Knowledge graph construction and application method based on AI intelligent recommendation algorithm

Abstract

The invention provides a knowledge graph construction and application method based on an AI intelligent recommendation algorithm. The method comprises the following steps: S1, acquiring required data in a campus; s2, cleaning and labeling the collected required data to obtain preprocessed data; s3, constructing a campus knowledge graph by using the obtained preprocessed data; s4, analyzing behavior data of students, teachers and managers according to the established campus knowledge graph and crowd identities, and establishing a user model; and S5, providing data support for campus management and education by utilizing behavior characteristics embodied in the constructed user model. The beneficial effects of the invention are that the invention aims to provide a technology capable of better managing and utilizing campus big data and providing personalized campus services, and provides more intelligent and efficient information retrieval and decision support for students, teachers and managers by integrating multi-source data in a campus and constructing a campus knowledge graph by utilizing an AI intelligent recommendation algorithm.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and in particular relates to a knowledge graph construction and application method based on an AI intelligent recommendation algorithm. Background Art

[0002] A large amount of data is generated on campus, including student academic performance, teacher teaching records, course information, campus activities and other data, but traditional data management and utilization methods have problems of information fragmentation and inefficiency. The construction and application of campus knowledge graphs are expected to solve these problems, but traditional methods usually rely on manual editing and maintenance. Summary of the invention

[0003] In view of this, the present invention aims to propose a knowledge graph construction and application method based on AI intelligent recommendation algorithm, aiming to provide a technology that can better manage and utilize campus big data and provide personalized campus services. By integrating multi-source data on campus and using AI intelligent recommendation algorithm to construct a campus knowledge graph, it can provide students, teachers and administrators with more intelligent and efficient information retrieval and decision-making support.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0005] In the first aspect, this solution discloses a method for constructing a knowledge graph based on an AI intelligent recommendation algorithm, comprising:

[0006] S1. Obtain the required data on campus;

[0007] S2. Clean and annotate the collected required data to obtain preprocessed data;

[0008] S3, using the obtained pre-processed data to construct a campus knowledge graph;

[0009] S4. Based on the constructed campus knowledge graph, the behavioral data of students, teachers and administrators are analyzed according to the identities of the groups to establish a user model;

[0010] S5. Use the behavioral characteristics reflected in the constructed user model to provide data support for campus management and education.

[0011] Furthermore, in step S1, the required data is obtained through the campus information management system, the Internet of Things devices and the network log, and the required data includes:

[0012] Student information: student records, academic records, and behavioral data;

[0013] Teacher information: teacher profile, course schedule, teaching feedback;

[0014] Manager information: attendance records, management task allocation;

[0015] Campus infrastructure information: classroom usage, library borrowing records, cafeteria consumption records;

[0016] The total amount of data collected Dtotal is:

[0017] D total =D student +D teacher +D staff +D infrastructure ;

[0018] Among them, Dstudent, Dteacher, Dstaff, and Dinfrastructure represent the amount of data collected from students, teachers, administrators, and infrastructure, respectively.

[0019] Furthermore, in step S2, the method for cleaning and labeling the collected required data includes:

[0020] First, feature extraction is performed on the cleaned data;

[0021] Secondly, the data is classified and labeled according to the extracted features, including:

[0022] Entity annotation: labeling people, places, and events in the data as specific entity types;

[0023] Relationship annotation: annotate the relationship between different entities;

[0024] Time marking: Time marking of events to indicate the time point or time range of occurrence;

[0025] Finally, to ensure the quality of the annotation, a variety of verification and validation measures are carried out, including:

[0026] Labeling consistency check: evaluate the consistency of labeling by calculating the Kappa coefficient of the labeling results;

[0027] Annotation accuracy evaluation: Calculate the annotation accuracy by comparing the results of manual annotation and automatic annotation;

[0028] Among them, the Kappa coefficient is used to evaluate the consistency between multiple annotators, and the calculation formula is:

[0029]

[0030] Among them, Po represents the actual consistency ratio between annotators; Pe represents the expected ratio of random consistency among annotators.

