Human resource management system and method based on artificial intelligence

Abstract

The invention provides a human resource management system and method based on artificial intelligence, and relates to the technical field of human resource management. Multi-dimensional feature data of target enterprise employees are collected, and talent tag codes are determined based on the multi-dimensional feature data; obtaining a current post demand vector, obtaining post compatibility based on the current post demand vector and the talent tag code, and determining a post adjustment urgency coefficient of the target enterprise employee according to the post compatibility and a urgency threshold; performing on-duty contribution evaluation on the target enterprise employees through the historical on-duty data to obtain post contribution degrees, and performing talent loss early warning according to the post contribution degrees and the on-duty adjustment urgency coefficients of the target enterprise employees to obtain remission risk indexes of the target enterprise employees; and determining a talent management strategy of the target enterprise employee according to the demission risk index. According to the method, the accuracy of early warning of potential talent loss can be improved, the demission probability of key talents is reduced, and the scientificity and refinement level of enterprise human resource management are improved.

Description

Technical Field

[0001] This application relates to the field of human resource management technology, and more specifically, to an artificial intelligence-based human resource management system and method. Background Technology

[0002] With the development of artificial intelligence and big data technologies, existing human resource management is gradually incorporating information technology and intelligent methods. By collecting and processing employees' basic information, work experience, job resumes, and performance data, it is possible to model and analyze employee characteristics. Some systems utilize matching methods between job requirements and employee competency characteristics to assist in job allocation and person-job matching; meanwhile, some studies use statistical analysis of employees' historical performance data to achieve quantitative evaluation of employee contributions and performance management. The application of these technologies provides enterprises with data-driven human resource management tools, gradually promoting the scientification and automation of the management process.

[0003] Current human resource management technologies typically rely on information systems to collect and manage employee basic information, job requirements, and performance data to assist companies in job allocation and performance appraisal. However, as companies expand and job requirements diversify, traditional data statistics methods alone are insufficient to comprehensively depict the multidimensional characteristics of employees, achieve accurate matching between employees and positions, or effectively predict and manage potential employee turnover risks. Therefore, improving the accuracy of early warnings of potential talent loss, reducing the probability of key personnel leaving, and enhancing the scientific and sophisticated level of corporate human resource management have become challenges facing the industry. Summary of the Invention

[0004] This application provides an artificial intelligence-based human resource management system and method, which can improve the accuracy of early warning of potential talent loss, reduce the probability of key personnel leaving, and enhance the scientific and refined level of enterprise human resource management.

[0005] Firstly, this application provides an artificial intelligence-based human resource management method, which includes the following steps: Collect multidimensional feature data of employees of the target company, and determine the talent tag code of the employees of the target company based on the multidimensional feature data; Obtain the current job demand vector of the target company's employees, conduct a job compatibility assessment of the target company's employees based on the current job demand vector and the talent tag code, obtain the job compatibility degree of the target company's employees, and determine the job transfer urgency coefficient of the target company's employees based on the job compatibility degree and the urgency threshold. Obtain historical on-the-job data of employees of the target company, evaluate the on-the-job contribution of the employees of the target company based on the historical on-the-job data, obtain the job contribution degree of the employees of the target company to their current positions, and conduct talent loss warning based on the job contribution degree and the job transfer urgency coefficient of the employees of the target company, thereby obtaining the turnover risk index of the employees of the target company. The talent management strategy for the target company's employees is determined based on the turnover risk index.

[0006] In this embodiment, the collection of multidimensional feature data of the target company's employees is achieved by extracting multidimensional feature data of the target company's employees from the artificial intelligence backend system.

[0007] In this embodiment, the job compatibility assessment of the target company's employees based on the current job demand vector and the talent tag code, to obtain the job compatibility degree of the target company's employees, specifically includes: Based on the current job demand vector, the talent tag encoding is aligned in the feature space to obtain the talent tag vector; The job compatibility of the target company's employees is obtained by evaluating the compatibility similarity between the talent tag vector and the current job requirement vector.

