Intelligent talent information management system in technology transfer process

Abstract

The invention relates to the field of information management, in particular to an intelligent talent information management system in a technology transfer process, which comprises a talent information management module, a project information management module, a project analysis module and a skill matching module. A mean value clustering algorithm based on a flight path is used for carrying out clustering analysis on the comprehensive vector, the capability and adaptability of each talent are comprehensively reflected, and high-dimensional data integration is beneficial to considering more factors during matching, so that the matching precision is improved; the outlier detection technology is used in the skill matching module for confirmation and analysis, and the integrity and accuracy of a data set are ensured by identifying and eliminating abnormal values, so that an enterprise can more effectively allocate human resources and project budget, and more efficient resource allocation and cost control are realized.

Description

Technical Field

[0001] The present invention relates to the field of information management, and in particular to an intelligent management system for talent information in the process of technology transfer. Background Art

[0002] With the advancement of science and technology, there have been many significant changes and innovations in the field of information management. However, there are few systems for matching talents to projects, and general matching methods have problems such as inaccurate matching and slow processes. Talent information and project requirements are scattered in different systems and lack effective integration, which makes it difficult to accurately identify suitable talents. A large amount of manual intervention is required for screening and review, resulting in a slow decision-making process and delays in project progress. Ordinary matching methods have problems such as low data quality and wrong decisions. Abnormal data points may be caused by data entry errors, sensor failures or measurement errors. If these outliers are not detected and excluded, the overall data quality will be affected, resulting in reduced accuracy of analysis results. In addition, incorrect matching may cause companies to invest a lot of resources in inappropriate talents or projects, wasting time and money, thus affecting overall operational efficiency. Summary of the invention

[0003] In view of the above situation, the present invention provides an intelligent management system for talent information in the process of technology transfer. In view of the problems of inaccurate matching and slow process in general corresponding methods, the present invention combines the personal information of talents and the characteristic information of projects into a comprehensive vector in the skill matching module, and uses a mean clustering algorithm based on flight trajectories to perform cluster analysis on the comprehensive vector, which comprehensively reflects the ability and adaptability of each talent. High-dimensional data integration helps to consider more factors during matching, thereby improving the accuracy of matching, and by introducing clustering, the talent screening process is automated, reducing the time investment of human resources in talent matching, thereby accelerating the time of project startup and implementation; in view of the problems of low data quality and decision-making errors in ordinary corresponding methods, the present invention uses outlier detection technology in the skill matching module for confirmation and analysis, and ensures the integrity and accuracy of the data set by identifying and excluding outliers, eliminates mismatches caused by data errors or anomalies, and ensures the reliability of system analysis results. Enterprises can more effectively allocate human resources and project budgets, thereby achieving more efficient resource allocation and cost control.

[0004] The present invention provides an intelligent management system for talent information in a technology transfer process, including a talent information management module, a project information management module, a project analysis module and a skill matching module, which specifically includes the following contents:

[0005] The talent information management module collects personal information of talents, including name, contact information, education, work experience, professional skills and fields, and stores it using a database management system;

[0006] The project information management module records the basic information of the technology transfer project, including the project name, project description, project requirements, start date and end date, and is stored in a relational database;

[0007] The project analysis module uses NLP to analyze the project description and technical requirements to obtain a technology transfer project analysis report, which includes the project's technical details, key skills, and implementation plan;

[0008] The skill matching module matches the technology transfer project analysis report with the personal information of the talent to obtain a matching result.

