Performance assessment index evaluation method and device and medium

Abstract

The invention discloses a performance assessment index evaluation method and device and a medium, and the method comprises the steps: carrying out the correlation of performance assessment data through a knowledge graph technology, and determining a causal relationship between the performance assessment data; generating a training environment of a performance appraisal evaluation model according to task requirements of an enterprise, so as to train the performance appraisal evaluation model; inputting the performance assessment data of the employees, the causal relationship and the enterprise periodic performance weight rule into a performance assessment evaluation model to generate a first evaluation result; comparing the performance assessment data of the employees with the enterprise knowledge base according to a preset innovation comparison rule to generate a second evaluation result; and inputting the first evaluation result and the second evaluation result into an evaluation report generation model, and generating an evaluation report of the employee according to the three-section generation logic. According to the invention, the weight of each performance in different enterprise periods is judged through the enterprise period performance weight rule, the reliability and authority of performance assessment are improved, and the assessment flexibility is improved.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a performance appraisal indicator evaluation method, device, and medium. Background Art

[0002] In the current performance appraisal system of enterprises, the evaluation method of performance appraisal indicators is relatively traditional, and there are usually the following technical problems that need to be solved: Manually evaluating performance appraisal indicators one by one consumes a lot of time and manpower costs, especially in a complex appraisal system with multiple departments, multiple positions, and multiple indicators. The human resources department and department heads need to spend a lot of energy collecting, organizing, and evaluating data, resulting in low efficiency in the evaluation of performance appraisal indicators; secondly, although some companies have tried to introduce some simple data analysis tools to assist in performance appraisal evaluation, these tools often have limited functions and cannot handle complex unstructured data. It is also difficult to fully explore and utilize the company's performance appraisal data, resulting in the appraisal results being unable to fully and accurately reflect the employees' work performance and contributions. Summary of the Invention

[0003] The embodiments of the present application provide a performance appraisal indicator evaluation method, device and medium for solving the problems of low evaluation efficiency and inaccurate evaluation results in existing performance appraisal indicator evaluation methods.

[0004] The embodiments of this application adopt the following technical solutions: In one aspect, an embodiment of the present application provides a performance evaluation index evaluation method, the method comprising: In one example, the employee's performance appraisal data, the causal relationship and the enterprise cycle performance weight rule are input into a trained performance appraisal evaluation model to generate a first evaluation result, which specifically includes: establishing an association between employee performance appraisal data based on the causal relationship; assigning different weight coefficients to the employee's performance appraisal data based on the enterprise cycle performance weight; obtaining each score of the employee's performance appraisal data based on a preset weight coefficient score table and the weight coefficient; and adding each score of the associated data based on the association between the employee's performance appraisal data to obtain a score group of the associated data to constitute the first evaluation result of the employee.

[0005] In one example, according to preset innovation comparison rules, the employee's performance appraisal data is compared with the enterprise knowledge base to generate a second evaluation result, which specifically includes: traversing the employee's performance appraisal data and comparing the employee's performance appraisal data with the corresponding data in the enterprise knowledge base. If there is no content that meets the preset innovation comparison rules, a first-level second evaluation result is generated; if there is content that meets the preset innovation comparison rules, a second-level second evaluation result is generated; the performance score of the first-level second evaluation result is lower than the performance score of the second-level second evaluation result.

[0006] In one example, a training environment for a performance appraisal evaluation model is generated based on the task requirements of an enterprise to train the performance appraisal evaluation model, specifically including: matching the environment with the task requirements of the enterprise according to a preset task environment matching table; when the match is successful, generating a training environment for the performance appraisal evaluation model based on the successfully matched environment in the task environment matching table; when the match fails, generating a training environment for the performance appraisal evaluation model based on the highest matching environment in the task environment matching table, and sending a request for environment matching failure to the client.

[0007] In one example, the first evaluation result and the second evaluation result are input into a trained evaluation report generation model, and an employee evaluation report is generated according to a three-stage generation logic, specifically including: marking the associated data score group with the lowest score in the first evaluation result; determining the employee's problems and the causes of the problems based on the associated data score group with the lowest score; determining solutions to the employee's problems based on the employee's historical performance data and the second evaluation result; and integrating the employee's problems, causes of the problems, and solutions to generate an employee evaluation report.

