Talent data analysis management method and device based on big data
Through the talent data analysis and management method based on big data, enterprises can effectively manage talents, formulate personalized career development plans, solve the problem of inefficient traditional human resource management, and achieve efficient and accurate talent management and organizational efficiency improvement.
Patent Information
- Application Number
- CN202411410216.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2025-02-11
AI Technical Summary
Enterprises face inefficiency and frequent errors in the process of talent selection, training and development, and cannot effectively tap the potential abilities of employees, resulting in the loss of talents or underutilization.
The talent data analysis and management method based on big data is adopted to obtain multi-dimensional data of employees from multiple sources, convert them into a unified format, and use pre-trained analytical models for analysis to obtain employees' potential resignation risks and career development trajectory. Then, the analytical data is presented to human resource managers through a visual interface, and feedback data is obtained and personalized career development plans are formulated.
It achieves efficient and accurate talent management, comprehensively understands employees' work performance and development needs, improves employees' career satisfaction and work efficiency, and enhances the overall effectiveness and competitiveness of the organization.
Smart Images
Figure CN119417427A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of human resources, and in particular to a talent data analysis and management method and device based on big data. Background Art
[0002] Currently, companies face many challenges in the process of talent selection, training and development. Traditional human resource management methods rely on manually collated data and basic statistical tools to make decisions, which is inefficient and prone to errors.
[0003] In addition, it is impossible to effectively tap the potential of employees, which may lead to talent loss or under-utilization. Therefore, how to manage talents efficiently and accurately remains to be solved. Summary of the invention
[0004] In order to achieve efficient and accurate talent management, the present application provides a talent data analysis management method and device based on big data.
[0005] In the first aspect, the present application provides a talent data analysis and management method based on big data, which adopts the following technical solutions:
[0006] A talent data analysis management method based on big data, comprising: obtaining employee-related multi-dimensional data from multiple sources, and converting the multi-dimensional data into a unified format, wherein the multi-dimensional data includes but is not limited to performance records, training history, and job satisfaction surveys; retrieving a pre-trained analysis model, inputting the multi-dimensional data in the unified format into the analysis model for analysis to obtain corresponding analysis data, wherein the analysis data includes the potential risk of employee resignation and career development trajectory; displaying the analysis data to a human resources manager through a visual interface, obtaining guidance feedback data from the human resources manager, and formulating corresponding career development plans for employees based on the analysis data and the guidance feedback data.
[0007] By adopting the above technical solutions and integrating multi-dimensional data such as performance records, training history, and job satisfaction surveys, companies can fully understand employees' work performance, skill levels, and development needs; based on the analysis results, formulate personalized career development plans for each employee to improve employees' career satisfaction; combined with the guidance and feedback data from human resource managers, continuously optimize the analysis model and career development plan to ensure the effectiveness and adaptability of talent management strategies; through the above steps, companies can achieve efficient and accurate talent management and improve the overall effectiveness of the organization.
[0008] Optionally, in the process of obtaining the guidance feedback data of the human resources manager, the method also includes: obtaining the employee's behavior data through work logs, email records, time management tools or wearable devices, identifying the employee's behavior data, and determining the employee's corresponding work habit data and work efficiency data; generating corresponding guidance opinions based on the employee's work habit data and work efficiency data, and displaying the guidance opinions to the human resources manager through a visual interface; obtaining the human resources manager's selection of corresponding target modification opinions on the visual interface based on the guidance opinions, and generating corresponding guidance feedback opinions based on all the target modification opinions selected by the human resources manager, wherein there are multiple modification opinions on the visual interface for the human resources manager to select.
[0009] By adopting the above technical solutions, through a visual interface, human resource managers can directly participate in the decision-making process and choose the most appropriate modification opinions, which enhances the managers' sense of participation and decision-making flexibility, making the management process more transparent and interactive. In addition, by identifying employees' work habits and efficiency issues, and making improvement suggestions, it helps employees optimize work processes and improve productivity, thereby reducing ineffective work time and improving the overall work efficiency of the team.
