A research and development management method and device based on big data, equipment and storage medium

Abstract

This application relates to the fields of artificial intelligence and work performance management, and particularly to a big data-based method, apparatus, computer equipment, and storage medium for performance management. It involves acquiring raw work data containing a set of employees, extracting corresponding performance evaluation element sets for segmentation, and obtaining corresponding evaluation element sets. The similarity of each performance evaluation element in each evaluation element set is calculated, and the calculation results are classified to obtain multiple corresponding performance evaluation categories. The resolution coefficient of the performance evaluation elements in each performance evaluation category is calculated, and the evaluation weight is calculated based on the resolution coefficient. Based on the evaluation weight, an employee evaluation profile is constructed. This invention proposes a more comprehensive, accurate, and effective supervision scheme for performance evaluation to incentivize individual or team work and ensure that enterprises can accurately grasp the true work situation of individuals or teams.

Description

Technical Field

[0001] This application relates to the fields of artificial intelligence and work performance management, and in particular to a big data-based work performance management method, device, computer equipment, and storage medium. Background Technology

[0002] In insurance claims work, the process is more diverse than in other professions, resulting in insufficient intuitive data to support performance evaluations of individuals or teams. Most evaluations rely on fragmented data. Furthermore, issues such as lack of oversight, potential for manipulation of evaluation content, and a lack of connection between the evaluators and the evaluated individuals contribute to inaccurate and unfair performance assessments. Therefore, a more comprehensive, accurate, and effectively monitored performance evaluation system is needed to incentivize individuals and teams and ensure that companies accurately grasp their true performance. Summary of the Invention

[0003] The purpose of this application is to propose a big data-based research and development management method to solve the security problem of monitoring whether there are unauthorized devices in the company's internal network in the prior art.

[0004] To address the aforementioned technical problems, this application provides a big data-based research and development performance management method, employing the following technical solution:

[0005] Obtain raw work data containing a set of employee objects, extract the corresponding performance evaluation element set based on the set of employee objects, divide the performance evaluation element set according to a preset data type, and obtain the corresponding evaluation element set.

[0006] Calculate the pairwise similarity between multiple performance evaluation elements contained in each set of evaluation elements to obtain multiple similarity values ​​corresponding to each performance evaluation element. Classify the performance evaluation elements according to the similarity values ​​of all performance evaluation elements in the set of performance evaluation elements to obtain multiple corresponding performance evaluation categories. Each performance evaluation category corresponds to an evaluation dimension.

[0007] Calculate the resolution coefficient of each research and evaluation element in each of the research and evaluation categories, and calculate the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient;

[0008] Employee evaluation profiles are constructed based on the evaluation weights.

[0009] Furthermore, the method also includes:

[0010] Obtain the research and evaluation indicators, and perform fitting calculations based on the research and evaluation elements in the research and evaluation category and the research and evaluation indicators to obtain the initial fitting results;

[0011] The decision coefficients are obtained by calculating the sum of squared deviations and residuals of the research and evaluation indicators based on the initial fitting results.

[0012] The resolution coefficients are preprocessed, and the processed resolution coefficients are used as the evaluation weights of the research and evaluation elements in the corresponding evaluation dimensions.

[0013] Furthermore, the method also includes:

[0014] Data for each evaluation element and the evaluation weights are obtained to calculate scores, resulting in multiple initial scores based on the evaluation dimensions.

[0015] The initial score is fitted by a pre-built learning model to obtain the corresponding evaluation dimension score;

[0016] By integrating the evaluation dimensions and the initial score, and performing distribution calculations, the corresponding research and evaluation results are obtained.

[0017] Employee evaluation profiles are constructed based on the evaluation results.

[0018] Furthermore, the method also includes:

[0019] Extract the preset research effectiveness correction coefficient;

[0020] The evaluation weights are adjusted using the performance correction coefficient according to preset rules, wherein the preset rules include the corresponding evaluation relationship of the evaluation category to which the evaluation element belongs.

[0021] Furthermore, the method also includes:

[0022] The evaluation elements are processed into word vectors to obtain a set of evaluation word vectors;

[0023] Calculate the cosine similarity between each pair of comment word vectors in each of the comment word vector sets to obtain a first-order similarity value set;

[0024] The set of similar values ​​is classified a second time using a preset target threshold, and multiple evaluation categories are obtained by aggregation.

