Label and portrait construction method and system based on digital human resource management

Abstract

The invention belongs to the field of label and portrait construction of digital human resource management, and particularly relates to a label and portrait construction method based on digital human resource management. Basic data are collected, data labels are defined, and a complete label library is constructed; associating the collected basic data information with definitions in a label library, and performing label assignment; constructing employee portraits and post portraits based on the label data; performing intelligent matching by applying artificial intelligence and data analysis methods through employee and post portrait analysis; a data query function is provided, and a user is helped to obtain information from mass data. By constructing the portraits of the employees and the posts, the enterprise can more accurately match the requirements of the applicants and the posts. Multi-dimensional information such as personal characteristics, capabilities and potentials of employees is comprehensively considered in the employee portraits, and the post portraits reflect skills, responsibilities, experience requirements and the like required by posts.

Description

Technical Field

[0001] The present invention belongs to the field of partial discharge detection of power equipment, and specifically relates to a label and portrait construction method based on digital human resource management. Background Art

[0002] In modern enterprise management, how to conduct talent recruitment, job allocation, employee development and performance evaluation scientifically and effectively has become a key component of the core competitiveness of enterprises. As the complexity of human resource management continues to increase, traditional manual experience judgment and management methods can no longer meet the needs of enterprises for efficient talent management. Therefore, more and more companies are beginning to use advanced technologies such as big data, artificial intelligence and machine learning to improve the scientificity and accuracy of human resource management. Building employee portraits and job portraits, and managing talents through accurate data analysis, has gradually become a trend.

[0003] Employee portrait refers to the establishment of a model that comprehensively reflects the ability and potential of employees by collecting and analyzing multi-dimensional data such as employees' basic information, skill characteristics, experience background, work performance, and potential. Job portraits form a detailed description of a job by analyzing factors such as job responsibilities, work content, required skills, work environment, and job requirements. The combination of the two can help companies make more accurate decisions in recruitment, training, performance evaluation, and other aspects.

[0004] In the traditional human resource management model, companies usually rely on simplified personnel assessment and job requirements comparison, recruitment interviews and experience judgment to determine employees' job arrangements, promotions and development paths. This approach often has the following problems:

[0005] Inaccurate talent matching: Traditional recruitment and job matching rely more on the interviewer’s intuitive judgment and experience, lacking quantitative data support, which can easily lead to poor compatibility between employees and positions, thus affecting work performance and employee satisfaction.

[0006] Performance evaluation is highly subjective: Since performance evaluation relies too much on the subjective judgment of managers, it may be biased and unfair, especially the evaluation of employees' comprehensive abilities and development potential is relatively vague, resulting in unequal development opportunities for employees.

[0007] Unclear employee career development paths: Due to the lack of accurate employee and job profiles, it is difficult for companies to effectively plan employees' career development paths, resulting in employee growth and promotion often relying on management's personal opinions rather than systematic data support.

[0008] High turnover rate and low employee satisfaction: Due to the mismatch between positions and employees' actual abilities and interests, employees' work performance is often poor, which leads to high turnover rate and low satisfaction, affecting the long-term development of the company.

[0009] In recent years, with the rapid development of big data and artificial intelligence technology, more and more companies have begun to adopt a data-driven approach to human resource management. By collecting various employee data (such as work experience, training records, skill tests, performance evaluations, etc.), combining job analysis, and building employee and job profiles, the efficiency and accuracy of talent management can be greatly improved. Using data analysis and machine learning models, companies can more accurately determine the match between employees and positions, discover employee potential, and develop personalized career development plans.

[0010] Although existing technologies have made some progress in employee-job matching, recruitment, and performance evaluation, there are still some limitations in actual application:

[0011] Data integration issues: Existing employee portraits and job portraits often come from different systems and platforms (such as recruitment systems, assessment systems, HR management systems, etc.), resulting in inconsistent and incomplete data, affecting the accuracy and consistency of analysis.

[0012] Single modeling method: Most current systems rely only on basic statistical analysis and rule engines, lacking more in-depth machine learning or deep learning models to achieve more accurate predictions and analysis. Although some companies have tried to use artificial intelligence technology, its application depth is still limited, making it difficult to achieve a comprehensive and multi-dimensional employee portrait construction.

[0013] Difficulty of actual operation: Building accurate employee and job portraits requires a large amount of historical data as support, and the ability to cope with different business scenarios varies greatly. How to customize development according to different organizational needs has become a challenge faced by enterprises during the implementation process.