[0010] Optionally, the method also includes retrieving multi-dimensional data corresponding to the employee, wherein the multi-dimensional data also includes the employee's behavioral data and interests and hobbies; extracting target skill data associated with the employee's work ability and interests based on the multi-dimensional data; and generating a corresponding recommendation list for the employee based on the target skill data, wherein the recommendation list includes multiple projects or work tasks.
[0011] By adopting the above technical solutions, personalized project or work task recommendations can be generated based on employees' specific skills and interests, helping employees find the career development path that best suits them, thereby improving employees' career satisfaction and work motivation and promoting their long-term career growth; it not only improves the level of refinement of talent management, but also enhances employees' career development and personal growth, ultimately promoting the overall effectiveness and competitiveness of the organization.
[0012] Optionally, the method also includes: retrieving interaction data between employees and colleagues; constructing a social network diagram between employees and colleagues based on the interaction data, wherein nodes represent employees and edges represent the strength of connections between employees; and adjusting team composition based on the social network diagram.
[0013] By adopting the above technical solutions, the key paths of knowledge dissemination can be identified through the social network diagram, which can promote the effective sharing of knowledge and experience within the team, thereby improving the knowledge level and innovation ability of the entire team; more refined and scientific talent management can be achieved, which not only improves the overall effectiveness of the team, but also promotes the career development and personal satisfaction of employees.
[0014] Optionally, in the process of adjusting the team composition based on the social network graph, the method also includes: retrieving the performance records in the multi-dimensional data corresponding to the employees, and determining the corresponding performance set; performing corresponding performance ranking on all employees based on the performance set, and obtaining corresponding employee capability configuration; and optimizing the team composition based on the social network graph and the employee capability configuration.
[0015] By adopting the above technical solutions, the system can dynamically adjust the team composition as employee performance and social networks change to ensure that the team is always in the best condition; enabling organizations to flexibly respond to market and technological changes to quickly adjust talent allocation strategies.
[0016] Optionally, the method also includes: regularly obtaining work status data corresponding to the employees, wherein the work status data includes physiological data, behavioral data and internal communication data; performing anomaly identification based on the work status data, wherein anomaly identification includes emotional fluctuations, physiological abnormalities, behavioral abnormalities and interaction abnormalities; when an abnormal situation is detected, automatically triggering a warning signal to be sent to a human resources manager.
[0017] By adopting the above technical solutions, by detecting abnormal conditions of employees, such as mood swings or physiological abnormalities as early as possible, human resource managers can quickly take intervention measures and provide necessary support; then through timely intervention, the decline in work efficiency and potential risk of resignation caused by employee health problems or emotional problems can be reduced.
[0018] Optionally, the training process of the analysis model also includes: collecting historical data corresponding to employees from multiple sources, preprocessing the collected historical data to obtain a corresponding data set, the historical data including but not limited to performance records, training history, and job satisfaction surveys; dividing the preprocessed data set into a training set and a test set, using the training set data to train the model, and verifying the model performance on the test set; using cross-validation to optimize the model, and after the model training converges, determining the model as the corresponding analysis model.
[0019] By adopting the above technical solutions and combining the advantages of big data and machine learning, enterprises are provided with powerful tools to optimize human resource management strategies. Based on the prediction results of the model, human resources can be reasonably allocated and key positions can be assigned to the most suitable employees, which can improve overall work efficiency.
[0020] In the second aspect, the present application provides a talent data analysis and management device based on big data, which adopts the following technical solution:
[0021] A talent data analysis and management device method based on big data, comprising:
[0022] A multi-dimensional data acquisition module, used to acquire multi-dimensional data related to employees from multiple sources and convert the multi-dimensional data into a unified format, wherein the multi-dimensional data includes but is not limited to performance records, training history, and job satisfaction surveys;
[0023] An analysis data acquisition module retrieves a pre-trained analysis model, inputs the multi-dimensional data in a unified format into the analysis model for analysis to obtain corresponding analysis data, wherein the analysis data includes the potential resignation risk and career development trajectory of the employee;
[0024] The career development planning module displays the analysis data to the human resource manager through a visual interface, obtains the guidance feedback data of the human resource manager, and formulates corresponding career development plans for employees based on the analysis data and the guidance feedback data.