[0008] In one example, solutions to employee problems are determined based on the employee's historical performance data and the second evaluation result, specifically including: determining a primary solution to the employee's problem based on the employee's historical performance data; judging the employee's second evaluation result, and when the second evaluation result is a first-level second evaluation result, generating an innovation incentive plan for the employee, and integrating the innovation incentive plan with the primary solution to obtain a solution to the employee's problem; when the second evaluation result is a second-level second evaluation result, determining the primary solution as the solution to the employee's problem.

[0009] In one example, the employee's performance appraisal data, the causal relationship and the enterprise cycle performance weight are input into a trained performance appraisal evaluation model. Before generating the first evaluation result, the method also includes: obtaining structured data of employee performance appraisal through a human resources system; the structured data includes historical performance, project completion status, video conference recordings, voice communication records and work scene images; obtaining unstructured data of employee performance appraisal through an enterprise email system; normalizing the structured data to obtain standard structured data; cleaning and formatting the unstructured data to obtain standard unstructured data; integrating and segmenting the standard structured data and the standard unstructured data to obtain employee performance appraisal data.

[0010] In one example, the first evaluation result and the second evaluation result are input into a trained performance appraisal evaluation model, and after generating an evaluation report for the employee according to the three-stage generation logic, the method further includes: returning the evaluation report to the client and storing it; when the employee is subjected to performance appraisal again, the weight of the performance appraisal data involved in the evaluation report is reset to the highest level as the basis for generating the first evaluation result.

[0011] On the other hand, an embodiment of the present application provides a performance appraisal indicator evaluation device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned performance appraisal indicator evaluation methods.

[0012] On the other hand, an embodiment of the present application provides a performance appraisal indicator evaluation non-volatile computer storage medium storing computer executable instructions, which can execute any of the above-mentioned performance appraisal indicator evaluation methods.

[0013] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: Through knowledge graph technology, performance appraisal models can understand the underlying logic between indicators, avoiding isolated evaluations. Multi-dimensional data collection transcends the limitations of traditional textual data and comprehensively captures employees' implicit performance (such as difficult-to-quantify indicators like team influence and communication skills). Furthermore, multimodal data can serve as objective support for qualitative indicators. By using enterprise-cycle performance weighting rules to assess the weight of various performance indicators across different enterprise cycles, this approach addresses the lag inherent in traditional appraisals, increases the credibility and authority of performance appraisals, and enhances their flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below with reference to the accompanying drawings, in which: Figure 1 A flowchart of a performance evaluation method provided in an embodiment of the present application; Figure 2 This is a diagram of the overall operation page of a performance appraisal indicator evaluation method provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a performance appraisal indicator evaluation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0016] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0017] Figure 1 This is a flow chart of a performance evaluation method provided in an embodiment of the present application. This method can be applied to different business areas. Certain input parameters or intermediate results in this process allow for manual adjustment to help improve accuracy.

[0018] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For ease of understanding and description, the following embodiments are described in detail using a controller as an example.

[0019] Based on this, Figure 1 The process in may include the following steps: S101: Correlate performance appraisal data through knowledge graph technology to determine the causal relationship between performance appraisal data.

[0020] In some embodiments of the present application, historical performance data, corporate strategic goals, and job competency models are used to construct a knowledge graph to clarify the causal relationship between assessment indicators (such as the correlation between "customer satisfaction" and "repurchase rate") and hierarchical relationships (such as the decomposition of company-level KPIs into department / individual indicators).

[0021] Furthermore, the knowledge graph is embedded and represented through the graph neural network (GNN), and the indicator correlation features are transmitted synchronously when input into the large model.

[0022] Through knowledge graph technology, the big model can understand the deep logic between indicators and avoid isolated evaluation (for example, when an employee's "sales" meets the target but the "customer complaint rate" increases, automatic correlation analysis and lowering of performance scores are performed). It also supports dynamic indicator decomposition and automatically generates personalized assessment indicators based on corporate strategic adjustments (for example, when adding the "digital transformation participation" indicator, it is associated with the "technological innovation" dimension through the knowledge graph).

[0023] S102: Generate a training environment for a performance appraisal evaluation model according to the task requirements of the enterprise to train the performance appraisal evaluation model.

