Cognitive ability analysis method and system based on knowledge graph

Abstract

The application provides a knowledge graph-based cognitive ability analysis method and system, which can construct a corresponding knowledge graph according to the historical knowledge learning records of different target objects, determine the cognitive analysis error of the target object according to the knowledge graph, and correct the knowledge graph, so as to effectively avoid the occurrence of knowledge graph construction deviation caused by the data defects of the historical knowledge learning records, finally, re-determine the cognitive ability evaluation value of the target object according to the corrected knowledge graph, accurately and reliably evaluate the target object, and adjust the knowledge data learning progress of the target object according to the cognitive ability evaluation value, thereby maximizing the learning efficiency and learning quality of the target object.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent education, and in particular to a cognitive ability analysis method and system based on knowledge graphs. Background Technology

[0002] Currently, knowledge graphs are typically used to describe a target object's mastery of different knowledge points during its historical learning process and the relationships between these knowledge points. Different target objects have different knowledge graphs. By analyzing these knowledge graphs, the cognitive abilities of the corresponding target objects can be accurately determined. However, in practice, because knowledge graphs are constructed based on the target object's historical learning knowledge points, and the acquisition of these historical knowledge points does not perfectly match the target object's actual learning process, the constructed knowledge graph can easily fail to accurately reflect the target object's actual cognitive abilities. This can lead to biases in the subsequent determination of the target object's cognitive abilities. Therefore, existing technologies need methods that can effectively correct the cognitive ability analysis results obtained from the target object's own knowledge graph based on its actual knowledge learning records. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a cognitive ability analysis method and system based on knowledge graphs. It acquires the historical knowledge learning records of a target object, preprocesses these records, and extracts knowledge points. Based on the extracted knowledge point data, a corresponding knowledge graph for the target object is constructed. The cognitive analysis error value of the target object is determined based on this knowledge graph, and the knowledge graph is then corrected to eliminate knowledge point association errors. Based on the corrected knowledge graph, the cognitive ability evaluation value of the target object is re-determined, and the target object's knowledge data is adjusted accordingly. According to the learning progress, it can be seen that this knowledge graph-based cognitive ability analysis method and system can construct corresponding knowledge graphs based on the historical knowledge learning records of different target objects. Then, based on the knowledge graph, the cognitive analysis error of the target object is determined, and the knowledge graph is corrected accordingly. This can effectively avoid the deviation in knowledge graph construction caused by the data defects of the historical knowledge learning records themselves. Finally, the cognitive ability evaluation value of the target object is re-determined based on the corrected knowledge graph, so as to conduct accurate and reliable assessment of the target object. Based on the cognitive ability evaluation value, the knowledge data learning progress of the target object is adjusted, thereby maximizing the learning efficiency and learning quality of the target object.

[0004] This invention provides a cognitive ability analysis method based on knowledge graphs, characterized by comprising the following steps:

[0005] Step S1: Obtain the historical knowledge learning records of the target object, preprocess the historical knowledge learning records and extract knowledge points, and then construct the corresponding knowledge graph of the target object based on the extracted knowledge point data;

[0006] Step S2: Based on the knowledge graph, determine the cognitive analysis error value of the target object, and correct the knowledge graph based on the cognitive analysis error value, thereby eliminating the knowledge point association error of the knowledge graph;

[0007] Step S3: Based on the result of correcting the knowledge graph, redetermine the cognitive ability evaluation value of the target object, and adjust the knowledge data learning progress of the target object according to the cognitive ability evaluation value;

[0008] Furthermore, in step S1, acquiring the historical knowledge learning records of the target object, preprocessing and extracting knowledge points from the historical knowledge learning records, and then constructing a corresponding knowledge graph of the target object based on the extracted knowledge point data specifically includes:

[0009] Step S101: Obtain the course knowledge data browsed by the target object during the online learning process, and compare the actual browsing duration of each course knowledge data with the preset browsing time threshold. If the actual browsing duration is greater than or equal to the preset browsing time threshold, the corresponding course knowledge data is used as the historical knowledge learning record.