[0025] In the third aspect, the present application provides a talent data analysis and management method based on big data, which adopts the following technical solutions:
[0026] A talent data analysis and management method based on big data comprises a processor, wherein the program of any one of the talent data analysis and management methods based on big data described above is run in the processor.
[0027] In a fourth aspect, the present application provides a storage medium, which adopts the following technical solution:
[0028] A storage medium storing a program of any one of the above-mentioned methods for analyzing and managing talent data based on big data.
[0029] To summarize, this application includes at least one of the following beneficial technical effects: by integrating multi-dimensional data such as performance records, training history, job satisfaction surveys, etc., the company can fully understand the employees' work performance, skill level and development needs; combined with performance ranking and employee capability allocation, dynamically adjust the team composition to ensure that the team is always in the best condition; thereby achieving efficient and accurate talent management and improving the overall effectiveness of the organization. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 The present invention is a flowchart of a talent data analysis and management method based on big data according to an exemplary embodiment.
[0031] Figure 2It is a structural block diagram of a talent data analysis and management method device based on big data according to an exemplary embodiment. DETAILED DESCRIPTION
[0032] Embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings.
[0033] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0034] The present application embodiment discloses a talent data analysis and management method based on big data, referring to Figure 1 ,include:
[0035] S100, obtains multi-dimensional data related to employees from multiple sources and converts the multi-dimensional data into a unified format.
[0036] Among them, multi-dimensional data of employees can be collected from multiple sources (such as HR information systems, performance management systems, training record systems, employee questionnaires, etc.), and the multi-dimensional data includes but is not limited to performance records, training histories, job satisfaction surveys, behavioral data, interests and hobbies, social network data, etc.; through multi-dimensional data, it is convenient to fully understand the employees' work performance, skill levels, development needs and personal preferences.
[0037] In addition, multi-dimensional data needs to be cleaned (to remove noise and invalid data), deduplicated, and formatted in a standardized manner to ensure data quality and consistency, thereby integrating data from different sources into a unified format for subsequent analysis.
[0038] S110, calling a pre-trained analysis model, inputting the multi-dimensional data in a unified format into the analysis model for analysis to obtain corresponding analysis data.
[0039] The analysis model is trained in advance, and the specific training process includes the following steps:
[0040] S1101, collecting historical data corresponding to employees from multiple sources, and preprocessing the collected historical data to obtain corresponding data sets.
[0041] Among them, historical data includes but is not limited to performance records, training history, and job satisfaction surveys; and it is necessary to remove noise and invalid data, such as missing values, outliers, duplicate records, etc., and then extract useful features, and possibly perform feature selection or dimensionality reduction to improve model performance so that it can be input into the machine learning model
[0042] S1102, divide the preprocessed data set into a training set and a test set, use the training set data to train the model, and verify the model performance on the test set.
[0043] Among them, the dataset is usually divided into a training set (used for training the model) and a test set (used to verify the model performance), and the common split ratios are 70% training set and 30% test set, or 80% training set and 20% test set; then the training set data can be used to train the model, the model will learn the patterns and rules in the data, and adjust its parameters to minimize the prediction error; at the same time, the performance of the model can be evaluated through the test set, and commonly used evaluation indicators include accuracy, precision, recall rate, F1 score, AUC-ROC curve, etc.
[0044] S1103, using cross-validation to optimize the model, and after the model training converges, determining the model as the corresponding analysis model.
[0045] Among them, in order to more comprehensively evaluate the model performance, cross-validation technology can be used. A common method is K-Fold Cross-Validation, which divides the data set into K subsets, and uses K-1 subsets as training sets each time, and the remaining subset as a validation set. This is repeated K times, and the average performance is finally taken as the evaluation result of the model.
[0046] When the model reaches a stable state during training, that is, when the loss function no longer decreases significantly, the model is considered to have converged; after cross-validation and hyperparameter tuning, the model with the best performance is selected as the final analysis model. Through multiple verifications and tuning, it is ensured that the final selected model can maintain good performance in various situations.
[0047] It should be pointed out here that the analysis data includes employees' potential turnover risks and career development trajectories. By analyzing employees' historical data, the analysis model can identify potential turnover risks and help companies take measures in advance to reduce the loss of key talents. In addition, the analysis model can provide career development advice and paths based on employees' abilities and interests to help employees plan for the future.