[0008] In this embodiment, determining the urgency coefficient of a target company's employee's job transfer based on the job compatibility and urgency threshold specifically includes: Initialize the urgent threshold; The job compatibility is filtered based on the urgency threshold to obtain the job transfer urgency coefficient of the target company's employees.

[0009] In this embodiment, the on-the-job contribution of the target company's employees is evaluated using the historical on-the-job data to obtain the specific contribution level of the target company's employees to their current positions, including: Feature construction is performed on the historical on-the-job data to obtain job-related word vectors; Initialize the contribution weights of each job term vector; The contribution of each employee in the target company to their current position is determined based on the contribution weights of each contribution and the word vectors of the job positions.

[0010] In this embodiment, talent loss early warning is generated based on the job contribution level and the urgency coefficient of the target company's employees for job transfer. The resulting employee turnover risk index specifically includes: The job sensitivity coefficient of the target company's employees is determined by the job contribution level. The employee turnover risk index of the target company is determined based on the job sensitivity coefficient and the job transfer urgency coefficient.

[0011] In this embodiment, determining the talent management strategy for the target company's employees based on the turnover risk index specifically includes: Initialize the target company's various talent management measures for its employees; By screening various talent management measures using the turnover risk index, a talent management strategy for the target company's employees can be obtained.

[0012] Secondly, this application provides an artificial intelligence-based human resource management system for executing an artificial intelligence-based human resource management method, the human resource management system comprising: The tag encoding module is used to collect multidimensional feature data of employees of the target company and determine the talent tag code of the employees of the target company based on the multidimensional feature data. The job reassignment urgency module is used to obtain the current job demand vector of the target company's employees, perform job compatibility assessment on the target company's employees based on the current job demand vector and the talent tag code, obtain the job compatibility degree of the target company's employees, and determine the job reassignment urgency coefficient of the target company's employees based on the job compatibility degree and the urgency threshold. The turnover risk module is used to obtain the historical on-the-job data of the target company's employees, evaluate the on-the-job contribution of the target company's employees based on the historical on-the-job data, obtain the job contribution degree of the target company's employees to the current position, and conduct talent loss warning based on the job contribution degree and the job transfer urgency coefficient of the target company's employees, thereby obtaining the turnover risk index of the target company's employees. The talent protection module is used to determine the talent management strategy for the target company's employees based on the turnover risk index.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory for storing computer programs, and the processor for calling and running the computer programs from the memory, so that the computer device performs the aforementioned artificial intelligence-based human resource management method.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned artificial intelligence-based human resource management method.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: Collect multidimensional feature data of employees of the target company, and determine the talent tag code of the employees based on the multidimensional feature data; obtain the current job demand vector of the employees of the target company, and conduct a job compatibility assessment of the employees based on the current job demand vector and the talent tag code to obtain the job compatibility degree of the employees of the target company, and determine the job transfer urgency coefficient of the employees of the target company based on the job compatibility degree and the urgency threshold; obtain the historical on-the-job data of the employees of the target company, and conduct an on-the-job contribution assessment of the employees based on the historical on-the-job data to obtain the job contribution degree of the employees of the target company to the current position, and conduct talent loss warning based on the job contribution degree and the job transfer urgency coefficient of the employees of the target company to obtain the turnover risk index of the employees of the target company; determine the talent management strategy for the employees of the target company based on the turnover risk index.

