Employee learning ability profiling method and related device

Abstract

The present invention relates to the field of data processing technology, and discloses a method for profiling employee learning ability and related devices, including: obtaining employees' historical assessment data, historical training data, job resource knowledge graphs and question bank data; digitizing the historical assessment data to obtain a historical assessment matrix; performing knowledge point annotation processing on each test question in the question bank data to obtain a knowledge point matrix; calculating the employee's knowledge mastery based on the historical assessment data and historical training data; establishing a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery; applying a latent semantic model based on the employee's knowledge point scoring matrix and the job resource knowledge graph to evaluate the employee's learning ability and obtain target portrait data. By implementing the method provided by this application, the analysis and evaluation of the employee's learning ability can be accurately realized, which helps to improve the employee's professional learning ability so that they can be better qualified for their job.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method for profiling employee learning abilities and related devices. Background Art

[0002] In the process of employee training, in order to accurately find out the employees' mastery of job knowledge points, the dichotomy method is usually adopted: correct answers are considered to be mastered; wrong answers are considered to be unmastered. The problem with this method is that the judgment criteria are too absolute, and the evaluation method for objective questions is not comprehensive enough, which affects the recommendation strategy of knowledge points and the adaptive learning effect in the subsequent learning process. Traditional training and learning cannot meet the requirements for the training of high-tech talents in professional fields. With the development of intelligent equipment, training and learning have gradually entered the mode of personalized autonomous learning. Accurately evaluating the learning ability of different employees can solve the dilemma of training high-tech talents in professional fields. Summary of the invention

[0003] The present invention provides an employee learning ability profiling method and related devices to solve the technical problem of accurately evaluating the learning abilities of different employees.

[0004] First, a method for profiling employee learning capabilities is provided, including:

[0005] Obtain employees' historical assessment data, historical training data, job resource knowledge graph and test question database data;

[0006] Perform digital processing on historical assessment data to obtain a historical assessment matrix;

[0007] Perform knowledge point labeling on each test question in the test question database data to obtain a knowledge point matrix;

[0008] Calculate employees' knowledge mastery based on historical assessment data and historical training data;

[0009] Establish a knowledge point scoring matrix based on the historical assessment matrix, knowledge point matrix and employee knowledge mastery level;

[0010] Based on the employee knowledge point scoring matrix and job resource knowledge graph, the latent semantic model is applied to evaluate the employee's learning ability and obtain target portrait data.

[0011] In the second aspect, a device for profiling employee learning ability is provided, including:

[0012] The acquisition module is used to obtain employees' historical assessment data, historical training data, job resource knowledge graph and test question database data;

[0013] The first processing module is used to perform digital processing on the historical assessment data to obtain a historical assessment matrix;

[0014] The second processing module is used to perform knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix;

[0015] The third processing module is used to calculate the employee's knowledge mastery level based on historical assessment data and historical training data;

[0016] The fourth processing module is used to establish a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery level;

[0017] The fifth processing module is used to evaluate the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph, and obtain target portrait data by applying the latent semantic model.

[0018] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned employee learning ability profiling method when executing the computer program.

[0019] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned employee learning ability profiling method are implemented.

[0020] In the scheme implemented by the above-mentioned employee learning ability portrait method and related devices, by obtaining the employee's historical assessment data, historical training data, job resource knowledge map and question bank data, the historical assessment data can be digitized to obtain a historical assessment matrix, and each test question in the question bank data can be labeled with knowledge points to obtain a knowledge point matrix, so as to further calculate the employee's knowledge mastery level based on the historical assessment data and historical training data, so as to establish a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery level, and then the employee's learning ability can be evaluated based on the employee's knowledge point scoring matrix and the job resource knowledge map by applying the latent semantic model to obtain accurate target portrait data, which can accurately realize the analysis and evaluation of the employee's learning ability, and help improve the employee's professional learning ability so that they can better perform their job duties. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0022] Figure 1 This is a schematic diagram of an application environment of an employee learning ability profiling method in one embodiment of the present invention;

[0023] Figure 2 It is a flow chart of a method for profiling employee learning capabilities in one embodiment of the present invention;

[0024] Figure 3 It is a structural schematic diagram of an employee learning ability profiling device in one embodiment of the present invention;