[0048] S120, displaying the analysis data to the human resource manager through a visual interface, obtaining the guidance feedback data from the human resource manager, and formulating corresponding career development plans for the employees based on the analysis data and the guidance feedback data.
[0049] First, the analysis results are presented to human resource managers in an intuitive way through visualization tools (such as charts, dashboards, etc.). Then, human resource managers can view the analysis results through a visualization interface and provide feedback, such as confirmation of certain analysis results, modification suggestions, etc. Finally, based on the analysis data and the feedback from human resource managers, personalized career development plans are formulated for employees, including training plans, promotion paths, project allocations, etc.
[0050] It should be pointed out here that in the process of obtaining guidance feedback data from human resource managers, the method also includes:
[0051] S121, obtaining employee behavior data through work logs, email records, time management tools or wearable devices, identifying the employee behavior data, and determining the employee's corresponding work habit data and work efficiency data.
[0052] Among them, work logs: record employees' daily work content, task completion status, etc.; email records: analyze the frequency, content and time distribution of employees' email exchanges; time management tools: use project management software (such as Trello, Asana) or time tracking tools (such as RescueTime) to record employees' time allocation; wearable devices: collect employees' physiological data (such as heart rate, sleep quality) and activity data (such as steps, active time) through devices such as smart bracelets or watches.
[0053] In addition, natural language processing (NLP) is used to extract useful information from text data, such as emotional tendencies, work priorities, etc. Work habit data: analyze employees' schedules, task priorities, communication patterns, etc. to determine their work habits; Work efficiency data: evaluate employees' work efficiency through time management and task completion, including task completion speed, multi-tasking ability, etc.
[0054] By providing objective evaluation results based on actual data rather than subjective judgment, managers can make more accurate decisions, thereby identifying deficiencies in employees’ work habits and efficiency and providing a basis for subsequent guidance.
[0055] S122, generating corresponding guidance opinions based on the employee's work habit data and work efficiency data, and displaying the guidance opinions to the human resource manager through a visual interface.
[0056] Among them, work habit data and work efficiency data can be combined to analyze employees' strengths and room for improvement, and based on the corresponding analysis results, specific guidance opinions can be generated, such as time management suggestions, task allocation suggestions, communication method optimization, etc.; at the same time, interactive functions are provided through a visual interface, so that human resource managers can clearly see the analysis results and suggestions, and enhance the transparency of the decision-making process.
[0057] S123, obtaining the corresponding target modification opinions selected by the human resources manager in the visual interface based on the guidance opinions, and generating corresponding guidance feedback opinions based on all the target modification opinions selected by the human resources manager.
[0058] Among them, there are multiple modification opinions for human resource managers to choose from on the visual interface, and human resource managers can choose appropriate modification opinions through the visual interface, such as adjusting working hours, increasing training opportunities, improving communication methods, etc.; based on all the modification opinions selected by managers, combined with the feedback from human resource managers, the guidance opinions are continuously optimized to ensure the effectiveness and adaptability of talent management strategies.
[0059] By executing steps S121 to S123, human resource managers can directly participate in the decision-making process, select the most appropriate modification opinions, and continuously optimize the guidance opinions based on the feedback from managers. This not only improves the scientificity and accuracy of talent management, but also enhances the interaction between managers and employees, and promotes more efficient and personalized employee development plans.
[0060] In the embodiment of the present application, the method further comprises the following steps:
[0061] S124, retrieve the multi-dimensional data corresponding to the employee.
[0062] Among them, multi-dimensional data also includes employees' behavioral data and interests and hobbies. Information on employees' interests and hobbies can be obtained through questionnaires, social media analysis, etc. Combining behavioral data and interests and hobbies can more accurately assess employees' abilities and interests, providing a basis for subsequent personalized recommendations.
[0063] S125, extracting target skill data related to employee work ability and interest based on multi-dimensional data.