[0016] Therefore, this application demonstrates several key advantages. First, by collecting multidimensional characteristic data of employees and generating unified talent tag codes, it is possible to structure and quantify the complex information of employees, achieving objective comparability between different employees. This not only avoids the subjective bias of manual assessment but also provides a unified characteristic benchmark for subsequent job matching, contribution evaluation, and risk warning. Second, by obtaining the job requirement vector of the target company's employees and conducting compatibility assessment with the employees' talent tag codes, the suitability of employees for their current positions can be accurately quantified. Furthermore, by combining this with an urgency threshold to calculate a job reassignment urgency coefficient, the risk of job mismatch can be dynamically identified, and potential skill gaps can be discovered in a timely manner. This not only avoids the one-sidedness and lag of traditional reliance on human experience but also provides companies with scientific and quantifiable basis for job reassignment, thereby improving the rationality of job allocation and the efficiency of person-job matching. Third, by acquiring and analyzing the historical on-the-job data of the target company's employees, it is possible to comprehensively reflect the actual output and long-term performance of employees in their positions. Based on this, by combining job contribution and job reassignment urgency coefficients for talent loss warning, the employee's turnover risk index can be quantitatively calculated, thereby identifying potential turnover risks in advance. It not only overcomes the lag and uncertainty of traditional reliance on managers' subjective judgment, but also enables real-time and dynamic monitoring of talent status, providing enterprises with scientific and data-driven risk warning basis, effectively reducing the probability of core talent loss, and improving the foresight and accuracy of human resource management; finally, by implementing human resource management for target enterprise employees based on the turnover risk index, it can achieve graded identification and personalized intervention for high-risk employees, automatically match protective measures, and form a closed-loop management mechanism from risk discovery to protection implementation.

[0017] In summary, the technical solution adopted in this application can improve the accuracy of early warning of potential talent loss, reduce the probability of key personnel leaving, and enhance the scientific and refined level of enterprise human resource management. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an exemplary flowchart of an artificial intelligence-based human resource management method provided in this application; Figure 2 This is an exemplary flowchart for obtaining the job compatibility of the target company's employees, provided in this application. Figure 3 This is an exemplary flowchart provided in this application for obtaining the job contribution of the target company's employees to their current positions; Figure 4 This is a module structure diagram of the artificial intelligence-based human resource management system provided in this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing an artificial intelligence-based human resource management method according to the present application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This application provides an artificial intelligence-based human resource management system and method. Its core involves collecting multi-dimensional feature data of employees in a target company, determining talent tag codes for these employees based on the multi-dimensional feature data, obtaining the current job demand vector of the employees, evaluating job compatibility based on the current job demand vector and the talent tag codes to obtain the employee's job compatibility degree, and determining the employee's job transfer urgency coefficient based on the job compatibility degree and an urgency threshold. It also involves acquiring the employees' historical on-the-job data, evaluating their on-the-job contribution based on this data to obtain their contribution to their current position, and using this contribution and the job transfer urgency coefficient to provide talent loss early warning, resulting in the employee's turnover risk index. Finally, it determines the employee's talent management strategy based on the turnover risk index. This approach can improve the accuracy of early warning of potential talent loss, reduce the probability of key personnel leaving, and enhance the scientific and refined level of enterprise human resource management.

[0022] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown, this figure is an exemplary flowchart of an artificial intelligence-based human resource management method according to this embodiment of the present application. The human resource management method includes the following steps: In step S1, multidimensional feature data of the target company's employees are collected, and talent tag codes of the target company's employees are determined based on the multidimensional feature data.

[0023] In this embodiment, the collection of multidimensional feature data of the target company's employees is achieved by extracting multidimensional feature data of the target company's employees from the artificial intelligence backend system.

[0024] In practice, basic information, job experience, attendance records, and performance scores of employees of the target company can be extracted from the AI ​​backend system, and then used as multi-dimensional feature data of the employees of the target company.

[0025] In practice, the talent tag code of the target company's employees can be determined based on the multidimensional feature data. That is, the multidimensional feature data can be modally encoded, such as: (basic information: name, gender, age, skills; job experience: on-the-job time, job title; attendance records: number of late attendances per month; performance rating: average monthly performance). These multi-category codes can be merged into a searchable code under the name of the target company's employees, and the merged result can be used as the talent tag code of the target company's employees.