[0031] Furthermore, in step S3, using the obtained preprocessed data to construct a campus knowledge graph includes:

[0032] Entity extraction: identify the core entities in the data;

[0033] Relationship extraction: analyzing the relationships between different entities;

[0034] Knowledge graph construction: Use the extracted entities and relationships to build a knowledge graph and optimize the graph structure, including:

[0035] The knowledge graph is represented by a triple (Ei, Rij, Ej), where:

[0036] Ei and Ej represent two entities, and Rij represents the relationship between the two entities.

[0037] Furthermore, in step S4, it specifically includes:

[0038] Using the knowledge graph constructed in step S3, we can build an accurate user model by analyzing the behavioral data of people with different identities, including:

[0039] Student model: used to analyze students’ learning behavior, performance changes, and social activities;

[0040] Teacher model: used to analyze teachers’ teaching behaviors, course schedules, and teaching feedback;

[0041] Manager model: used to analyze the work arrangements and execution of managers;

[0042] Among them, the user model can be expressed by the following formula:

[0043] U k =f(B k , T k );

[0044] Among them, Uk represents the user model; Bk represents the user's behavioral characteristics; Tk represents the user's behavior time series.

[0045] Furthermore, in step S5, based on the behavioral characteristics extracted from the user model, a recommendation algorithm is used to provide accurate data support for campus management and educational decision-making, specifically including:

[0046] Personalized teaching plan recommendation: recommend the most suitable teaching methods and courses based on the student model;

[0047] Teacher teaching improvement suggestions: Analyze teaching effects based on the teacher model and provide improvement suggestions;

[0048] Optimal allocation of campus resources: optimize resource allocation based on the management personnel model to improve management efficiency;

[0049] The recommendation algorithm is expressed by the following formula:

[0050] R(x)=arg max y∈Y Score(x,y);

[0051] Among them, R(x) represents the best result recommended for input x; y represents the candidate item; Score(x, y) represents the matching score between input x and candidate item y.

[0052] In the second aspect, the present solution discloses an electronic device, comprising a processor and a memory that is communicatively connected to the processor and is used to store executable instructions of the processor, wherein the processor is used to execute a knowledge graph construction method based on an AI intelligent recommendation algorithm as described in the first aspect.

[0053] In the third aspect, the present solution discloses a server, comprising at least one processor and a memory communicatively connected to the processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the processor so that the at least one processor executes a knowledge graph construction method based on an AI intelligent recommendation algorithm as described in the first aspect.

[0054] In the fourth aspect, the present solution discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the knowledge graph construction method based on the AI ​​intelligent recommendation algorithm described in the first aspect.

[0055] Compared with the prior art, the knowledge graph construction and application method based on AI intelligent recommendation algorithm described in the present invention has the following beneficial effects:

[0056] The knowledge graph construction method based on AI intelligent recommendation algorithm described in the present invention aims to provide a technology that can better manage and utilize campus big data and provide personalized campus services. By integrating multi-source data on campus and using AI intelligent recommendation algorithm to construct a campus knowledge graph, it provides students, teachers and administrators with more intelligent and efficient information retrieval and decision-making support. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0058] Figure 1 A schematic diagram of constructing a knowledge graph based on an AI intelligent recommendation algorithm described in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0060] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0061] The main purpose of the present invention is to provide a campus big data knowledge graph construction and application method based on AI intelligent recommendation algorithm, which includes the following steps:

[0062] 1. Data integration: Collect and integrate data from various data sources on campus, including student information, teacher information, course information, grade information, campus activity information, etc.;

[0063] 2. Data cleaning and annotation: Clean the integrated data, process missing data and erroneous data, and annotate them to build a knowledge graph;

[0064] 3. Knowledge graph construction: Use AI intelligent recommendation algorithm to automatically build campus knowledge graph, including student nodes, teacher nodes, course nodes, activity nodes, etc., and the relationships between them;

[0065] 4. User modeling: Analyze the behavioral data of students, teachers, and administrators to establish user models, including students’ learning interests, teachers’ teaching preferences, and management needs;

[0066] 5. Intelligent recommendation: Based on the user model and the content of the knowledge graph, the recommendation algorithm is used to generate personalized campus services for users, including course recommendations, learning resource recommendations, activity recommendations, etc.;

[0067] 6. User feedback and optimization: Collect user feedback information, including clicks, ratings, comments, etc., to continuously optimize the quality of recommendation algorithms and knowledge graphs;

[0068] 7. Application areas: Apply this method to campus management, student counseling, teaching support and other fields to improve the value of campus data and service quality;

[0069] like Figure 1 As shown, this plan specifically includes:

[0070] 1. Data collection layer:

[0071] Data sources: including student information system, academic affairs system, library system, campus activity management system, etc.