[0064] Among them, the collected multi-dimensional data are integrated to form a comprehensive data set, and then natural language processing is used to extract features related to employees' work ability and interests from the data set. That is, based on the interest and hobby data, the characteristics such as employees' areas of interest and activity types are extracted. Then, the work ability and interest characteristics can be combined to identify the employees' current skills and potential development directions.
[0065] S126, generating a corresponding recommendation list for the employee based on the target skill data.
[0066] The recommendation list includes multiple projects or work tasks. Based on the employee's professional skills and experience, projects that match their abilities are recommended. Based on the employee's interests and career development goals, tasks that match their interests and development directions are recommended.
[0067] By executing steps S124 to S126, personalized project or work task recommendations are generated based on employees' work abilities and interests, thereby improving employees' career satisfaction and work motivation; and resources are allocated reasonably to arrange employees to the projects or tasks that best suit them, thereby improving overall work efficiency; by recommending tasks that are consistent with employees' interests and development directions, employees are helped to achieve career growth and improve their long-term career satisfaction.
[0068] In addition, during the management of employees, it is necessary to optimize the team to which the employee belongs. The specific process includes the following steps:
[0069] S127, retrieve the interaction data between the employee and his colleagues.
[0070] Among them, the interaction data between employees and colleagues is collected from multiple sources (such as email records, internal communication tools, meeting minutes, project management systems, etc.); through multi-channel data collection, the company can fully understand the interaction patterns and communication frequency between employees.
[0071] S128, construct a social network graph between employees and colleagues based on the interaction data.
[0072] Here, each employee is defined as a node in the social network graph, and the edges between nodes are defined based on the interaction data. The weight of the edge can represent the strength of the connection between employees, such as the frequency of email exchanges, the number of times they have participated in a joint project, etc.
[0073] Then, you can use graph theory algorithms (such as adjacency matrix, adjacency list, etc.) to generate a social network graph, and display the social network graph through visualization tools (such as Gephi, NetworkX, etc.), so that managers can intuitively see the relationship structure between employees.
[0074] Through the social network diagram, managers can intuitively see the relationship structure and connection strength among employees, and can also see employees with high influence in the network (such as opinion leaders, information hubs), who play an important leadership and coordination role in the team.
[0075] S129, Adjusting team composition based on social network graph.
[0076] Among them, team roles and responsibilities can be reallocated based on the employees’ positions in the network and the strength of their connections. For example, employees with strong connections can be placed in the same project group to improve collaboration efficiency.
[0077] In order to more reasonably optimize the team composition, 5. In the process of adjusting the team composition based on the social network graph, the method specifically includes:
[0078] S1291, retrieve the performance record in the multi-dimensional data corresponding to the employee, and determine the corresponding performance set.
[0079] Among them, performance records include KPI completion status, project results, customer feedback, colleague evaluation, etc., and performance records can be data from the most recent quarter, half year or year, depending on the company's evaluation cycle, and then the collected performance data will be integrated to form a comprehensive performance set.
[0080] S1292, sorting all employees by performance based on the performance set, and obtaining corresponding employee capability configurations.
[0081] Among them, based on the performance data, a scoring system is established to quantitatively score the performance of employees, and the performance scores of all employees are sorted using appropriate sorting algorithms (such as bubble sort, quick sort, etc.); then, based on the performance sorting results, an employee capability matrix is constructed to show the performance of each employee in different aspects, and employees are divided into different capability levels, such as high-performance employees, medium-performance employees, low-performance employees, etc.
[0082] S1293, Optimizing team composition based on social network graph and employee capability configuration.
[0083] Among them, the community detection algorithm in the social network graph can be used to identify naturally formed subgroups, and high-performance employees can be placed in key positions based on their capabilities to ensure that they can play their greatest role. At the same time, it is necessary to ensure that there are employees with different levels of capabilities within the team to achieve skill complementarity and improve overall work efficiency.
[0084] In addition, social network diagrams and performance data need to be updated regularly. On the one hand, they can monitor changes in relationships and performance among employees. On the other hand, they can dynamically adjust team composition based on the latest data to ensure that the team is always in the best condition.