[0025] Figure 4 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0026] Figure 5 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The employee learning ability profiling method provided by the embodiment of the present invention can be applied in the following aspects: Figure 1In an application environment, the client communicates with the server through a network. Exemplarily, taking the scenario of evaluating the learning ability of employees as an example, the target user (such as R&D personnel, etc.) can upload the employee's historical assessment data, historical training data, job resource knowledge graph and question bank data through the client. Correspondingly, the server can obtain the employee's historical assessment data, historical training data, job resource knowledge graph and question bank data through the client, so as to digitize the historical assessment data to obtain a historical assessment matrix, and perform knowledge point annotation processing on each question in the question bank data to obtain a knowledge point matrix, so as to further calculate the employee's knowledge mastery degree based on the historical assessment data and historical training data, so as to establish a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery degree, and then apply the latent semantic model based on the employee's knowledge point scoring matrix and the job resource knowledge graph to evaluate the employee's learning ability, obtain accurate target portrait data, and feed the target portrait data back to the client. Correspondingly, the client can receive the target portrait data from the server, and can display the target portrait data on the client for the target user to query or browse. By adopting the employee learning ability profiling method provided in this application, the employee learning ability can be accurately analyzed and evaluated, which helps to improve the professional learning ability of employees so that they can better perform their job duties.

[0029] The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0030] See also Figure 2 As shown, Figure 2 A flow chart of a method for profiling employee learning capabilities provided by an embodiment of the present invention includes the following steps:

[0031] S10: Obtain employees’ historical assessment data, historical training data, job resource knowledge graph and question bank data.

[0032] Among them, the employee's historical assessment data may include the scores, evaluations and other related information of various assessments that the employee has experienced in the historical time period, which can reflect the employee's performance in various assessments in the past. The historical assessment data can come from the enterprise's internal assessment system. The historical training data may include the relevant record data of various trainings that the employee has participated in the historical time period, such as the name of the training course, the training duration, the training effect evaluation, etc. The historical training data can reflect the training that the employee has received.

[0033] The job resource knowledge graph can provide the structure and relationship of the knowledge required for each job. The job resource knowledge graph can be constructed based on the job descriptions and business needs of each enterprise, and this application does not limit this. The question bank data may include various types of questions used to assess the knowledge level of employees. It is understandable that by obtaining the question bank data, the overall and comprehensive knowledge point data required by employees corresponding to different positions can be understood, and this application does not limit this.

[0034] S20: Perform digital processing on the historical assessment data to obtain a historical assessment matrix.

[0035] The server can further organize the acquired historical assessment data into a matrix form by digitizing it, so as to organize all the assessment data of all employees in an orderly manner, thereby facilitating subsequent mathematical analysis and calculation.

[0036] Optionally, the server performs digital processing on the historical assessment data to obtain a historical assessment matrix, including: the server may use the following formula to implement the steps of performing digital processing on the historical assessment data to obtain a historical assessment matrix:

[0037]

[0038] Among them, S (m，n) represents the historical assessment matrix, m represents the employee index, and n represents the test question index; S 1，1 Indicates employee 1's assessment result on question 1; S 1，2 Indicates employee 1's assessment result on question 2; S 1，n represents the assessment result of employee 1 on the nth test question; S 2，1 Indicates employee 2's assessment result on question 1; S 2，2 Indicates the assessment result of employee 2 on the second test question; S 2，n S represents the assessment result of employee 2 on the nth test question; m，1 represents the assessment result of employee m on the first test question; S m，2 Indicates the assessment result of employee m on the second test question; S m，n Indicates the assessment result of employee m on the nth test question.

[0039] It should be noted that the server can use the matrix S (m，n) To represent the scores of different users for different test questions. It can be understood that when S m，n = 0, it means that employee m gave an incorrect answer to question n; when S m，n =1, it means that employee m answered question n correctly; when S m，n When it is empty, it means that employee m has no assessment record for question n.

[0040] S30: Perform knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix.

[0041] The server performs knowledge point labeling on each test question in the test question database data to obtain a knowledge point matrix, thereby clarifying the knowledge points involved in each test question and clearly seeing the correspondence between the test questions and the knowledge points through the obtained knowledge point matrix.

[0042] Optionally, the server performs knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix, including: the server may use the following formula to implement the step of performing knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix:

[0043]

[0044] Among them, K (i，j) represents the knowledge point matrix, i represents the test question index, j represents the knowledge point index; K 1，1 Indicates the marking of knowledge point 1 in question 1; K 1，2 Indicates the marking of knowledge point 2 in question 1; K 1，j Indicates the annotation of knowledge point j in question 1; K 2，1 Indicates the marking of knowledge point 1 in question 2; K 2，2 Indicates the marking of knowledge point 2 in question 2; K 2，j Indicates the marking of knowledge point j in question 2; K i，1 Indicates the annotation of knowledge point 1 in question i; K i，2 Indicates the marking of knowledge point 2 in question i; K i，j Indicates the marking status of knowledge point j in test question i.