[0014] With the continuous development of artificial intelligence and machine learning technologies, more and more companies are aware of the necessity of building employee and job profiles through data-driven methods. Especially in a market environment with talent shortage and frequent employee turnover, how to efficiently and accurately match employees with positions, improve employee career development, and optimize organizational structure has become a core issue for companies to enhance their competitiveness. Summary of the invention

[0015] In view of the above problems existing in the prior art, the present invention is proposed.

[0016] In order to solve the above technical problems, the present invention provides the following technical solutions: a label and portrait construction method based on digital human resource management, comprising: collecting basic data, defining data labels, and constructing a complete label library;

[0017] Associate the collected basic data information with the definition in the tag library and assign tags;

[0018] Build employee and job profiles based on label data;

[0019] Through employee and job profile analysis, apply artificial intelligence and data analysis methods for intelligent matching;

[0020] Provides data query function to help users obtain information from massive data.

[0021] As a preferred solution of the label and portrait construction method based on digital human resource management described in the present invention, wherein: the basic data includes collecting employee data and collecting position data;

[0022] The employee data includes basic personal information, work performance, training and development information;

[0023] The job data includes basic job requirements, job performance requirements, and changes in job responsibilities.

[0024] As a preferred solution of the method for constructing labels and portraits based on digital human resource management described in the present invention, the collecting of partial discharge signals includes collecting partial discharge signals using a UHF antenna.

[0025] As a preferred solution of the label and portrait construction method based on digital human resource management described in the present invention, wherein: the defined data label includes employee label definition, position label definition, and label assignment rules;

[0026] The label assignment rules include setting evaluation criteria for each label and clarifying how to assign labels to employees or positions based on different data.

[0027] As a preferred solution of the label and portrait construction method based on digital human resource management described in the present invention, the employee portrait construction includes: calculating the score of the label in each dimension through a weighted formula, weighted summing up multiple label scores of the same dimension to form a total score of the dimension, and calculating the overall portrait score according to the weights of different dimensions;

[0028] When an employee or job label changes, the system automatically recalculates the score of the corresponding dimension. Managers view the portrait through visualization tools and manually adjust the label weight. In the person-job matching scenario, employee portraits are compared with job portraits in real time for matching.

[0029] As a preferred solution of the label and portrait construction method based on digital human resource management described in the present invention, the job portrait construction is based on data, quantified through logical rules and mathematical models, and generates a comprehensive job feature description.

[0030] As a preferred solution of the label and portrait construction method based on digital human resource management described in the present invention, wherein: the intelligent matching includes calculating the matching degree between the employee portrait and the position portrait, taking the dimension score of the employee portrait and the requirement score of the position portrait as input, and using cosine similarity to calculate the matching degree. If the matching degree is higher than a threshold, the position is judged as a high-matching position;

[0031] Comprehensively consider the weight of each dimension, generate the total score of the match between employees and positions, determine the weight of each dimension, calculate the gap between employees and positions in each dimension, calculate the weighted total score, and obtain the final matching result.

[0032] As a preferred solution of the label and portrait construction system based on digital human resource management described in the present invention, it includes: a data collection module, a label management module, a portrait construction module, an intelligent matching module, and a data query module.

[0033] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of any one of the methods for constructing labels and portraits based on digital human resource management.

[0034] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of any one of the methods for constructing labels and portraits based on digital human resource management are implemented.

[0035] Beneficial effects of the present invention: By constructing employee and position portraits, companies can more accurately match applicants with job requirements. Employee portraits comprehensively consider multi-dimensional information such as employees' personal characteristics, abilities, and potential, while position portraits reflect the skills, responsibilities, and experience requirements required for the position. Using similarity calculation models (such as cosine similarity), companies can efficiently evaluate the match between candidates and positions, thereby avoiding high turnover or low performance caused by improper matching during the recruitment process.

[0036] By calculating the similarity between the employee and the job profile (for example, through the cosine similarity model), the system can give a specific matching score to help the HR department make decisions quickly. For example, a high matching degree between an employee and a job means that the employee has a higher potential to achieve better performance in the job.

[0037] Whether employees can successfully adapt to their positions and make full use of their expertise at work depends on the fit between their skills and job requirements. By building accurate employee portraits, companies can assess whether employees have the potential to be competent for a certain position and design career development paths for employees in advance.

