Talent development path planning system and method based on multi-dimensional data

Abstract

The invention discloses a talent development path planning system and method based on multi-dimensional data, and relates to the technical field of talent development path planning. The system comprises a data acquisition and processing module, an employee feature portrait construction module, a development path feature portrait construction module, a colleague development path feature portrait construction module, a first and second development path recommendation list generation module and a talent development path generation module. The matching degree of employees and development path feature portraits is measured by using a cosine similarity algorithm, colleague development path feature portraits are constructed, matching scores of the employees and colleague paths are calculated, two recommendation lists are integrally processed to generate an optimal development path, recommendation reasons are output, personal features and occupational interests of the employees are considered, and the recommendation efficiency is improved. And in combination with experience and preference of colleagues and requirements of companies, the accuracy and practicability of path planning are ensured. According to the invention, through multi-dimensional data analysis, scientificity and individuation of talent development path planning are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of talent development path planning, and specifically relates to a talent development path planning system and method based on multi-dimensional data. Background Art

[0002] In the modern corporate environment, employee career development and talent management are one of the key factors for organizational success. With the rapid changes in the market environment and the rapid advancement of technology, companies need a more scientific and personalized approach to planning employees' career development paths to ensure that they can keep up with the pace of industry development and meet the talent needs within the company.

[0003] Traditional talent development path planning methods usually rely on static job descriptions and individual performance evaluations, which have certain limitations.

[0004] In recent years, with the development of big data analysis and machine learning technology, new ways to optimize talent development paths have emerged through quantitative analysis and intelligent algorithms. However, most existing solutions focus on single-dimensional data analysis, such as focusing only on work performance or skill level, while ignoring other important aspects such as career interests, work attitudes, industry development trends, etc. This single-dimensional analysis can easily lead to one-sided recommendation results and cannot fully reflect the actual situation and development needs of employees.

[0005] In order to solve the above problems, the present invention proposes a talent development path planning system based on multi-dimensional data to improve the scientificity and personalization of talent development path planning, enhance employees' career satisfaction and development motivation, help enterprises effectively cultivate and retain talents, and promote the long-term development of the organization. Summary of the invention

[0006] In order to overcome the shortcomings and deficiencies of the above-mentioned prior art, the first purpose of the present invention is to provide a talent development path planning system based on multi-dimensional data; the second purpose of the present invention is to provide a talent development path planning method based on multi-dimensional data.

[0007] The first object of the present invention adopts the following technical solution: The talent development path planning system based on multi-dimensional data includes a data collection and processing module: used to collect employees' personal information, work performance, career interests, and skill levels, and vectorize the features to form a multi-dimensional vector; collect the features of the development path, including the difficulty level of the development path, required skills, industry trends, promotion opportunities, and salary growth potential, and vectorize them; Employee profile building module: Create a detailed profile for each employee based on the collected data, including professional skills, potential, areas of interest, work attitude, and historical performance; Development path feature profile building module: build feature profiles for different development paths based on career advancement routes, required skills, and industry development trends within the company; Colleague development path feature profile building module: By analyzing the development paths of colleagues with similar characteristics to the target employee, a feature profile that can reflect the colleague's career choice preferences is built; The first development path recommendation list generation module: uses the cosine similarity algorithm to calculate the matching degree between the development path feature profile and the employee feature profile, obtains the matching degree scores of different development paths for specific employees, sorts the development paths according to the matching degree scores and generates the first development path recommendation list; Second development path recommendation list generation module: Calculate the matching degree between employee feature profile and colleague development path feature profile to obtain the matching degree score between the employee and his / her colleague group’s development path preference, sort the development paths according to the matching degree score and generate the second development path recommendation list; Talent development path generation module: Integrate the first development path recommendation list with the second development path recommendation list, extract the top N candidate development path recommendation list, match the candidate development path recommendation list with the employee's feature profile based on the employee's work scenario and personal development goals, and generate the optimal development path.