[0026] It should be noted that by collecting multidimensional characteristic data of employees and generating unified talent tag codes, the complex information of employees can be structured and quantified, achieving objective comparability between different employees. This not only avoids the subjective bias of manual evaluation but also provides a unified characteristic benchmark for subsequent job matching, contribution assessment, and risk warning.

[0027] In step S2, the current job demand vector of the target company's employees is obtained. Based on the current job demand vector and the talent tag code, the job compatibility of the target company's employees is evaluated to obtain the job compatibility degree of the target company's employees. Based on the job compatibility degree and the urgency threshold, the job transfer urgency coefficient of the target company's employees is determined.

[0028] In practice, the current job requirement vector of the target company's employees can be obtained. That is, the various requirement elements of the current position can be extracted from the job description, such as skills, experience, and constraints (age, gender). The various requirement elements of the current position are used as vector elements to form a vector, and this vector is used as the current job requirement vector of the target company's employees.

[0029] Preferably, in this embodiment, reference Figure 2 As shown, this diagram is an exemplary flowchart for obtaining the job compatibility of employees of the target company in this embodiment of the application. In this embodiment, the job compatibility of employees of the target company is evaluated based on the current job demand vector and the talent tag code. The specific steps to obtain the job compatibility of employees of the target company can be as follows: In step S21, the talent tag encoding is aligned in the feature space based on the current job demand vector to obtain the talent tag vector; In step S22, the compatibility similarity is evaluated by the talent tag vector and the current job requirement vector to obtain the job compatibility of the target company's employees.

[0030] In specific implementation, firstly, the talent tag code can be aligned in feature space based on the current job requirement vector to obtain the talent tag vector. That is, the talent tag code can be aligned in feature space according to each dimension of the current job requirement vector, which includes skills, experience, and constraints (age, gender). The skills, on-the-job time, age, and gender of the target company's employees can be extracted from the talent tag code, and then the extracted skills, on-the-job time, age, and gender of the target company's employees can be combined into the talent tag vector. Then, the compatibility similarity between the talent tag vector and the current job requirement vector can be evaluated to obtain the job compatibility of the target company's employees. That is, the talent tag vector and the current job requirement vector can be numerically encoded to obtain the talent numerical encoding vector and the job requirement numerical encoding vector, such as: (skill encoding is skill level; experience encoding is on-the-job time; constraint encoding is age and gender, gender encoding is 0 for male and 1 for female), thus obtaining two four-dimensional vectors. Then, the talent numerical encoding vector and the job requirement numerical encoding vector are respectively processed by L2 norm normalization, so the job compatibility of the target company's employees can be obtained by the following formula:

[0031] in, Indicates job compatibility; This represents a numerical encoding vector for talent. This represents a numerical encoding vector representing job requirements. Indicates the number of dimensions of a vector; This indicates taking the maximum value of two numbers; This represents the i-th element in the numerical encoding vector of job requirements; This represents the i-th element in the talent numerical encoding vector; Let L2 norm represent the vector. It should be noted that job compatibility is a quantitative indicator of the degree of matching between employee competence characteristics and job requirements.

[0032] In this embodiment, determining the urgency coefficient of a target company's employee's job transfer based on the job compatibility and urgency threshold can be achieved through the following steps: Initialize the urgent threshold; The job compatibility is filtered based on the urgency threshold to obtain the job transfer urgency coefficient of the target company's employees.

[0033] In specific implementation, an urgency threshold can be initialized, that is, an urgency threshold can be preset based on experimental data statistics; then, the job compatibility can be filtered based on the urgency threshold to obtain the job transfer urgency coefficient of the target company's employees. That is, the job compatibility can be subtracted from the urgency threshold, and the result can be divided by the urgency threshold. The result is used as the job transfer urgency coefficient of the target company's employees. When the result is negative, the job transfer urgency coefficient is set to 0.