[0045] It should be noted that the server can use the matrix K (i，j) To represent the different knowledge points in different test questions. It can be understood that when K (i，j) = 0, it means that there is no knowledge point j in test question i; when K (i，j) When =1, it means that there is knowledge point j in test question i.

[0046] S40: Calculate employees’ knowledge mastery based on historical assessment data and historical training data.

[0047] Based on the correct or incorrect answers of each test question in the employee's historical assessment data, the degree of mastery of the knowledge points can be evaluated. According to the corresponding knowledge point record data in the employee's historical training data, the mastery of the corresponding knowledge points can be further assigned through the scores. The calculation of the employee's knowledge point mastery can comprehensively consider the employee's performance in the assessment and the mastery of the training received, and then quantify the employee's mastery of knowledge.

[0048] For example, taking the calculation of employee m's mastery of knowledge point a as an example, the server can use the following formula to calculate employee m's mastery of knowledge point a:

[0049]

[0050] Among them, K ma Indicates the degree of mastery of knowledge point a by employee m; B i Indicates the situation of answering the question for the i-th time, B i =1 means the answer to the i-th question is correct, B i =0 indicates that the i-th answer is wrong; n indicates the total number of answers for knowledge point a.

[0051] S50: Establish a knowledge point scoring matrix based on the historical assessment matrix, knowledge point matrix and employee knowledge mastery.

[0052] By applying the calculation method of employee knowledge point mastery on the existing basis, we can gradually calculate and predict the mastery of the knowledge points required for the employee's position, and thus construct a scoring matrix based on the employee's knowledge point mastery. By integrating the previously processed data, a matrix that can fully reflect the employee's mastery of each knowledge point is formed, which will serve as an important input for the subsequent application of the latent semantic model.

[0053] Among them, the scoring value can be divided into stages such as understanding, comprehension, mastery, and proficiency according to the employee's mastery of the knowledge point. For example, a mastery of less than 50% can be classified as understanding, a mastery of 50%-70% can be classified as comprehension, a mastery of 70%-90% can be classified as mastery, and a mastery of more than 90% can be classified as proficient, and this application does not limit this.

[0054] S60: Based on the employee knowledge point scoring matrix and job resource knowledge graph, the latent semantic model is applied to evaluate the employee's learning ability and obtain target portrait data.

[0055] This application uses the latent factor model (LFM) to explore the potential factors behind the knowledge mastery of employees, and further combines it with the knowledge structure required for the position, so as to accurately evaluate the learning ability of employees. Among them, the target portrait data can provide enterprises with quantitative results of employee learning ability to help enterprises formulate personalized training plans and human resource management strategies.

[0056] It should be understood that the process of evaluating the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph and applying the latent semantic model to obtain the target portrait data refers to the process of evaluating the learning ability based on the latent semantic model. Among them, step S60, that is, evaluating the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph and applying the latent semantic model to obtain the target portrait data, includes the following steps:

[0057] S61: Estimating scores for unmastered knowledge points according to the employee knowledge point scoring matrix to obtain estimated scores for unmastered knowledge points;

[0058] S62: Determine reference unmastered knowledge points based on the estimated scores of unmastered knowledge points and a preset threshold;

[0059] S63: combining the reference unmastered knowledge points with the job resource knowledge graph to obtain target unmastered knowledge point data;

[0060] S64: Apply the latent semantic model to evaluate the learning ability based on the employee knowledge point scoring matrix and the target's unmastered knowledge point data to obtain the target portrait data.

[0061] It should be noted that the employee knowledge point scoring matrix may include the employee's score on the mastery of each knowledge point. By analyzing and processing the matrix, the score of the knowledge points that the employee has not mastered can be estimated. For example, some algorithms or rules can be used to infer the possible score of the knowledge points that the employee has not mastered based on the score of the knowledge points that the employee has mastered and the related knowledge associations.