[0009] Furthermore, the skill matching module matches the talent's personal information according to the analysis report, specifically including the following steps:

[0010] Step S1: Data preprocessing, extracting project requirements and technical details from the project information management module and the project analysis module, extracting the professional skills, work experience and fields of talents from the talent information management module, and outputting the above data to step S2 after structuring and standardizing operations;

[0011] Step S2: feature extraction, converting the data output in step S1 into numerical features, forming a vector representation, and obtaining a project feature vector and a talent feature vector;

[0012] Step S3: Data analysis, using the mean clustering algorithm based on flight trajectory to perform clustering analysis and obtain clustering results;

[0013] Step S4: Anomaly detection, analyzing clustering results, identifying abnormal talent characteristics and project requirements, using outlier detection technology to confirm and analyze, and obtaining anomaly detection results;

[0014] Step S5: Output the matching results. Generate a matching list based on the clustering results, listing the talent information that matches the project requirements.

[0015] Furthermore, in step S3, a mean clustering algorithm based on flight trajectories is used to perform clustering analysis, which specifically includes the following steps:

[0016] Step S31: data preparation, extracting the project feature vector and the talent feature vector from step S2, combining the project feature vector and the talent feature vector into a comprehensive vector, and integrating them into a comprehensive talent data set, where each data point includes a combination of a project feature vector and a talent feature vector;

[0017] Step S32: Initialize parameters, set talent categories, set the initial number of clusters to k according to the talent categories, randomly select k data points from the comprehensive talent data set as initial cluster centers, and initialize the parameters of Lévy flight, including flight step length and flight number;

[0018] Step S33: Calculate the distance. Use the Euclidean distance to calculate the distance between each data point in the comprehensive talent dataset and the initial cluster center. The formula used is as follows: ;

[0019] in, is the data point, is the cluster center, Represents data points With cluster center The Euclidean distance between represents the dimension of the comprehensive vector, Represents the index of the comprehensive vector;

[0020] Step S34: forming clusters, dividing the data points in the comprehensive talent dataset into different clusters according to the distance between each data point and the initial cluster center, and each cluster contains all the data points assigned to the same cluster center;

[0021] Step S35: Generate a random search vector, determine the flight step length and the number of flights, use the Lévy flight trajectory to generate a random search vector, and iterate the search. The formula used is as follows: ; ;

[0022] in, Indicates the number of steps or times of iteration, is the shape parameter of the Lévy distribution, is the flight step length, is a random constant, is the control parameter for adjusting the flight step length distribution, represents the velocity vector;

[0023] Add it to the current cluster center to get the new cluster center. The formula used is as follows: θ j =rand a i , b i ×μsign[rand - 1 2 & Lévy, i = 1, 2, …, D ; ; ;

[0024] in, represents the first Quantity, and is the range parameter of the flight trajectory, represents the standard deviation of the Lévy distribution, sign[rand - 1 2 ] represents a sign function with a value of -1 or 1, represents a random number drawn from a Lévy distribution, represents the first Quantity, is a coefficient in the range [0,1], is the value of the next iteration, is a constant value in the range [0,1);

[0025] Step S36: Update the cluster center. Update the cluster center by combining the random search vector. Add the generated random search vector to the current cluster center to obtain the position of the new cluster center. Use the mean method to update the position of each cluster center. The formula used is as follows: ;

[0026] in, Indicates All data points in the clusters, Indicates The cluster center of each cluster;

[0027] Step S37: Iteration process, setting the convergence condition to whether the cluster center is stable and unchanged, if the convergence condition is not met, returning to step S32 until the convergence condition is met, and when the convergence condition is met, the iteration ends and the determined cluster center is output;

[0028] Step S38: Result output: based on the determined cluster center, generate the data points in the comprehensive talent data set contained in each cluster, and output the cluster list, cluster center information and cluster statistical information, specifically including the following contents:

[0029] Cluster list: comprehensive talent vector in each cluster, showing the matching of talent and project characteristics;

[0030] Cluster center information: extract the characteristics of the cluster center of each cluster;

[0031] Cluster statistics: Provides the number and distribution of data points in each cluster, and analyzes the size and composition of different talent categories.

