Dynamic talent occupational transformation adaptation method and device based on artificial intelligence

Abstract

The invention relates to a dynamic talent occupational transformation adaptation method and device based on artificial intelligence. The method comprises the steps of obtaining occupational skill portraits of different occupations and personal skill portraits of all talents, and constructing an occupational skill matrix based on the occupational skill portraits of all the occupations; on the basis of the occupational skill matrix, identifying similarities and differences feature information among the occupations, and on the basis of the similarities and differences feature information among the occupations, generating a meta-skill library through a meta-skill identification strategy; for each talent, based on the personal skill portrait of the talent and the occupational skill portrait of each occupational, through the meta-skill library, evaluating occupational adaptation information between the talent and each occupational through the meta-skill library, and based on the occupational adaptation information between the talent and each occupational, evaluating the occupational adaptation information between the talent and each occupational through the meta-skill library; and generating an occupational transformation adaptation evaluation result of the talent. By adopting the method, the adaptation degree of dynamic talent occupational transformation based on artificial intelligence can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of big data and career transformation analysis, and in particular to a dynamic talent career transformation adaptation method and device based on artificial intelligence. Background Art

[0002] Against the backdrop of globalization, accelerating technological change, and shortening career lifecycles, individual career paths are becoming increasingly nonlinear, and career transitions across industries and fields are becoming increasingly common. At the same time, when recruiting, internally transferring, and formulating development plans, companies urgently need to understand the similarities and differences in skill requirements across different positions and professions, particularly identifying highly transferable core competencies. Therefore, when preparing talent for career transitions, improving their suitability for transitions and the adaptability of their core competencies is a key focus.

[0003] The existing method of talent career transformation is to identify the target careers that different talents can transform into through methods based on expert knowledge or qualitative analysis. However, this method has a greater subjective influence and focuses less on skills, especially soft skills. Soft skills are one of the main goals that affect whether one can quickly adapt to the career or efficiently complete career tasks after career transition. This makes the assessment accuracy of career migration poor, resulting in a low adaptability to dynamic talent career transformation based on artificial intelligence. Summary of the Invention

[0004] Based on this, it is necessary to provide an artificial intelligence-based dynamic talent career transformation adaptation method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems.

[0005] In the first aspect, this application provides a dynamic talent career transformation adaptation method based on artificial intelligence, including:

[0006] Obtain professional skill profiles of different professions and personal skill profiles of each talent, and construct a professional skill matrix based on the professional skill profiles of each profession;

[0007] Based on the occupational skill matrix, identifying the similarities and differences between the occupations, and generating a meta-skill library based on the similarities and differences between the occupations through a meta-skill identification strategy;

[0008] For each talent, based on the personal skill profile of the talent and the professional skill profile of each of the professions, the meta-skill library is used to evaluate the professional adaptation information between the talent and each of the professions, and based on the professional adaptation information between the talent and each of the professions, the talent's professional transformation adaptation evaluation result is generated.

[0009] Optionally, constructing a professional skills matrix based on the professional skills profiles of the respective professions includes:

[0010] Perform data preprocessing on the professional skill profiles of each of the occupations to obtain standard professional profiles of each of the occupations;

[0011] Obtain the standard occupational portrait weight information of each occupation, and based on the standard occupational portraits of each of the occupations and the standard occupational portrait weight information of each of the occupations, generate an occupational skill matrix through a sparse matrix construction strategy.

[0012] Optionally, identifying the similarities and differences between the occupations based on the occupational skill matrix includes:

[0013] Based on the occupational skill matrix, identifying the skill difference between each of the skills for each occupation using a skill difference algorithm, and based on the occupational skill matrix, identifying the occupational difference between each of the occupations in the occupational skill matrix using an occupational similarity algorithm;

[0014] For each occupation, based on the skills of the occupation in the occupational skill matrix, a significant difference test strategy is used to identify the skills with significant differences, thereby obtaining a sub-significant difference set for the occupation, and the sub-significant difference sets of all occupations are used as the significant difference set corresponding to the occupational skill matrix;

[0015] The skill difference between each skill of each profession, the occupation difference between each profession, and the significant difference set are used as the similarities and differences feature information between each profession.

[0016] Optionally, generating a meta-skill library based on the similarities and differences between the occupations through a meta-skill identification strategy includes:

[0017] Based on the similarities and differences between the occupations, the first meta-skill in each occupational skill is screened through a double-threshold determination strategy;

[0018] Based on the similarities and differences between the occupations, the stability evaluation results of the skills of each occupation are calculated by using a coefficient of variation algorithm, and based on the stability evaluation results of the skills, the secondary skills of each occupation are screened;

[0019] A meta-skill library is constructed based on the first meta-skill in each professional skill and the second meta-skill in each professional skill.

[0020] Optionally, the evaluating the career compatibility information between the talent and each of the careers based on the personal skill profile of the talent and the career skill profile of each of the careers through the meta-skills database includes:

[0021] Based on the personal skill profile of the talent and the professional skill profiles of each of the professions, respectively calculating the skill matching degree between the talent and each of the professions, and the skill gap vector between each skill of the talent and the skills of each of the professions;

[0022] Based on the individual skill profile of the talent and the meta-skill library, a meta-skill transfer algorithm is used to calculate the talent's meta-skill transfer index. Based on the skill gap vectors between each skill of the talent and the skills of each of the occupations, a gap severity algorithm is used to calculate the skill gap severity between each skill of the talent and the skills of each of the occupations.