[0062] It should be understood that the process of performing an estimated score on the unmastered knowledge points according to the employee knowledge point scoring matrix to obtain the estimated score on the unmastered knowledge points refers to the process of performing an estimated score on the unmastered knowledge points. In step S61, that is, performing an estimated score on the unmastered knowledge points according to the employee knowledge point scoring matrix to obtain the estimated score on the unmastered knowledge points includes the following steps:

[0063] S611: Determine the mean of employee knowledge point scores according to the employee knowledge point score matrix;

[0064] S612: Determine employee similarity data based on the employee knowledge point scoring matrix;

[0065] S613: Calculate the weighted average of the scores based on the employee knowledge point score average and employee similarity data to obtain the estimated score of the knowledge point that has not been mastered;

[0066] Among them, the following formula is used to calculate the weighted average score based on the employee knowledge point score mean and employee similarity data to obtain the estimated score of the knowledge points that have not been mastered:

[0067]

[0068] Among them, P u，i It represents the estimated score of the knowledge point that has not been mastered, that is, the estimated score of employee u for the knowledge point i that has not been mastered; represents the mean score of employee knowledge points, that is, the mean score of employee u’s knowledge points; S u，v Represents employee similarity data, that is, the similarity between employee u and employee v; R v,i represents the elements in the employee knowledge point rating matrix, that is, the rating of employee v for knowledge point i; represents the average rating of employee v; Indicates that the employee similarity data is rounded up.

[0069] By setting a preset threshold, when the estimated score of the unmastered knowledge point is lower than the preset threshold, the knowledge point can be determined as a reference unmastered knowledge point. It is understandable that the setting of the preset threshold can be determined according to the actual situation and experience of the enterprise, for example, by analyzing the past learning situation of employees and job requirements to obtain the preset threshold, and this application does not limit this.

[0070] The job resource knowledge graph provides the structure and relationship of the knowledge required for the job. Combining the reference unmastered knowledge points with the job resource knowledge graph can further clarify the position and importance of the unmastered knowledge points in the job knowledge system, thereby obtaining more targeted and practical target unmastered knowledge point data. For example, the job resource knowledge graph can show whether certain unmastered knowledge points are knowledge nodes on the critical path, or the degree of correlation with other important knowledge points, which is not limited in this application.

[0071] The latent semantic model can explore the potential factors behind the employees' knowledge mastery. By inputting the employee knowledge point scoring matrix and the target unmastered knowledge point data into the latent semantic model, the model can evaluate the employees' learning ability by analyzing the relationship between the employees' performance in knowledge point mastery and the overall knowledge structure. For example, the model can analyze which types of knowledge points employees have difficulty mastering, and the relationship between these difficulties and the knowledge points that employees have mastered, so as to comprehensively evaluate the employees' learning ability and output target portrait data for enterprise decision-making reference. For example, the enterprise can formulate personalized training plans for each employee based on the target portrait data, etc. This application does not limit this.

[0072] It should be understood that applying the latent semantic model to evaluate the learning ability of employees based on the employee knowledge point scoring matrix and the target unmastered knowledge point data to obtain the target portrait data refers to the process of evaluating the learning ability of employees. Among them, step S64, that is, applying the latent semantic model to evaluate the learning ability of employees based on the employee knowledge point scoring matrix and the target unmastered knowledge point data to obtain the target portrait data, includes the following steps:

[0073] S641: performing interval scaling of the number of knowledge point learning times according to the employee knowledge point scoring matrix to obtain interval scaling data;

[0074] S642: According to the number of knowledge points and the average number of learning times in the employee's knowledge point scoring matrix, the employee's current learning ability is evaluated to obtain current learning ability portrait data;

[0075] S643: Perform interval scaling processing on the current learning ability portrait data to obtain current learning ability level data;

[0076] S644: Based on the current learning ability level data, the latent semantic model is applied to mine the potential relationship between employees and knowledge points to obtain the target portrait data.

[0077] By performing interval scaling on the number of knowledge point learning times in the employee knowledge point scoring matrix to obtain interval scaling data, the number of learning times of different magnitudes can be normalized into a unified interval for subsequent comparison and analysis.

[0078] Optionally, the server can implement the steps of scaling the knowledge point learning times according to the employee knowledge point scoring matrix and obtaining the scaling data by the following formula:

[0079]

[0080] Among them, r u，i represents interval scaling data, that is, the value of employee u's learning times for knowledge point i after interval scaling, with a value range of (0, 1); nu，i represents the original number of learning times of employee u for knowledge point i; n min Indicates the minimum number of ratings; n max Indicates the maximum number of ratings.

[0081] The server evaluates the employee's current learning ability based on the number of knowledge points in the employee's knowledge point scoring matrix and the average number of learning times, and obtains the current learning ability portrait data. It can further extract quantitative indicators that can reflect the employee's learning ability from the employee's existing learning status data.

[0082] For example, taking the calculation of the current learning ability evaluation of employee u as an example, the server can use the following formula to calculate the current learning ability evaluation of employee u:

[0083]

[0084] Among them, n u represents the current learning ability profile data of employee u; |N(u)| represents the set of knowledge points that employee u has learned; avg u Represents the average number of learning times of employee u.