[0010] Step S102: Perform data deduplication preprocessing on all course knowledge data contained in the historical knowledge learning record, and then extract the corresponding knowledge point keywords from each course knowledge data that has undergone the data deduplication preprocessing.

[0011] Step S103: Based on the semantic correlation between the extracted keywords of different knowledge points, construct the corresponding knowledge graph of the target object;

[0012] Furthermore, in step S2, determining the cognitive analysis error value of the target object based on the knowledge graph, and correcting the knowledge graph based on the cognitive analysis error value to eliminate the knowledge point association error of the knowledge graph specifically includes:

[0013] Step S201: Based on the knowledge graph, determine the cognitive analysis results of the target object on issues related to different knowledge points;

[0014] Step S202: Based on the cognitive analysis results of the target object regarding different knowledge points and the following formula (1), determine the cognitive analysis error value W of the target object:

[0015]

[0016] In the above formula (1), P k (t) represents the quantitative result value corresponding to the cognitive analysis result of the target object on the k-th related question of the t-th knowledge point, P k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, m represents the total number of related questions of the knowledge point, and n represents the total number of related questions of the knowledge point.

[0017] Step S203: According to the following formula (2), the quantitative result value corresponding to the cognitive analysis result of the knowledge point related issues is corrected to obtain the corrected quantitative result value:

[0018]

[0019] In the above formula (2), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related question, and W represents the cognitive analysis error value of the target object. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point;

[0020] Furthermore, in step S3, based on the result of correcting the knowledge graph, the cognitive ability evaluation value of the target object is re-determined, and the knowledge data learning progress of the target object is adjusted according to the cognitive ability evaluation value, specifically including:

[0021] Step S301, according to the following formula (3), redetermine the cognitive ability evaluation value RE of the target object:

[0022]

[0023] In the above formula (3), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related issue. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point;

[0024] Step S302: Compare the cognitive ability evaluation value RE with the preset cognitive ability evaluation threshold. If the cognitive ability evaluation value RE is less than or equal to the preset cognitive ability evaluation threshold, reduce the total learning time of the knowledge course for the target object; otherwise, increase the total learning time of the knowledge course for the target object.

[0025] This invention also provides a cognitive ability analysis system based on a knowledge graph, characterized in that it includes a historical knowledge learning record acquisition and processing module, a knowledge graph construction module, a cognitive analysis error determination and correction module, a cognitive ability evaluation module, and a learning progress adjustment module; wherein,

[0026] The historical knowledge learning record acquisition and processing module is used to acquire the historical knowledge learning records of the target object, and to preprocess and extract knowledge points from the historical knowledge learning records.

[0027] The knowledge graph construction module is used to construct a knowledge graph corresponding to the target object based on the extracted knowledge point data;

[0028] The cognitive analysis error determination and correction module is used to determine the cognitive analysis error value of the target object based on the knowledge graph, and to correct the knowledge graph based on the cognitive analysis error value, thereby eliminating the knowledge point association error of the knowledge graph.

[0029] The cognitive ability evaluation module is used to redetermine the cognitive ability evaluation value of the target object based on the result of the correction of the knowledge graph;

[0030] The learning progress adjustment module is used to adjust the learning progress of the target object's knowledge data based on the cognitive ability evaluation value.

[0031] Furthermore, the historical knowledge learning record acquisition and processing module acquires the historical knowledge learning records of the target object, and performs preprocessing and knowledge point extraction processing on the historical knowledge learning records, specifically including:

[0032] The target object obtains the course knowledge data browsed during the online learning process, and compares the actual browsing duration of each course knowledge data with a preset browsing time threshold. If the actual browsing duration is greater than or equal to the preset browsing time threshold, the corresponding course knowledge data is used as the historical knowledge learning record.

[0033] Next, the historical knowledge learning records are subjected to data deduplication preprocessing for all course knowledge data, and then the corresponding knowledge point keywords are extracted from each course knowledge data after the data deduplication preprocessing.