[0034] It's important to note that by obtaining the job requirement vectors of employees in target companies and assessing their compatibility with employee talent tag codes, the suitability of employees for their current positions can be accurately quantified. Furthermore, by combining this with an urgency threshold to calculate a job reassignment urgency coefficient, the risk of job mismatch can be dynamically identified, and potential skill gaps can be promptly discovered. This not only avoids the bias and lag inherent in traditional methods relying on human experience, but also provides companies with a scientific and quantifiable basis for job reassignment, thereby improving the rationality of job allocation and the efficiency of person-job matching.

[0035] In step S3, historical on-the-job data of the target company's employees is obtained. The on-the-job contribution of the target company's employees is evaluated based on the historical on-the-job data to obtain the job contribution degree of the target company's employees to their current positions. Based on the job contribution degree and the job transfer urgency coefficient of the target company's employees, a talent loss warning is issued to obtain the turnover risk index of the target company's employees.

[0036] In practice, to obtain the historical on-the-job data of the target company's employees, one can extract the job experience, attendance records, and performance ratings from the talent tag codes of the target company's employees, and use the job experience, attendance records, and performance ratings as the historical on-the-job data of the target company's employees.

[0037] Preferably, in this embodiment, reference Figure 3 As shown, this diagram is an exemplary flowchart for obtaining the job contribution of a target company's employee to their current position in this embodiment of the application. In this embodiment, the on-the-job contribution of the target company's employee is evaluated based on the historical on-the-job data to obtain the job contribution of the target company's employee to their current position. This can be achieved through the following steps: In step S31, feature construction is performed on the historical on-the-job data to obtain job-related word vectors; In step S32, the contribution weights in the job term vectors are initialized; In step S33, the contribution of the target company's employees to their current positions is determined based on each contribution weight and the job term vector.

[0038] In specific implementation, firstly, feature construction can be performed on the historical on-the-job data to obtain job-related word vectors. That is, the historical on-the-job data can be transformed into job-related word vectors in the same semantic space. This involves reconstructing the features of the job resume, attendance records, and performance ratings in the historical on-the-job data to obtain on-the-job time, monthly late attendance count, and average monthly performance. These on-the-job time, monthly late attendance count, and average monthly performance are then used as vector elements and merged into a three-dimensional vector, which is then used as the job-related word vector. Next, the contribution weights of each element in the job-related word vector can be initialized. That is, personalized weights can be set for different types of jobs using historical data, such as: (Sales position: monthly...) The weights for average performance (0.7), monthly late attendance (0.2), and on-duty time (0.1) are calculated. For internships, the weights for average monthly performance (0.4), monthly late attendance (0.3), and on-duty time (0.3) are calculated. Finally, the employee's contribution to the current position can be determined based on the weights of each contribution and the job term vector. Specifically, the on-duty time, monthly late attendance, and average monthly performance from the job term vector are multiplied by each contribution weight and then summed. The sum is then used as the employee's contribution to the current position. It should be noted that the contribution refers to the degree to which the employee demonstrates their ability in the current position.

[0039] In this embodiment, the talent loss early warning based on the job contribution level and the urgency coefficient of the target company's employees for job transfer can be achieved through the following steps: The job sensitivity coefficient of the target company's employees is determined by the job contribution level. The employee turnover risk index of the target company is determined based on the job sensitivity coefficient and the job transfer urgency coefficient.

[0040] In practice, the job sensitivity coefficient of the target company's employees can be determined through the job contribution level. That is, the job sensitivity coefficient can be obtained by the following formula:

[0041] in, Indicates the job sensitivity coefficient; The job contribution level is represented by the job sensitivity coefficient and the job transfer urgency coefficient. Then, the turnover risk index of the target company's employees can be determined based on the job sensitivity coefficient and the job transfer urgency coefficient. That is, the job sensitivity coefficient can be subtracted from 1, and the result can be multiplied by the job transfer urgency coefficient. The result can be used as the turnover risk index of the target company's employees. It should be noted that the job sensitivity coefficient refers to the employee's sensitivity to the current job.

