommendation precision is low and the requirements of users on knowledge points cannot be well met due to the fact that knowledge point recommendation cannot be carried out based on knowledge connectivity in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The application mainly aims to provide a knowledge point recommendation method, a knowledge point recommendation device, a storage medium and an electronic device based on a knowledge graph, so as to solve the problems that the recommendation precision is low and the requirements of a user on knowledge points cannot be well met due to the fact that knowledge point recommendation cannot be carried out based on knowledge connectivity.
In order to achieve the above object, according to one aspect of the present application, there is provided a knowledge point recommendation method based on a knowledge graph.
The knowledge point recommendation method based on the knowledge graph comprises the following steps: generating a knowledge graph according to the constructed subject level model and the mapping relation of the knowledge points; and determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user through a knowledge connectivity algorithm based on the knowledge map.
Further, the building of the discipline hierarchy model comprises the following steps: respectively constructing subject labels and course labels, course labels and chapter knowledge labels, and mapping relations between chapter knowledge labels and knowledge point labels; and building a discipline hierarchical model according to the mapping relation.
Further, the construction of the knowledge point mapping relation comprises the following steps: constructing a mapping relation between the first knowledge point and the second knowledge point and between the first knowledge point and the third knowledge point; the second knowledge point is a precursor knowledge point needing to be learned before the first knowledge point is learned; the third knowledge point is a subsequent knowledge point which needs to be learned after the first knowledge point is learned.
Further, after the knowledge connection degree between the learned knowledge point and the knowledge point to be learned of the target user is determined through a knowledge connection degree algorithm based on the knowledge map, the method further comprises the following steps: sorting and selecting the knowledge points to be learned in a descending order according to the connectivity of the knowledge points; generating a to-be-recommended list of knowledge points based on the sorting and selecting result; and recommending the list to be recommended to the target user.
Further, the method also comprises the following steps: acquiring an implicit characteristic vector of a user; calculating the similarity of the implicit characteristic vectors by adopting a similarity algorithm; sorting the similarity in a descending order, and selecting a user with the similarity before a preset threshold as a similar user of a target user; and calculating the interest degree of the target user to the knowledge point based on the historical scores of the similar users to the knowledge point and the corresponding similarity.
Further, based on the historical scores and the corresponding similarities of the similar users to the knowledge points, after the interest degree of the target user to the knowledge points is calculated, the method further includes: sorting and selecting the knowledge points to be learned in a descending order according to the interest degree; generating a to-be-recommended list of knowledge points based on the sorting and selecting result; and recommending the list to be recommended to the target user.
Further, based on the historical scores and the corresponding similarities of the similar users to the knowledge points, after the interest degree of the target user to the knowledge points is calculated, the method further includes: performing dynamic linear fusion weighting based on the knowledge connectivity and the interest degree, and calculating to obtain the recommendation degree of the knowledge point to the target user; sorting and selecting the knowledge points to be learned in a descending order according to the recommendation degree; generating a to-be-recommended list of knowledge points based on the sorting and selecting result; and recommending the list to be recommended to the target user.
In order to achieve the above object, according to another aspect of the present application, there is provided a knowledge point recommending apparatus based on a knowledge graph.
The knowledge-graph-based knowledge point recommendation device according to the application comprises: the generating module is used for generating a knowledge graph according to the constructed discipline level model and the mapping relation of the knowledge points; and the determining module is used for determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user through a knowledge connectivity algorithm based on the knowledge map.
In order to achieve the above object, according to another aspect of the present application, there is provided a storage medium.
A storage medium according to the application, having stored therein a computer program, wherein the computer program is arranged to perform the method as set forth in any one of the preceding claims when executed.
In order to achieve the above object, according to another aspect of the present application, there is provided an electronic device.
An electronic device according to the application, comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the method of any of the above.