[0072] Data collection tools: web crawlers, API interfaces, database connections, etc.

[0073] 2. Data processing and cleaning layer:

[0074] Data cleaning: Processing errors, missing and redundant data to ensure data quality.

[0075] Data annotation: adding labels and entity recognition to data in order to build a knowledge graph.

[0076] 3. Knowledge graph construction layer:

[0077] Knowledge graph database: stores campus knowledge graph data using graph database technology.

[0078] Knowledge graph construction algorithm: including entity recognition, relationship extraction, graph representation learning, etc.

[0079] 4. User modeling layer:

[0080] User behavior data: including students’ click, browse, and rating behavior data.

[0081] User modeling algorithm: Analyze user interests, needs and behavior patterns to generate user models.

[0082] 5. Intelligent recommendation layer:

[0083] Recommendation algorithm: Based on the user model and the content of the knowledge graph, personalized recommendations are generated using collaborative filtering, deep learning and other algorithms.

[0084] Recommendation results: course recommendations, learning resource recommendations, activity recommendations, etc.

[0085] 6. User feedback and optimization layer:

[0086] User feedback data: including user clicks, ratings, comments and other feedback information.

[0087] Algorithm optimization: Use feedback data to continuously optimize the quality of recommendation algorithms and knowledge graphs.

[0088] 7. Application areas:

[0089] Campus management: providing decision support, resource management and other services.

[0090] Student services: provide learning resources, activity recommendations and other services.

[0091] Education quality improvement: supporting teachers’ teaching and students’ learning.

[0092] The specific steps involved are:

[0093] 1. Data collection and integration:

[0094] At this stage, you need to collect data from different data sources, then integrate and clean it. The following is a Python code example that demonstrates how to read student information from a CSV file and integrate the data:

[0095] import pandas as pd

[0096] #Read student information from the file

[0097] student_data=pd.read_csv('student_data.csv')

[0098] #Data integration and cleaning, assuming you need to select specific fields

[0099] selected_columns=['student_id','name','major','gpa']

[0100] cleaned_data=student_data[selected_columns]

[0101] 2. Knowledge graph construction:

[0102] At this stage, the data is converted into nodes and relationships of the knowledge graph. The following is an example of creating knowledge graph nodes and relationships using Python's Neo4j driver:

[0103]

[0104]

[0105] 3. User modeling:

[0106] At this stage, it is necessary to analyze user behavior data to build a user model. The following is an example of how to use Python's machine learning library Scikit-Learn for user behavior analysis:

[0107] Python

[0108] from sklearn.cluster import KMeans

[0109] #Suppose there is a user behavior data

[0110] user_behavior_data=[...]

[0111] #Use K-Means algorithm to group users

[0112] kmeans=KMeans(n_clusters=3)

[0113] user_clusters=kmeans.fit_predict(user_behavior_data)

[0114] 4. Intelligent recommendation:

[0115] Campus student performance warning can be achieved using collaborative filtering recommendation algorithm

[0116]

[0117]

[0118]

[0119]

[0120] Use the Apache Commons Math library to perform SVD singular value decomposition, and then generate grade warning information based on the reconstruction error and threshold.

[0121] Those of ordinary skill in the art will appreciate that the units and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0122] In the several embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the division of the units described above is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The above-mentioned units may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A knowledge graph construction method based on AI intelligent recommendation algorithm, characterized in that: include: S1. Obtain the required data on campus; S2. Clean and annotate the collected required data to obtain preprocessed data; S3, using the obtained pre-processed data to construct a campus knowledge graph; S4. Based on the constructed campus knowledge graph, the behavioral data of students, teachers and administrators are analyzed according to the identities of the groups to establish a user model; S5. Use the behavioral characteristics reflected in the constructed user model to provide data support for campus management and education.