[0042] It's important to note that by acquiring and analyzing historical on-the-job data of employees in target companies, a comprehensive reflection of their actual output and long-term performance in their positions can be achieved. Based on this, combining job contribution and the urgency of job reassignment can provide early warnings of talent loss, quantifying the employee's turnover risk index and thus identifying potential turnover risks in advance. This not only overcomes the lag and uncertainty of traditional methods relying on managers' subjective judgment but also enables real-time, dynamic monitoring of talent status, providing companies with scientific, data-driven risk warnings, effectively reducing the probability of core talent loss, and enhancing the foresight and accuracy of human resource management.

[0043] In step S4, the talent management strategy for the target company's employees is determined based on the turnover risk index.

[0044] In this embodiment, determining the talent management strategy for the target company's employees based on the turnover risk index specifically includes: Initialize the target company's various talent management measures for its employees; By screening various talent management measures using the turnover risk index, a talent management strategy for the target company's employees can be obtained.

[0045] In practice, the various talent management measures for the target company's employees can be initialized. That is, the various talent management measures for the target company's employees can be extracted from the AI ​​backend system, such as: (career development (training, promotion, job transfer), welfare (long-term contracts, health support, family benefits)). Then, the various talent management measures can be screened using the turnover risk index to obtain the talent management strategy for the target company's employees. That is, based on the turnover risk index of the target company's employees, the talent management measures corresponding to the turnover risk index can be screened from the various talent management measures, and the obtained talent management measures can be used as the talent management strategy for the target company's employees. For example, when the turnover risk index is below 0.7 and above 0.5, welfare is selected; when the turnover risk index is above 0.7, career development and welfare are selected.

[0046] It should be noted that by implementing human resource management for employees of target companies based on the turnover risk index, it is possible to achieve graded identification and personalized intervention for high-risk employees, automatically match protective measures, and form a closed-loop management mechanism from risk discovery to protection implementation.

[0047] Therefore, this application demonstrates several key advantages. First, by collecting multidimensional characteristic data of employees and generating unified talent tag codes, it is possible to structure and quantify the complex information of employees, achieving objective comparability between different employees. This not only avoids the subjective bias of manual assessment but also provides a unified characteristic benchmark for subsequent job matching, contribution evaluation, and risk warning. Second, by obtaining the job requirement vector of the target company's employees and conducting compatibility assessment with the employees' talent tag codes, the suitability of employees for their current positions can be accurately quantified. Furthermore, by combining this with an urgency threshold to calculate a job reassignment urgency coefficient, the risk of job mismatch can be dynamically identified, and potential skill gaps can be discovered in a timely manner. This not only avoids the one-sidedness and lag of traditional reliance on human experience but also provides companies with scientific and quantifiable basis for job reassignment, thereby improving the rationality of job allocation and the efficiency of person-job matching. Third, by acquiring and analyzing the historical on-the-job data of the target company's employees, it is possible to comprehensively reflect the actual output and long-term performance of employees in their positions. Based on this, by combining job contribution and job reassignment urgency coefficients for talent loss warning, the employee's turnover risk index can be quantitatively calculated, thereby identifying potential turnover risks in advance. It not only overcomes the lag and uncertainty of traditional reliance on managers' subjective judgment, but also enables real-time and dynamic monitoring of talent status, providing enterprises with scientific and data-driven risk warning basis, effectively reducing the probability of core talent loss, and improving the foresight and accuracy of human resource management; finally, by implementing human resource management for target enterprise employees based on the turnover risk index, it can achieve graded identification and personalized intervention for high-risk employees, automatically match protective measures, and form a closed-loop management mechanism from risk discovery to protection implementation.