In the embodiment of the application, a knowledge graph is generated by referring to a built subject level model and a knowledge point mapping relation in a knowledge point recommendation mode based on the knowledge graph; determining the knowledge connectivity between learned knowledge points and knowledge points to be learned of a target user through a knowledge connectivity algorithm based on a knowledge map; the method achieves the purpose of recommending the knowledge points based on the knowledge connectivity, thereby effectively improving the recommendation precision, and the recommended knowledge points can well meet the technical effect of user requirements, and further solves the technical problems that the recommendation precision is low and the requirements of the user on the knowledge points cannot be well met due to the fact that the knowledge point recommendation cannot be carried out based on the knowledge connectivity.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a flow diagram of a knowledge-graph based knowledge point recommendation method according to an embodiment of the application;
FIG. 2 is a schematic diagram of a knowledge-graph based knowledge point recommendation device according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a storage medium according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
FIG. 5 is a diagram of a discipline level model in accordance with a preferred embodiment of the present application;
fig. 6 is a schematic diagram of a knowledge point mapping relationship according to another preferred embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the invention and its embodiments and are not intended to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meanings of these terms in the present invention can be understood by those skilled in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meanings of the above terms in the present invention can be understood by those of ordinary skill in the art according to specific situations.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
According to an embodiment of the present invention, there is provided a knowledge point recommendation method based on a knowledge graph, as shown in fig. 1, the method includes the following steps S101 to S102:
s101, generating a knowledge graph by referring to the constructed subject level model and the mapping relation of knowledge points;
the discipline hierarchical model can reflect the relation between the knowledge points and other knowledge structure labels; the mapping relation of the knowledge points can reflect the relation between different knowledge points; combining the discipline level model and the knowledge point mapping relation to generate a knowledge graph; therefore, the constructed knowledge graph network can fully reflect the disciplinary knowledge structure and characteristics and can fully reflect the sequence among knowledge points; therefore, guarantee can be provided for the determination of knowledge connectivity.
In a preferred embodiment, the building of the discipline hierarchy model includes:
respectively constructing subject labels and course labels, course labels and chapter knowledge labels, and mapping relations between chapter knowledge labels and knowledge point labels;
and building a discipline hierarchical model according to the mapping relation.
A discipline hierarchical model shown in FIG. 5 can be established according to the discipline knowledge structure and characteristics; specifically, the subject knowledge structure and characteristics are as follows: the subject can be divided into course 1, course 2, etc.; the course 1 can be divided into chapter knowledge 1, chapter knowledge 2 and the like, and the course 2 can be divided into chapter knowledge 3, chapter knowledge 4 and the like; chapter knowledge 1 can be divided into knowledge points 1, knowledge points 2, etc., chapter knowledge 2 can be divided into knowledge points 3, knowledge points 4, etc., chapter knowledge 3 can be divided into knowledge points 5, knowledge points 6, etc., and chapter knowledge 4 can be divided into knowledge points 7, knowledge points 8, etc. According to the subject knowledge structure and characteristics, mapping relations among the subject labels and the course labels, the course labels and the chapter knowledge labels, and the chapter knowledge labels and the knowledge point labels are constructed, and therefore a subject hierarchy model capable of reflecting the subject knowledge structure and characteristics is obtained.
In a preferred embodiment, the construction of the knowledge point mapping relation comprises:
constructing a mapping relation between the first knowledge point and the second knowledge point and between the first knowledge point and the third knowledge point; the second knowledge point is a precursor knowledge point needing to be learned before the first knowledge point is learned; the third knowledge point is a subsequent knowledge point which needs to be learned after the first knowledge point is learned.
In this embodiment, the relationship between knowledge points mainly takes predecessor and successor as main attributes. As shown in fig. 6, the knowledge point a must be learned before the knowledge point B is learned, and the knowledge point a is called a predecessor knowledge point of the knowledge point B; and after learning the knowledge point B, learning the knowledge point C, and then calling the knowledge point B as a successor of the knowledge point C. And respectively establishing mapping relations among the knowledge points according to the definition.
And S102, determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user through a knowledge connectivity algorithm based on the knowledge map.
In one embodiment, in knowledge-graph G (V, E), V represents a set of knowledge and E represents a set of relationships between knowledge points. For a target user u with historical behaviors, the user knowledge base K (u) is a set of all knowledge points which have been learned by the user, and the resource knowledge base K (F) is a set of all knowledge points to be learned by the user. The knowledge connectivity from the knowledge points k _ i in the resource knowledge base k (f) to the user knowledge base k (u) is calculated and disclosed as follows:
in|kii represents the degree of the knowledge point ki;
KSn represents the nth knowledge domain of a discipline, such as the nth chapter knowledge in the above figures. When the nodes Ki and Kj belong to the same knowledge domain KSn, the shortest path value between Ki and Kj is 1; when the nodes Ki and Kj are the same knowledge point or no path exists between the Ki and the Kj, the shortest path value between the Ki and the Kj is 0; in other cases, the shortest path value between the nodes Ki and Kj is the shortest number of edges from Ki to Kj in the knowledge graph;
The shorter the path between knowledge points is, the tighter the knowledge connection is; the greater the degree of income of a knowledge point, the more important the knowledge point is. By combining the two methods, the smaller the sum of the total paths of the knowledge points to be learned and the learned knowledge points in the resource knowledge base is, the tighter the connection between the knowledge points to be learned and the user knowledge base is, the more suitable the resource is to be recommended to the user for learning. Therefore, the knowledge connection degree between each learned knowledge point and each to-be-learned knowledge point of the target user can be calculated through the formula.