[0034] as well as,

[0035] The knowledge graph construction module constructs a knowledge graph corresponding to the target object based on the extracted knowledge point data, specifically including:

[0036] Based on the semantic correlation between the extracted keywords of different knowledge points, a knowledge graph corresponding to the target object is constructed.

[0037] Furthermore, the cognitive analysis error determination and correction module determines the cognitive analysis error value of the target object based on the knowledge graph, and corrects the knowledge graph based on the cognitive analysis error value to eliminate the knowledge point association error of the knowledge graph. Specifically, this includes:

[0038] Based on the knowledge graph, determine the cognitive analysis results of the target object on issues related to different knowledge points;

[0039] Based on the cognitive analysis results of the target object on different knowledge points and the following formula (1), the cognitive analysis error value W of the target object is determined:

[0040]

[0041] In the above formula (1), P k (t) represents the quantitative result value corresponding to the cognitive analysis result of the target object on the k-th related question of the t-th knowledge point, P k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, m represents the total number of related questions of the knowledge point, and n represents the total number of related questions of the knowledge point.

[0042] Then, according to the formula (2) below, the quantitative result value corresponding to the cognitive analysis result of the knowledge point-related issues is corrected to obtain the corrected quantitative result value:

[0043]

[0044] In the above formula (2), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related question, and W represents the cognitive analysis error value of the target object. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point;

[0045] Furthermore, the cognitive ability evaluation module, based on the result of correcting the knowledge graph, specifically redetermines the cognitive ability evaluation value of the target object, including:

[0046] Based on the following formula (3), the cognitive ability evaluation value RE of the target object is re-determined:

[0047]

[0048] In the above formula (3), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related issue. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point;

[0049] as well as,

[0050] The learning progress adjustment module adjusts the learning progress of the target object's knowledge data based on the cognitive ability evaluation value, specifically including:

[0051] The cognitive ability evaluation value RE is compared with a preset cognitive ability evaluation threshold. If the cognitive ability evaluation value RE is less than or equal to the preset cognitive ability evaluation threshold, the total learning time of the target object's knowledge courses is reduced; otherwise, the total learning time of the target object's knowledge courses is increased.

[0052] Compared to existing technologies, this knowledge graph-based cognitive ability analysis method and system acquires the target object's historical knowledge learning records, preprocesses these records, extracts knowledge points, constructs a corresponding knowledge graph for the target object, determines the cognitive analysis error value based on this knowledge graph, and corrects the knowledge graph to eliminate knowledge point association errors. Based on the corrected knowledge graph, the system then re-determines the target object's cognitive ability evaluation value and adjusts the target object's knowledge data learning progress accordingly. It is evident that this knowledge graph-based cognitive ability analysis method and system can construct corresponding knowledge graphs based on the historical knowledge learning records of different target objects. Then, based on these knowledge graphs, the cognitive analysis errors of the target objects are determined, and the knowledge graphs are corrected accordingly. This effectively avoids deviations in knowledge graph construction caused by data defects in the historical knowledge learning records themselves. Finally, the cognitive ability evaluation value of the target objects is re-determined based on the corrected knowledge graph, thereby providing an accurate and reliable assessment of the target objects. The learning progress of the target objects' knowledge data is adjusted based on this cognitive ability evaluation value, thus maximizing the learning efficiency and quality of the target objects.

[0053] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0054] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart illustrating the cognitive ability analysis method based on knowledge graphs provided by the present invention.

[0057] Figure 2 This is a schematic diagram of the structure of the knowledge graph-based cognitive ability analysis system provided by the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] See Figure 1 This is a flowchart illustrating the knowledge graph-based cognitive ability analysis method provided in an embodiment of the present invention. The knowledge graph-based cognitive ability analysis method includes the following steps:

[0060] Step S1: Obtain the historical knowledge learning records of the target object, preprocess the historical knowledge learning records and extract knowledge points, and then construct the corresponding knowledge graph of the target object based on the extracted knowledge point data.