[0048] In summary, the technical solution adopted in this application can improve the accuracy of early warning of potential talent loss, reduce the probability of key personnel leaving, and enhance the scientific and refined level of enterprise human resource management.

[0049] Example 2: This application provides a reference for an artificial intelligence-based human resource management system. Figure 4 As shown in the figure, this is a module structure diagram of an artificial intelligence-based human resource management system according to this embodiment of the present application. The artificial intelligence-based human resource management system includes: The tag encoding module 100 is used to collect multi-dimensional feature data of employees of the target enterprise and determine the talent tag code of the employees of the target enterprise based on the multi-dimensional feature data. The job reassignment urgency module 200 is used to obtain the current job demand vector of the target company's employees, perform job compatibility assessment on the target company's employees based on the current job demand vector and the talent tag code, obtain the job compatibility degree of the target company's employees, and determine the job reassignment urgency coefficient of the target company's employees based on the job compatibility degree and the urgency threshold. The turnover risk module 300 is used to obtain the historical on-the-job data of the target company's employees, evaluate the on-the-job contribution of the target company's employees based on the historical on-the-job data, obtain the job contribution degree of the target company's employees to the current position, and conduct talent loss warning based on the job contribution degree and the job transfer urgency coefficient of the target company's employees, thereby obtaining the turnover risk index of the target company's employees. The talent protection module 400 is used to determine the talent management strategy for the target company's employees based on the turnover risk index.

[0050] The foregoing has detailed examples of an artificial intelligence-based human resource management system and method provided in the embodiments of this application. It is understood that the corresponding apparatus, in order to achieve the above functions, includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0051] In embodiment three, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing computer programs, and the processor for calling and running the computer programs from the memory, so that the computer device executes the above-described artificial intelligence-based human resource management method.

[0052] In this embodiment, reference Figure 5 The dashed lines in the figure indicate that the unit or module is optional. This figure is a structural schematic diagram of a computer device for an artificial intelligence-based human resource management system according to an embodiment of this application. The aforementioned artificial intelligence-based human resource management method in the above embodiment can... Figure 5 The computer device shown is used to implement this, and the computer device includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device may be a terminal device, a server or a chip.

[0053] Processor 501 can be a general-purpose processor or a special-purpose processor. For example, processor 501 can be a central processing unit (CPU), which can be used to control computer devices, execute software programs, and process data from software programs. The computer device may also include a communication unit 505 to realize signal input (reception) and output (transmission).

[0054] For example, the computer device may be a chip, and the communication unit 505 may be the input and / or output circuit of the chip, or the communication unit 505 may be the communication interface of the chip, which may be a component of a terminal device, network device or other device.

[0055] For example, the computer device may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0056] The computer device may include one or more memories 502 storing a program 504. The program 504 can be executed by a processor 501 to generate instructions 503, causing the processor 501 to perform the methods described in the above method embodiments according to the instructions 503. Optionally, the memory 502 may also store data (such as a target audit model). Optionally, the processor 501 may also read data stored in the memory 502, which may be stored at the same storage address as the program 504, or the data may be stored at a different storage address than the program 504.

[0057] The processor 501 and memory 502 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0058] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in processor 501. Processor 501 can be a central processing unit, digital signal processor (DSP), application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other programmable logic device, such as discrete gate, transistor logic device, or discrete hardware component.

[0059] 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.

[0060] In embodiment four, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned artificial intelligence-based human resource management method.

[0061] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0062] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A human resource management method based on artificial intelligence, characterized in that, The management method includes: Collect multidimensional feature data of employees of the target company, and determine the talent tag code of the employees of the target company based on the multidimensional feature data; Obtain the current job demand vector of the target company's employees, conduct job compatibility assessment of the target company's employees based on the current job demand vector and the talent tag code, obtain the job compatibility degree of the target company's employees, and determine the job transfer urgency coefficient of the target company's employees based on the job compatibility degree and the urgency threshold. Obtain historical on-the-job data of employees of the target company, evaluate the on-the-job contribution of the employees of the target company based on the historical on-the-job data, obtain the job contribution degree of the employees of the target company to their current positions, and conduct talent loss warning based on the job contribution degree and the job transfer urgency coefficient of the employees of the target company, thereby obtaining the turnover risk index of the employees of the target company. The talent management strategy for the target company's employees is determined based on the turnover risk index.