[0025] Furthermore, the method also includes:

[0026] Extract the corresponding job level based on the employee object set;

[0027] The original work data was compared to the standard data types of each job level to determine if any data was missing.

[0028] If any data is missing, it will be filled in to complete the original working data.

[0029] To address the aforementioned technical problems, this application also provides a research and development performance management method and apparatus based on big data, employing the following technical solution:

[0030] A big data-based research and development performance management device, the device comprising:

[0031] Data acquisition module: used to acquire raw work data containing employee object set, extract corresponding performance evaluation element set based on the employee object set, divide the performance evaluation element set according to preset data type to obtain corresponding evaluation element set;

[0032] Similarity classification model: used to calculate the similarity of each of the research and evaluation elements in each of the evaluation element sets one by one, to obtain the corresponding calculation results, and to classify the research and evaluation elements in each of the evaluation element sets according to the calculation results, to obtain multiple corresponding research and evaluation categories, and each research and evaluation category corresponds to an evaluation dimension;

[0033] Weight calculation module: used to calculate the resolution coefficient of each research and evaluation element in the research and evaluation category, and to calculate the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient;

[0034] Profile Output Module: Used to construct employee evaluation profiles based on the evaluation weights.

[0035] Furthermore, the device also includes:

[0036] Preliminary Fitting Submodule: Used to obtain research and evaluation indicators, and to perform fitting calculations between the research and evaluation elements in the research and evaluation category and the research and evaluation indicators to obtain initial fitting results;

[0037] Resolution calculation submodule: used to calculate the sum of squared deviations and residuals of the research and evaluation indicators based on the initial fitting results to obtain the resolution coefficients;

[0038] Weight output submodule: used to preprocess the decision coefficients and use them as the evaluation weights of the research and evaluation elements in the corresponding evaluation dimensions.

[0039] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0040] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the big data-based research and performance management method described above.

[0041] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0042] A computer-readable storage medium is characterized in that it stores computer-readable instructions, which, when executed by a processor, implement the steps of the big data-based research and performance management method described above.

[0043] Compared with the prior art, the embodiments of this application have the following main advantages:

[0044] By acquiring the original work set, analyzing the performance evaluation elements in the work tasks of the employee objects within the original work set, and initially dividing the evaluation element set, further classification is performed by similarity calculation on the performance evaluation elements in the initially divided evaluation element set, resulting in multiple performance evaluation categories. Evaluation dimensions for each performance evaluation category are defined to construct employee evaluation profiles, thereby conducting comprehensive, accurate, and fair evaluations of employees. This aims to motivate individual or team work and ensure that the company can accurately grasp the true work performance of individuals or teams. Attached Figure Description

[0045] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0047] Figure 2 This is a flowchart of one implementation of the big data-based research and performance management method according to this application;

[0048] Figure 3 This is a structural diagram of one embodiment of the big data-based research and performance management device according to this application;

[0049] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0051] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0052] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0053] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0054] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, and social online platform software.

[0055] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0056] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0057] It should be noted that the big data-based research and development management method provided in this application is generally developed by... Serve Device / Terminal Equipment Accordingly, network data security monitoring devices are generally installed in Server / Terminal Equipment middle.

[0058] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0059] Continue to refer to Figure 2 The diagram illustrates a flowchart of an embodiment of the big data-based research and development management method proposed in this application. This embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that utilize digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0060] Artificial intelligence (AI) foundational technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly include computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning. The aforementioned big data-based research and performance management method includes the following steps:

[0061] S201: Obtain the original work data containing the employee object set, extract the corresponding performance evaluation element set based on the employee object set, divide the performance evaluation element set according to the preset data type, and obtain the corresponding evaluation element set.

[0062] Specifically, in the embodiments, it should be noted that the source of the original work data is the work task data of the employee. Taking the performance evaluation of insurance work tasks as an example, the corresponding work task data obtained includes the job information, job responsibilities, detailed work task process, corresponding work task assessment requirements, and corresponding work task reporting data of the corresponding departments related to the insurance work tasks.

[0063] Based on the employee object, the original work data is extracted to form a set of evaluation elements. In this application, the extraction can be carried out by associating the employee object's name with the corresponding department information, job position information, work tasks, and task process node identification data contained in the original work data. After field extraction, multiple evaluation elements are obtained, and the evaluation element set is obtained by summarizing them.