[0032] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0033] (1) In view of the problems of inaccurate matching and slow process in general matching methods, the present invention combines the personal information of talents and the characteristic information of projects into a comprehensive vector in the skill matching module, and uses the mean clustering algorithm based on flight trajectory to perform cluster analysis on the comprehensive vector, which comprehensively reflects the ability and adaptability of each talent. High-dimensional data integration helps to consider more factors during matching, thereby improving the matching accuracy. In addition, by introducing clustering, the talent screening process is automated, reducing the time investment of human resources in talent matching, thereby accelerating the time of project launch and implementation;

[0034] (2) In view of the problems of low data quality and wrong decisions in ordinary matching methods, the present invention uses outlier detection technology in the skill matching module for confirmation and analysis. By identifying and excluding outliers, the integrity and accuracy of the data set are ensured, and mismatches caused by data errors or anomalies are eliminated. The reliability of the system analysis results is guaranteed, and enterprises can allocate human resources and project budgets more effectively, thereby achieving more efficient resource allocation and cost control. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic diagram of an intelligent management system for talent information in a technology transfer process provided by the present invention.

[0036] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0039] Example 1, see Figure 1The present invention provides an intelligent management system for talent information in the process of technology transfer, including a talent information management module, a project information management module, a project analysis module and a skill matching module, which specifically includes the following contents:

[0040] The talent information management module collects personal information of talents, including name, contact information, education, work experience, professional skills and fields, and stores it using a database management system;

[0041] The project information management module records the basic information of the technology transfer project, including the project name, project description, project requirements, start date and end date, and is stored in a relational database;

[0042] The project analysis module uses NLP to analyze the project description and technical requirements to obtain a technology transfer project analysis report, which includes the project's technical details, key skills, and implementation plan;

[0043] The skill matching module matches the technology transfer project analysis report with the personal information of the talent to obtain a matching result.

[0044] In this embodiment, the personal information is refined in the talent information management module, as shown in the following example:

[0045] Talent A:

[0046] Name: Zhang San;

[0047] Contact information: 138xxxxxxxx;

[0048] Education: Master (Computer Science);

[0049] Work experience: 5 years (ABC Company, software development engineer);

[0050] Professional skills: Python (advanced), Java (intermediate);

[0051] Field: Artificial Intelligence;

[0052] The basic information of the technology transfer project is detailed as follows:

[0053] Project name: Smart home system development;

[0054] Project Description: Develop a smart home control application;

[0055] Project requirements: Professional skills in mobile application development and Internet of Things technology;

[0056] Start date: January 2025;

[0057] End date: December 2025;

[0058] Person in charge information: Li Si, contact information: 139xxxxxxxx;

[0059] In the project analysis module, natural language processing (NLP) analysis is performed on the project description and requirements to obtain a technology transfer project analysis report. An example is as follows:

[0060] Technical details: intelligent control system architecture, sensor technology;

[0061] Key skills: mobile application development, cloud computing;

[0062] Implementation plan: Phase 1 (requirements analysis), Phase 2 (design), Phase 3 (development and testing);

[0063] After clustering in the skill matching module, the matching results are obtained:

[0064] The matching score between Talent A and the project "Smart Home System Development" is 90%, indicating that his skills are highly consistent with the project requirements.

[0065] Embodiment 2: This embodiment is based on the above embodiment. The skill matching module matches the talent's personal information according to the analysis report, and specifically includes the following steps:

[0066] Step S1: Data preprocessing, extracting project requirements and technical details from the project information management module and the project analysis module, extracting the professional skills, work experience and fields of talents from the talent information management module, and outputting the above data to step S2 after structuring and standardizing operations;

[0067] Step S2: feature extraction, converting the data output in step S1 into numerical features, forming a vector representation, and obtaining a project feature vector and a talent feature vector;

[0068] Step S3: Data analysis, using the mean clustering algorithm based on flight trajectory to perform clustering analysis and obtain clustering results;

[0069] Step S4: Anomaly detection, analyzing clustering results, identifying abnormal talent characteristics and project requirements, using outlier detection technology to confirm and analyze, and obtaining anomaly detection results;

[0070] Step S5: Output the matching results. Generate a matching list based on the clustering results, listing the talent information that matches the project requirements.