In the embodiment, the knowledge points with the highest knowledge point connectivity can be recommended to the target user, all the knowledge points to be learned can be directly recommended to the user after being sorted, and a plurality of knowledge points can be selected to be recommended to the user after all the knowledge points to be learned are sorted; knowledge point recommendation based on knowledge connectivity is achieved, the structure and the characteristics of subject knowledge and the learning sequence of the knowledge points are fully considered in the recommendation mode, so that the recommendation precision is effectively improved, and the requirements of users on the knowledge points can be well met.
In an alternative embodiment, after determining the knowledge connectivity between the learned knowledge point and the learned knowledge point of the target user through the knowledge connectivity algorithm based on the knowledge map, the method further includes:
sorting and selecting the knowledge points to be learned in a descending order according to the connectivity of the knowledge points;
generating a to-be-recommended list of knowledge points based on the sorting and selecting result;
and recommending the list to be recommended to the target user.
The knowledge connection degree algorithm based on the knowledge map calculates the connection degree of knowledge points between a plurality of groups of learned knowledge points and knowledge points to be learned, a descending order algorithm is adopted to order the connection degree of the plurality of groups of knowledge points, and the knowledge points to be learned corresponding to the connection degree of the plurality of groups of knowledge points arranged in the front row are selected according to a preset group number threshold; and listing the knowledge points to be learned in a list to be recommended and recommending the knowledge points to the target user. The knowledge point recommendation is realized, and the recommendation mode based on the knowledge point connectivity is adopted, so that the structure and the characteristics of subject knowledge and the sequence of learning of the knowledge points can be fully considered, the recommendation precision is effectively improved, and the requirements of users on the knowledge points can be well met.
From the above description, it can be seen that the present invention achieves the following technical effects:
in the embodiment of the application, a knowledge graph is generated by referring to a built subject level model and a knowledge point mapping relation in a knowledge point recommendation mode based on the knowledge graph; determining the knowledge connectivity between learned knowledge points and knowledge points to be learned of a target user through a knowledge connectivity algorithm based on a knowledge map; the method achieves the purpose of recommending the knowledge points based on the knowledge connectivity, thereby effectively improving the recommendation precision, and the recommended knowledge points can well meet the technical effect of user requirements, and further solves the technical problems that the recommendation precision is low and the requirements of the user on the knowledge points cannot be well met due to the fact that the knowledge point recommendation cannot be carried out based on the knowledge connectivity.
According to the embodiment of the present invention, it is preferable that:
acquiring an implicit characteristic vector of a user;
calculating the similarity of the implicit characteristic vectors by adopting a similarity algorithm;
sorting the similarity in a descending order, and selecting a user with the similarity before a preset threshold as a similar user of a target user;
and calculating the interest degree of the target user to the knowledge point based on the historical scores of the similar users to the knowledge point and the corresponding similarity.
Specifically, the user implicit feature extraction is mainly carried out through an LSTM network according to the description information features of the user historical scoring knowledge points.
Input sequence for LSTM networks
The implicit feature vector of the historical scoring course of the user i according to the time sequence is output as the implicit feature vector of the user i.
Wherein, W1，W2，W3，W4Is a mapping matrix. b1，b2，b3，b4Is an offset. ClCell state at time l. y isi∈RDIs the implicit feature vector of user i. σ (.) is the sigmoid activation function.
And calculating the similarity between the implicit feature vectors of the users according to the obtained implicit feature vectors of the users. Common similarity calculation methods are: cosine similarity, modified cosine similarity, pearson correlation coefficient, and the like. In this embodiment, a cosine similarity calculation method is adopted.
Wherein u isiIs an implicit feature vector, u, of user ijIs the implicit feature vector of user j.
And performing descending sorting on the cosine similarity obtained by calculation according to the formula, and selecting a user with the top Nu of the cosine similarity as a similar user group for each user.
