A method, system, and medium for evaluating employee performance based on project completion.

Abstract

This application discloses a method, system, and medium for evaluating employee performance based on project completion, solving the technical problem in existing enterprise management where it is impossible to conduct refined evaluations of employee work performance using project data from completed projects. The method includes: determining a project knowledge graph based on project data from completed projects by the employee to be evaluated; acquiring historical project data and training a preset model based on this data to determine a scoring model; wherein the preset model includes a first preset model and a second preset model, and the scoring model includes a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining the score obtained by the employee in completing a certain module of the project; and determining the comprehensive score of the employee's completed project based on the project knowledge graph and the scoring model. This application achieves refined evaluation of employee work performance through the above method.

Description

Technical Field

[0001] This application relates to the field of enterprise management technology, and in particular to a method, system and medium for evaluating employee performance based on project completion. Background Technology

[0002] As enterprises develop and their scale expands, it becomes necessary to gradually shift from extensive expansion to refined management. For management and human resources departments, accurately and effectively evaluating employee performance is crucial for refined management, playing a significant role in employee performance appraisals and job evaluations.

[0003] Project completion status is an important way to assess employee efficiency. However, due to the different difficulties and completion quality of different projects, as well as the different roles employees play in projects, it is difficult to directly use simple statistical methods to assess employee work efficiency based on project completion status. Summary of the Invention

[0004] This application provides a method, system, and medium for evaluating employee performance based on project completion, which solves the technical problem in existing enterprise management that it is impossible to conduct a refined evaluation of employee work performance by utilizing project data on employee project completion.

[0005] In a first aspect, embodiments of this application provide a method for evaluating employee performance based on project completion, comprising: determining a project knowledge graph based on project data of the employee to be evaluated completing the project; acquiring historical project data and training a preset model based on the historical project data to determine a scoring model; wherein the preset model includes a first preset model and a second preset model, and the scoring model includes a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining the score obtained by the employee to be evaluated for completing a certain module of the project; and determining the comprehensive score of the employee to be evaluated for completing the project based on the project knowledge graph and the scoring model.

[0006] This application constructs a knowledge graph consisting of projects, employees to be evaluated, and related relationships, using projects and employees as nodes. The knowledge graph contains various labeled data, clearly demonstrating the project completion status of the employees to be evaluated. By utilizing a large amount of historical project data to train a preset model, a scoring model is obtained, enabling the scoring model to obtain accurate evaluation results when evaluating employees. This application's method for evaluating employee project completion not only avoids the non-standardization of traditional assessment methods but also saves significant time and manpower costs.

[0007] In one implementation of this application, a project knowledge graph is determined based on project data of the employee to be evaluated. Specifically, this includes: determining the structure of the knowledge graph based on historical project data; determining preset tags for the knowledge graph based on the specific type of the project and the project role of the employee to be evaluated; wherein the preset tags include preset project tags, preset employee tags, and preset relationship tags; determining the tag attributes of the preset tags based on historical project data; and integrating the structure of the knowledge graph, the preset tags, and the tag attributes corresponding to the preset tags to determine the project knowledge graph.

[0008] In one implementation of this application, after determining the preset tags based on the specific type of the project and the project role of the employee to be evaluated, the method further includes: determining the knowledge graph of each single module in the project completed by the employee to be evaluated based on the project knowledge graph; determining the rating tags among the preset tags based on the type of the preset tags; wherein, the rating tags include positive tags, negative tags, and correction tags; positive tags are tags that increase the rating of the employee to be evaluated, negative tags are tags that decrease the rating of the employee to be evaluated, and correction tags are tags that correct unreasonable ratings of the employee's project completion.

[0009] In one implementation of this application, before obtaining historical project data, the method further includes: creating a historical project index database based on a preset project server to store historical project data.

[0010] In one implementation of this application, a preset model is trained based on historical project data to determine the scoring model. Specifically, this includes: acquiring historical project data stored in a historical project index database and processing the historical project data to form a project data training set; training the preset model based on the project data training set to determine the scoring model; wherein, the historical project data includes relevant records of employees completing projects, as well as the single-module scores and comprehensive scores of the corresponding employees completing projects.