[0038] The weighted matching score between employee profile and job profile can help HR departments analyze the fit between employee potential and job requirements. For employees with higher potential, companies can design personalized training and promotion paths to help them better adapt to job changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 A flowchart of a label and portrait construction method based on digital human resource management is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0042] Example 1

[0043] Reference Figure 1 , which is the first embodiment of the present invention, and provides a label and portrait construction method based on digital human resource management, such as Figure 1 As shown, including:

[0044] S1: Collect basic data, define data labels, and build a complete label library;

[0045] The basic data includes collecting employee data and collecting job position data;

[0046] The employee data includes basic personal information, work performance, training and development information;

[0047] The job data includes basic job requirements, job performance requirements, and changes in job responsibilities.

[0048] The defined data tags include employee tag definition, position tag definition, and tag assignment rules;

[0049] The label assignment rules include setting evaluation criteria for each label and clarifying how to assign labels to employees or positions based on different data.

[0050] The system needs to collect basic data of employees and positions comprehensively to lay the foundation for subsequent data analysis and label assignment. The collection of employee data includes basic personal information, work performance, and training and development information. Basic personal information refers to the name, gender, age, education, department, and rank of employees, which are obtained through the human resource management system (HRIS) and formatted uniformly. For example, the education level is uniformly coded as "1 = undergraduate, 2 = master, 3 = doctorate". Work performance data includes employee performance appraisal results, KPI achievement rate, reward and punishment records, etc., which are extracted through the performance management system (PMS) and core performance indicators such as sales achievement rate are extracted using data mining technology. In order to ensure the universality of performance data, data from different sources need to be normalized and converted into a score range of 0 to 100. Training and development information comes from the learning management system (LMS), including training courses attended by employees, academic performance, completion rate, and certificates obtained. By counting the training participation rate and completion rate of employees, the training effect and its role in promoting employee development can be further analyzed.

[0051] The collection of job data involves basic job requirements, performance requirements, and changes in responsibilities. Basic job requirements include education, skills, work experience, etc., which are usually extracted from job descriptions or demand documents provided by the employing department. Using natural language processing technology, key information in job descriptions can be automatically parsed, and skill requirements (such as "proficient in Python") and experience requirements (such as "at least 5 years of industry experience") can be structured and stored. Job performance requirements mainly include key performance indicators (KPIs) and goal achievement standards for jobs. These data are obtained through historical performance statistics and departmental goal setting tables, and are aggregated and calculated to form the performance benchmark value of the job. Job responsibilities changes record the adjustments to job tasks and content. By comparing historical versions and using natural language processing technology, the core content of changes in responsibilities is automatically extracted to provide support for dynamic label assignment.

[0052] After data collection is completed, the system needs to define labels for employees and positions in order to describe employee characteristics and job requirements in a structured manner. Employee labels include basic labels, performance labels, and behavioral trait labels. Basic labels can be defined as "age group: 20-30 years old" or "education: bachelor degree and above"; performance labels can be defined as "high-performance employees" or "continuous improvement"; behavioral trait labels can be defined as "high stress resistance" or "high learning initiative". Position labels are divided into responsibility labels, skill labels, and characteristic labels. Responsibility labels can be defined as "team management positions" or "core technical positions"; skill labels can be defined as "advanced programming skills" or "cross-departmental collaboration capabilities"; characteristic labels can be defined as "high-intensity positions" or "high collaboration needs". Each label must have a clear structure, including label name, category, and description to ensure the clarity of the label meaning.

[0053] The label assignment rule is the core part of the system, which determines the accuracy and applicability of the label. The assignment rules include single-condition rules, multi-condition combination rules, and interval matching rules. Single-condition rules refer to directly assigning labels based on a single data field. For example, "age between 25 and 30" can be directly assigned the "young employee" label, or "skill score greater than 90" can be assigned the "senior technical ability" label. Multi-condition combination rules require the integration of multiple field information and logical judgment. "Age between 25 and 35 and skill score greater than 80" can be assigned the "technical backbone" label. For label assignment of continuous data, the interval matching rule is used, and "working experience between 5 and 10 years" is assigned the "intermediate position" label.

[0054] During the assignment process, the rule engine will determine whether the conditions are met for each data field one by one. If they are met, the corresponding label will be assigned a value. The label assignment is scored and weighted by a mathematical model to quantify the degree of label adaptation. Use the weighted scoring formula:

[0055]

[0056] Among them, W i is the conditional weight, F i is the result of the condition match (0 or 1). The formula is used to combine the results of multiple conditions to generate an accurate label score.