[0024] In some embodiments of the present application, when an enterprise's assessment and evaluation task is received, the size of the enterprise's assessment and evaluation task will be evaluated first, and then the environment matching of the enterprise's task requirements will be performed according to the preset task environment matching table. If the size of the enterprise's assessment and evaluation task is relatively large, a model training environment with a higher configuration will be matched to train the assessment and evaluation model. If the size of the enterprise's assessment and evaluation task is relatively small, a model training environment with a lower configuration will be matched to train the assessment and evaluation model. When the match is successful, a training environment for the performance assessment and evaluation model is generated based on the successfully matched environment in the task environment matching table. When the match fails, a training environment for the performance assessment and evaluation model is generated based on the highest matching environment in the task environment matching table, and a request for environment matching failure is sent to the client. For example, the training environment is a basic version with 16GB memory + RTX3060 graphics card, which can support 1.5B / 7B models.

[0025] According to the scale of the model and the amount of training data, the GPU memory allocation, number of threads and other parameters are reasonably adjusted to ensure the efficiency and stability of the training process, which greatly improves the efficiency of assessment and evaluation.

[0026] Furthermore, after the training environment is matched, the performance evaluation model is trained, and the pre-processed training data cases are input into the model. The output of the model is calculated through forward propagation, and then the difference between the predicted result and the true label is calculated based on the loss function. The parameters of the model are then updated through the back propagation algorithm. This process is repeated until the model converges or the preset training stop condition is reached. For example, during the training process, the performance of the model can be evaluated on the validation set at a certain number of iterations, and the trend of the loss function can be observed. When the loss function no longer decreases significantly or the performance of the model on the validation set no longer improves, the model is considered to have converged. The cross entropy loss function is used in the training process. Evaluate model performance by comparing the changing trends of the probability distribution of the true labels with the probability distribution predicted by the model, and judge the stability of the model training based on the convergence of the model.

[0027] Furthermore, after training is completed, the model is comprehensively evaluated using the test set, and various performance indicators of the model on the test set, such as accuracy, recall rate, mean square error, etc., are calculated to accurately measure the generalization ability and actual effect of the model.

[0028] S103: Input the employee's performance appraisal data, the causal relationship, and the enterprise cycle performance weight rule into the trained performance appraisal evaluation model to generate a first evaluation result.

[0029] In some embodiments of the present application, before inputting the employee's performance appraisal data, the causal relationship, and the enterprise cycle performance weighting rule into the trained performance appraisal evaluation model to generate the first evaluation result, it is also necessary to obtain the employee's performance appraisal structured data, specifically: Obtain structured data for employee performance appraisals through the human resources system. Structured data includes historical performance, project completion status, video conference recordings, voice communication records, and work scene images. Then, obtain unstructured data for employee performance appraisals through the corporate email system. Furthermore, the structured data is normalized to obtain standard structured data, the unstructured data is cleaned and formatted to obtain standard unstructured data, and finally the standard structured data and standard unstructured data are integrated and segmented to obtain employee performance appraisal data.

[0030] Furthermore, after obtaining the structured data for employee performance appraisals, correlations are established between employee performance appraisal data based on causal relationships between the data. Based on the company's cyclical performance weights, different weight coefficients are assigned to employee performance appraisal data (e.g., a 15% increase in the weight of "sales" during peak season, and an increase in the weight of "customer retention rate" during off-season). Then, based on a preset weight coefficient score table and the weight coefficients, scores are obtained for each item in the employee's performance appraisal data. Finally, based on the correlations between the employee's performance appraisal data, the scores for each item in the correlated data are summed to obtain a score group for the correlated data, which forms the employee's first evaluation result.

[0031] By judging the weight of each performance in different enterprise cycles through the enterprise cycle performance weight rules, the lag problem of traditional assessment is solved, the credibility and authority of performance assessment is increased, and the flexibility of assessment is improved.

[0032] S104: According to the preset innovation comparison rules, the employee's performance appraisal data is compared with the enterprise knowledge base to generate a second evaluation result.

[0033] In some embodiments of the present application, while inputting the employee's performance appraisal data, causal relationships, and enterprise cycle performance weight rules into a trained performance appraisal evaluation model, the employee's performance appraisal data is traversed and compared with the corresponding data in the enterprise knowledge base (e.g., if the appraisal data is the completion of the work, then what is compared with the knowledge base is the technology or ability and time required to complete the work). If there is no content that meets the preset innovation comparison rules, a first-level second evaluation result is generated, which means that the employee has no innovation in the work and is just following the rules to complete the work. If there is content that meets the preset innovation comparison rules, a second-level second evaluation result is generated, which means that the employee has made outstanding contributions in the work or invented a method that does not exist in the knowledge base, etc. The performance score of the first-level second evaluation result is lower than the performance score of the second-level second evaluation result.