[0023] The skill matching degree between the talent and each of the occupations, the skill gap vector between each of the talent's skills and the skills of each of the occupations, the talent's meta-skill transfer index, and the severity of the skill gap between the talent and each of the occupations are used as the occupational adaptation information between the talent and each of the occupations.

[0024] Optionally, generating a career conversion adaptation assessment result of the talent based on the career adaptation information between the talent and each of the careers includes:

[0025] Generating a career adaptation sequence for the talent based on the skill matching between the talent and each of the careers, and the talent's meta-skill transfer index;

[0026] Obtain an industry course library, and based on the skill gap vectors between the talent's skills and the skills of each of the occupations, generate a meta-skill improvement list for the talent for each occupation and skill optimization suggestions for the talent for each occupation using the industry course library;

[0027] The talent's meta-skill improvement list for each profession and the talent's skill optimization suggestions for each profession are filled into the talent's career adaptation sequence to generate the talent's career transformation adaptation evaluation result.

[0028] Secondly, this application also provides an artificial intelligence-based dynamic talent career transformation adaptation device, including:

[0029] An acquisition module is used to obtain professional skill profiles of different professions and personal skill profiles of each talent, and to construct a professional skill matrix based on the professional skill profiles of each profession;

[0030] an identification module for identifying the similarities and differences between the occupations based on the occupational skill matrix, and generating a meta-skill library based on the similarities and differences between the occupations through a meta-skill identification strategy;

[0031] A generation module is used to evaluate the career adaptation information between each talent and each of the careers based on the personal skill profile of the talent and the career skill profile of each of the careers through the meta-skill library, and generate the career conversion adaptation evaluation result of the talent based on the career adaptation information between the talent and each of the careers.

[0032] Optionally, the acquisition module is specifically configured to:

[0033] Perform data preprocessing on the professional skill profiles of each of the occupations to obtain standard professional profiles of each of the occupations;

[0034] Obtain the standard occupational portrait weight information of each occupation, and based on the standard occupational portraits of each of the occupations and the standard occupational portrait weight information of each of the occupations, generate an occupational skill matrix through a sparse matrix construction strategy.

[0035] Optionally, the identification module is specifically configured to:

[0036] Based on the occupational skill matrix, identifying the skill difference between each of the skills for each occupation using a skill difference algorithm, and based on the occupational skill matrix, identifying the occupational difference between each of the occupations in the occupational skill matrix using an occupational similarity algorithm;

[0037] For each occupation, based on the skills of the occupation in the occupational skill matrix, a significant difference test strategy is used to identify the skills with significant differences, thereby obtaining a sub-significant difference set for the occupation, and the sub-significant difference sets of all occupations are used as the significant difference set corresponding to the occupational skill matrix;

[0038] The skill difference between each skill of each profession, the occupation difference between each profession, and the significant difference set are used as the similarities and differences feature information between each profession.

[0039] Optionally, the identification module is specifically configured to:

[0040] Based on the similarities and differences between the occupations, the first meta-skill in each occupational skill is screened through a double-threshold determination strategy;

[0041] Based on the similarities and differences between the occupations, the stability evaluation results of the skills of each occupation are calculated by using a coefficient of variation algorithm, and based on the stability evaluation results of the skills, the secondary skills of each occupation are screened;

[0042] A meta-skill library is constructed based on the first meta-skill in each professional skill and the second meta-skill in each professional skill.

[0043] Optionally, the generating module is specifically configured to:

[0044] Based on the personal skill profile of the talent and the professional skill profiles of each of the professions, respectively calculating the skill matching degree between the talent and each of the professions, and the skill gap vector between each skill of the talent and the skills of each of the professions;

[0045] Based on the individual skill profile of the talent and the meta-skill library, a meta-skill transfer algorithm is used to calculate the talent's meta-skill transfer index. Based on the skill gap vectors between each skill of the talent and the skills of each of the occupations, a gap severity algorithm is used to calculate the skill gap severity between each skill of the talent and the skills of each of the occupations.

[0046] The skill matching degree between the talent and each of the occupations, the skill gap vector between each of the talent's skills and the skills of each of the occupations, the talent's meta-skill transfer index, and the severity of the skill gap between the talent and each of the occupations are used as the occupational adaptation information between the talent and each of the occupations.

[0047] Optionally, the generating module is specifically configured to:

[0048] Generating a career adaptation sequence for the talent based on the skill matching between the talent and each of the careers, and the talent's meta-skill transfer index;

[0049] Obtain an industry course library, and based on the skill gap vectors between the talent's skills and the skills of each of the occupations, generate a meta-skill improvement list for the talent for each occupation and skill optimization suggestions for the talent for each occupation using the industry course library;

[0050] The talent's meta-skill improvement list for each profession and the talent's skill optimization suggestions for each profession are filled into the talent's career adaptation sequence to generate the talent's career transformation adaptation evaluation result.

[0051] In a third aspect, the present application provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0052] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods in the first aspect.

[0053] In a fifth aspect, the present application provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.