[0061] Step S2: Based on the knowledge graph, determine the cognitive analysis error value of the target object, and based on the cognitive analysis error value, correct the knowledge graph to eliminate the knowledge point association error of the knowledge graph.

[0062] Step S3: Based on the result of correcting the knowledge graph, redetermine the cognitive ability evaluation value of the target object, and adjust the knowledge data learning progress of the target object according to the cognitive ability evaluation value.

[0063] The beneficial effects of the above technical solution are as follows: This knowledge graph-based cognitive ability analysis method can construct corresponding knowledge graphs based on the historical knowledge learning records of different target objects, determine the cognitive analysis error of the target object based on the knowledge graph, and correct the knowledge graph accordingly. This can effectively avoid the deviation in knowledge graph construction caused by data defects in the historical knowledge learning records themselves. Finally, the cognitive ability evaluation value of the target object is re-determined based on the corrected knowledge graph, so as to conduct an accurate and reliable assessment of the target object, and adjust the target object's knowledge data learning progress based on the cognitive ability evaluation value, thereby maximizing the learning efficiency and learning quality of the target object.

[0064] Preferably, in step S1, the historical knowledge learning records of the target object are obtained, and the historical knowledge learning records are preprocessed and knowledge point extraction is performed. Then, based on the extracted knowledge point data, a knowledge graph corresponding to the target object is constructed, specifically including:

[0065] Step S101: Obtain the course knowledge data browsed by the target object during the online learning process, and compare the actual browsing duration of each course knowledge data with the preset browsing time threshold. If the actual browsing duration is greater than or equal to the preset browsing time threshold, the corresponding course knowledge data is used as the historical knowledge learning record.

[0066] Step S102: Perform deduplication preprocessing on all course knowledge data contained in the historical knowledge learning record, and then extract the corresponding knowledge point keywords from each course knowledge data after the deduplication preprocessing.

[0067] Step S103: Based on the semantic correlation between the extracted keywords of different knowledge points, construct the corresponding knowledge graph of the target object.

[0068] The beneficial effects of the above technical solution are as follows: by comparing and judging the actual browsing time of the course knowledge data browsed by the target object during the online learning process, it can ensure to the greatest extent that the selected course knowledge data is the knowledge data that the target object is truly interested in, thereby ensuring the reliability of the acquisition of the historical knowledge learning record; in addition, the data deduplication preprocessing of the historical knowledge learning record can reduce the data redundancy of the historical knowledge learning record, thereby greatly reducing the workload of data processing of the historical knowledge learning record.

[0069] Preferably, in step S2, determining the cognitive analysis error value of the target object based on the knowledge graph, and correcting the knowledge graph based on the cognitive analysis error value to eliminate the knowledge point association error of the knowledge graph specifically includes:

[0070] Step S201: Based on the knowledge graph, determine the cognitive analysis results of the target object on questions related to different knowledge points. The questions related to different knowledge points refer to objective or subjective questions about different knowledge points. The cognitive analysis results refer to the actual answers of the target object to the objective or subjective questions.

[0071] Step S202: Based on the cognitive analysis results of the target object regarding different knowledge points and the following formula (1), determine the cognitive analysis error value W of the target object:

[0072]

[0073] In the above formula (1), P k (t) represents the quantitative result value corresponding to the cognitive analysis result of the target object on the k-th related question of the t-th knowledge point, P k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, m represents the total number of related questions of the knowledge point, and n represents the total number of related questions of the knowledge point.

[0074] Step S203: According to the formula (2) below, correct the quantitative result value corresponding to the cognitive analysis result of the knowledge point related to the question, so as to obtain the corrected quantitative result value:

[0075]

[0076] In the above formula (2), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related question, and W represents the cognitive analysis error value of the target object. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point.

[0077] The beneficial effects of the above technical solution are as follows: by determining the cognitive analysis error value of the target object and the quantitative result value corresponding to the cognitive analysis result of the target object on the knowledge point related issues through the above formulas (1) and (2), the cognitive analysis state of the target object can be quantitatively determined, so as to make targeted and controllable correction of the cognitive analysis result of the target object.