[0011] In one implementation of this application, the comprehensive score for the employee's project completion is determined based on a knowledge graph and scoring model of the employee's project completion status. Specifically, this includes: determining scoring tags and weight coefficients for each module based on the project knowledge graph; determining the individual module scores for each module based on the individual module scoring model, scoring tag attributes, and weight coefficients of the scoring tags; and determining the comprehensive score for the employee's project completion based on the comprehensive scoring model, individual module scores, and weight coefficients of each module.

[0012] In one implementation of this application, the first preset model is:

[0013]

[0014] Where, n P n represents the number of positive labels in this industry. N n represents the number of negative labels in this industry. C The number of corrected labels in this industry. (P) wei Let a be the value of the i-th positive label of employee w in single module e. i Let N be the weight coefficient of the i-th positive label of employee w in a single module e. wei Let b be the value of the i-th negative label for employee w in module e. i Let C be the weight coefficient of the i-th negative label of employee w in a single module e. wi Let c be the value of the i-th correction label for employee w. P c N a0 and b0 are model parameters.

[0015] In one implementation of this application, the second preset model is:

[0016]

[0017] Among them, S wi D represents the single-module score obtained by employee w in single-module i. i is the weighting coefficient of module i, and k is the nonlinear exponent.

[0018] Secondly, this application also provides an employee performance evaluation system based on project completion, including: a knowledge graph determination module, a scoring model determination module, and a scoring determination module; the knowledge graph determination module is used to determine a project knowledge graph based on project data of the employee to be evaluated completing the project; the scoring model determination module is used to acquire historical project data and train a preset model based on the historical project data to determine the scoring model; wherein, the preset model includes a first preset model and a second preset model, and the scoring model includes a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining the score obtained by the employee to be evaluated for completing a certain module of the project; the scoring determination module is used to determine the comprehensive score of the employee to be evaluated for completing the project based on the project knowledge graph and the scoring model.

[0019] Thirdly, embodiments of this application also provide a non-volatile computer storage medium for employee performance evaluation based on project completion, storing computer-executable instructions. These instructions are configured to: determine a project knowledge graph based on project data of the employee being evaluated completing the project; acquire historical project data and train a preset model based on the historical project data to determine a scoring model; wherein the preset model includes a first preset model and a second preset model, and the scoring model includes a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining the score obtained by the employee being evaluated for completing a certain module of the project; and determine the comprehensive score of the employee being evaluated for completing the project based on the project knowledge graph and the scoring model. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0021] Figure 1 A flowchart illustrating an employee performance evaluation method based on project completion status, provided in this application embodiment;

[0022] Figure 2 This is a schematic diagram of an employee performance evaluation system based on project completion status, provided as an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] To clarify the complex relationships between projects and employees, and to facilitate the design of algorithms for calculating employee efficiency, knowledge graphs can be used as a tool. The concept of knowledge graphs originated in 2012, first proposed by Google. Knowledge graphs were initially developed to accurately describe the relationships between people, things, and events, and were first applied to search engines. A knowledge graph is a knowledge database that describes text semantics and establishes entity relationships in nature. Generally, we can use a relational graph to represent a knowledge graph. The three components of a knowledge graph are: entities, relations, and attributes. Entities refer to objectively existing and distinguishable things; they can be concrete people, things, or events, or abstract concepts or relationships. Entities are the most basic element in a knowledge graph. In a knowledge graph, edges represent relations, used to represent certain connections between different entities. In addition, entities and relations in a knowledge graph can each have their own attributes.

[0025] Knowledge graphs help clarify the relationships between projects and employees. Using projects and employees as nodes, a knowledge graph is constructed, consisting of projects, employees, and their relationships. Based on the basic structure of the graph, relevant attributes are then assigned to each relationship and node to form a knowledge graph of project completion status. This allows for the design of algorithms to evaluate employee performance using the relationships and attributes on the knowledge graph.

[0026] This application provides a method, system, and medium for evaluating employee performance based on project completion, which solves the technical problem in existing enterprise management that it is impossible to conduct a refined evaluation of employee work performance by utilizing project data on employee project completion.

[0027] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 A flowchart illustrating an employee performance evaluation method based on project completion status, provided as an embodiment of this application. Figure 1 As shown in the figure, the employee performance evaluation method based on project completion provided in this application specifically includes the following steps:

[0029] Step 101: Based on the project data of the employees to be evaluated, determine the project knowledge graph.