[0008] The second object of the present invention adopts the following technical solution: The talent development path planning method based on multi-dimensional data is used to realize the talent development path planning system based on multi-dimensional data. The method flow is as follows: Step 1: Calculate the matching degree between the employee feature profile and the development path feature profile using the cosine similarity algorithm, and generate a first development path recommendation list based on the matching score; Step 2: Construct a characteristic profile of the colleague's development path, including the selection of the initial cluster center, distance calculation, probability definition to select the cluster center, repeated clustering until multiple occupational groups are formed, user neighbor matrix construction, sparse processing, and neighbor learning path extraction; Step 3: Calculate the user-colleague path matching score by comparing the similarity between the employee feature profile and the colleague development path feature profile, and generate a second development path recommendation list based on the score; Step 4: Integrate the first development path recommendation list and the second development path recommendation list to generate the optimal development path, including identifying common elements to generate intersection A, extracting elements that only appear in one list to generate sets B and C, and sorting the paths in sets B and C according to the weighted fusion scores to generate a final recommendation list; Step 5: Output the reasons for recommending the development path, including skill level matching, career interest matching, difficulty gradient matching, and company needs matching.

[0009] Preferably, the employee characteristics in step 1 include basic information characteristics, preference characteristics and behavior record characteristics of the employee, wherein: Basic information characteristics: including work experience, educational background, and position; Preference characteristics: including career interests, past career development speed, and career satisfaction; Behavioral record characteristics: including frequency of interactions within the company and project participation; Career path characteristics: including the career path's difficulty level, required skills, industry trends, advancement opportunities, and salary growth potential.

[0010] Preferably, the matching degree calculation formula in step 1 is: ; in, is the employee feature vector; is the development path feature vector; Represents vector dot product; and They are vectors and Model; matching degree The value of The closer the value is to 1, the more the employee characteristic profile matches the development path characteristic profile.

[0011] Preferably, the selection of cluster centers in step 2 includes: S21, randomly select any sample point from the employee feature data set as the initial cluster center; S22, calculating the shortest distance between each sample point and the current cluster center; S23, defining the distance ratio as the probability of each sample point being selected as the next cluster center, and selecting the sample point corresponding to the maximum probability value as the next cluster center; S24. Repeat the above steps until 7 cluster centers are selected, corresponding to the technical expertise deepening group, leadership and management ability improvement group, cross-domain comprehensive development group, innovation and entrepreneurship cultivation group, internationalization and global vision expansion group, customer orientation and service improvement group, and sustainable development and social responsibility group.

[0012] Preferably, the calculation of the user-colleague path matching score in step 3 includes the calculation of the primary value, the secondary value and the ultimate value, and the calculation formula is as follows: Primary Value: ; Secondary Value: ; Final value: ; in, , Representing users and users Right career path The rating vector of Is the path and The similarity between is the weight coefficient.

[0013] Preferably, the integration processing in step 4 includes listing the paths in the intersection A in a high priority position in the recommendation list, and sorting the paths in the sets B and C according to the weighted fusion scores and adding them to the final recommendation list.

[0014] Preferably, outputting the reasons for recommending the development path in step five includes providing the employee with detailed reasons for the recommendation, covering skill level matching, career interest matching, difficulty gradient matching, and company demand matching.

[0015] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: 1. The present invention quantifies the characteristics of employees' personal information, work performance, professional interests, skill levels, etc. through the collection and processing of multi-dimensional data, and conducts a comprehensive analysis based on the difficulty level, required skills, industry trends, promotion opportunities, salary growth potential, etc. of the career development path. In addition, the system uses a variety of intelligent algorithms such as cosine similarity algorithm, cluster analysis, and user neighbor matrix construction to achieve accurate matching between employee feature portraits and development path feature portraits; 2. The present invention constructs a characteristic profile that can reflect the career choice preferences of colleagues with similar characteristics to the target employee by analyzing the career choice preferences of colleagues, so that the system not only relies on the characteristics of the employees themselves, but also draws on the successful experiences and career paths of colleagues to further optimize the planning results; 3. The present invention integrates the first development path recommendation list (based on the matching of employee characteristics and development path characteristics) with the second development path recommendation list (based on the matching of employee characteristics and colleague development path characteristics), extracts common elements and performs weighted fusion to generate the optimal development path. In addition, detailed reasons for development path recommendation are provided, covering multiple aspects such as skill level matching, career interest matching, difficulty gradient matching, and company demand matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A module diagram of a talent development path planning system based on multi-dimensional data of the present invention is shown; Figure 2 A flow chart of a talent development path planning method based on multi-dimensional data of the present invention is shown. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0020] Embodiment 1:

[0021] See also Figure 1 As shown, the talent development path planning system based on multi-dimensional data of this embodiment includes Data collection and processing module: used to collect employees' personal information (such as work experience, educational background), work performance (such as performance evaluation results), career interests, and skill levels, and vectorize these features to form multi-dimensional vectors. Collect the characteristics of the development path, including the difficulty level of the development path, required skills, industry trends, promotion opportunities, salary growth potential, etc., and also vectorize them.