[0054] The above-mentioned dynamic talent career transformation adaptation method and device based on artificial intelligence obtains the career skill portraits of different occupations and the personal skill portraits of each talent, and constructs a career skill matrix based on the career skill portraits of each occupation; based on the career skill matrix, identifies the similarities and differences between the characteristic information of each occupation, and based on the similarities and differences between the characteristic information of each occupation, generates a meta-skill library through a meta-skill identification strategy; for each talent, based on the personal skill portrait of the talent and the career skill portraits of each occupation, evaluates the career adaptation information between the talent and each occupation through the meta-skill library, and generates the talent's career transformation adaptation evaluation result based on the career adaptation information between the talent and each occupation. This solution, through the technical chain of "latest personal / professional skill profiles (dynamically acquired as profiles change in real time) → cross-professional alignment → dual-threshold meta-skill identification → matching-gap-path migration assessment," first constructs a professional skill matrix using the latest dynamically acquired professional skill profiles. This avoids the technical issues of distorted cross-professional comparisons caused by inconsistent job description formats and word frequency affected by text length. By measuring different professional profiles in the same coordinate system, noise and deviation are significantly reduced, laying a reliable baseline for subsequent statistical threshold judgments. Then, by identifying the similarities and differences in characteristic information between the described professions to generate a meta-skill library, it eliminates high-frequency words specific to each profession, increases attention to meta-skills within professional skills, and avoids subjective factors influencing high-frequency professional skills. Finally, this solution uses the constructed meta-skill library to evaluate the career compatibility between each talent and various occupations based on the dynamically updated recruitment / resume data of talents or enterprises. This not only effectively increases the attention on the soft skills between talents and various occupations, improves the adaptability of talents to new occupations after career change, and the efficiency of completing new career tasks, but also provides talents with adaptation evaluation information between each occupation and themselves, thereby effectively avoiding the one-sidedness and limitations of human evaluation, and comprehensively improving the adaptability of dynamic talent career transformation based on artificial intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technical personnel in this field, other drawings can be obtained based on these drawings without any creative work.

[0056] Figure 1 1. A flowchart of a dynamic talent career transformation adaptation method based on artificial intelligence in one embodiment;

[0057] Figure 2 A flowchart of an example of dynamic talent career transformation adaptation based on artificial intelligence in one embodiment;

[0058] Figure 3 This is a structural block diagram of a dynamic talent career transformation adaptation device based on artificial intelligence in one embodiment;

[0059] Figure 4 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0061] The dynamic talent career transformation adaptation method based on artificial intelligence provided in the embodiment of the present application can be applied to the dynamic talent career transformation adaptation system based on artificial intelligence. The system can be applied to terminals, which can be but not limited to various personal computers, laptops, mid-range computers, etc. Among them, the terminal first constructs a career skill matrix through the latest career skill portrait obtained dynamically through the technical chain of "the latest personal / professional skill portrait (the latest portrait can be dynamically obtained as the portrait changes in real time) → cross-professional alignment → dual-threshold meta-skill identification → matching-gap-path migration evaluation", avoiding the technical problems of different formats of multi-source job descriptions and word frequency being affected by text length, which leads to distortion of cross-professional comparisons, so that different career portraits are measured in the same coordinate system, and the noise and deviation are significantly reduced; laying a reliable baseline for subsequent statistical threshold judgment. Then, by identifying the similarities and differences in characteristic information between the said occupations to generate a meta-skill library, the occupation-specific high-frequency words are excluded; the attention to the meta-skills in the occupational skills is increased, and the subjective influencing factors of high-frequency occupational skills are avoided. Finally, this solution uses the constructed meta-skill library to evaluate the career compatibility between each talent and various occupations based on the dynamically updated recruitment / resume data of talents or enterprises. This not only effectively increases the attention on the soft skills between talents and various occupations, improves the adaptability of talents to new occupations after career change, and the efficiency of completing new career tasks, but also provides talents with adaptation evaluation information between each occupation and themselves, thereby effectively avoiding the one-sidedness and limitations of human evaluation, and comprehensively improving the adaptability of dynamic talent career transformation based on artificial intelligence.

[0062] In an exemplary embodiment, Figure 1 As shown, a dynamic talent career transformation adaptation method based on artificial intelligence is provided, which is described by taking the application of the method to a terminal as an example, and includes the following steps S101 to S103. Among them:

[0063] Step S101: Obtain the professional skill portraits of different professions and the personal skill portraits of each talent, and construct a professional skill matrix based on the professional skill portraits of each profession.

[0064] In this embodiment, the terminal responds to the staff's information upload operation and obtains the professional skill portraits constructed by the staff based on the professional skill requirements of different occupations, as well as the personal skill portraits constructed by different talents based on their personal skills. Among them, the professional skill portrait and the talent skill portrait are skill portraits corresponding to soft skills built on a soft skill quantitative framework including primary, secondary, and tertiary dimensions, and containing quantitative indicators such as relative word frequency. Both include hard skills and soft skills. Then, the terminal constructs a professional skill matrix based on the professional skill portraits of each occupation. Specifically, the different data structures in the professional skill portrait or personal skill portrait can have the same structural meaning as represented in Table 1.

[0065] Table 1: Explanation of the meaning of the data structure

[0066]

[0067] The specific method of constructing the professional skills matrix will be explained in detail later.

[0068] Step S102: Based on the occupational skill matrix, identify the similarities and differences between the occupations, and generate a meta-skill library based on the similarities and differences between the occupations through a meta-skill identification strategy.