[0030] Since the elements constituting a knowledge graph include entities, relationships, and attributes, in the embodiments of this application, the entities are the projects completed by the employee to be evaluated and the employee to be evaluated, and the relationships are the events completed by the roles the employee played during the project completion process. It should be noted that the employee to be evaluated may have two or more roles when completing a project; therefore, the relationships cannot be based on a single role. Taking software development in the IT industry as an example, among developers, there may be employees who act as project managers and also as business personnel communicating with target clients; therefore, the relationships cannot be reflected solely in the project completion level.

[0031] After determining the entities and relationships within the knowledge graph, the structural foundation of the project knowledge graph is established. Therefore, determining the complete knowledge graph also requires defining its attributes. Determining the attributes should begin with establishing pre-defined tags based on the specific project type and the project roles of the employees being evaluated. These pre-defined tags will reveal the composition of the knowledge graph's attributes. These pre-defined tags can be categorized into pre-defined project tags, pre-defined employee tags, and pre-defined relationship tags. For example, pre-defined project tags might include project difficulty level, estimated duration, actual duration, and level of functionality implementation; pre-defined employee tags might include role name; and pre-defined relationship tags might include work content, workload percentage, and completion time.

[0032] After determining the preset tags for the knowledge graph, values ​​are assigned to the preset tags based on historical project data to determine their tag attributes. Once the structure of the knowledge graph, its preset tags, and their corresponding tag attributes are determined, all elements constituting the project's knowledge graph are obtained. The knowledge graph's structure, preset tags, and their corresponding tag attributes are then integrated to finalize the project's knowledge graph.

[0033] Step 102: Obtain historical project data and train a preset model based on the historical project data to determine the scoring model.

[0034] In one embodiment of this application, before acquiring historical project data to train a preset model, a historical project index database should be created based on a preset project server to store the historical project data. It should be noted that, in addition to creating the historical project index database, a complete service should be deployed on the preset project server to realize data updates of the historical project index database and training of the preset model.

[0035] It should also be noted that the historical project data stored in the historical project index database does not need to be similar. Taking IT software development companies as an example, the historical project index database can store data of completed software projects, bidding project data, annual meeting project data, etc.

[0036] When acquiring historical project data to train a pre-defined model, historical project data similar to the types of projects completed by the employee being evaluated should be retrieved from the historical project index database. It should be noted that the historical project data stored in the historical project index database should include relevant records of employee project completion, as well as the corresponding single-module score and overall score for each employee's project completion; the single-module score refers to the score obtained by the employee for completing a specific module within the project.

[0037] After obtaining historical project data, the dataset obtained by organizing the historical project data is used to form a project data training set, which is then input into the preset model for training until a converged scoring model is output.

[0038] It should be noted that the pre-defined model should be able to score employees for each module and the overall project performance. Each project in the training dataset should be presented as a knowledge graph, and this knowledge graph should include the individual module knowledge graphs for each employee. Furthermore, based on the types of pre-defined labels in the knowledge graph, scoring labels should be determined, along with the weighting coefficients for each scoring label and each module. Scoring labels should include positive labels, negative labels, and correction labels; positive labels increase the score for the employee being evaluated, negative labels decrease the score, and correction labels correct any unreasonable scoring.

[0039] In one embodiment of this application, a reasonable preset model is provided, including a first preset model and a second preset model. The first preset model is used to train a single-module scoring model, and the second prediction model is used to train a comprehensive scoring model.

[0040] The first preset model is

[0041]

[0042] Where, n P n represents the number of positive labels in this industry. N n represents the number of negative labels in this industry. C The number of corrected labels in this industry. (P) wei Let a be the value of the i-th positive label of employee w in single module e. i Let N be the weight coefficient of the i-th positive label of employee w in a single module e.wei Let b be the value of the i-th negative label for employee w in module e. i Let C be the weight coefficient of the i-th negative label of employee w in a single module e. wi Let c be the value of the i-th correction label for employee w. P c N a0 and b0 are model parameters.

[0043] To ensure that neither positive nor negative labels cause an employee's single-module score to increase or decrease indefinitely, thereby preventing a single module from having an infinitely large impact on the overall score, the single-item score should have a theoretical maximum and minimum value. Therefore, the first preset model in the embodiment of this application sets parameter c. P and c N This ensures that the first preset model can guarantee the single-module score S. we The value range is - N and c P between.