[0064] Furthermore, in another embodiment, the original work data is compared with the standard data type of the job level of each employee in the employee object set to see if there is any missing data; if there is missing data, data is filled in to complete the original work data.

[0065] S202: Calculate the similarity between each pair of multiple performance evaluation elements contained in each set of evaluation elements to obtain multiple similarity values ​​corresponding to each performance evaluation element. Classify the performance evaluation elements according to the similarity values ​​of all performance evaluation elements in the set of performance evaluation elements to obtain multiple corresponding performance evaluation categories. Each performance evaluation category corresponds to an evaluation dimension.

[0066] Specifically, in this embodiment, the evaluation elements are converted into word vectors, and the similarity is calculated using existing arbitrary word similarity algorithms. This application compares the similarity values ​​calculated by the similarity algorithm with the preset threshold to classify the evaluation elements into the same category, and merges the evaluation elements of the same category to obtain multiple corresponding evaluation categories.

[0067] Based on the definitions of evaluation dimensions for multiple research and evaluation categories, such as the evaluation elements related to on-site investigation tasks obtained after classification, and the evaluation dimensions for the research and evaluation categories of on-site investigation tasks defined based on the teams and departments related to the on-site investigation tasks; for example, in the research and evaluation elements of on-site investigation tasks, on-site investigation staff and teams will divide the dimensions by the classified cases, arrival status, case closure status and abnormal situations to obtain the arrival dimension, and then adjust the categories of research and evaluation elements based on the defined evaluation dimensions.

[0068] Furthermore, the evaluation elements are processed into word vectors to obtain a set of evaluation word vectors; the cosine similarity between each pair of evaluation word vectors in each set of evaluation word vectors is calculated to obtain a set of primary similarity values; the primary similarity value set is classified a second time using a preset target threshold to aggregate multiple evaluation categories.

[0069] In another embodiment, a fuzzy clustering algorithm and a clustering effectiveness index can be used to determine the number of research and performance evaluation clusters based on the research and performance evaluation index; a partitioning matrix is ​​determined according to the number of research and performance evaluation clusters, and R nearest neighbors of the same class and different classes are found from the partitioning matrix to calculate the weights of the research and performance evaluation features in the research and performance evaluation index; the research and performance evaluation categories are obtained by genetic iteration and evolution of each of the research and performance evaluation features according to a genetic algorithm fused with simulated annealing algorithm.

[0070] S203: Calculate the resolution coefficient of the research and evaluation element in each of the research and evaluation categories, and calculate the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient.

[0071] Specifically, in this embodiment, the performance evaluation index is a fitting index set based on any pre-defined work task. The performance evaluation index is obtained, and a linear fitting calculation is performed between the performance evaluation elements in the performance evaluation category and the performance evaluation index to obtain an initial fitting result. Based on the initial fitting result, the deviation and sum of squared residuals of the performance evaluation index are calculated to obtain the decision coefficient. After data preprocessing, the decision coefficient is used as the evaluation weight of the performance evaluation element in the corresponding evaluation dimension. For example, let the performance evaluation element be A. i (i=n), the evaluation index is B, and the decision coefficient between the two is Z. 2 After linear fitting, the fitting function f(Z) = na + c is obtained. The method for calculating the decision coefficients of the fitting function is the existing algorithm, which will not be elaborated here.

[0072] S204: Construct employee evaluation profiles based on the evaluation weights.

[0073] Specifically, in this embodiment, after calculating the evaluation weights, the evaluation elements for each month are calculated using the evaluation weights. Combining the weights of the evaluation elements, multiple initial scores for each evaluation dimension can be obtained. The initial scores are fitted using a pre-built learning model to obtain the corresponding evaluation dimension scores. After fusing the evaluation dimensions and the initial scores, a distribution calculation is performed to obtain the corresponding evaluation results.

[0074] Furthermore, when the evaluation results are obtained, the corresponding employees are extracted and their evaluation results are marked. The evaluation results are marked as excellent, good, medium, average, and poor, covering a wide range, in order to construct an employee evaluation profile.