[0069] In this embodiment, the terminal identifies the similarities and differences between occupations based on the occupational skill matrix. Based on this information, a meta-skills library is generated using a meta-skills identification strategy. This meta-skills library contains "meta-skills" that are essential for each occupational skill, are highly versatile, and have high transfer value. The specific generation process will be described in detail later. The similarities and differences between occupations include the skill differences between each skill, the occupational differences between occupations, and the significant difference set. The specific identification process will be described in detail later.

[0070] Step S103: For each talent, based on the talent's personal skill profile and the professional skill profiles of each profession, the meta-skill library is used to evaluate the career adaptation information between the talent and each profession, and based on the career adaptation information between the talent and each profession, the talent's career transformation adaptation evaluation result is generated.

[0071] In this embodiment, the terminal evaluates each talent's career compatibility with each occupation using a meta-skills database based on their individual skill profile and the professional skill profiles of each occupation. Based on this compatibility information, the terminal generates a career transition adaptation assessment result for the talent. This career transition adaptation assessment result includes the talent's corresponding career adaptation sequence, as well as a meta-skill improvement list and skill optimization recommendations for each occupation. The specific generation process will be described in detail later.

[0072] Based on the above solution, through the technical chain of "latest personal / professional skill profile (the latest profile can be dynamically obtained as the profile changes in real time) → cross-professional alignment → dual-threshold meta-skill identification → matching-gap-path migration assessment", we first construct a professional skill matrix through the latest professional skill profile obtained dynamically. This avoids the technical problems of different formats of multi-source job descriptions and word frequency being affected by text length, which leads to distortion in cross-professional comparisons. Different professional profiles are measured in the same coordinate system, significantly reducing noise and deviation; laying a reliable baseline for subsequent statistical threshold judgments. Then, by identifying the similarities and differences in characteristic information between the described professions to generate a meta-skill library, we eliminate high-frequency words specific to each profession, increase the focus on meta-skills in professional skills, and avoid subjective influencing factors of high-frequency professional skills. Finally, this solution uses the constructed meta-skill library to evaluate the career compatibility between each talent and various occupations based on the dynamically updated recruitment / resume data of talents or enterprises. This not only effectively increases the attention on the soft skills between talents and various occupations, improves the adaptability of talents to new occupations after career change, and the efficiency of completing new career tasks, but also provides talents with adaptation evaluation information between each occupation and themselves, thereby effectively avoiding the one-sidedness and limitations of human evaluation, and comprehensively improving the adaptability of dynamic talent career transformation based on artificial intelligence.

[0073] Optionally, a professional skills matrix is ​​constructed based on the professional skills portraits of each profession, including: performing data preprocessing on the professional skills portraits of each profession to obtain standard professional portraits of each profession; obtaining the weight information of the standard professional portraits of each profession, and based on the standard professional portraits of each profession and the weight information of the standard professional portraits of each profession, a sparse matrix construction strategy is used to generate a professional skills matrix.

[0074] In this embodiment, the terminal performs data preprocessing on the professional skill profiles of each profession to obtain the standard professional profiles of each profession. The data preprocessing process is as follows:

[0075] (1) Unified format

[0076] Supports CSV, JSON, and Parquet; all are converted to Parquet+Snappy and encoded as UTF-8.

[0077] (2) Hierarchical mapping

[0078] Based on the unified soft skills framework, free text labels are mapped to L1-L3; entries without mappings enter the "pending review pool".

[0079] (3) Word frequency standardization

[0080]

[0081] where μs , is the mean of skill s in all professions, σ s is the standard deviation of skill s in all occupations.

[0082] (4) Elimination of outliers

[0083] if |std_freq o,s |>3, it is set to missing and logged.

[0084] (5) Missing value filling

[0085] The median of the same level and occupation is filled in; if the missing ratio is greater than 30%, the entire row is discarded.

[0086] (6) Cache index construction

[0087] Create a column index by occupation_id; create an inverted index by skill_id to speed up subsequent matrix queries.

[0088] Then, the terminal obtains the standard occupational profile weight information of each occupation, and based on the standard occupational profile of each occupation and the standard occupational profile weight information of each occupation, generates an occupational skill matrix through a sparse matrix construction strategy. The coefficient matrix construction strategy includes the calculation formula for constructing the occupational skill matrix:

[0089] M o,s =std_freq o,s ×w s

[0090] Among them, w s The weight set for the level or expert, o is occupation, s is skill.

[0091] Based on the above scheme, a professional skill matrix is ​​constructed after preprocessing, so that occupations with different professional portraits can be measured in the same coordinate system, the noise and deviation are significantly reduced, and quantitative comparative analysis can be performed between each other, which improves the dataization effect of skills for different occupations.

[0092] Optionally, based on the occupational skill matrix, identifying the similarities and differences between occupations, including: based on the occupational skill matrix, identifying the skill differences between each skill of each occupation through a skill difference algorithm, and based on the occupational skill matrix, identifying the occupational differences between each occupation in the occupational skill matrix through an occupational similarity algorithm; for each occupation, based on each skill of the occupation in the occupational skill matrix, identifying each significantly different skill through a significant difference test strategy, obtaining a sub-significant difference set of the occupation, and using the sub-significant difference set of all occupations as the significant difference set corresponding to the occupational skill matrix; using the skill difference between each skill of each occupation, the occupational difference between each occupation, and the significant difference set as the similarities and differences between occupations.

[0093] In this embodiment, the terminal identifies the skill differences between each skill of each occupation based on the occupational skill matrix through a skill difference algorithm, and identifies the occupational differences between each occupation in the occupational skill matrix through an occupational similarity algorithm based on the occupational skill matrix.