[0034] S105: Input the first evaluation result and the second evaluation result into the trained evaluation report generation model, and generate the employee evaluation report according to the three-stage generation logic.

[0035] In some embodiments of the present application, after obtaining the first evaluation result and the second evaluation result, the first evaluation result and the second evaluation result will be input into the trained evaluation report generation model, and an evaluation report will be generated according to the "problem-cause-solution" three-stage generation logic (such as "sales volume does not meet the target → customer follow-up frequency is insufficient → it is recommended to increase customer visits by 2 times per week and participate in "Customer Negotiation Skills" training").

[0036] Specifically: mark the associated data score group with the lowest score in the first evaluation result, and then determine the employee's problems and the causes of the problems based on the associated data score group with the lowest score; at the same time, determine the solutions to the employee's problems based on the employee's historical performance data and the second evaluation result; finally, integrate the employee's problems, causes of the problems and solutions to generate an employee evaluation report.

[0037] Specifically, the solution to the employee's problem is determined based on the employee's historical performance data and the second evaluation results. Then determine the employee's second evaluation result. When the second evaluation result is a first-level second evaluation result, generate an innovation incentive plan for the employee, and integrate the innovation incentive plan with the primary solution to obtain a solution to the employee's problem. When the second evaluation result is a second-level second evaluation result, determine the primary solution as the solution to the employee's problem.

[0038] Furthermore, the evaluation report is returned to the client and stored. When the employee's performance evaluation is conducted again, the performance evaluation data involved in the evaluation report is reset to the highest weight to serve as the basis for generating the first evaluation result.

[0039] It should be noted that although the embodiments of this application are based on Figure 1 Steps S101 to S105 are described in sequence, but this does not mean that steps S101 to S105 must be performed in a strict order. Figure 1 The order shown in FIG1 is to introduce and explain step S101 to step S105 in order to facilitate those skilled in the art to understand the technical solution of the embodiment of the present application. In other words, in the embodiment of the present application, the order between step S101 to step S105 can be appropriately adjusted according to actual needs.

[0040] pass Figure 1 This application uses knowledge graph technology to enable performance appraisal models to understand the underlying logic between indicators, avoiding isolated evaluations. Through multi-dimensional data collection, it breaks through the limitations of traditional text data and comprehensively captures employees' implicit performance (such as difficult-to-quantify indicators such as team influence and communication skills). Furthermore, multimodal data can serve as objective support for qualitative indicators. By using enterprise cycle performance weighting rules to assess the weight of various performance indicators in different enterprise cycles, this approach addresses the lag problem of traditional appraisals, increases the credibility and authority of performance appraisals, and enhances their flexibility.

[0041] Figure 2 This is a diagram of the overall operation page of a performance appraisal indicator evaluation method provided in an embodiment of the present application.

[0042] exist Figure 2 The following diagram shows the operation page for data preprocessing, model training, and evaluation output in this application. This includes steps such as screening and noise reduction, and training supervision.

[0043] Figure 3 A schematic diagram of the structure of a performance evaluation index evaluation device provided in an embodiment of the present application includes: at least one processor; and, a memory communicatively connected to at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the above-mentioned performance appraisal indicator evaluation methods.

[0044] Some embodiments of the present application provide a non-volatile computer storage medium for evaluating performance appraisal indicators, which stores computer-executable instructions capable of executing any of the above-mentioned performance appraisal indicator evaluation methods.

[0045] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0046] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0047] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0051] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0052] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM), and non-volatile memory such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0053] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0054] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0055] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the technical principles of the present application should fall within the scope of protection of the present application.

Claims

1. A performance appraisal indicator evaluation method, characterized in that: The method comprises: Use knowledge graph technology to associate performance appraisal data and determine the causal relationship between performance appraisal data; Generating a training environment for a performance appraisal model based on the enterprise's task requirements to train the performance appraisal model; Inputting the employee's performance appraisal data, the causal relationship, and the enterprise cycle performance weighting rule into the trained performance appraisal evaluation model to generate a first evaluation result; According to the preset innovation comparison rules, the employee's performance evaluation data is compared with the enterprise knowledge base to generate the second evaluation result; The first evaluation result and the second evaluation result are input into the trained evaluation report generation model, and the employee evaluation report is generated according to the three-stage generation logic.