2. The artificial intelligence-based human resource management method as described in claim 1, characterized in that, Collecting multidimensional feature data of employees of target companies involves extracting multidimensional feature data of employees of target companies from an artificial intelligence back-end system.

3. The artificial intelligence-based human resource management method as described in claim 1, characterized in that, Based on the current job demand vector and the talent tag code, a job compatibility assessment is conducted on the target company's employees to obtain the job compatibility degree of the target company's employees, specifically including: Based on the current job demand vector, the talent tag encoding is aligned in the feature space to obtain the talent tag vector; The job compatibility of the target company's employees is obtained by evaluating the compatibility similarity between the talent tag vector and the current job requirement vector.

4. The artificial intelligence-based human resource management method as described in claim 1, characterized in that, Determining the job reassignment urgency coefficient of employees in the target company based on the aforementioned job compatibility and urgency threshold specifically includes: Initialize the urgent threshold; The job compatibility is filtered based on the urgency threshold to obtain the job transfer urgency coefficient of the target company's employees.

5. The artificial intelligence-based human resource management method as described in claim 1, characterized in that, By evaluating the on-the-job contributions of employees in the target company using the historical on-the-job data, the specific contribution level of each employee to their current position is obtained, including: Feature construction is performed on the historical on-the-job data to obtain job-related word vectors; Initialize the contribution weights of each job term vector; The contribution of each employee in the target company to their current position is determined based on the contribution weights of each contribution and the word vectors of the job positions.

6. The artificial intelligence-based human resource management method as described in claim 1, characterized in that, Based on the aforementioned job contribution and the urgency coefficient of the target company's employees for job reassignment, a talent loss early warning is generated, resulting in the target company's employee turnover risk index, which specifically includes: The job sensitivity coefficient of the target company's employees is determined by the job contribution level. The employee turnover risk index of the target company is determined based on the job sensitivity coefficient and the job transfer urgency coefficient.

7. The artificial intelligence-based human resource management method as described in claim 1, characterized in that, The talent management strategies for target companies, determined based on the turnover risk index, specifically include: Initialize the target company's various talent management measures for its employees; By screening various talent management measures using the turnover risk index, a talent management strategy for the target company's employees can be obtained.

8. An artificial intelligence-based human resource management system, used to execute an artificial intelligence-based human resource management method as described in any one of claims 1 to 7, characterized in that, The human resource management system includes: The tag encoding module is used to collect multidimensional feature data of employees of the target company and determine the talent tag code of the employees of the target company based on the multidimensional feature data. The job reassignment urgency module is used to obtain the current job demand vector of the target company's employees, perform job compatibility assessment on the target company's employees based on the current job demand vector and the talent tag code, obtain the job compatibility degree of the target company's employees, and determine the job reassignment urgency coefficient of the target company's employees based on the job compatibility degree and the urgency threshold. The turnover risk module is used to obtain the historical on-the-job data of the target company's employees, evaluate the on-the-job contribution of the target company's employees based on the historical on-the-job data, obtain the job contribution degree of the target company's employees to the current position, and conduct talent loss warning based on the job contribution degree and the job transfer urgency coefficient of the target company's employees, thereby obtaining the turnover risk index of the target company's employees. The talent protection module is used to determine the talent management strategy for the target company's employees based on the turnover risk index.

9. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to call and run the computer programs from the memory, so that the computer device performs an artificial intelligence-based human resource management method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement an artificial intelligence-based human resource management method as described in any one of claims 1 to 7.

Images