[0057] Build a dynamically updated tag library to store all defined tags in a tree structure, including basic information tags, performance tags, responsibility tags, and skill tags. The tag library supports dynamic updates. When employee data or job requirements change, the system can recalculate and update related tags in real time. The system must have version management functions, save historical versions of tag rules, and support backtracking and analysis.

[0058] The system can comprehensively collect and structuredly store employee and job data, accurately assign labels through clear rules and mathematical models, and maintain the timeliness of the label library through dynamic updates, providing a solid foundation for subsequent employee and job profile construction and intelligent analysis.

[0059] S2: Associate the collected basic data information with the definition in the tag library and assign tags;

[0060] The associating the collected basic data information with the definitions in the tag library includes associating and assigning values ​​from the basic data to the tags by defining association rules and introducing a calculation model.

[0061] Starting with the input of basic data, the system needs to collect multi-dimensional information about employees and positions to provide the necessary basis for subsequent label association. These data include employees' basic personal information, skill scores, performance data, training records, etc., as well as job descriptions, skill requirements, performance goals, and experience requirements of the positions. The system will clean and format these data to ensure data consistency and operability. For example, employees' skill scores may come from different systems. In order to unify the standards, the scores need to be normalized and converted to the same dimension (such as a range of 0 to 100) so that subsequent label matching is comparable. Position data such as job descriptions and skill requirements are automatically extracted from job descriptions through natural language processing technology and stored in a structured manner.

[0062] The system establishes the association between data and tags based on the defined tag library. The tag library contains various tags for employees and positions, such as "high potential employees", "strong technical ability", "senior management position", etc. Each tag consists of clear definitions and rules. The rules describe the applicable conditions of the tag. For example, employees with "skill score ≥ 85" can be assigned the value of "strong technical ability". The system loads the rules defined in the tag library and maps them with the basic data fields. Association rules include single condition rules, multi-condition combination rules, and interval matching rules.

[0063] Single-condition rules are the simplest type of rules, which match directly based on a single data field. For example, "skill score ≥ 85" can be assigned the label "strong technical ability", or "age between 25 and 30" can be assigned the label "young employee". Multi-condition combination rules are more complex, and multiple field conditions must be met at the same time to complete the label assignment. For example, "age between 25 and 35 and skill score ≥ 80" can be assigned the label "technical backbone", or "work experience ≥ 5 years and management score ≥ 70" can be assigned the label "senior management position". Interval matching rules are used to process continuous data fields, and matches are performed by judging whether the data value is within a certain interval, such as "work experience between 5 and 10 years" is assigned the label "intermediate position".

[0064] When dealing with complex association logic, the system will introduce mathematical models to quantitatively analyze label assignments. Label scores are generated by assigning weights to each condition and calculating the matching results of the conditions. For the "High Potential Employee" label, the weight of the performance score can be set to 0.5, the weight of the skill score to 0.3, and the weight of the behavior score to 0.2. Then, the scores of these conditions are calculated comprehensively. The formula is:

[0065] Tag score = (performance score × 0.5) + (skill score × 0.3) + (behavior score × 0.2)

[0066] If the calculated result reaches a certain threshold (such as 80 points), the system can assign a "high potential employee" label to the employee.

[0067] The similarity calculation model is used to evaluate the similarity between employees or positions and label definitions. The model represents data features and label definitions as vectors and uses cosine similarity to calculate the similarity between the two. For example, an employee's skill score, performance score, and years of experience can be represented as a vector [85,90,6], and the feature vector of the label "technical backbone" is [80,85,5]. The formula:

[0068]

[0069] The matching degree between the employee and the label can be obtained. If the similarity is higher than a certain threshold (such as 0.9), the system will assign the label to the employee.

[0070] The decision tree uses a branch structure to represent the associated conditions of labels. For example, "management experience ≥ 5 years" is the root node, "management score ≥ 70" is the branch node, and when it finally reaches the leaf node, the "senior management position" label can be assigned. The decision tree model can clearly express the logical relationship between conditions and support automated judgment and assignment.

[0071] The results of association and calculation are stored as label information, and these labels are attached to the corresponding employee or position profile. If the basic data changes, such as an employee completing a new skill training or a job responsibilities adjustment, the system will dynamically re-run the rules and models and update the label assignment results in real time. This dynamism ensures the timeliness and accuracy of label information.