[0094] The calculation formula of the skill difference algorithm is:

[0095]

[0096] The calculation formula of the occupation similarity algorithm is:

[0097]

[0098] For each occupation, the terminal uses a significant difference test strategy based on the skills in the occupational skill matrix to identify the significantly different skills. This results in a sub-set of significant differences for the occupation, and all sub-sets of significant differences for all occupations are considered the significant difference set corresponding to the occupational skill matrix. The significant difference test strategy involves using a two-sample t-test or Mann-Whitney U test for each skill s; if p < 0.05, the skill is included in the significant difference set ∑.

[0099] Finally, the terminal uses the skill difference between each skill of each profession, the occupation difference between each profession, and the significant difference set as the similarities and differences feature information between each profession.

[0100] Based on the above scheme, through the above matrixization and statistical tests, this module provides quantifiable and traceable input features for the subsequent "importance and universality" rules, while eliminating the interference factors caused by sample size and text length.

[0101] Optionally, based on the characteristic information of similarities and differences between various occupations, a meta-skill library is generated through a meta-skill identification strategy, including: based on the characteristic information of similarities and differences between various occupations, a dual-threshold judgment strategy is used to screen the first meta-skill in each occupational skill; based on the characteristic information of similarities and differences between various occupations, a coefficient of variation algorithm is used to calculate the stability evaluation results of each skill of each occupation, and based on the stability evaluation results of each skill, the second meta-skill in each occupational skill is screened; based on the first meta-skill in each occupational skill, and the second meta-skill in each occupational skill, a meta-skill library is constructed.

[0102] In this embodiment, the terminal uses a dual-threshold determination strategy to screen the first-element skills in each occupational skill based on the similarities and differences between occupations. Specifically, the dual-threshold determination strategy is a determination strategy corresponding to the importance-universality dual-threshold method:

[0103] (1) Importance of computing skills

[0104] I o,s =M o,s

[0105] Press I for all skills in the same profession O o,s The values ​​are sorted and the top K% are set as high importance intervals.

[0106] (2) Set the threshold

[0107] Importance threshold α: default K=30, which is recorded as "in the top 30%".

[0108] Universality threshold β: The default β = 70%, indicating coverage of ≥ 70% of occupations.

[0109] (3) Meta-skill determination

[0110] If the skill s meets

[0111]

[0112] Then record s in the meta-skill set

[0113] Then, based on the similarities and differences between the occupations, the terminal uses the coefficient of variation algorithm to calculate the stability evaluation results of each skill of each occupation, and based on the stability evaluation results of each skill, screens the secondary skills in each occupation. The calculation process of the coefficient of variation algorithm is as follows:

[0114] (1) Calculate the coefficient of variation

[0115] (μ s ,σ s For I o,sMean and standard deviation across all occupations)

[0116] (2) Stability threshold

[0117] Set γ (default 0.25). If CV s ≤γ and μ s Not lower than the overall Pth percentile (default 50%), also recorded

[0118] Finally, the terminal constructs a meta-skill library based on the first meta-skill of each professional skill and the second meta-skill of each professional skill. Internal skills are recursively inserted according to the L3→L2→L1 relationship to generate a "MetaSkillTree" (i.e., meta-skill library), which supports query and visualization.

[0119] Based on the above solution, by building a meta-skill library, we can identify the meta-skills in each occupation, thereby improving the comprehensiveness and accuracy of the analysis of the compatibility of talents with the occupation.

[0120] Optionally, based on the personal skill profile of the talent and the professional skill profile of each profession, the career adaptation information between the talent and each profession is evaluated through the meta-skill library, including: based on the personal skill profile of the talent and the professional skill profile of each profession, respectively calculating the skill matching degree between the talent and each profession, and the skill gap vector between each skill of the talent and the skills of each profession; based on the personal skill profile of the talent and the meta-skill library, calculating the meta-skill transfer index of the talent through the meta-skill transfer algorithm, and based on the skill gap vector between each skill of the talent and the skills of each profession, respectively calculating the skill gap severity between each skill of the talent and the skills of each profession through the gap severity algorithm; the skill matching degree between the talent and each profession, the skill gap vector between each skill of the talent and the skills of each profession, the meta-skill transfer index of the talent, and the skill gap severity between the talent and each profession are used as the career adaptation information between the talent and each profession.

[0121] In this embodiment, the terminal calculates the skill matching degree between the talent and each profession, and the skill gap vector between each skill of the talent and the skills of each profession based on the personal skill profile of the talent and the professional skill profile of each profession.

[0122] The calculation formula for the skill matching degree is:

[0123]

[0124] The calculation formula of the skill gap vector is:

[0125] Gi =max(0,T i -S i )

[0126] Get

[0127]

[0128] Among them, G meta is the skill gap vector of meta-skill, G spec is the skill gap vector of non-meta skills.

[0129] Based on the talent's personal skill profile and meta-skill database, the meta-skill transfer algorithm is used to calculate the talent's meta-skill transfer index. Based on the skill gap vectors between the talent's skills and the skills of each occupation, the gap severity algorithm is used to calculate the skill gap severity between the talent's skills and the skills of each occupation. The calculation formula of the meta-skill transfer algorithm is:

[0130]

[0131] The calculation formula of the gap severity algorithm is:

[0132]

[0133] Finally, the terminal uses the skill matching degree between talents and various occupations, the skill gap vector between talents' various skills and the skills of various occupations, the meta-skill transfer index of talents, and the severity of the skill gap between talents and various occupations as the career adaptation information between talents and various occupations.