[0085] Team optimization through the above steps first provides objective performance evaluation results based on actual data rather than subjective judgment. Through performance ranking, the relative position and contribution of each employee in the team are clarified. Then, by combining social network diagrams and employee capability configuration, good working relationships and complementary skills are ensured among team members. Employees with strong cooperative relationships and high performance are combined to improve the execution efficiency and success rate of projects. Finally, it not only improves the scientificity and accuracy of talent management, but also enhances the interaction between managers and employees, and promotes more efficient and personalized team building.
[0086] In the process of enterprise employee management, it is necessary not only to monitor performance, but also to take into account the emotional value of employees. Therefore, this application plan also specifically implements the following steps:
[0087] S111, regularly obtain the work status data corresponding to the employee.
[0088] Among them, work status data includes physiological data, behavioral data and internal communication data. Employees' physiological data such as heart rate, blood pressure, sleep quality, etc. can be collected through wearable devices (such as smart bracelets and smart watches), and employees' internal communication data can be collected through email records and instant messaging tools (such as corporate WeChat and Slack), including the frequency, content and time distribution of email exchanges.
[0089] S112, performing abnormality identification based on the working status data.
[0090] Among them, abnormality identification includes emotional fluctuations, physiological abnormalities, behavioral abnormalities and interaction abnormalities. Emotional fluctuations: Analyze employees' emails and chat records through natural language processing (NLP) technology to identify signs of emotional fluctuations, such as the frequent appearance of negative words; Physiological abnormalities: Use statistical methods or machine learning models to detect whether employees' physiological data exceeds the normal range, such as a sudden increase in heart rate, decreased sleep quality, etc.; Behavioral abnormalities: Analyze employees' behavioral data to identify behavioral patterns that are significantly different from usual, such as a significant reduction in working hours, a sharp drop in task completion rate, etc.; Interaction abnormalities: Through social network analysis, identify abnormal patterns of employees in internal communications, such as a sudden drop in communication frequency, major changes in communication objects, etc.
[0091] S113, when an abnormal situation is detected, an early warning signal is automatically triggered and sent to the human resources manager.
[0092] Among them, thresholds for various abnormal situations can be set based on historical data and industry standards. The system monitors employees' work status data in real time. Once an abnormal situation is found, an early warning signal is immediately triggered. The early warning signal can be sent to human resource managers through a variety of methods (such as email, text message, and system notification).
[0093] By executing the above steps S111 to S113, first through multi-channel data collection, the enterprise can comprehensively monitor the physiological conditions, work behaviors and communication patterns of employees, and then through abnormality identification, the enterprise can discover possible problems of employees at an early stage, such as health problems, emotional problems, etc. On the one hand, it can reduce the decline in work efficiency and potential risks of resignation due to health problems or emotional problems. On the other hand, by solving problems in a timely manner, it can ensure that employees maintain a good working state and improve the work efficiency of the overall team.
[0094] The present application also discloses a talent data analysis and management device based on big data, see Figure 2 , including but not limited to:
[0095] A multi-dimensional data acquisition module 200 is used to acquire multi-dimensional data related to employees from multiple sources and convert the multi-dimensional data into a unified format, wherein the multi-dimensional data includes but is not limited to performance records, training history, and job satisfaction surveys;
[0096] The analysis data acquisition module 210 retrieves a pre-trained analysis model, inputs the multi-dimensional data in a unified format into the analysis model for analysis to obtain corresponding analysis data, wherein the analysis data includes the potential resignation risk and career development trajectory of the employee;
[0097] The career development planning module 220 displays the analysis data to the human resource manager through a visual interface, obtains the guidance feedback data from the human resource manager, and formulates corresponding career development plans for employees based on the analysis data and the guidance feedback data.
[0098] Furthermore, the device includes but is not limited to:
[0099] The behavior data recognition module obtains the employee's behavior data through work logs, email records, time management tools or wearable devices, and is used to identify the employee's behavior data and determine the employee's corresponding work habit data and work efficiency data;
[0100] The guidance generation module generates corresponding guidance based on employees' work habit data and work efficiency data, and displays the guidance to human resource managers through a visual interface;
[0101] The target modification opinion acquisition module is used to obtain the corresponding target modification opinions selected by the human resources manager based on the guidance opinions in the visual interface, and generate corresponding guidance feedback opinions based on all the target modification opinions selected by the human resources manager, wherein there are multiple modification opinions available for the human resources manager to select on the visual interface.