[0085] Furthermore, the server can obtain the employee's current learning ability level data by interval scaling the current learning ability profile data. The current learning ability level data can be implicitly fed back through the number of learning times. For example, if the employee learns a large number of knowledge points and the average number of learning times is low, the current learning ability level data can be higher; conversely, if the employee learns a small number of knowledge points and the average number of learning times is high, the current learning ability level data can be lower.

[0086] The latent semantic model can discover the deep connection between employee learning ability and knowledge points hidden behind the data. The target portrait data can provide a more valuable reference for enterprises to understand employee learning ability. Exemplarily, the latent semantic model can construct a latent factor k between employees and knowledge points to decompose the employee's knowledge point score matrix R into two dense factor matrices, such as the first dense factor matrix P∈Rk×m and the second dense factor matrix Q∈Rk×n. Then the portrait data of employee u for knowledge point i can be:

[0087]

[0088] in, Represents the profile data of employee u for knowledge point i, which is used to evaluate the employee's mastery or scoring of a specific knowledge point; q j represents the jth column of the first dense factor matrix Q; q j T represents the transpose of the jth column of the second dense factor matrix Q; pu represents the u-th column of the dense factor matrix P.

[0089] It can be understood that the latent semantic model uses the idea of ​​linear regression to fit the errors between the predicted scores and the true scores corresponding to the first dense factor matrix P and the second dense factor matrix Q by minimizing the score error between the predicted scores and the true scores, and evaluates the model's predictions through the regression evaluation indicator root mean square error.

[0090] This application predicts the employees' unlearned content and the knowledge points they have not mastered in the assessment based on the knowledge points they have mastered, and evaluates the target employees' unlearned knowledge points based on similar employees by finding the common knowledge points they have not mastered. Based on the evaluation results, personalized recommendations are made for the knowledge points that employees have not mastered, which can effectively improve employees' learning of professional skills and enable them to better perform their job duties.

[0091] It can be seen that in the above scheme, by obtaining the employees' historical assessment data, historical training data, job resource knowledge graph and question bank data, the historical assessment data can be digitized to obtain the historical assessment matrix, and each test question in the question bank data can be labeled with knowledge points to obtain the knowledge point matrix, so as to further calculate the employees' knowledge mastery level based on the historical assessment data and historical training data, and thus establish a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employees' knowledge mastery level, and then evaluate the employees' learning ability based on the employees' knowledge point scoring matrix and the job resource knowledge graph by applying the latent semantic model, and obtain accurate target portrait data, which can accurately realize the analysis and evaluation of employees' learning ability, and help improve the employees' professional learning ability so that they can better perform their job duties.

[0092] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0093] In one embodiment, a device for profiling employee learning ability is provided, and the device for profiling employee learning ability corresponds one-to-one to the method for profiling employee learning ability in the above embodiment. Figure 3 As shown, the employee learning ability profiling device includes an acquisition module 101, a first processing module 102, a second processing module 103, a third processing module 104, a fourth processing module 105, and a fifth processing module 106. The functional modules are described in detail as follows:

[0094] Acquisition module 101, used for acquiring the historical assessment data, historical training data, job resource knowledge graph and test question database data of employees;

[0095] The first processing module 102 is used to perform data processing on the historical assessment data to obtain a historical assessment matrix;

[0096] The second processing module 103 is used to perform knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix;

[0097] The third processing module 104 is used to calculate the employee's knowledge mastery level based on the historical assessment data and historical training data;

[0098] The fourth processing module 105 is used to establish a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery level;

[0099] The fifth processing module 106 is used to evaluate the learning ability of employees according to the employee knowledge point scoring matrix and the job resource knowledge graph by applying the latent semantic model to obtain target portrait data.

[0100] In one embodiment, the fifth processing module 106 is used to evaluate the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph, and obtain target profile data by applying the latent semantic model, which is specifically used to:

[0101] According to the employee knowledge point scoring matrix, the estimated scores of the knowledge points that have not been mastered are evaluated to obtain the estimated scores of the knowledge points that have not been mastered;

[0102] Determine the reference unmastered knowledge points based on the estimated scores of the unmastered knowledge points and the preset thresholds;

[0103] Combine the reference unmastered knowledge points with the job resource knowledge graph to obtain the target unmastered knowledge point data;

[0104] By applying the latent semantic model, learning ability is evaluated based on the employee knowledge point scoring matrix and the target's unmastered knowledge points data to obtain the target portrait data.