[0134] Based on the above scheme, by analyzing the occupational adaptation information between talents and each occupation from the perspectives of skill matching between talents and each occupation, skill gap vector between talents' skills and skills of each occupation, meta-skill transfer index of talents, and severity of skill gap between talents and each occupation, the accuracy of adaptation identification between talents and each occupation and the comprehensiveness of adaptation angle identification are improved.

[0135] Optionally, based on the career adaptation information between the talent and each occupation, the talent's career transformation adaptation assessment results are generated, including: based on the skill matching between the talent and each occupation, and the talent's meta-skill migration index, generating the talent's career transformation adaptation sequence; obtaining the industry course library, and based on the skill gap vector between the talent's various skills and the skills of each occupation, generating the talent's meta-skill improvement list for each occupation, and the talent's skill optimization suggestions for each occupation through the industry course library; filling the talent's meta-skill improvement list for each occupation, and the talent's skill optimization suggestions for each occupation into the talent's career adaptation sequence, to generate the talent's career transformation adaptation assessment results.

[0136] In this embodiment, the terminal generates a career adaptation sequence for the talent based on the skill match between the talent and each occupation and the talent's meta-skill transfer index. The career adaptation sequence is obtained by sorting the occupations in descending order of skill match and meta-skill transfer index.

[0137] Then, the terminal obtains the industry course library of the industry in which the talent is located, and based on the skill gap vector between the talent's various skills and the skills of each occupation, generates the talent's meta-skill improvement list for each occupation and the talent's skill optimization suggestions for each occupation through the industry course library. Among them, the terminal sorts the skills in order from high to low according to the skill gap vector to obtain a meta-skill improvement list. Among them, the industry course database includes the correspondence between different courses and the improvement degree range of different meta-skills. Based on the skill gap vector, the terminal identifies the course corresponding to each meta-skill in the meta-skill improvement list through the association information between the skill gap vector preset in the terminal and the degree of skill improvement demand (the association information includes the correspondence between different skill gap vectors and the degree of skill improvement demand range).

[0138] Finally, the terminal fills the talent's meta-skill improvement list for each occupation and the talent's skill optimization suggestions for each occupation into the talent's career adaptation sequence, and generates the talent's career transformation adaptation assessment results.

[0139] Based on the above scheme, this scheme can not only quantify the skill matching degree to sort the transfer occupations suitable for each talent, thereby generating a career recommendation sequence for the talent, but also generate training plans for the meta-skills that are lacking or insufficient in each occupation to which the talent is adapted, avoiding blind improvement, thereby specifically reducing the meta-skill gap between the talent and each occupation, and improving the comprehensiveness and accuracy of the generated career conversion adaptation assessment results.

[0140] The application also provides an example of dynamic talent career transformation adaptation based on artificial intelligence, such as Figure 2 As shown, the specific processing process includes the following steps:

[0141] Step S201, obtaining professional skill portraits of different professions and personal skill portraits of each talent.

[0142] Step S202: pre-process the professional skill profiles of each profession to obtain standard professional profiles of each profession.

[0143] Step S203: Obtain the standard occupational portrait weight information of each occupation, and generate an occupational skill matrix through a sparse matrix construction strategy based on the standard occupational portrait of each occupation and the standard occupational portrait weight information of each occupation.

[0144] Step S204: Based on the occupational skill matrix, the skill difference algorithm is used to identify the skill difference between each skill of each occupation, and based on the occupational skill matrix, the occupation similarity algorithm is used to identify the occupation difference between each occupation in the occupational skill matrix.

[0145] In step S205, for each occupation, based on the skills of the occupation in the occupational skill matrix, a significant difference test strategy is used to identify the significant difference skills, obtain the sub-significant difference set of the occupation, and use the sub-significant difference sets of all occupations as the significant difference sets corresponding to the occupational skill matrix.

[0146] In step S206, the skill difference between each skill of each profession, the occupation difference between each profession, and the significant difference set are used as the similarities and differences feature information between each profession.

[0147] Step S207 , based on the similarities and differences between the characteristic information of each occupation, the first meta-skill in each occupational skill is screened through a dual-threshold determination strategy.

[0148] Step S208, based on the similarities and differences between the characteristic information of each occupation, calculate the stability evaluation results of each skill of each occupation through the coefficient of variation algorithm, and based on the stability evaluation results of each skill, screen the secondary skills in each occupation skill.

[0149] Step S209: construct a meta-skill library based on the first meta-skill in each professional skill and the second meta-skill in each professional skill.

[0150] Step S210 , based on the personal skill profile of the talent and the professional skill profile of each profession, respectively calculate the skill matching degree between the talent and each profession, and the skill gap vector between each skill of the talent and the skills of each profession.

[0151] Step S211, based on the personal skill profile of the talent and the meta-skill library, the meta-skill transfer algorithm is used to calculate the meta-skill transfer index of the talent, and based on the skill gap vector between each skill of the talent and the skills of each profession, the skill gap severity between each skill of the talent and the skills of each profession is calculated respectively through the gap severity algorithm.