And acquiring historical scoring knowledge points of the similar user group, and calculating the interest degree of the target learning user on the knowledge points to be learned according to the following formula by using the similarity between the target user and the users of the similar user group.
Where K (i) represents the set of users who scored course f. S (u, N) represents the N users most similar to user u.
Average scores for all scored courses for user u. r isviScoring lesson i for user v.
In an optional implementation manner, after calculating the interest degree of the target user in the knowledge point based on the historical scores and the corresponding similarities of the similar users to the knowledge point, the method further includes:
sorting and selecting the knowledge points to be learned in a descending order according to the interest degree;
generating a to-be-recommended list of knowledge points based on the sorting and selecting result;
and recommending the list to be recommended to the target user.
And performing descending sorting according to the interest degree, and selecting a knowledge point Nk before the interest degree for each user as a recommendation candidate set. Specifically, a descending sorting algorithm is adopted to sort a plurality of groups of interest degrees, and the knowledge points to be learned corresponding to the plurality of groups of interest degrees arranged in the front are selected according to a preset group number threshold; and listing the knowledge points to be learned in a list to be recommended and recommending the knowledge points to the target user. The knowledge point recommendation method based on the collaborative filtering recommendation algorithm of the user is realized, similar learning users have similar interests and hobbies, favorite knowledge points are approximately the same, and the knowledge points which are liked by the similar learning users are recommended to the target learning user.
According to the embodiment of the present invention, preferably, after calculating the interest degree of the target user in the knowledge point based on the historical scores and the corresponding similarities of the similar users to the knowledge point, the method further includes:
performing dynamic linear fusion weighting based on the knowledge connectivity and the interest degree to obtain the recommendation degree of the knowledge point to be learned to the target user;
sorting and selecting the knowledge points to be learned in a descending order according to the recommendation degree;
generating a to-be-recommended list of knowledge points based on the sorting and selecting result;
and recommending the list to be recommended to the target user.
Defining the recommendation degree of the knowledge point k _ i in the resource knowledge base to the learner u as follows:
parameter alpha1、α2Respectively representing the importance degrees of the similarity of the knowledge point and the learner interest and the knowledge connection degree of the knowledge point to be learned and the knowledge point learned by the learner when the knowledge point is recommended to the learner.
In this embodiment, U is a target user set, r (U) is a recommendation list recommended to a user according to a behavior of the user on a training set, and t (U) is a behavior list of the user on a test set.
The data set consists of all learners, all knowledge points, and all learner scores for all knowledge points. The recommendation algorithm divides a data set by adopting a 5-fold cross validation mode, the 5-fold cross validation method randomly divides samples of the data set into 5 samples, 4 samples (80% of samples) are randomly selected as a training set each time, and the rest (20%) is used as a testing set.
Accuracy (Precision)
The accuracy rate represents the proportion of accurate items recommended to the user by the recommendation system in the total recommended number, and the precision rate is measured. Higher accuracy rates represent more accurate items recommended to the user by the recommendation system. The formula is defined as follows:
recall ratio (Recall)
The recall rate represents the proportion of accurate items in the real action items of the user recommended to the target user by the recommendation system, and the recall rate is measured. Higher recall rates represent more comprehensive than real-life behavior of items recommended to the user by the recommendation system. The formula is defined as follows:
F1-score
the higher the F1-score, the better the performance of the algorithm.
Respectively taking different recommended knowledge point quantities K and converting alpha into alpha1Is taken from Sα(e.g., 0.1) starting, each time ε is incremented, α is calculated1And F1-score is used as a basis for comprehensively judging the recommendation effect under different recommendation knowledge point numbers K. Examining the number of specific recommended knowledge points, and calculating alpha when the maximum value of F1-score is calculated1Value of (a)2Can be according to 1-alpha1To find out1、α2Substituting the recommendation formula to obtain a knowledge point k in the resource knowledge baseiRecommendation degree recommended to learner (target user) u.
The recommendation method not only considers similar users, but also fully considers subject knowledge structure and characteristics and the sequence learning sequence of knowledge points, thereby greatly improving the recommendation precision and well meeting the requirements of users on the knowledge points.