[0044] The second preset model is

[0045]

[0046] Among them, S wi D represents the single-module score obtained by employee w in single-module i. i is the weighting coefficient of module i, and k is the nonlinear exponent.

[0047] The overall score of the employee being evaluated should be calculated by combining the scores obtained in each individual module, but cannot be directly accumulated. Each project should have a corresponding weighting coefficient D based on its duration or importance. i =1,…, D The overall score is obtained by non-linear weighted averaging based on weight coefficients. The calculation of S can be adjusted by changing the value of k. w The degree of nonlinearity in the process: when k < 1, the accumulation of workload has an amplifying effect on the score; when k < 1, the accumulation of workload has a reducing effect on the score.

[0048] It is understandable that the project data training set is input into the preset model for training in order to obtain the model parameters of the preset model.

[0049] In one embodiment of this application, in addition to training the model parameters using a machine learning-based training method, the parameters can also be defined by the company's managers or human resources department and relevant experts in the business field. The model parameters in the model can be manually defined based on factors such as the importance of different labels, the importance and difficulty of the role and responsibilities of the employee to be evaluated, etc.

[0050] Step 103: Based on the project knowledge graph and the scoring model, determine the comprehensive score of the employee to be evaluated for completing the project.

[0051] Before inputting the project knowledge graph of the employee's completed project into the scoring model for calculation, the knowledge graph of each individual module in the project should first be determined based on the project knowledge graph. Then, based on the types of preset tags in the project knowledge graph, the scoring tags within the preset tags should be determined, as well as the weight coefficients of the scoring tags and each individual module. Next, the scoring tag attributes and weight coefficients of each individual module's knowledge graph are input into the trained individual module scoring model to determine the employee's individual module score.

[0052] After determining the individual module scores of the employee to be evaluated in each module, the overall score of the employee's project completion is determined based on the comprehensive scoring model, the individual module scores, and the weighting coefficients of each module.

[0053] This application embodiment utilizes a knowledge graph to illustrate the relationships between the employee being evaluated and the project, deriving various graph-based tag features and attributes. A pre-defined, relatively reasonable scoring calculation model is used. Historical data or expert knowledge is employed to determine relevant model parameters, ensuring model accuracy. Finally, a comprehensive score for the employee is obtained by performing a non-linear weighted calculation on the individual module scores for each module. The pre-defined model used in this evaluation method balances rationality and flexibility, and can have different parameters and tag definitions for different companies and different fields of scoring.

[0054] Based on the same inventive concept, this application also provides an employee performance evaluation system based on project completion status, the structural diagram of which is shown below. Figure 2 As shown.

[0055] Figure 2 This is a schematic diagram of an employee performance evaluation system based on project completion status, provided as an embodiment of this application. Figure 2 As shown in the embodiment of this application, an employee performance evaluation system 200 based on project completion status includes: a knowledge graph determination module 201, a scoring model determination module 202, and a scoring determination module 203.

[0056] Those skilled in the art will understand that Figure 2 The presented structure of an employee performance evaluation system based on project completion does not constitute a limitation on employee performance evaluation systems based on project completion. In fact, employee performance evaluation systems based on project completion can include more than... Figure 2 This refers to more or fewer components, or combinations of certain components, or arrangements of different components.

[0057] In one embodiment of this application, the knowledge graph determination module 201 is used to determine a project knowledge graph based on project data of the employee to be evaluated completing the project; the scoring model determination module 202 is used to acquire historical project data and train a preset model based on the historical project data to determine the scoring model; wherein, the preset model includes a first preset model and a second preset model, and the scoring model includes a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining the score obtained by the employee to be evaluated for completing a certain module of the project; the scoring determination module 203 is used to determine the comprehensive score of the employee to be evaluated for completing the project based on the project knowledge graph and the scoring model.

[0058] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium for employee performance evaluation based on project completion, storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0059] Based on the project data of the employees to be evaluated, a project knowledge graph is determined.

[0060] Historical project data is acquired, and a preset model is trained based on the historical project data to determine the scoring model; wherein, the preset model includes a first preset model and a second preset model, and the scoring model includes a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining the score obtained by the employee being evaluated for completing a certain module of the project;

[0061] Based on the project knowledge graph and scoring model, the comprehensive score of the employee's completion of the project is determined.