[0022] Employee profile building module: Create a detailed profile for each employee based on the collected data, including but not limited to professional skills, potential, areas of interest, work attitude, historical performance, etc.

[0023] Development path feature portrait construction module: establish feature portraits for different development paths based on factors such as career advancement routes within the company, required skills, industry development trends, etc.

[0024] Colleague development path characteristic profile construction module: By analyzing the development paths of colleagues with similar characteristics to the target employees, a characteristic profile that can reflect the career choice preferences of these colleagues is constructed.

[0025] The first development path recommendation list generation module: uses the cosine similarity algorithm to calculate the matching degree of the development path feature profile and the employee feature profile to obtain the matching degree score of different development paths for specific employees. According to the matching degree score, the development paths are sorted and the first development path recommendation list is generated.

[0026] The second development path recommendation list generation module: calculates the matching degree between the employee feature portrait and the colleague development path feature portrait to obtain the matching score of the development path preference between the employee and his / her colleague group, sorts the development paths according to the matching score and generates the second development path recommendation list.

[0027] Talent development path generation module: Integrate the first development path recommendation list with the second development path recommendation list to extract the top N candidate development path recommendation lists. Based on the employee's work scenario and personal development goals, match the candidate development path recommendation list with the employee's feature profile to generate the optimal development path.

[0028] The beneficial effects of this embodiment are: through multi-dimensional data analysis, accurate matching of employee personal characteristics and development paths not only improves the scientificity and personalization of talent development path planning, but also enhances employees' career satisfaction and development motivation. At the same time, the system integrates the first and second recommendation lists to ensure that the recommended development path not only complies with the company's internal promotion rules, but also reflects the successful experience of colleagues, thereby improving the accuracy and practicality of development path recommendations, helping enterprises to effectively cultivate and retain talents and promote long-term development of organizations.

[0029] Embodiment 2:

[0030] See also Figure 2 As shown, the talent development path planning method based on multi-dimensional data in this embodiment has the following process: Step 1: Use the cosine similarity algorithm to measure the match between the employee feature profile and the development path feature profile.

[0031] The matching degree calculation formula is as follows: ; in, is the employee feature vector; is the development path feature vector; Represents vector dot product; and They are vectors and Model.

[0032] Match The value of The closer the value is to 1, the more the employee characteristic profile matches the development path characteristic profile.

[0033] According to the matching scores, the development paths are sorted and a first development path recommendation list is generated.

[0034] Step 2: Build a characteristic profile of your colleagues’ development paths.

[0035] In order to take into account the experience and preferences of colleagues, employees with similar development paths are classified and formed into professional groups with different characteristics. The specific steps are as follows: S21. Initial cluster center selection: Randomly select any sample point from the employee feature data set as the initial cluster center.

[0036] S22, distance calculation: calculate the shortest distance between each sample point and the current cluster center ,in, is the sample point, is the cluster center.

[0037] S23, Probability definition: Define the distance ratio as the probability of each sample point being selected as the next cluster center , and select the sample point corresponding to the maximum probability value as the next cluster center ;in, Represents sample points The maximum probability of being selected as the next cluster center; Indicates The cluster centers of the iterations; Indicates the operation of taking the maximum value; S24. Repeat clustering: Repeat the above steps until 7 cluster centers are selected, corresponding to the technical expertise deepening group, leadership and management ability improvement group, cross-domain comprehensive development group, innovation and entrepreneurship cultivation group, internationalization and global vision expansion group, customer orientation and service improvement group, and sustainable development and social responsibility group.

[0038] Technical expertise deepening group: Employees can be recommended to participate in advanced technical training, participate in technological innovation projects, etc.

[0039] Leadership and management capacity improvement group: Employees can be arranged to intern in management positions, participate in leadership training courses, etc.