Sorting the multiple groups of recommendation degrees by adopting a descending sorting algorithm, and selecting to-be-learned knowledge points corresponding to the multiple groups of recommendation degrees arranged in the front according to a preset group number threshold; and listing the knowledge points to be learned in a list to be recommended and recommending the knowledge points to the target user. The knowledge point recommendation is realized, and because a recommendation mode based on knowledge point connectivity and the interest degree is adopted, not only are similar users considered, but also the subject knowledge structure and characteristics and the learning sequence of the knowledge points are fully considered, so that the recommendation precision is greatly improved, and the requirements of the users on the knowledge points can be well met.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present invention, there is also provided an apparatus for implementing the above knowledge point recommendation method based on a knowledge graph, as shown in fig. 2, the apparatus includes:
the generating module 10 is used for generating a knowledge graph according to the constructed discipline level model and the mapping relation of the knowledge points;
and the determining module 20 is configured to determine the knowledge connectivity between the learned knowledge point and the knowledge point to be learned of the target user through a knowledge connectivity algorithm based on the knowledge graph.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation manners, and details of this embodiment are not described herein again.
According to an embodiment of the present invention, there is also provided a storage medium for storing the above knowledge point recommendation method based on a knowledge graph, as shown in fig. 3, wherein the storage medium stores therein a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.
In this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation manners, and details of this embodiment are not described herein again.
According to an embodiment of the present invention, there is also provided an electronic device for storing and executing the above knowledge point recommendation method based on knowledge graph, as shown in fig. 4, the electronic device includes a memory 100 and a processor 200, the memory 100 stores therein a computer program, and the processor 200 is configured to execute the computer program to perform the steps in any of the above method embodiments.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation manners, and details of this embodiment are not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A knowledge point recommendation method based on knowledge graph is characterized by comprising the following steps:
generating a knowledge graph according to the constructed subject level model and the mapping relation of the knowledge points;
and determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user through a knowledge connectivity algorithm based on the knowledge map.
2. The knowledge point recommendation method of claim 1, wherein the building of the discipline hierarchy model comprises:
respectively constructing subject labels and course labels, course labels and chapter knowledge labels, and mapping relations between chapter knowledge labels and knowledge point labels;
and building a discipline hierarchical model according to the mapping relation.
3. The knowledge point recommendation method according to claim 1, wherein the construction of the knowledge point mapping relationship comprises:
constructing a mapping relation between the first knowledge point and the second knowledge point and between the first knowledge point and the third knowledge point; the second knowledge point is a precursor knowledge point needing to be learned before the first knowledge point is learned; the third knowledge point is a subsequent knowledge point which needs to be learned after the first knowledge point is learned.
4. The knowledge point recommendation method according to claim 1, wherein after determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user by the knowledge connectivity algorithm based on the knowledge graph, the method further comprises:
sorting and selecting the knowledge points to be learned in a descending order according to the connectivity of the knowledge points;
generating a to-be-recommended list of knowledge points based on the sorting and selecting result;
and recommending the list to be recommended to the target user.
5. The knowledge point recommendation method according to claim 1, further comprising:
acquiring an implicit characteristic vector of a user;
calculating the similarity of the implicit characteristic vectors by adopting a similarity algorithm;
sorting the similarity in a descending order, and selecting a user with the similarity before a preset threshold as a similar user of a target user;
and calculating the interest degree of the target user to the knowledge point based on the historical scores of the similar users to the knowledge point and the corresponding similarity.
6. The knowledge point recommendation method according to claim 5, wherein after calculating the interest degree of the target user in the knowledge point based on the historical scores and the corresponding similarities of the similar users to the knowledge point, the method further comprises:
sorting and selecting the knowledge points to be learned in a descending order according to the interest degree;
generating a to-be-recommended list of knowledge points based on the sorting and selecting result;
and recommending the list to be recommended to the target user.
7. The knowledge point recommendation method according to claim 5, wherein after calculating the interest degree of the target user in the knowledge point based on the historical scores and the corresponding similarities of the similar users to the knowledge point, the method further comprises:
performing dynamic linear fusion weighting based on the knowledge connectivity and the interest degree to obtain the recommendation degree of the knowledge point to be learned to the target user;
sorting and selecting the knowledge points to be learned in a descending order according to the recommendation degree;
generating a to-be-recommended list of knowledge points based on the sorting and selecting result;
and recommending the list to be recommended to the target user.
8. A knowledge point recommendation device based on knowledge graph is characterized by comprising:
the generating module is used for generating a knowledge graph according to the constructed discipline level model and the mapping relation of the knowledge points;
and the determining module is used for determining the knowledge connectivity between the learned knowledge points and the knowledge points to be learned of the target user through a knowledge connectivity algorithm based on the knowledge map.