[0078] Preferably, in step S3, based on the result of correcting the knowledge graph, the cognitive ability evaluation value of the target object is re-determined, and the knowledge data learning progress of the target object is adjusted according to the cognitive ability evaluation value, specifically including:

[0079] Step S301, according to the following formula (3), redetermine the cognitive ability evaluation value RE of the target object:

[0080]

[0081] In the above formula (3), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related issue. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point;

[0082] Step S302: Compare the cognitive ability evaluation value RE with the preset cognitive ability evaluation threshold. If the cognitive ability evaluation value RE is less than or equal to the preset cognitive ability evaluation threshold, reduce the total learning time of the target object's knowledge courses; otherwise, increase the total learning time of the target object's knowledge courses.

[0083] The beneficial effects of the above technical solution are as follows: by quantitatively determining the cognitive ability evaluation value of the target object through the above formula (3), a reliable and effective basis can be provided for adjusting the knowledge data learning progress of the target object in the future, thereby ensuring that the total learning time of the adjusted knowledge course can match the cognitive ability of the target object to the greatest extent.

[0084] See Figure 2 This is a schematic diagram of the structure of a knowledge graph-based cognitive ability analysis system provided in an embodiment of the present invention. The knowledge graph-based cognitive ability analysis system includes a historical knowledge learning record acquisition and processing module, a knowledge graph construction module, a cognitive analysis error determination and correction module, a cognitive ability evaluation module, and a learning progress adjustment module; wherein,

[0085] The historical knowledge learning record acquisition and processing module is used to acquire the historical knowledge learning records of the target object, and to preprocess and extract knowledge points from the historical knowledge learning records.

[0086] This knowledge graph construction module is used to construct the corresponding knowledge graph for the target object based on the extracted knowledge point data;

[0087] The cognitive analysis error determination and correction module is used to determine the cognitive analysis error value of the target object based on the knowledge graph, and to correct the knowledge graph based on the cognitive analysis error value, thereby eliminating the knowledge point association error of the knowledge graph.

[0088] This cognitive ability assessment module is used to redetermine the cognitive ability assessment value of the target object based on the result of the correction of the knowledge graph;

[0089] This learning progress adjustment module is used to adjust the learning progress of the target object's knowledge data based on the cognitive ability evaluation value.

[0090] The beneficial effects of the above technical solution are as follows: This knowledge graph-based cognitive ability analysis system can construct corresponding knowledge graphs based on the historical knowledge learning records of different target objects, determine the cognitive analysis error of the target object based on the knowledge graph, and correct the knowledge graph accordingly. This can effectively avoid the occurrence of deviations in knowledge graph construction due to data defects in the historical knowledge learning records themselves. Finally, the cognitive ability evaluation value of the target object is re-determined based on the corrected knowledge graph, thereby conducting an accurate and reliable assessment of the target object, and adjusting the target object's knowledge data learning progress based on the cognitive ability evaluation value, thereby maximizing the learning efficiency and quality of the target object.

[0091] Preferably, the historical knowledge learning record acquisition and processing module acquires the historical knowledge learning records of the target object, and performs preprocessing and knowledge point extraction on the historical knowledge learning records, specifically including:

[0092] The system retrieves the course knowledge data viewed during the online learning process of the target object, and compares the actual viewing duration of each course knowledge data with a preset viewing time threshold. If the actual viewing duration is greater than or equal to the preset viewing time threshold, the corresponding course knowledge data is used as the historical knowledge learning record.

[0093] Next, perform deduplication preprocessing on all course knowledge data contained in the historical knowledge learning record, and then extract the corresponding knowledge point keywords from each course knowledge data after the deduplication preprocessing.

[0094] as well as,

[0095] The knowledge graph construction module constructs a knowledge graph corresponding to the target object based on the extracted knowledge point data, specifically including:

[0096] Based on the semantic correlation between the extracted keywords of different knowledge points, a knowledge graph corresponding to the target object is constructed.