[0152] In step S212, the skill matching degree between the talent and each occupation, the skill gap vector between each skill of the talent and the skills of each occupation, the meta-skill transfer index of the talent, and the severity of the skill gap between the talent and each occupation are used as the occupational adaptation information between the talent and each occupation.

[0153] Step S213: Generate a career adaptation sequence for the talent based on the skill matching between the talent and each career, and the talent's meta-skill transfer index.

[0154] Step S214: obtain the industry course library, and based on the skill gap vector between the talent's skills and the skills of each profession, generate the talent's meta-skill improvement list for each profession and the talent's skill optimization suggestions for each profession through the industry course library.

[0155] In step S215, the talent's meta-skill improvement list for each occupation and the talent's skill optimization suggestions for each occupation are filled into the talent's occupational adaptation sequence to generate the talent's occupational transformation adaptation assessment result.

[0156] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0157] Based on the same inventive concept, the embodiments of the present application also provide an AI-based dynamic talent career transformation adaptation device for implementing the aforementioned AI-based dynamic talent career transformation adaptation method. The implementation solution provided by this device is similar to the implementation solution described in the aforementioned method. Therefore, the specific limitations of one or more AI-based dynamic talent career transformation adaptation device embodiments provided below can be found in the limitations of the AI-based dynamic talent career transformation adaptation method above and will not be repeated here.

[0158] In an exemplary embodiment, Figure 3 As shown, a dynamic talent career transformation adaptation device based on artificial intelligence is provided, including: an acquisition module 310, an identification module 320 and a generation module 330, wherein:

[0159] An acquisition module 310 is configured to acquire professional skill profiles of different professions and personal skill profiles of each talent, and construct a professional skill matrix based on the professional skill profiles of each profession;

[0160] An identification module 320 is configured to identify the similarities and differences between the occupations based on the occupational skill matrix, and generate a meta-skill library based on the similarities and differences between the occupations using a meta-skill identification strategy;

[0161] The generation module 330 is used to evaluate the career adaptation information between each talent and each of the careers based on the personal skill profile of the talent and the career skill profile of each of the careers through the meta-skill library, and generate the career conversion adaptation evaluation result of the talent based on the career adaptation information between the talent and each of the careers.

[0162] Optionally, the acquisition module 310 is specifically configured to:

[0163] Perform data preprocessing on the professional skill profiles of each of the occupations to obtain standard professional profiles of each of the occupations;

[0164] Obtain the standard occupational portrait weight information of each occupation, and based on the standard occupational portraits of each of the occupations and the standard occupational portrait weight information of each of the occupations, generate an occupational skill matrix through a sparse matrix construction strategy.

[0165] Optionally, the identification module 320 is specifically configured to:

[0166] Based on the occupational skill matrix, identifying the skill difference between each of the skills for each occupation using a skill difference algorithm, and based on the occupational skill matrix, identifying the occupational difference between each of the occupations in the occupational skill matrix using an occupational similarity algorithm;

[0167] For each occupation, based on the skills of the occupation in the occupational skill matrix, a significant difference test strategy is used to identify the skills with significant differences, thereby obtaining a sub-significant difference set for the occupation, and the sub-significant difference sets of all occupations are used as the significant difference set corresponding to the occupational skill matrix;

[0168] The skill difference between each skill of each profession, the occupation difference between each profession, and the significant difference set are used as the similarities and differences feature information between each profession.

[0169] Optionally, the identification module 320 is specifically configured to:

[0170] Based on the similarities and differences between the occupations, the first meta-skill in each occupational skill is screened through a double-threshold determination strategy;

[0171] Based on the similarities and differences between the occupations, the stability evaluation results of the skills of each occupation are calculated by using a coefficient of variation algorithm, and based on the stability evaluation results of the skills, the secondary skills of each occupation are screened;

[0172] A meta-skill library is constructed based on the first meta-skill in each professional skill and the second meta-skill in each professional skill.

[0173] Optionally, the generating module 330 is specifically configured to:

[0174] Based on the personal skill profile of the talent and the professional skill profiles of each of the professions, respectively calculating the skill matching degree between the talent and each of the professions, and the skill gap vector between each skill of the talent and the skills of each of the professions;

[0175] Based on the individual skill profile of the talent and the meta-skill library, a meta-skill transfer algorithm is used to calculate the talent's meta-skill transfer index. Based on the skill gap vectors between each skill of the talent and the skills of each of the occupations, a gap severity algorithm is used to calculate the skill gap severity between each skill of the talent and the skills of each of the occupations.

[0176] The skill matching degree between the talent and each of the occupations, the skill gap vector between each of the talent's skills and the skills of each of the occupations, the talent's meta-skill transfer index, and the severity of the skill gap between the talent and each of the occupations are used as the occupational adaptation information between the talent and each of the occupations.

[0177] Optionally, the generating module 330 is specifically configured to:

[0178] Generating a career adaptation sequence for the talent based on the skill matching between the talent and each of the careers, and the talent's meta-skill transfer index;

[0179] Obtain an industry course library, and based on the skill gap vectors between the talent's skills and the skills of each of the occupations, generate a meta-skill improvement list for the talent for each occupation and skill optimization suggestions for the talent for each occupation using the industry course library;

[0180] The talent's meta-skill improvement list for each profession and the talent's skill optimization suggestions for each profession are filled into the talent's career adaptation sequence to generate the talent's career transformation adaptation evaluation result.