[0071] In this embodiment, the examples are as follows:

[0072] Project Information: Project requirements include "Advanced Python development, 5 years of work experience", structured as follows:

[0073] { "skills": "Python", "experience": "5", "level": "Advanced" }

[0074] Talent information: Talent A's skill "Python, 8 years of experience" is structured as follows: { "skills": "Python", "experience": "8", "level": "Advanced" };

[0075] In step S2, the structured data is converted into numerical features, for example, the proficiency of each skill is represented by a numerical value (such as level 1-5), and the work experience is represented by years;

[0076] For example, the feature vector of a project is generated based on the project requirements, and the technical requirements and experience requirements are quantified in a similar way;

[0077] Here is an example:

[0078] The feature vector of talent A is ["Python: 4", "Work experience: 8", "Field: Artificial Intelligence"], corresponding to the vector [4, 8, 1];

[0079] The feature vector of the project “Smart Home System Development” is [“Python:5”, “Work Experience:5”, “Field: Internet of Things”], corresponding to the vector [5,5,2];

[0080] In step S4, anomaly detection is performed. The requirements of the project "Smart Home System Development" are mainly advanced Python skills, but a candidate's Python skill score is 2 and his work experience is only 1 year. This is considered an anomaly. The system triggers a warning and prompts the project manager to review the matching results.

[0081] The final matching list is as follows: [ { "talent_name": "Zhang San", "matching_score": 90, "skills": ["Python", "AI"], "experience": 8 }, { "talent_name": "Li Si", "matching_score": 85, "skills": ["Java", "Web Development"], "experience": 6 } ];

[0083] The system recommends Zhang San as the preferred candidate for the project "Smart Home System Development" with a matching score of 90%.

[0084] Embodiment 3, based on the above embodiment, uses a mean clustering algorithm based on flight trajectories to perform cluster analysis in step S3, specifically comprising the following steps:

[0085] Step S31: data preparation, extracting the project feature vector and the talent feature vector from step S2, combining the project feature vector and the talent feature vector into a comprehensive vector, and integrating them into a comprehensive talent data set, where each data point includes a combination of a project feature vector and a talent feature vector;

[0086] Step S32: Initialize parameters, set talent categories, set the initial number of clusters to k according to the talent categories, randomly select k data points from the comprehensive talent data set as initial cluster centers, and initialize the parameters of Lévy flight, including flight step length and flight number;

[0087] Step S33: Calculate the distance. Use the Euclidean distance to calculate the distance between each data point in the comprehensive talent dataset and the initial cluster center. The formula used is as follows: ;

[0088] in, is the data point, is the cluster center, Represents data points With cluster center The Euclidean distance between represents the dimension of the comprehensive vector, Represents the index of the comprehensive vector;

[0089] Step S34: forming clusters, dividing the data points in the comprehensive talent dataset into different clusters according to the distance between each data point and the initial cluster center, and each cluster contains all the data points assigned to the same cluster center;

[0090] Step S35: Generate a random search vector, determine the flight step length and the number of flights, use the Lévy flight trajectory to generate a random search vector, and iterate the search. The formula used is as follows: ; ;

[0091] in, Indicates the number of steps or times of iteration, is the shape parameter of the Lévy distribution, is the flight step length, is a random constant, is the control parameter for adjusting the flight step length distribution, represents the velocity vector;

[0092] Add it to the current cluster center to get the new cluster center. The formula used is as follows: θ j =rand a i , b i ×μsign[rand - 1 2 & Lévy, i = 1, 2, …, D ; ; ;