[0105] In one embodiment, the fifth processing module 106 is used to estimate and score the unmastered knowledge points according to the employee knowledge point scoring matrix to obtain the estimated scores of the unmastered knowledge points, specifically for:

[0106] Determine the mean of employee knowledge point scores based on the employee knowledge point score matrix;

[0107] Determine employee similarity data based on employee knowledge point scoring matrix;

[0108] Based on the mean score of employees’ knowledge points and employee similarity data, a weighted average score calculation is performed to obtain the estimated score of the knowledge points that have not been mastered;

[0109] Among them, the following formula is used to calculate the weighted average score based on the employee knowledge point score mean and employee similarity data to obtain the estimated score of the knowledge points that have not been mastered:

[0110]

[0111] Among them, P u，i It represents the estimated score of the knowledge point that has not been mastered, that is, the estimated score of employee u for the knowledge point i that has not been mastered; represents the mean score of employee knowledge points, that is, the mean score of employee u’s knowledge points; S u，v Represents employee similarity data, that is, the similarity between employee u and employee v; R v,i represents the elements in the employee knowledge point rating matrix, that is, the rating of employee v for knowledge point i; represents the average rating of employee v; Indicates that the employee similarity data is rounded up.

[0112] In one embodiment, the fifth processing module 106 is used to apply a latent semantic model to evaluate learning ability according to the employee knowledge point scoring matrix and the target unmastered knowledge point data to obtain target portrait data, which is specifically used to:

[0113] According to the employee knowledge point scoring matrix, the knowledge point learning frequency interval is scaled to obtain the interval scaling data;

[0114] According to the number of knowledge points and average learning times in the employee knowledge point scoring matrix, the employee's current learning ability is evaluated to obtain the current learning ability portrait data;

[0115] According to the interval scaling data, the current learning ability portrait data is interval scaled to obtain the current learning ability level data;

[0116] According to the current learning ability level data, the latent semantic model is applied to mine the potential relationship between employees and knowledge points to obtain the target portrait data.

[0117] In one embodiment, the fifth processing module 106 is used to apply the latent semantic model to mine the potential relationship between employees and knowledge points according to the current learning ability level data to obtain target portrait data, which is specifically used to:

[0118] Through latent semantic model, latent factors are constructed between employees and knowledge points;

[0119] Based on the latent factors, the employee knowledge point score matrix is ​​decomposed to obtain the first dense factor matrix and the second dense factor matrix;

[0120] Obtaining target image data according to the first dense factor matrix and the second dense factor matrix;

[0121] Among them, the step of obtaining the target image data according to the first dense factor matrix and the second dense factor matrix is ​​realized by the following formula:

[0122]

[0123] in, represents the portrait data of employee u for knowledge point i in the target portrait data; q j represents the jth column of the first dense factor matrix; q j T represents the transpose of the jth column of the second dense factor matrix; p u represents the u-th column of the dense factor matrix P.

[0124] The present invention provides an employee learning ability portrait device. By acquiring the employee's historical assessment data, historical training data, job resource knowledge graph and question bank data, the historical assessment data can be digitized to obtain a historical assessment matrix, and each test question in the question bank data can be labeled with knowledge points to obtain a knowledge point matrix, so as to further calculate the employee's knowledge mastery level based on the historical assessment data and historical training data, so as to establish a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery level, and then the employee's learning ability can be evaluated based on the employee's knowledge point scoring matrix and the job resource knowledge graph by applying a latent semantic model to obtain accurate target portrait data, which can accurately realize the analysis and evaluation of the employee's learning ability, and help to improve the employee's professional learning ability so as to better perform job duties.

[0125] For the specific definition of the employee learning ability profiling device, please refer to the definition of the employee learning ability profiling method above, which will not be repeated here. Each module in the above-mentioned employee learning ability profiling device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0126] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client through a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the server side of a method for profiling employee learning capabilities.

[0127] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a method for profiling employee learning capabilities.

[0128] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0129] Obtain employees' historical assessment data, historical training data, job resource knowledge graph and test question database data;

[0130] Perform digital processing on historical assessment data to obtain a historical assessment matrix;

[0131] Perform knowledge point labeling on each test question in the test question database data to obtain a knowledge point matrix;

[0132] Calculate employees' knowledge mastery based on historical assessment data and historical training data;

[0133] Establish a knowledge point scoring matrix based on the historical assessment matrix, knowledge point matrix and employee knowledge mastery level;

[0134] Based on the employee knowledge point scoring matrix and job resource knowledge graph, the latent semantic model is applied to evaluate the employee's learning ability and obtain target portrait data.