[0040] Cross-disciplinary comprehensive development group: Employees can be assigned to rotation projects and cross-departmental cooperation projects to broaden their career horizons.

[0041] Innovation and Entrepreneurship Development Group: Employees can be encouraged to participate in internal entrepreneurial projects, innovation labs, etc.

[0042] Internationalization and Global Vision Development Group: Employees can be assigned to overseas branches, participate in international projects, etc.

[0043] Customer Orientation and Service Improvement Group: Employees can be assigned to customer service improvement projects, customer feedback analysis, etc.

[0044] Sustainability and Social Responsibility Group: Employees can participate in the company's sustainable development projects, social responsibility activities, etc.

[0045] S25. User neighbor matrix construction: Calculate the matrix similarity between employee feature profiles and each cluster center, form a similarity network between users, and construct a user neighbor matrix.

[0046] S26, sparse processing: according to the set threshold, the users below the set threshold are regarded as having no significant similarity, and the corresponding matrix elements are set to 0 to sparse the matrix and reduce the computational complexity and storage requirements.

[0047] S27, Neighbor learning path extraction: Select the closest N neighbors in the user's similar neighbor matrix, extract the development path preference subset of these neighbors, and construct a characteristic portrait of the neighbor's development path.

[0048] Step 3: Calculate the user-colleague path matching score by comparing the similarity between the employee feature profile and the colleague development path feature profile.

[0049] Primary Value: ; Secondary Value: ; Final value: ; in, , Representing users and users The development path The rating vector of Is the path and The similarity between is the weight coefficient.

[0050] According to the final value , sort the development paths and generate a second development path recommendation list.

[0051] Step 4: Integrate the first development path recommendation list and the second development path recommendation list to generate the optimal development path.

[0052] Intersection A: Identify and extract the common elements of the first development path recommendation list and the second development path recommendation list to generate intersection A. These paths are recognized by both recommendation methods.

[0053] Sets B and C: Extract the learning path elements recommended by only the first development path recommendation list or only the second development path recommendation list to generate sets B and C.

[0054] Fusion recommendation: The paths in intersection A are listed in the high-priority position of the recommendation list, and then the paths in sets B and C are sorted according to the weighted fusion scores and added to the final recommendation list.

[0055] Determine the recommendation list: Based on the fusion recommendation score, determine and extract the top N candidate development path recommendation list, and match it with the employee feature profile to generate the optimal development path.

[0056] Step 5: Output the reasons for recommending the development path.

[0057] Provide detailed rationale for each recommended development path, including but not limited to: Skill level matching: Path X starts with basic skills and gradually transitions to advanced applications, which is consistent with the current skill level of employees.

[0058] Career interest matching: The path includes areas of interest to employees, such as data analysis, project management, etc., which are highly consistent with their career interests.

[0059] Difficulty gradient matching: From entry-level tasks to complex projects, the difficulty gradually increases, which is conducive to the steady improvement of employees.

[0060] Matching company needs: The path content is closely aligned with the company's business development direction and meets the company's strategic requirements.

[0061] The beneficial effects of this embodiment are as follows: This embodiment accurately plans talent development paths through multi-dimensional data analysis, and improves the matching degree between talents and talent development paths. At the same time, it takes into account the experience and preferences of colleagues, optimizes the recommendation results, ensures that the path planning is in line with both personal development and company needs, and is conducive to talent growth and sustainable development of enterprises.

[0062] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0063] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A talent development path planning system based on multi-dimensional data, characterized by: The system includes a data collection and processing module: used to collect personal information, work performance, career interests, and skill levels of employees, and vectorize the features to form a multi-dimensional vector; collect the features of the development path, including the difficulty level of the development path, required skills, industry trends, promotion opportunities, and salary growth potential, and vectorize them; Employee profile building module: Create a detailed profile for each employee based on the collected data, including professional skills, potential, areas of interest, work attitude, and historical performance; Development path feature profile building module: build feature profiles for different development paths based on career advancement routes, required skills, and industry development trends within the company; Colleague development path feature profile building module: By analyzing the development paths of colleagues with similar characteristics to the target employee, a feature profile that can reflect the colleague's career choice preferences is built; The first development path recommendation list generation module: uses the cosine similarity algorithm to calculate the matching degree between the development path feature profile and the employee feature profile, obtains the matching degree scores of different development paths for specific employees, sorts the development paths according to the matching degree scores and generates the first development path recommendation list; Second development path recommendation list generation module: Calculate the matching degree between employee feature profile and colleague development path feature profile to obtain the matching degree score between the employee and his / her colleague group’s development path preference, sort the development paths according to the matching degree score and generate the second development path recommendation list; Talent development path generation module: Integrate the first development path recommendation list with the second development path recommendation list, extract the top N candidate development path recommendation list, match the candidate development path recommendation list with the employee's feature profile based on the employee's work scenario and personal development goals, and generate the optimal development path.