[0075] Compared with the prior art, the embodiments of this application have the following main advantages:

[0076] By acquiring the original work set, analyzing the performance evaluation elements in the work tasks of the employee objects within the original work set, and initially dividing the evaluation element set, further classification is performed by similarity calculation on the performance evaluation elements in the divided evaluation element set to obtain multiple performance evaluation categories. Evaluation dimensions for each performance evaluation category are defined to construct employee evaluation profiles, thereby conducting comprehensive, accurate, and fair evaluations of employees. This aims to motivate individual or team work and ensure that the company can accurately grasp the true work performance of individuals or teams.

[0077] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0078] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0079] Further reference Figure 4 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of a big data-based research and development management device 300, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0080] Data acquisition module 310: used to acquire raw work data containing a set of employee objects, extract the corresponding performance evaluation element set based on the set of employee objects, divide the performance evaluation element set according to a preset data type, and obtain the corresponding evaluation element set.

[0081] Specifically, in the embodiments, it should be noted that the source of the original work data is the work task data of the employee. Taking the performance evaluation of insurance work tasks as an example, the corresponding work task data obtained includes the job information, job responsibilities, detailed work task process, corresponding work task assessment requirements, and corresponding work task reporting data of the corresponding departments related to the insurance work tasks.

[0082] Based on the employee object, the original work data is extracted to form a set of evaluation elements. In this application, the extraction can be carried out by associating the employee object's name with the corresponding department information, job position information, work tasks, and task process node identification data contained in the original work data. After field extraction, multiple evaluation elements are obtained, and the evaluation element set is obtained by summarizing them.

[0083] Furthermore, in another embodiment, the original work data is compared with the standard data type of the job level of each employee in the employee object set to see if there is any missing data; if there is missing data, data is filled in to complete the original work data.

[0084] Similarity classification module 320: is used to calculate the similarity between each pair of multiple performance evaluation elements contained in each evaluation element set, to obtain multiple similarity values ​​corresponding to each performance evaluation element, and to classify the performance evaluation elements according to the similarity values ​​of all performance evaluation elements in the performance evaluation element set, to obtain multiple corresponding performance evaluation categories, and each performance evaluation category corresponds to an evaluation dimension.

[0085] Specifically, in this embodiment, the evaluation elements are converted into word vectors, and the similarity is calculated using existing arbitrary word similarity algorithms. This application compares the similarity values ​​calculated by the similarity algorithm with the preset threshold to classify the evaluation elements into the same category, and merges the evaluation elements of the same category to obtain multiple corresponding evaluation categories.

[0086] Based on the definitions of evaluation dimensions for multiple research and evaluation categories, such as the evaluation elements related to on-site investigation tasks obtained after classification, and the evaluation dimensions for the research and evaluation categories of on-site investigation tasks defined based on the teams and departments related to the on-site investigation tasks; for example, in the research and evaluation elements of on-site investigation tasks, on-site investigation staff and teams will divide the dimensions by the classified cases, arrival status, case closure status and abnormal situations to obtain the arrival dimension, and then adjust the categories of research and evaluation elements based on the defined evaluation dimensions.

[0087] Furthermore, the similarity classification module performs word vectorization on the evaluation elements to obtain a set of evaluation word vectors; calculates the cosine similarity between each pair of evaluation word vectors in each set of evaluation word vectors to obtain a set of primary similarity values; and performs secondary classification on the set of primary similarity values ​​using a preset target threshold to aggregate multiple evaluation categories.

[0088] In another embodiment, the similarity classification module uses a fuzzy clustering algorithm and a clustering effectiveness index to determine the number of research and performance evaluation clusters based on the research and performance evaluation index; it determines a partitioning matrix based on the number of research and performance evaluation clusters, and finds R nearest neighbors of the same class and different classes from the partitioning matrix to calculate the weights of the research and performance evaluation features in the research and performance evaluation index; it performs genetic iteration and evolution on each of the research and performance evaluation features based on a genetic algorithm fused with a simulated annealing algorithm to obtain the research and performance evaluation category.

[0089] Weight calculation module 330: used to calculate the resolution coefficient of each research and evaluation element in the research and evaluation category, and calculate the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient.

[0090] In this embodiment, the weight calculation module 330 further includes a preliminary fitting submodule 331: used to obtain the research and evaluation indicators, and to perform fitting calculations based on the research and evaluation elements in the research and evaluation category and the research and evaluation indicators to obtain an initial fitting result.

[0091] Specifically, in this embodiment, the research and evaluation index is a fitting index set based on any pre-defined work task. The research and evaluation index is obtained, and a linear fitting calculation is performed between the research and evaluation elements in the research and evaluation category and the research and evaluation index to obtain the initial fitting result.