[0093] in, represents the first Quantity, and is the range parameter of the flight trajectory, represents the standard deviation of the Lévy distribution, sign[rand - 1 2 ] represents a sign function with a value of -1 or 1, represents a random number drawn from a Lévy distribution, represents the first Quantity, is a coefficient in the range [0,1], is the value of the next iteration, is a constant value in the range [0,1);

[0094] Step S36: Update the cluster center. Update the cluster center by combining the random search vector. Add the generated random search vector to the current cluster center to obtain the position of the new cluster center. Use the mean method to update the position of each cluster center. The formula used is as follows: ;

[0095] in, Indicates All data points in the clusters, Indicates The cluster center of each cluster;

[0096] Step S37: Iteration process, setting the convergence condition to whether the cluster center is stable and unchanged, if the convergence condition is not met, return to step S32 until the convergence condition is met, and when the convergence condition is met, the iteration ends and the determined cluster center is output;

[0097] Step S38: Result output: based on the determined cluster center, generate the data points in the comprehensive talent data set contained in each cluster, and output the cluster list, cluster center information and cluster statistical information.

[0098] Embodiment 4: This embodiment is based on the above embodiment. In step S38, a cluster list, cluster center information and cluster statistical information are output, which specifically includes the following contents:

[0099] Cluster list: comprehensive talent vector in each cluster, showing the matching of talent and project characteristics;

[0100] Cluster center information: extract the characteristics of the cluster center of each cluster;

[0101] Cluster statistics: Provides the number and distribution of data points in each cluster, and analyzes the size and composition of different talent categories.

[0102] Embodiment 5: This embodiment is based on the above embodiment. For steps S31 to S38, a specific example is used to illustrate the application of the algorithm:

[0103] Step S31: Project feature vector: [“Python: 5”, “Work experience: 5”, “Field: Internet of Things”], the corresponding vector is [5, 5, 2];

[0104] Talent feature vector: ["Python: 4", "Work experience: 6", "Field: Internet of Things"], the corresponding vector is [4, 6, 2];

[0105] Comprehensive vector: [5,5,2,4,6,2], representing a combination of a project and a talent;

[0106] Step S32: Assuming that there are three talent categories, set the initial cluster number k=3, randomly select three data points from the comprehensive data set as the initial cluster centers, the flight step s=0.5, and the flight number t=100;

[0107] Step S33: ;

[0108] Step S34: the closest cluster center of data point 1 is c1, so the data point is assigned to cluster 1;

[0109] Step S35: Setting =1.5,γ=1.2, =0.5, randomly generate search vector [0.2,-0.3,0.1];

[0110] Step S36: Assuming that the data points in cluster 1 are [5,5,2], [4,6,2][5,5,2], [4,6,2][5,5,2], [4,6,2], the new cluster center is c 1 = 1 2 5,5,2 + 4,6,2 =[4.5,5.5,2] ;

[0111] Step S37: If the difference between the new and old cluster centers is less than 0.01, the clustering is considered to have converged, and the final cluster center is output;

[0112] Step S38: The clustering result is output as:

[0113] { "cluster_1": { "center": [4.5, 5.5, 2], "data_points": 10, "average_distance": 0.2 }, "cluster_2": { "center": [3.5, 4.0, 1], "data_points": 15, "average_distance": 0.3 } }.

[0114] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0115] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0116] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An intelligent management system for talent information in the process of technology transfer, characterized by: It includes talent information management module, project information management module, project analysis module and skill matching module, specifically including the following contents: The talent information management module collects personal information of talents, including name, contact information, education, work experience, professional skills and fields, and stores it using a database management system; The project information management module records the basic information of the technology transfer project, including the project name, project description, project requirements, start date and end date, and is stored in a relational database; The project analysis module uses NLP to analyze the project description and technical requirements to obtain a technology transfer project analysis report, which includes the project's technical details, key skills, and implementation plan; The skill matching module matches the technology transfer project analysis report with the personal information of the talent to obtain a matching result.