[0097] The beneficial effects of the above technical solution are as follows: by comparing and judging the actual browsing time of the course knowledge data browsed by the target object during the online learning process, it can ensure to the greatest extent that the selected course knowledge data is the knowledge data that the target object is truly interested in, thereby ensuring the reliability of the acquisition of the historical knowledge learning record; in addition, the data deduplication preprocessing of the historical knowledge learning record can reduce the data redundancy of the historical knowledge learning record, thereby greatly reducing the workload of data processing of the historical knowledge learning record.

[0098] Preferably, the cognitive analysis error determination and correction module determines the cognitive analysis error value of the target object based on the knowledge graph, and corrects the knowledge graph based on the cognitive analysis error value, thereby eliminating the knowledge point association error of the knowledge graph. Specifically, this includes:

[0099] Based on the knowledge graph, the cognitive analysis results of the target object on different knowledge point related questions are determined. Here, the different knowledge point related questions refer to objective or subjective questions about different knowledge point content, and the cognitive analysis results refer to the target object's actual answers to the objective or subjective questions.

[0100] Based on the cognitive analysis results of the target object regarding different knowledge points and the following formula (1), the cognitive analysis error value W of the target object is determined:

[0101]

[0102] In the above formula (1), P k (t) represents the quantitative result value corresponding to the cognitive analysis result of the target object on the k-th related question of the t-th knowledge point, P k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, m represents the total number of related questions of the knowledge point, and n represents the total number of related questions of the knowledge point.

[0103] Then, according to the formula (2) below, the quantitative result value corresponding to the cognitive analysis result of the relevant issues of this knowledge point is corrected to obtain the corrected quantitative result value:

[0104]

[0105] In the above formula (2), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related question, and W represents the cognitive analysis error value of the target object. k0(t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point.

[0106] The beneficial effects of the above technical solution are as follows: by determining the cognitive analysis error value of the target object and the quantitative result value corresponding to the cognitive analysis result of the target object on the knowledge point related issues through the above formulas (1) and (2), the cognitive analysis state of the target object can be quantitatively determined, so as to make targeted and controllable correction of the cognitive analysis result of the target object.

[0107] Preferably, the cognitive ability evaluation module, based on the result of correcting the knowledge graph, redetermines the cognitive ability evaluation value of the target object, specifically including:

[0108] Based on the formula (3) below, redetermine the cognitive ability evaluation value RE of the target object:

[0109]

[0110] In the above formula (3), P(t) represents the corrected quantitative result value of the target object's cognitive analysis result of the t-th knowledge point related issue. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, and m represents the total number of related questions of the knowledge point;

[0111] as well as,

[0112] This learning progress adjustment module adjusts the learning progress of the target object's knowledge data based on the cognitive ability evaluation value, specifically including:

[0113] The cognitive ability evaluation value RE is compared with the preset cognitive ability evaluation threshold. If the cognitive ability evaluation value RE is less than or equal to the preset cognitive ability evaluation threshold, the total learning time of the target object's knowledge courses is reduced; otherwise, the total learning time of the target object's knowledge courses is increased.

[0114] The beneficial effects of the above technical solution are as follows: by quantitatively determining the cognitive ability evaluation value of the target object through the above formula (3), a reliable and effective basis can be provided for adjusting the knowledge data learning progress of the target object in the future, thereby ensuring that the total learning time of the adjusted knowledge course can match the cognitive ability of the target object to the greatest extent.