2. According to claim 1, a knowledge graph construction method based on AI intelligent recommendation algorithm is characterized in that: In step S1, the required data is obtained through the campus information management system, IoT devices and network logs. The required data includes: Student information: student records, academic records, and behavioral data; Teacher information: teacher profile, course schedule, teaching feedback; Manager information: attendance records, management task allocation; Campus infrastructure information: classroom usage, library borrowing records, cafeteria consumption records; The total amount of data collected Dtotal is: D total =D student +D teacher +D staff +D infrastructure ; Among them, Dstudent, Dteacher, Dstaff, and Dinfrastructure represent the amount of data collected from students, teachers, administrators, and infrastructure, respectively.

3. According to claim 1, a knowledge graph construction method based on AI intelligent recommendation algorithm is characterized in that: In step S2, the method for cleaning and labeling the collected required data includes: First, feature extraction is performed on the cleaned data; Secondly, the data is classified and labeled according to the extracted features, including: Entity annotation: labeling people, places, and events in the data as specific entity types; Relationship annotation: annotate the relationship between different entities; Time marking: Time marking of events to indicate the time point or time range of occurrence; Finally, to ensure the quality of the annotation, a variety of verification and validation measures are carried out, including: Labeling consistency check: evaluate the consistency of labeling by calculating the Kappa coefficient of the labeling results; Annotation accuracy evaluation: Calculate the annotation accuracy by comparing the results of manual annotation and automatic annotation; Among them, the Kappa coefficient is used to evaluate the consistency between multiple annotators, and the calculation formula is: Among them, Po represents the actual consistency ratio between annotators; Pe represents the expected ratio of random consistency among annotators.

4. According to claim 1, a knowledge graph construction method based on AI intelligent recommendation algorithm is characterized in that: In step S3, using the obtained preprocessed data to construct a campus knowledge graph includes: Entity extraction: identify the core entities in the data; Relationship extraction: analyzing the relationships between different entities; Knowledge graph construction: Use the extracted entities and relationships to build a knowledge graph and optimize the graph structure, including: The knowledge graph is represented by a triple (Ei, Rij, Ej), where: Ei and Ej represent two entities, and Rij represents the relationship between the two entities.

5. According to claim 1, a knowledge graph construction method based on AI intelligent recommendation algorithm is characterized in that: In step S4, it specifically includes: Using the knowledge graph constructed in step S3, we can build an accurate user model by analyzing the behavioral data of people with different identities, including: Student model: used to analyze students’ learning behavior, performance changes, and social activities; Teacher model: used to analyze teachers’ teaching behaviors, course schedules, and teaching feedback; Manager model: used to analyze the work arrangements and execution of managers; Among them, the user model can be expressed by the following formula: U k =f(B k ,T k ); Among them, Uk represents the user model; Bk represents the user's behavioral characteristics; Tk represents the user's behavior time series.

6. The method for constructing a knowledge graph based on an AI intelligent recommendation algorithm according to claim 1, characterized in that: In step S5, based on the behavioral characteristics extracted from the user model, a recommendation algorithm is used to provide accurate data support for campus management and educational decision-making, including: Personalized teaching plan recommendation: recommend the most suitable teaching methods and courses based on the student model; Teacher teaching improvement suggestions: Analyze teaching effects based on the teacher model and provide improvement suggestions; Optimal allocation of campus resources: optimize resource allocation based on the management personnel model to improve management efficiency; The recommendation algorithm is expressed by the following formula: R(x)=arg max y∈Y Score(x,y); Among them, R(x) represents the best result recommended for input x; y represents the candidate; Score(x,y) represents the matching score between input x and candidate y.

7. An electronic device, comprising a processor and a memory connected to the processor for storing instructions executable by the processor, characterized in that: The processor is used to execute a knowledge graph construction method based on an AI intelligent recommendation algorithm as described in any one of claims 1 to 6 above.

8. A server, characterized in that: It includes at least one processor and a memory that is communicatively connected to the processor, wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the processor so that the at least one processor executes a knowledge graph construction method based on an AI intelligent recommendation algorithm as described in any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, it implements a knowledge graph construction method based on an AI intelligent recommendation algorithm as described in any one of claims 1 to 6.

Images