[0102] Furthermore, the device includes but is not limited to:
[0103] A multi-dimensional data retrieval module is used to retrieve the multi-dimensional data corresponding to the employee, wherein the multi-dimensional data also includes the employee's behavior data and interests and hobbies;
[0104] Target skill data extraction module, which is used to extract target skill data related to employees' work ability and interests based on multi-dimensional data;
[0105] The recommendation list production module is used to generate a corresponding recommendation list for an employee based on the target skill data, wherein the recommendation list includes multiple projects or work tasks.
[0106] Furthermore, the device includes but is not limited to:
[0107] Interaction data retrieval module, used to retrieve interaction data between employees and colleagues;
[0108] The social network graph construction module is used to construct a social network graph between employees and their colleagues based on the interaction data, where nodes represent employees and edges represent the strength of connections between employees;
[0109] The team adjustment module is used to adjust the team composition based on the social network graph.
[0110] Furthermore, the device includes but is not limited to:
[0111] The performance record retrieval module is used to retrieve the performance records in the multi-dimensional data corresponding to the employee and determine the corresponding performance set;
[0112] The ranking module is used to sort all employees according to their performance based on the performance set and obtain the corresponding employee capability configuration;
[0113] The team optimization module is used to optimize team composition based on social network graph and employee capability configuration.
[0114] Furthermore, the device includes but is not limited to:
[0115] A work status data acquisition module is used to regularly acquire the work status data corresponding to the employee, wherein the work status data includes physiological data, behavioral data and internal communication data;
[0116] Anomaly recognition module, which is used to perform anomaly recognition based on working status data, wherein anomaly recognition includes emotional fluctuations, physiological anomalies, behavioral anomalies, and interaction anomalies;
[0117] The early warning module is used to automatically trigger an early warning signal to be sent to the human resource manager when an abnormal situation is detected.
[0118] Furthermore, the device includes but is not limited to:
[0119] A data set acquisition module collects historical data corresponding to employees from multiple sources and pre-processes the collected historical data to obtain corresponding data sets. The historical data includes but is not limited to performance records, training history, and job satisfaction surveys.
[0120] The differentiation module is used to divide the preprocessed data set into a training set and a test set, use the training set data to train the model, and verify the model performance on the test set;
[0121] The analysis model determination module uses cross-validation to optimize the model. After the model training converges, it is used to determine the model as the corresponding analysis model.
[0122] An embodiment of the present application further discloses a talent data analysis and management method based on big data, comprising a processor, wherein a program of any one of the talent data analysis and management methods based on big data described above is run in the processor.
[0123] The embodiment of the present application also discloses a storage medium storing a program of any one of the above-mentioned talent data analysis and management methods based on big data.
[0124] In summary, the solutions in the embodiments of the present application can play the following comprehensive roles:
[0125] 1. Through the integration and analysis of multi-dimensional data, we can achieve a comprehensive understanding of employees and refined management.
[0126] 2. Develop personalized career development plans based on employees’ specific circumstances to improve their career satisfaction and loyalty.
[0127] 3. Enhance the transparency and flexibility of decision-making through visual interfaces and direct participation of managers.
[0128] 4. Continuously optimize models and strategies based on managers’ feedback to ensure the effectiveness and adaptability of talent management strategies.
[0129] 5. Rationally allocate human resources, assign key positions to the most suitable employees, and improve overall work efficiency.
[0130] 5. Discover and resolve employee problems as early as possible to reduce potential risks and costs.
[0131] Through the above methods, enterprises can not only achieve efficient and accurate talent management, but also improve employee satisfaction and the overall effectiveness of the organization, thereby maintaining their advantages in the highly competitive market.
[0132] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A talent data analysis and management method based on big data, characterized in that: include: Acquire multi-dimensional data related to employees from multiple sources and convert the multi-dimensional data into a unified format, wherein the multi-dimensional data includes but is not limited to performance records, training history, and job satisfaction surveys; Retrieving a pre-trained analysis model, inputting the multi-dimensional data in a unified format into the analysis model for analysis to obtain corresponding analysis data, wherein the analysis data includes the potential resignation risk and career development trajectory of the employee; The analysis data is displayed to a human resource manager through a visual interface, guidance feedback data from the human resource manager is obtained, and corresponding career development plans are formulated for the employees based on the analysis data and the guidance feedback data.