[0072] Through integration, the system realizes the complete process from basic data to label assignment. Single-condition and multi-condition rules provide basic logical judgment capabilities, and mathematical models provide quantitative analysis support for complex associations. The label information generated by the system lays a solid foundation for subsequent employee profiling, job profiling, and intelligent matching and analysis.

[0073] S3: Build employee and job profiles based on label data;

[0074] The employee portrait construction includes calculating the score of the label in each dimension through a weighted formula, weighting and summing the scores of multiple labels in the same dimension to form a total score of the dimension, and calculating the overall portrait score according to the weights of different dimensions;

[0075] When an employee or job label changes, the system automatically recalculates the score of the corresponding dimension. Managers view the portrait through visualization tools and manually adjust the label weight. In the person-job matching scenario, employee portraits are compared with job portraits in real time for matching.

[0076] The job profile is constructed based on data, quantified through logical rules and mathematical models, and generates a comprehensive description of job characteristics.

[0077] The last step in building an employee portrait is to integrate multi-dimensional data to form a standardized feature vector. After the data of each dimension is weighted, it is uniformly converted into a specific score. For example, the weight of technical ability is 50%, the weight of performance score is 30%, and the weight of behavioral characteristics is 20%. The total score of the employee is calculated comprehensively, and the formula is:

[0078]

[0079] Among them, W i Expressed as dimension weight, S i Represented as employee dimension scores; the integrated data can be intuitively presented through radar charts, tag clouds and timeline views, showing the distribution of employees' scores in different dimensions and the trend of their ability changes.

[0080] The data of the job profile also needs to be integrated to form a structured feature vector. The requirements of each dimension are standardized and weighted to form a score. For example, the weight of skill requirements is 50%, the weight of experience requirements is 30%, and the weight of feature requirements is 20%. The total score of the job requirements is calculated comprehensively:

[0081]

[0082] Among them, W i Expressed as dimension weight, S i The final job profile can be presented through radar charts, tag clouds and hierarchical views, showing the weight distribution and importance of the job in terms of skills, experience and feature requirements.

[0083] The construction of employee portraits and job portraits is closely related. The two must be consistent in terms of label library definition, data dimension division and scoring model, so as to achieve efficient comparison of feature vectors in the subsequent matching process. Through this standardized portrait construction method, enterprises can clearly understand the gap between employee capabilities and job requirements, and provide scientific data support for intelligent matching, career development planning and job deployment.

[0084] S4: Through employee and job profile analysis, apply artificial intelligence and data analysis methods for intelligent matching;

[0085] The intelligent matching includes calculating the matching degree between the employee portrait and the job portrait, taking the dimension score of the employee portrait and the requirement score of the job portrait as input, and using cosine similarity to calculate the matching degree. If the matching degree is higher than a threshold, the job is judged as a high matching job;

[0086] Comprehensively consider the weight of each dimension, generate the total score of the match between employees and positions, determine the weight of each dimension, calculate the gap between employees and positions in each dimension, calculate the weighted total score, and obtain the final matching result.

[0087] Intelligent matching is based on the constructed employee and job profiles, taking the dimensional scores of both as input, using artificial intelligence and data analysis methods to calculate the fit between employees and positions, and then screening out highly matched positions or employees. This process not only relies on label assignment rules, but also combines global analysis of the portrait dimensions to optimize matching results through mathematical models.

[0088] The dimension scores in the employee portrait (such as skill scores, performance scores, and experience scores) and the requirement scores in the job portrait (such as skill requirements, performance goals, and experience requirements) constitute feature vectors. The core of intelligent matching is to calculate the matching degree of these two sets of vectors, combine gap analysis and weight optimization, and generate a total matching score.

[0089] Intelligent matching uses two core methods: cosine similarity to calculate the matching degree and weighted scoring model to calculate the total score. Cosine similarity is used to judge the overall fit and ensure the consistency of employee characteristics and job requirements in direction; the weighted scoring model is used to refine the gaps in each dimension and highlight the importance of key dimensions based on weights.

[0090] The system standardizes the scoring vectors of employee portraits and job portraits, and preprocesses them in combination with the set dimension weights. Cosine similarity calculates the dot product and modulus of two sets of vectors to generate a matching value between 0 and 1. When the matching degree is higher than the threshold (such as 0.8), the system preliminarily determines that the position is a "high matching position". Further, the gaps in each dimension are quantitatively analyzed through a weighted scoring model. The model normalizes the gap between employee characteristics and job requirements in proportion, and then calculates the total score in combination with the dimension weights. The total matching score is between 0 and 1, and the higher the total score, the better the matching effect.