[0092] In this embodiment, the weight calculation module 330 further includes a resolution calculation submodule 332, which is used to calculate the sum of squares of the deviation and residuals of the research and evaluation index based on the initial fitting result to obtain the resolution coefficient.

[0093] The decision coefficient is obtained by calculating the sum of squared deviations and residuals of the research and evaluation index based on the initial fitting results. For example, let the research and evaluation element be Ai (i = n), and the research and evaluation index be B, then the decision coefficient between them is Z. 2 After linear fitting, the fitting function f(B) = na + c is obtained. The method for calculating the decision coefficients of the fitting function is the existing algorithm, which will not be elaborated here.

[0094] In this embodiment, the weight calculation module 330 further includes a weight output submodule 333: used to preprocess the decision coefficients and use them as the evaluation weights of the research and evaluation elements in the corresponding evaluation dimensions.

[0095] Image output module 340: used to construct employee evaluation profiles based on the evaluation weights.

[0096] Specifically, in this embodiment, after calculating the evaluation weights, the evaluation elements for each month are calculated using the evaluation weights. Combining the weights of the evaluation elements, multiple initial scores for each evaluation dimension can be obtained. The initial scores are fitted using a pre-built learning model to obtain the corresponding evaluation dimension scores. After fusing the evaluation dimensions and the initial scores, a distribution calculation is performed to obtain the corresponding evaluation results.

[0097] Furthermore, when the evaluation results are obtained, the corresponding employees are extracted and their evaluation results are marked. The evaluation results are marked as excellent, good, medium, average, and poor, covering a wide range, in order to construct an employee evaluation profile.

[0098] Compared with the prior art, the embodiments of this application have the following main advantages:

[0099] By acquiring the original work set, analyzing the performance evaluation elements in the work tasks of the employee objects within the original work set, and initially dividing the evaluation element set, further classification is performed by similarity calculation on the performance evaluation elements in the divided evaluation element set to obtain multiple performance evaluation categories. Evaluation dimensions for each performance evaluation category are defined to construct employee evaluation profiles, thereby conducting comprehensive, accurate, and fair evaluations of employees. This aims to motivate individual or team work and ensure that the company can accurately grasp the true work performance of individuals or teams.

[0100] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0101] The computer device 5 includes a memory 51, a processor 52, and a network interface 53 that are interconnected via a system bus. It should be noted that only the computer device 5 with components 51-53 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0102] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0103] The memory 51 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 51 may be an internal storage unit of the computer device 5, such as the hard disk or memory of the computer device 5. In other embodiments, the memory 51 may also be an external storage device of the computer device 5, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 5. Of course, the memory 51 may include both the internal storage unit and its external storage device of the computer device 5. In this embodiment, the memory 51 is typically used to store the operating system and various application software installed on the computer device 5, such as the program code of method X. In addition, the memory 51 can also be used to temporarily store various types of data that have been output or will be output.

[0104] In some embodiments, the processor 52 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 52 is typically used to control the overall operation of the computer device 5. In this embodiment, the processor 52 is used to run program code stored in the memory 51 or process data, for example, to run the program code for the X method.

[0105] The network interface 53 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 5 and other electronic devices.

[0106] This application also provides another implementation, namely, providing a computer-readable storage medium storing the network data security monitoring program, which can be executed by at least one processor to cause the at least one processor to perform the steps of the big data-based research and development management method described above.