9. A storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110084853.8A CN112733035A (en) | 2021-01-21 | 2021-01-21 | Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110084853.8A CN112733035A (en) | 2021-01-21 | 2021-01-21 | Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112733035A true CN112733035A (en) | 2021-04-30 |
Family
ID=75594920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110084853.8A Pending CN112733035A (en) | 2021-01-21 | 2021-01-21 | Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112733035A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113297419A (en) * | 2021-06-23 | 2021-08-24 | 南京谦萃智能科技服务有限公司 | Video knowledge point determining method and device, electronic equipment and storage medium |
| CN115329200A (en) * | 2022-08-26 | 2022-11-11 | 国家开放大学 | Teaching resource recommendation method based on knowledge graph and user similarity |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991197A (en) * | 2017-05-30 | 2017-07-28 | 海南大学 | The study point and learning path of a kind of target drives of knowledge based collection of illustrative plates recommend method |
| CN110941723A (en) * | 2019-11-18 | 2020-03-31 | 广东宜学通教育科技有限公司 | Method, system and storage medium for constructing knowledge graph |
| CN111309927A (en) * | 2020-02-17 | 2020-06-19 | 山东大学 | Knowledge graph mining-based personalized learning path recommendation method and system |
-
2021
- 2021-01-21 CN CN202110084853.8A patent/CN112733035A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991197A (en) * | 2017-05-30 | 2017-07-28 | 海南大学 | The study point and learning path of a kind of target drives of knowledge based collection of illustrative plates recommend method |
| CN110941723A (en) * | 2019-11-18 | 2020-03-31 | 广东宜学通教育科技有限公司 | Method, system and storage medium for constructing knowledge graph |
| CN111309927A (en) * | 2020-02-17 | 2020-06-19 | 山东大学 | Knowledge graph mining-based personalized learning path recommendation method and system |
Non-Patent Citations (1)
| Title |
|---|
| 张迪: "基于知识图谱的教学资源推荐方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113297419A (en) * | 2021-06-23 | 2021-08-24 | 南京谦萃智能科技服务有限公司 | Video knowledge point determining method and device, electronic equipment and storage medium |
| CN113297419B (en) * | 2021-06-23 | 2024-04-09 | 南京谦萃智能科技服务有限公司 | Video knowledge point determining method, device, electronic equipment and storage medium |
| CN115329200A (en) * | 2022-08-26 | 2022-11-11 | 国家开放大学 | Teaching resource recommendation method based on knowledge graph and user similarity |
| CN115329200B (en) * | 2022-08-26 | 2024-04-26 | 国家开放大学 | Teaching resource recommendation method based on knowledge graph and user similarity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | General functional matrix factorization using gradient boosting | |
| Xu et al. | Classifier cascades and trees for minimizing feature evaluation cost | |
| Liu et al. | Question quality analysis and prediction in community question answering services with coupled mutual reinforcement | |
| Sen et al. | A total error framework for digital traces of humans | |
| CN109766454A (en) | A kind of investor's classification method, device, equipment and medium | |
| CN110889450B (en) | Super-parameter tuning and model construction method and device | |
| CN112819023A (en) | Sample set acquisition method and device, computer equipment and storage medium | |
| CN111210072B (en) | Prediction model training and user resource limit determining method and device | |
| CN112733035A (en) | Knowledge point recommendation method and device based on knowledge graph, storage medium and electronic device | |
| CN112257818A (en) | Sample data processing method and device and computer equipment | |
| CN113656699B (en) | User feature vector determining method, related equipment and medium | |
| Arai et al. | Predicting quality of answer in collaborative Q/A community | |
| Yan et al. | A novel clustering algorithm based on fitness proportionate sharing | |
| CN112651487B (en) | Data recommendation method, system and medium based on graph collapse convolution neural network | |
| Greenberg | Criminal careers: Discrete or continuous? | |
| CN112463964B (en) | Text classification and model training method, device, equipment and storage medium | |
| CN112733036A (en) | Knowledge point recommendation method and device, storage medium and electronic device | |
| CN115564578B (en) | Fraud recognition model generation method | |
| CN113159976B (en) | Identification method for important users of microblog network | |
| Mohammed et al. | Contextualised student modelling for enculturated systems | |
| CN114357297A (en) | Student portrait construction and learning resource distribution method, computer device and storage medium | |
| CN114529096A (en) | Social network link prediction method and system based on ternary closure graph embedding | |
| CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment | |
| CN112507185A (en) | User portrait determination method and device | |
| CN112231572A (en) | User feature extraction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210430 |