2. The talent data analysis and management method based on big data according to claim 1 is characterized in that: In the process of obtaining the guidance feedback data of the human resources manager, the method further includes: Obtain employee behavior data through work logs, email records, time management tools or wearable devices, identify employee behavior data, and determine the employee's corresponding work habit data and work efficiency data; Generate corresponding guidance opinions based on the employee's work habit data and work efficiency data, and display the guidance opinions to the human resources manager through a visual interface; Obtain the corresponding target modification opinions selected by the human resources manager on the visualization interface based on the guidance opinions, and generate corresponding guidance feedback opinions based on all the target modification opinions selected by the human resources manager, wherein there are multiple modification opinions available for the human resources manager to select on the visualization interface.
3. The talent data analysis and management method based on big data according to claim 2 is characterized in that: The method also includes: Retrieve the multi-dimensional data corresponding to the employees, where the multi-dimensional data also includes the employees' behavioral data and interests and hobbies; Extracting target skill data associated with employee work ability and interest based on the multi-dimensional data; A corresponding recommendation list is generated for the employee based on the target skill data, wherein the recommendation list includes a plurality of projects or work tasks.
4. The talent data analysis and management method based on big data according to claim 1 is characterized in that: The method also includes: Retrieve data on interactions between employees and their colleagues; Building a social network graph between employees and colleagues based on the interaction data, where nodes represent employees and edges represent the strength of connections between employees; The team composition is adjusted based on the social network graph.
5. The talent data analysis and management method based on big data according to claim 4 is characterized in that: In the process of adjusting the team composition based on the social network graph, the method further includes: Retrieving the performance record in the multi-dimensional data corresponding to the employee, and determining the corresponding performance set; Based on the performance set, all employees are ranked according to their performance, and corresponding employee capability configurations are obtained; The team composition is optimized based on the social network graph and the employee capability configuration.
6. The talent data analysis and management method based on big data according to claim 1 is characterized in that: The method also includes: Regularly obtain the work status data corresponding to the employees, where the work status data includes physiological data, behavioral data, and internal communication data; Performing abnormality identification based on the working status data, wherein abnormality identification includes emotional fluctuations, physiological abnormalities, behavioral abnormalities, and interaction abnormalities; When an abnormal situation is detected, an early warning signal is automatically triggered and sent to the human resources manager.
7. The talent data analysis and management method based on big data according to claim 1 is characterized in that: The training process of the analysis model, the method also includes: Collect historical data corresponding to employees from multiple sources, and pre-process the collected historical data to obtain corresponding data sets. The historical data include but are not limited to performance records, training history, and job satisfaction surveys; Divide the preprocessed data set into a training set and a test set, use the training set data to train the model, and verify the model performance on the test set; Use cross-validation to optimize the model, and after the model training converges, determine the model as the corresponding analysis model.
8. A talent data analysis and management device based on big data, characterized in that: include: A multi-dimensional data acquisition module, used to acquire multi-dimensional data related to employees from multiple sources and convert the multi-dimensional data into a unified format, wherein the multi-dimensional data includes but is not limited to performance records, training history, and job satisfaction surveys; An analysis data acquisition module retrieves a pre-trained analysis model, inputs the multi-dimensional data in a unified format into the analysis model for analysis to obtain corresponding analysis data, wherein the analysis data includes the potential resignation risk and career development trajectory of the employee; The career development planning module displays the analysis data to the human resource manager through a visual interface, obtains the guidance feedback data of the human resource manager, and formulates corresponding career development plans for employees based on the analysis data and the guidance feedback data.
9. A talent data analysis and management method based on big data, characterized in that: It includes a processor, in which runs a program of a talent data analysis and management method based on big data as described in any one of claims 1 to 7.
10. A storage medium, characterized in that: A program storing the talent data analysis and management method based on big data as described in any one of claims 1 to 7.