[0062] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0063] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0064] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0069] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0070] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (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, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0071] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0072] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An employee performance evaluation method based on project completion, characterized by, The method comprises: Based on the project data of the employee to be evaluated completing the project, determine the project knowledge graph, including: determining the structure of the knowledge graph based on the project historical data, determining the preset label of the knowledge graph based on the specific type of the project and the project role of the employee to be evaluated, determining the knowledge graph of each single module in the project completed by the employee to be evaluated based on the project knowledge graph, determining the scoring label in the preset label based on the type of the preset label, wherein the preset label includes a preset project label, a preset employee to be evaluated label, and a preset correlation relationship label, the scoring label includes a positive label, a negative label, and a correction label, the positive label is a label that adds points to the score of the employee to be evaluated, the negative label is a label that reduces points to the score of the employee to be evaluated, and the correction label is a label that corrects the unreasonable score of the employee completing the project, determining the label attribute of the preset label based on the project historical data, and integrating the structure of the knowledge graph, the preset label, and the label attribute corresponding to the preset label to obtain the project knowledge graph; Obtain historical project data, and train a preset model based on the historical project data to determine a scoring model; wherein the preset model comprises a first preset model and a second preset model, and the scoring model comprises a single module scoring model and a comprehensive scoring model; the single module scoring model is a model for determining the score obtained by the employee to be evaluated in completing a module in the project; Based on the project knowledge graph and the scoring model, determine the comprehensive score of the employee to be evaluated completing the project.

2. The employee performance evaluation method based on project completion according to claim 1, wherein, Before obtaining the historical project data, the method further comprises: Based on the preset project server, create a historical project index database to store the historical project data.

3. The method for evaluating employee performance based on project completion according to claim 2, wherein, Based on the historical project data, train a preset model to determine a scoring model, specifically including: Obtain the historical project data stored in the historical project index database, and process the historical project data to form a project data training set; Based on the project data training set, train the preset model to determine the scoring model; Wherein the historical project data includes the relevant records of the employees completing the project, and the single module score and comprehensive score corresponding to the employees completing the project.

4. The method for evaluating employee performance based on project completion according to claim 1, wherein, Based on the employee to be evaluated project completion knowledge graph and the scoring model, determine the comprehensive score of the employee to be evaluated completing the project, specifically including: Based on the project knowledge graph, determine the scoring label and the weight coefficient of each single module; Based on the single module scoring model, the scoring label attribute, and the weight coefficient of the scoring label, determine the single module score of the employee to be evaluated in each single module; Based on the comprehensive scoring model, the single module score, and the weight coefficient of each single module, determine the comprehensive score of the employee to be evaluated completing the project.

5. The method for evaluating employee performance based on project completion according to claim 1, wherein, The first preset model is wherein, is the number of positive tags in the industry, is the number of negative tags in the industry, is the number of correction tags in the industry, is an employee takes a value of the positive tag in the single module e, is an employee is a weight coefficient of the positive tag in the single module e, is an employee takes a value of the negative tag in the single module e, is an employee is a weight coefficient of the negative tag in the single module e, is an employee takes a value of the correction tag, , , , are model parameters.

6. The method for evaluating employee performance based on project completion according to claim 1, wherein, The second preset model is wherein, for the employee in the single module obtained single module score, for the single module weighting factor for the single module, non-linear index.

7. An employee performance evaluation system based on project completion, characterized by, The system comprises a knowledge graph determination module, a scoring model determination module, and a scoring determination module; The knowledge graph determination module is configured to determine a project knowledge graph based on project data of an employee to be evaluated completing a project. The scoring model determining module is configured to acquire historical project data, and train a preset model based on the historical project data to determine a scoring model; wherein the preset model comprises a first preset model and a second preset model, and the scoring model comprises a single-module scoring model and a comprehensive scoring model; the single-module scoring model is a model for determining a score obtained by a to-be-evaluated employee in completing a certain module of a project. The scoring determining module is configured to determine a comprehensive score of the to-be-evaluated employee in completing the project based on the project knowledge graph and the scoring model.

8. A non-transitory computer storage medium storing computer-executable instructions for evaluating employee performance based on project completion, the computer-executable instructions comprising: The computer executable instructions are configured to perform the employee performance evaluation method based on a project completion condition according to any one of claims 1-6.

Images