[0135] The present invention provides a computer device, which can perform digitization processing on the historical assessment data to obtain a historical assessment matrix by acquiring the historical assessment data, historical training data, job resource knowledge graph and question bank data of employees, and perform knowledge point annotation processing on each question in the question bank data to obtain a knowledge point matrix, so as to further calculate the knowledge mastery of employees based on the historical assessment data and historical training data, thereby establishing a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the knowledge mastery of employees, and then evaluating the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph by applying a latent semantic model, obtaining accurate target portrait data, and accurately realizing the analysis and evaluation of the learning ability of employees, which is helpful to improve the professional learning ability of employees so as to better perform their job duties.

[0136] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0137] Obtain employees' historical assessment data, historical training data, job resource knowledge graph and test question database data;

[0138] Perform digital processing on historical assessment data to obtain a historical assessment matrix;

[0139] Perform knowledge point labeling on each test question in the test question database data to obtain a knowledge point matrix;

[0140] Calculate employees' knowledge mastery based on historical assessment data and historical training data;

[0141] Establish a knowledge point scoring matrix based on the historical assessment matrix, knowledge point matrix and employee knowledge mastery level;

[0142] Based on the employee knowledge point scoring matrix and job resource knowledge graph, the latent semantic model is applied to evaluate the employee's learning ability and obtain target portrait data.

[0143] The present invention provides a computer-readable storage medium. By acquiring employees' historical assessment data, historical training data, job resource knowledge graphs and question bank data, the historical assessment data can be digitized to obtain a historical assessment matrix, and each question in the question bank data can be labeled with knowledge points to obtain a knowledge point matrix, so as to further calculate the employees' knowledge mastery level based on the historical assessment data and historical training data, thereby establishing a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employees' knowledge mastery level, and then evaluating the employees' learning ability based on the employees' knowledge point scoring matrix and the job resource knowledge graph by applying a latent semantic model, obtaining accurate target portrait data, and accurately realizing the analysis and evaluation of the employees' learning ability, which is helpful to improve the employees' professional learning ability so as to better perform their job duties.

[0144] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0146] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0147] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for profiling employee learning ability, characterized in that: The method comprises: Obtain employees' historical assessment data, historical training data, job resource knowledge graph and test question database data; Performing data processing on the historical assessment data to obtain a historical assessment matrix; Performing knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix; Calculating the employee's knowledge mastery level based on the historical assessment data and the historical training data; Establishing a knowledge point scoring matrix based on the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery level; According to the employee knowledge point scoring matrix and the job resource knowledge graph, a latent semantic model is applied to evaluate the employee's learning ability to obtain target portrait data.

2. The employee learning ability profiling method according to claim 1 is characterized in that: The method of evaluating the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph and applying a latent semantic model to obtain target portrait data includes: According to the employee knowledge point scoring matrix, an estimated score is performed on the knowledge points that have not been mastered to obtain an estimated score of the knowledge points that have not been mastered; Determine the reference unmastered knowledge points according to the estimated scores of the unmastered knowledge points and the preset thresholds; Combine the reference unmastered knowledge points with the job resource knowledge graph to obtain target unmastered knowledge point data; The latent semantic model is applied to evaluate the learning ability according to the employee knowledge point scoring matrix and the target's unmastered knowledge point data to obtain the target portrait data.

3. The employee learning ability profiling method according to claim 2 is characterized in that: The step of performing an estimated score on the unmastered knowledge points according to the employee knowledge point scoring matrix to obtain an estimated score on the unmastered knowledge points includes: Determine the mean of the employee knowledge point scores according to the employee knowledge point score matrix; Determining employee similarity data according to the employee knowledge point scoring matrix; A weighted average calculation of the scores is performed based on the mean scores of the employee knowledge points and the employee similarity data to obtain an estimated score of the knowledge points that have not been mastered; Among them, the step of calculating the weighted average score based on the employee knowledge point score mean and the employee similarity data to obtain the estimated score of the unmastered knowledge point is realized by the following formula: Among them, P u,i It represents the estimated score of the knowledge point that has not been mastered, that is, the estimated score of employee u for the knowledge point i that has not been mastered; represents the mean score of employee knowledge points, that is, the mean score of employee u’s knowledge points; S u,v Represents employee similarity data, that is, the similarity between employee u and employee v; R v,i represents the elements in the employee knowledge point rating matrix, that is, the rating of employee v for knowledge point i; represents the average rating of employee v; Indicates that the employee similarity data is rounded up.