[0181] Each module in the aforementioned AI-based dynamic talent career transformation adaptation device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0182] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a dynamic talent career transformation adaptation method based on artificial intelligence is realized. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0183] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0184] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps corresponding to the dynamic talent career transformation adaptation method based on artificial intelligence are implemented.

[0185] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements the steps corresponding to the dynamic talent career transformation adaptation method based on artificial intelligence.

[0186] In one embodiment, a computer program product is provided, comprising a computer program that, when executed by a processor, implements steps corresponding to a dynamic talent career transformation adaptation method based on artificial intelligence.

[0187] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0188] It will be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0189] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A dynamic talent career transformation adaptation method based on artificial intelligence, characterized by: The method comprises: Obtain professional skill profiles of different professions and personal skill profiles of each talent, and construct a professional skill matrix based on the professional skill profiles of each profession; Based on the occupational skill matrix, identifying the similarities and differences between the occupations, and generating a meta-skill library based on the similarities and differences between the occupations through a meta-skill identification strategy; For each talent, based on the personal skill profile of the talent and the professional skill profile of each of the professions, the meta-skill library is used to evaluate the professional adaptation information between the talent and each of the professions, and based on the professional adaptation information between the talent and each of the professions, the talent's professional transformation adaptation evaluation result is generated.

2. The method according to claim 1, characterized in that The occupational skill matrix is ​​constructed based on the occupational skill profile of each occupation, including: Perform data preprocessing on the professional skill profiles of each of the occupations to obtain standard professional profiles of each of the occupations; Obtain the standard occupational portrait weight information of each occupation, and based on the standard occupational portraits of each of the occupations and the standard occupational portrait weight information of each of the occupations, generate an occupational skill matrix through a sparse matrix construction strategy.

3. The method according to claim 2, characterized in that The identifying of the similarities and differences between the occupations based on the occupational skill matrix includes: Based on the occupational skill matrix, identifying the skill difference between each of the skills for each occupation using a skill difference algorithm, and based on the occupational skill matrix, identifying the occupational difference between each of the occupations in the occupational skill matrix using an occupational similarity algorithm; For each occupation, based on the skills of the occupation in the occupational skill matrix, a significant difference test strategy is used to identify the skills with significant differences, thereby obtaining a sub-significant difference set for the occupation, and the sub-significant difference sets of all occupations are used as the significant difference set corresponding to the occupational skill matrix; The skill difference between each skill of each profession, the occupation difference between each profession, and the significant difference set are used as the similarities and differences feature information between each profession.

4. The method according to claim 1, wherein The meta-skill library is generated based on the similarities and differences between the occupations through a meta-skill identification strategy, including: Based on the similarities and differences between the occupations, the first meta-skill in each occupational skill is screened through a double-threshold determination strategy; Based on the similarities and differences between the occupations, the stability evaluation results of the skills of each occupation are calculated by using a coefficient of variation algorithm, and based on the stability evaluation results of the skills, the secondary skills of each occupation are screened; A meta-skill library is constructed based on the first meta-skill in each professional skill and the second meta-skill in each professional skill.

5. The method according to claim 1, wherein The evaluation of the career compatibility information between the talent and each of the careers based on the personal skill profile of the talent and the career skill profile of each of the careers through the meta-skills database includes: Based on the personal skill profile of the talent and the professional skill profiles of each of the professions, respectively calculating the skill matching degree between the talent and each of the professions, and the skill gap vector between each skill of the talent and the skills of each of the professions; Based on the individual skill profile of the talent and the meta-skill library, a meta-skill transfer algorithm is used to calculate the talent's meta-skill transfer index. Based on the skill gap vectors between each skill of the talent and the skills of each of the occupations, a gap severity algorithm is used to calculate the skill gap severity between each skill of the talent and the skills of each of the occupations. The skill matching degree between the talent and each of the occupations, the skill gap vector between each of the talent's skills and the skills of each of the occupations, the talent's meta-skill transfer index, and the severity of the skill gap between the talent and each of the occupations are used as the occupational adaptation information between the talent and each of the occupations.

6. The method according to claim 5, characterized in that Generating the career conversion adaptation evaluation result of the talent based on the career adaptation information between the talent and each of the careers includes: Generating a career adaptation sequence for the talent based on the skill matching between the talent and each of the careers, and the talent's meta-skill transfer index; Obtain an industry course library, and based on the skill gap vectors between the talent's skills and the skills of each of the occupations, generate a meta-skill improvement list for the talent for each occupation and skill optimization suggestions for the talent for each occupation using the industry course library; The talent's meta-skill improvement list for each profession and the talent's skill optimization suggestions for each profession are filled into the talent's career adaptation sequence to generate the talent's career transformation adaptation evaluation result.

7. A dynamic talent career transformation adaptation device based on artificial intelligence, characterized by: The device comprises: An acquisition module is used to obtain professional skill profiles of different professions and personal skill profiles of each talent, and to construct a professional skill matrix based on the professional skill profiles of each profession; an identification module for identifying the similarities and differences between the occupations based on the occupational skill matrix, and generating a meta-skill library based on the similarities and differences between the occupations through a meta-skill identification strategy; A generation module is used to evaluate the career adaptation information between each talent and each of the careers based on the personal skill profile of the talent and the career skill profile of each of the careers through the meta-skill library, and generate the career conversion adaptation evaluation result of the talent based on the career adaptation information between the talent and each of the careers.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images