[0107] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware online platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0108] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0109] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A research and performance management method based on big data, characterized in that, The method includes: Obtain raw work data containing a set of employee objects, extract the corresponding performance evaluation element set based on the set of employee objects, divide the performance evaluation element set according to a preset data type, and obtain the corresponding evaluation element set. Calculate the pairwise similarity between multiple performance evaluation elements contained in each set of evaluation elements to obtain multiple similarity values ​​corresponding to each performance evaluation element. Classify the performance evaluation elements according to the similarity values ​​of all performance evaluation elements in the set of performance evaluation elements to obtain multiple corresponding performance evaluation categories. Each performance evaluation category corresponds to an evaluation dimension. Calculate the resolution coefficient of each research and evaluation element in each of the research and evaluation categories, and calculate the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient; Employee evaluation profiles are constructed based on the evaluation weights. The calculation of the resolution coefficient of the evaluation element in each of the evaluation categories, and the calculation of the evaluation weight of the evaluation element in the corresponding evaluation dimension based on the resolution coefficient, specifically includes: Obtain the research and evaluation indicators, and perform fitting calculations based on the research and evaluation elements in the research and evaluation category and the research and evaluation indicators to obtain the initial fitting results; The decision coefficients are obtained by calculating the sum of squared deviations and residuals of the research and evaluation indicators based on the initial fitting results. The resolution coefficients are preprocessed, and the processed resolution coefficients are used as the evaluation weights of the research and evaluation elements in the corresponding evaluation dimensions. The construction of employee evaluation profiles based on the evaluation weights specifically includes: Data for each evaluation element and the evaluation weights are obtained to calculate scores, resulting in multiple initial scores based on the evaluation dimensions. The initial score is fitted by a pre-built learning model to obtain the corresponding evaluation dimension score; By integrating the evaluation dimensions and the initial score, and performing distribution calculations, the corresponding research and evaluation results are obtained. Employee evaluation profiles are constructed based on the evaluation results.

2. The research and performance management method based on big data according to claim 1, characterized in that, After calculating the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient, the method further includes: Extract the preset research effectiveness correction coefficient; The evaluation weights are adjusted using the research and evaluation correction coefficient according to preset rules, wherein the preset rules include the corresponding evaluation relationship of the research and evaluation category to which the research and evaluation element belongs.

3. The research and performance management method based on big data according to claim 1, characterized in that, The step of classifying the performance evaluation elements based on the similarity values ​​of all performance evaluation elements in the performance evaluation element set to obtain multiple corresponding performance evaluation categories specifically includes: The evaluation elements are processed into word vectors to obtain a set of evaluation word vectors; Calculate the cosine similarity between each pair of comment word vectors in each of the comment word vector sets to obtain a first-order similarity value set; The set of similar values ​​is classified a second time using a preset target threshold, and multiple evaluation categories are obtained by aggregation.

4. The research and performance management method based on big data according to claim 1, characterized in that, After extracting the corresponding performance evaluation element set based on the employee object set, the process also includes: Extract the corresponding job level based on the employee object set; The original work data was compared to the standard data types of each job level to determine if any data was missing. If any data is missing, it will be filled in to complete the original working data.

5. A research and development performance management device based on big data, characterized in that, The device includes: Data acquisition module: used to acquire raw work data containing employee object set, extract corresponding performance evaluation element set based on the employee object set, divide the performance evaluation element set according to preset data type to obtain corresponding evaluation element set; Similarity classification model: used to calculate the similarity of each of the research and evaluation elements in each of the evaluation element sets one by one, to obtain the corresponding calculation results, and to classify the research and evaluation elements in each of the evaluation element sets according to the calculation results, to obtain multiple corresponding research and evaluation categories, and each research and evaluation category corresponds to an evaluation dimension; Weight calculation module: used to calculate the resolution coefficient of each research and evaluation element in the research and evaluation category, and to calculate the evaluation weight of the research and evaluation element in the corresponding evaluation dimension based on the resolution coefficient; Profile output module: used to construct employee evaluation profiles based on the evaluation weights; The weight calculation module includes: Preliminary Fitting Submodule: Used to obtain research and evaluation indicators, and to perform fitting calculations between the research and evaluation elements in the research and evaluation category and the research and evaluation indicators to obtain initial fitting results; Resolution calculation submodule: used to calculate the sum of squared deviations and residuals of the research and evaluation indicators based on the initial fitting results to obtain the resolution coefficients; Weight output submodule: used to preprocess the decision coefficients and use them as the evaluation weights of the research and evaluation elements in the corresponding evaluation dimensions. The profile output module is also used to acquire data of each performance evaluation element and the evaluation weight to calculate scores and obtain multiple initial scores based on the evaluation dimensions; fit the initial scores through a pre-built learning model to obtain the corresponding evaluation dimension scores; fuse the evaluation dimensions and the initial scores and perform distribution calculations to obtain the corresponding performance evaluation results; and construct employee evaluation profiles based on the evaluation results.

6. A computer device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor, when executing the computer-readable instructions, implements the steps of the big data-based research and performance management method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the big data-based research and performance management method as described in any one of claims 1 to 4.

Images