2. The method according to claim 1, characterized in that Inputting the employee's performance appraisal data, the causal relationship, and the enterprise cycle performance weight rule into the trained performance appraisal evaluation model to generate a first evaluation result specifically includes: Establishing correlations between employee performance appraisal data based on the causal relationships; According to the enterprise cycle performance weight, different weight coefficients are assigned to the employee's performance appraisal data; Obtaining scores for each item of employee performance appraisal data based on a preset weight coefficient score table and the weight coefficients; According to the correlation between employee performance appraisal data, each score of the correlated data is added up to obtain a score group of the correlated data to form the first evaluation result of the employee.

3. The method according to claim 1, characterized in that The employee's performance evaluation data is compared with the enterprise knowledge base according to the preset innovation comparison rules to generate a second evaluation result, which specifically includes: Traverse the employee's performance appraisal data and compare it with the corresponding data in the enterprise knowledge base. If there is no content that meets the preset innovation comparison rules, generate a first-level second evaluation result; If there is content that meets the preset innovation comparison rules, a second-level second evaluation result is generated; the performance score of the first-level second evaluation result is lower than the performance score of the second-level second evaluation result.

4. The method according to claim 1, wherein Generating a training environment for a performance appraisal model based on the enterprise's task requirements to train the performance appraisal model specifically includes: According to the preset task environment matching table, the enterprise's task requirements are matched with the environment; When the match is successful, the training environment of the performance evaluation model is generated according to the successfully matched environment in the task environment matching table; When the matching fails, a training environment for the performance assessment evaluation model is generated based on the highest matching environment in the task environment matching table, and a request indicating that the environment matching failed is sent to the client.

5. The method according to claim 1, wherein Inputting the first evaluation result and the second evaluation result into the trained evaluation report generation model and generating the employee evaluation report according to the three-stage generation logic specifically includes: Mark the associated data score group with the lowest score in the first evaluation result; According to the lowest score of the associated data group, identify the problems and causes of the problems faced by employees; Determine solutions to employee problems based on employee historical performance data and second evaluation results; Integrate employee problems, causes of problems, and solutions to generate employee evaluation reports.

6. The method according to claim 5, characterized in that Determining solutions to employee problems based on employee historical performance data and the second evaluation results specifically includes: Identify primary solutions to employee problems based on historical employee performance data; Determine the employee's second evaluation result. If the second evaluation result is a first-level second evaluation result, generate an innovation incentive plan for the employee, and integrate the innovation incentive plan with the primary solution to obtain a solution to the employee's problem. When the second evaluation result is a second-level evaluation result, the primary solution is determined as a solution to the employee's problem.

7. The method according to claim 1, characterized in that Before inputting the employee's performance appraisal data, the causal relationship, and the enterprise cycle performance weight into the trained performance appraisal evaluation model to generate the first evaluation result, the method further includes: Obtaining structured data on employee performance appraisals through the human resources system; the structured data includes historical performance, project completion status, video conference recordings, voice communication records, and work scene images; Obtain unstructured data on employee performance appraisals through the corporate email system; Normalizing the structured data to obtain standard structured data; Performing data cleaning and formatting processing on the unstructured data to obtain standard unstructured data; The standard structured data and the standard unstructured data are integrated and segmented to obtain employee performance appraisal data.

8. The method according to claim 1, characterized in that After inputting the first evaluation result and the second evaluation result into the trained performance appraisal evaluation model and generating the employee evaluation report according to the three-stage generation logic, the method further includes: Returning the evaluation report to the client and storing it; When the performance appraisal of the employee is conducted again, the weight of the performance appraisal data involved in the appraisal report is reset to the highest weight to serve as the basis for generating the first evaluation result.

9. A performance evaluation index evaluation device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the performance appraisal indicator evaluation method described in any one of claims 1 to 8.

10. A performance evaluation index storage medium storing computer-executable instructions, characterized in that: The computer-executable instructions can execute a performance appraisal indicator evaluation method as described in any one of claims 1 to 8.

Images