[0115] As can be seen from the above embodiments, the knowledge graph-based cognitive ability analysis method and system acquire the historical knowledge learning records of the target object, preprocess and extract knowledge points from these records, construct a corresponding knowledge graph for the target object based on the extracted knowledge point data, determine the cognitive analysis error value of the target object based on the knowledge graph, and correct the knowledge graph based on the error value to eliminate the knowledge point association error. Based on the correction of the knowledge graph, the cognitive ability evaluation value of the target object is re-determined, and the target object's knowledge data learning is adjusted accordingly. Progress: As can be seen, this knowledge graph-based cognitive ability analysis method and system can construct corresponding knowledge graphs based on the historical knowledge learning records of different target objects. Then, based on the knowledge graph, the cognitive analysis error of the target object is determined, and the knowledge graph is corrected accordingly. This can effectively avoid the deviation in knowledge graph construction caused by data defects in the historical knowledge learning records themselves. Finally, the cognitive ability evaluation value of the target object is re-determined based on the corrected knowledge graph, so as to conduct accurate and reliable assessment of the target object. Based on the cognitive ability evaluation value, the knowledge data learning progress of the target object is adjusted, thereby maximizing the learning efficiency and learning quality of the target object.

[0116] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A cognitive ability analysis method based on knowledge graphs, characterized in that, It includes the following steps: Step S1: Obtain the historical knowledge learning records of the target object, preprocess the historical knowledge learning records and extract knowledge points, and then construct the corresponding knowledge graph of the target object based on the extracted knowledge point data; Step S2: Based on the knowledge graph, determine the cognitive analysis error value of the target object, and correct the knowledge graph based on the cognitive analysis error value, thereby eliminating the knowledge point association error of the knowledge graph; Step S3: Based on the result of correcting the knowledge graph, redetermine the cognitive ability evaluation value of the target object, and adjust the knowledge data learning progress of the target object according to the cognitive ability evaluation value; Specifically, step S2 includes: Step S201: Based on the knowledge graph, determine the cognitive analysis results of the target object on issues related to different knowledge points; Step S202: Based on the cognitive analysis results of the target object on different knowledge point related issues and the following formula (1), determine the cognitive analysis error value W of the target object: （1） In the above formula (1), P represents the quantitative result value corresponding to the cognitive analysis result of the target object on the k-th related question of the t-th knowledge point. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, where n represents the total number of related questions for the knowledge point and m represents the total number of knowledge points. Step S203: According to the following formula (2), the quantitative result value corresponding to the cognitive analysis result of the knowledge point related issues is corrected to obtain the corrected quantitative result value: （2） In the above formula (2), P represents the corrected quantitative result value of the target object's cognitive analysis result for the t-th knowledge point related question, where W represents the cognitive analysis error value of the target object. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph; m represents the total number of knowledge points.

2. The cognitive ability analysis method based on knowledge graphs as described in claim 1, characterized in that: In step S1, acquiring the historical knowledge learning records of the target object, preprocessing and extracting knowledge points from the historical knowledge learning records, and then constructing a corresponding knowledge graph of the target object based on the extracted knowledge point data specifically includes: Step S101: Obtain the course knowledge data browsed by the target object during the online learning process, and compare the actual browsing duration of each course knowledge data with the preset browsing time threshold. If the actual browsing duration is greater than or equal to the preset browsing time threshold, the corresponding course knowledge data is used as the historical knowledge learning record. Step S102: Perform data deduplication preprocessing on all course knowledge data contained in the historical knowledge learning record, and then extract the corresponding knowledge point keywords from each course knowledge data that has undergone the data deduplication preprocessing. Step S103: Based on the semantic correlation between the extracted keywords of different knowledge points, construct the corresponding knowledge graph of the target object.

3. The cognitive ability analysis method based on knowledge graphs as described in claim 1, characterized in that: In step S3, based on the result of correcting the knowledge graph, the cognitive ability evaluation value of the target object is re-determined, and the knowledge data learning progress of the target object is adjusted according to the cognitive ability evaluation value. This specifically includes: Step S301, according to the following formula (3), redetermine the cognitive ability evaluation value RE of the target object: （3） In the above formula (3), P represents the corrected quantitative result value of the target object's cognitive analysis result on the question related to the t-th knowledge point. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph; m represents the total number of knowledge points; Step S302: Compare the cognitive ability evaluation value RE with the preset cognitive ability evaluation threshold. If the cognitive ability evaluation value RE is less than or equal to the preset cognitive ability evaluation threshold, reduce the total learning time of the knowledge course for the target object; otherwise, increase the total learning time of the knowledge course for the target object.