2. According to claim 1, the intelligent management system for talent information in the process of technology transfer is characterized by: The skill matching module matches the talent's personal information according to the analysis report, specifically including the following steps: Step S1: Data preprocessing, extracting project requirements and technical details from the project information management module and the project analysis module, extracting the professional skills, work experience and fields of talents from the talent information management module, and outputting the above data to step S2 after structuring and standardizing operations; Step S2: feature extraction, converting the data output in step S1 into numerical features, forming a vector representation, and obtaining a project feature vector and a talent feature vector; Step S3: Data analysis, using the mean clustering algorithm based on flight trajectory to perform clustering analysis and obtain clustering results; Step S4: Anomaly detection, analyzing clustering results, identifying abnormal talent characteristics and project requirements, using outlier detection technology to confirm and analyze, and obtaining anomaly detection results; Step S5: Output the matching results. Generate a matching list based on the clustering results, listing the talent information that matches the project requirements.

3. An intelligent management system for talent information in the process of technology transfer according to claim 2, characterized in that: In step S3, cluster analysis is performed using a mean clustering algorithm based on flight trajectories, which specifically includes the following steps: Step S31: data preparation, extracting the project feature vector and the talent feature vector from step S2, combining the project feature vector and the talent feature vector into a comprehensive vector, and integrating them into a comprehensive talent data set, where each data point includes a combination of a project feature vector and a talent feature vector; Step S32: Initialize parameters, set talent categories, set the initial number of clusters to k according to the talent categories, randomly select k data points from the comprehensive talent data set as initial cluster centers, and initialize the parameters of Lévy flight, including flight step length and flight number; Step S33: Calculate the distance. Use the Euclidean distance to calculate the distance between each data point in the comprehensive talent dataset and the initial cluster center. The formula used is as follows: ; in, is the data point, is the cluster center, Represents data points With cluster center The Euclidean distance between represents the dimension of the comprehensive vector, Represents the index of the comprehensive vector; Step S34: forming clusters, dividing the data points in the comprehensive talent dataset into different clusters according to the distance between each data point and the initial cluster center, and each cluster contains all the data points assigned to the same cluster center; Step S35: Generate a random search vector, determine the flight step length and the number of flights, use the Lévy flight trajectory to generate a random search vector, and iterate the search. The formula used is as follows: ; ; in, Indicates the number of steps or times of iteration, is the shape parameter of the Lévy distribution, is the flight step length, is a random constant, is the control parameter for adjusting the flight step length distribution, represents the velocity vector; Add it to the current cluster center to get the new cluster center. The formula used is as follows: ; ; ; in, represents the first Quantity, and is the range parameter of the flight trajectory, represents the standard deviation of the Lévy distribution, represents a sign function with a value of -1 or 1, represents a random number drawn from a Lévy distribution, represents the first Quantity, is a coefficient in the range [0,1], is the value of the next iteration, is a constant value in the range [0,1); Step S36: Update the cluster center. Update the cluster center by combining the random search vector. Add the generated random search vector to the current cluster center to obtain the position of the new cluster center. Use the mean method to update the position of each cluster center. The formula used is as follows: ; in, Indicates All data points in the clusters, Indicates The cluster center of each cluster; Step S37: Iteration process, setting the convergence condition to whether the cluster center is stable and unchanged, if the convergence condition is not met, returning to step S32 until the convergence condition is met, and when the convergence condition is met, the iteration ends and the determined cluster center is output; Step S38: Result output: based on the determined cluster center, generate the data points in the comprehensive talent data set contained in each cluster, and output the cluster list, cluster center information and cluster statistical information, specifically including the following contents: Cluster list: comprehensive talent vector in each cluster, showing the matching of talent and project characteristics; Cluster center information: extract the characteristics of the cluster center of each cluster; Cluster statistics: Provides the number and distribution of data points in each cluster, and analyzes the size and composition of different talent categories.

Images