4. The employee learning ability profiling method according to claim 3 is characterized in that: The application of the latent semantic model performs learning ability assessment based on the employee knowledge point scoring matrix and the target's unmastered knowledge point data to obtain target portrait data, including: Perform interval scaling of the number of knowledge point learning times according to the employee knowledge point scoring matrix to obtain interval scaling data; According to the number of knowledge points and the average number of learning times in the employee knowledge point scoring matrix, the employee's current learning ability is evaluated to obtain current learning ability portrait data; According to the interval scaling data, the current learning ability portrait data is interval scaled to obtain current learning ability level data; According to the current learning ability level data, a latent semantic model is applied to mine the potential relationship between employees and knowledge points to obtain target portrait data.

5. The employee learning ability profiling method according to claim 4 is characterized in that: According to the current learning ability level data, the latent semantic model is applied to mine the potential relationship between employees and knowledge points to obtain target portrait data, including: Through latent semantic model, latent factors are constructed between employees and knowledge points; Based on the latent factors, the employee knowledge point score matrix is ​​decomposed to obtain a first dense factor matrix and a second dense factor matrix; Obtaining target image data according to the first dense factor matrix and the second dense factor matrix; Among them, the step of obtaining the target portrait data according to the first dense factor matrix and the second dense factor matrix is ​​realized by the following formula: in, represents the portrait data of employee u for knowledge point i in the target portrait data; q j represents the jth column of the first dense factor matrix; q j T represents the transpose of the jth column of the second dense factor matrix; p u represents the u-th column of the dense factor matrix P.

6. An employee learning ability profiling device, characterized in that: The employee learning ability profiling device comprises: The acquisition module is used to obtain employees' historical assessment data, historical training data, job resource knowledge graph and test question database data; A first processing module is used to perform data processing on the historical assessment data to obtain a historical assessment matrix; The second processing module is used to perform knowledge point labeling processing on each test question in the test question database data to obtain a knowledge point matrix; A third processing module is used to calculate the employee's knowledge mastery level based on the historical assessment data and the historical training data; A fourth processing module is used to establish a knowledge point scoring matrix according to the historical assessment matrix, the knowledge point matrix and the employee's knowledge mastery level; The fifth processing module is used to evaluate the learning ability of employees based on the employee knowledge point scoring matrix and the job resource knowledge graph, and obtain target portrait data by applying a latent semantic model.

7. The employee learning ability profiling device according to claim 6 is characterized in that: The fifth processing module is used to evaluate the learning ability of employees according to the employee knowledge point scoring matrix and the job resource knowledge graph, and obtain target portrait data by applying a latent semantic model, and is specifically used for: According to the employee knowledge point scoring matrix, an estimated score is performed on the knowledge points that have not been mastered to obtain an estimated score of the knowledge points that have not been mastered; Determine the reference unmastered knowledge points according to the estimated scores of the unmastered knowledge points and the preset thresholds; Combine the reference unmastered knowledge points with the job resource knowledge graph to obtain target unmastered knowledge point data; The latent semantic model is applied to evaluate the learning ability according to the employee knowledge point scoring matrix and the target's unmastered knowledge point data to obtain the target portrait data.

8. The employee learning ability profiling device according to claim 7 is characterized in that: The fifth processing module is used to estimate and score the unmastered knowledge points according to the employee knowledge point scoring matrix to obtain the estimated scores of the unmastered knowledge points, and is specifically used to: Determine the mean of the employee knowledge point scores according to the employee knowledge point score matrix; Determining employee similarity data according to the employee knowledge point scoring matrix; A weighted average calculation of the scores is performed based on the mean scores of the employee knowledge points and the employee similarity data to obtain an estimated score of the knowledge points that have not been mastered; Among them, the step of calculating the weighted average score based on the employee knowledge point score mean and the employee similarity data to obtain the estimated score of the unmastered knowledge point is realized by the following formula: Among them, P u,i It represents the estimated score of the knowledge point that has not been mastered, that is, the estimated score of employee u for the knowledge point i that has not been mastered; represents the mean score of employee knowledge points, that is, the mean score of employee u’s knowledge points; S u,v Represents employee similarity data, that is, the similarity between employee u and employee v; R v,i represents the elements in the employee knowledge point rating matrix, that is, the rating of employee v for knowledge point i; represents the average rating of employee v; Indicates that the employee similarity data is rounded up.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the employee learning ability profiling method as described in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the employee learning ability profiling method as described in any one of claims 1 to 5 is implemented.

Images