2. A talent development path planning method based on multi-dimensional data, used to implement a talent development path planning system based on multi-dimensional data as claimed in claim 1, characterized in that: The method flow is as follows: Step 1: Calculate the matching degree between the employee feature profile and the development path feature profile using the cosine similarity algorithm, and generate a first development path recommendation list based on the matching score; Step 2: Construct a characteristic profile of the colleague's development path, including the selection of the initial cluster center, distance calculation, probability definition to select the cluster center, repeated clustering until multiple occupational groups are formed, user neighbor matrix construction, sparse processing, and neighbor learning path extraction; Step 3: Calculate the user-colleague path matching score by comparing the similarity between the employee feature profile and the colleague development path feature profile, and generate a second development path recommendation list based on the score; Step 4: Integrate the first development path recommendation list and the second development path recommendation list to generate the optimal development path, including identifying common elements to generate intersection A, extracting elements that only appear in one list to generate sets B and C, and sorting the paths in sets B and C according to the weighted fusion scores to generate a final recommendation list; Step 5: Output the reasons for recommending the development path, including skill level matching, career interest matching, difficulty gradient matching, and company needs matching.

3. The talent development path planning method based on multi-dimensional data according to claim 2 is characterized in that: The employee characteristics in step 1 include the employee's basic information characteristics, preference characteristics and behavior record characteristics, among which: Basic information characteristics: including work experience, educational background, and position; Preference characteristics: including career interests, past career development speed, and career satisfaction; Behavioral record characteristics: including frequency of interactions within the company and project participation; Career path characteristics: including the career path's difficulty level, required skills, industry trends, advancement opportunities, and salary growth potential.

4. The talent development path planning method based on multi-dimensional data according to claim 2 is characterized in that: The matching degree calculation formula in step 1 is: ； in, is the employee feature vector; is the development path feature vector; Represents vector dot product; and They are vectors and Model; matching degree The value of The closer the value is to 1, the more the employee characteristic profile matches the development path characteristic profile.

5. The talent development path planning method based on multi-dimensional data according to claim 2 is characterized in that: The selection of cluster centers in step 2 includes: S21, randomly select any sample point from the employee feature data set as the initial cluster center; S22, calculating the shortest distance between each sample point and the current cluster center; S23, defining the distance ratio as the probability of each sample point being selected as the next cluster center, and selecting the sample point corresponding to the maximum probability value as the next cluster center; S24. Repeat the above steps until 7 cluster centers are selected, corresponding to the technical expertise deepening group, leadership and management ability improvement group, cross-domain comprehensive development group, innovation and entrepreneurship cultivation group, internationalization and global vision expansion group, customer orientation and service improvement group, and sustainable development and social responsibility group.

6. The talent development path planning method based on multi-dimensional data according to claim 2 is characterized in that: The calculation of the user-colleague path matching score in step 3 includes the calculation of the primary value, the secondary value and the ultimate value, and the calculation formula is as follows: Primary Value: ; Secondary Value: ; Final value: ; in, , Representing users and users Right career path The rating vector of Is the path and The similarity between is the weight coefficient.

7. The talent development path planning method based on multi-dimensional data according to claim 2 is characterized in that: The integration process in step 4 includes listing the paths in the intersection A in a high priority position in the recommendation list, and sorting the paths in the sets B and C according to the weighted fusion scores and adding them to the final recommendation list.

8. The talent development path planning method based on multi-dimensional data according to claim 2 is characterized in that: Outputting the reasons for recommending the development path in step five includes providing employees with detailed reasons for the recommendation, covering skill level matching, career interest matching, difficulty gradient matching, and company demand matching.

Images