4. A cognitive ability analysis system based on knowledge graphs, characterized in that, It includes modules for acquiring and processing historical knowledge learning records, constructing knowledge graphs, determining and correcting cognitive analysis errors, evaluating cognitive abilities, and adjusting learning progress; among which, The historical knowledge learning record acquisition and processing module is used to acquire the historical knowledge learning records of the target object, and to preprocess and extract knowledge points from the historical knowledge learning records. The knowledge graph construction module is used to construct a knowledge graph corresponding to the target object based on the extracted knowledge point data; The cognitive analysis error determination and correction module is used to determine the cognitive analysis error value of the target object based on the knowledge graph, and to correct the knowledge graph based on the cognitive analysis error value, thereby eliminating the knowledge point association error of the knowledge graph. The cognitive ability evaluation module is used to redetermine the cognitive ability evaluation value of the target object based on the result of the correction of the knowledge graph; The learning progress adjustment module is used to adjust the learning progress of the target object's knowledge data based on the cognitive ability evaluation value. Specifically, the cognitive analysis error determination and correction module is used for: Based on the knowledge graph, determine the cognitive analysis results of the target object on issues related to different knowledge points; Based on the cognitive analysis results of the target object on different knowledge points and the following formula (1), the cognitive analysis error value W of the target object is determined: （1） In the above formula (1), P represents the quantitative result value corresponding to the cognitive analysis result of the target object on the k-th related question of the t-th knowledge point. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph, where n represents the total number of related questions for the knowledge point and m represents the total number of knowledge points. Then, according to the formula (2) below, the quantitative result value corresponding to the cognitive analysis result of the knowledge point-related issues is corrected to obtain the corrected quantitative result value: （2） In the above formula (2), P represents the corrected quantitative result value of the target object's cognitive analysis result for the t-th knowledge point related question, where W represents the cognitive analysis error value of the target object. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph; m represents the total number of knowledge points.

5. The knowledge graph-based cognitive ability analysis system as described in claim 4, characterized in that: The historical knowledge learning record acquisition and processing module acquires the historical knowledge learning records of the target object, and performs preprocessing and knowledge point extraction on the historical knowledge learning records, specifically including: The target object obtains the course knowledge data browsed during the online learning process, and compares the actual browsing duration of each course knowledge data with a preset browsing time threshold. If the actual browsing duration is greater than or equal to the preset browsing time threshold, the corresponding course knowledge data is used as the historical knowledge learning record. Next, the historical knowledge learning records are subjected to data deduplication preprocessing for all course knowledge data, and then the corresponding knowledge point keywords are extracted from each course knowledge data after the data deduplication preprocessing. as well as, The knowledge graph construction module constructs a knowledge graph corresponding to the target object based on the extracted knowledge point data, specifically including: Based on the semantic correlation between the extracted keywords of different knowledge points, a knowledge graph corresponding to the target object is constructed.

6. The knowledge graph-based cognitive ability analysis system as described in claim 5, characterized in that: The cognitive ability evaluation module, based on the result of correcting the knowledge graph, specifically redetermines the cognitive ability evaluation value of the target object, including: The cognitive ability evaluation value RE of the target object is re-determined according to the following formula (3): （3） In the above formula (3), P represents the corrected quantitative result value of the target object's cognitive analysis result on the question related to the t-th knowledge point. k0 (t) represents the quantitative result value corresponding to the standard cognitive analysis result of the k-th related question of the t-th knowledge point according to the knowledge graph; m represents the total number of knowledge points; as well as, The learning progress adjustment module adjusts the learning progress of the target object's knowledge data based on the cognitive ability evaluation value, specifically including: The cognitive ability evaluation value RE is compared with a preset cognitive ability evaluation threshold. If the cognitive ability evaluation value RE is less than or equal to the preset cognitive ability evaluation threshold, the total learning time of the target object's knowledge courses is reduced; otherwise, the total learning time of the target object's knowledge courses is increased.

Images