[0091] Intelligent matching not only relies on single-dimensional conditional judgment, but also conducts in-depth assessment of the overall fit between employees and positions through comprehensive weights and gap analysis. The system will output the total match score, match level and gap analysis list, and provide job recommendation suggestions and optimization plans. For example, for low-matching positions, the system will output specific gaps, such as "skill requirement gap = 5 points", and provide recommended training courses or development paths.

[0092] The results of intelligent matching can be intuitively displayed through radar charts and gap lists, helping companies optimize job allocation and employee development decisions. Through this advanced analysis method, the key transformation from basic tags to intelligent recommendations provides companies with scientific and efficient talent management tools.

[0093] S5: Provides data query function to help users obtain information from massive data.

[0094] Example 2

[0095] The second embodiment of the present invention is different from the previous embodiment in that:

[0096] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0097] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0098] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0099] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0100] Example 3

[0101] The third embodiment of the present invention provides a label and portrait construction system based on digital human resource management, which is characterized by: including a data collection module, a label management module, a portrait construction module, an intelligent matching module, and a data query module.

[0102] Data collection module collects basic data, defines data labels, and builds a complete label library;

[0103] The tag management module associates the collected basic data information with the definition in the tag library and assigns tags;

[0104] The portrait construction module builds employee portraits and job portraits based on label data;

[0105] Intelligent matching module, which uses artificial intelligence and data analysis methods to perform intelligent matching through employee and job profile analysis;

[0106] The data query module provides data query functions to help users obtain information from massive data.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A label and portrait construction method based on digital human resource management, characterized by: include, Collect basic data, define data labels, and build a complete label library; Associate the collected basic data information with the definition in the tag library and assign tags; Build employee and job profiles based on label data; Through employee and job profile analysis, apply artificial intelligence and data analysis methods for intelligent matching; Provides data query function to help users obtain information from massive data.

2. A label and portrait construction method based on digital human resource management as claimed in claim 1, characterized in that: The basic data includes collecting employee data and collecting job position data; The employee data includes basic personal information, work performance, training and development information; The job data includes basic job requirements, job performance requirements, and changes in job responsibilities.

3. A label and portrait construction method based on digital human resource management as claimed in claim 2, characterized in that: The defined data tags include employee tag definition, position tag definition, and tag assignment rules; The label assignment rules include setting evaluation criteria for each label and assigning labels to employees or positions based on different data.

4. A label and portrait construction method based on digital human resource management as claimed in claim 3, characterized in that: The associating the collected basic data information with the definitions in the tag library includes associating and assigning values ​​from the basic data to the tags by defining association rules and introducing a calculation model.

5. A label and portrait construction method based on digital human resource management as claimed in claim 4, characterized in that: The employee portrait construction includes calculating the score of the label in each dimension through a weighted formula, weighting and summing the scores of multiple labels in the same dimension to form a total score of the dimension, and calculating the overall portrait score according to the weights of different dimensions; When an employee or job label changes, the system automatically recalculates the score of the corresponding dimension. Managers view the portrait through visualization tools and manually adjust the label weight. In the person-job matching scenario, employee portraits are compared with job portraits in real time for matching.

6. A label and portrait construction method based on digital human resource management as claimed in claim 5, characterized in that: The job profile is constructed based on data, quantified through logical rules and mathematical models, and generates a comprehensive description of job characteristics.

7. A label and portrait construction method based on digital human resource management as claimed in claim 6, characterized in that: The intelligent matching includes calculating the matching degree between the employee portrait and the job portrait, taking the dimension score of the employee portrait and the requirement score of the job portrait as input, and using cosine similarity to calculate the matching degree. If the matching degree is higher than a threshold, the job is judged as a high matching job; Comprehensively consider the weight of each dimension, generate the total score of the match between employees and positions, determine the weight of each dimension, calculate the gap between employees and positions in each dimension, calculate the weighted total score, and obtain the final matching result.

8. A system based on the method for building labels and portraits based on digital human resource management according to any one of claims 1 to 7, characterized in that: It includes data collection module, label management module, portrait construction module, intelligent matching module and data query module.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images