A career planning auxiliary analysis system

Abstract

The present application relates to the technical field of career planning, in particular to a kind of career planning auxiliary analysis system. Including: quantifying user ability vector and interest vector;Real-time labor market data is obtained, the skill demand vector of each occupation and market accommodation index are calculated;Transfer cost is constructed as the edge of career transfer directed graph, and transfer cost is fused between occupations Skill difference and target occupation market accommodation degree;The initial fitness of each occupation node is calculated, and the fitness is obtained by nonlinear synthesis from ability matching degree, interest fit degree and salary;With the maximization of the ratio of cumulative fitness and cumulative transfer cost as the optimization goal, the optimal career migration path is searched under the preset constraint, and the planning report containing transition occupation and the list of skills to be supplemented is output. The present application organically fuses market real-time supply and demand with personal multi-dimensional characteristics, and the generated career migration path has high feasibility and executability.

Description

Technical Field

[0001] This invention relates to the field of career planning technology, and more specifically, to a career planning auxiliary analysis system. Background Technology

[0002] Career planning is the process by which an individual, combining their own characteristics with the external environment, formulates career development goals and designs implementation paths. With increasing competition in the job market and rapid changes in job structures, traditional career planning methods are gradually revealing many limitations.

[0003] Existing career planning tools often rely on static career interest assessments or simple keyword matching, directly mapping users' assessment results to a specific category of recommended jobs without considering the feasibility and costs of migrating from the current job to the target job. In reality, workers often need to go through a series of transitional jobs to reach their ideal job. This migration process requires careful consideration of the overlap in skill requirements between the two jobs, the market supply and demand situation of the target job, and the overall optimization of the migration path. Traditional methods using simple weighted scoring models struggle to accurately express the non-linear interactions between various heterogeneous factors such as ability, interest, and salary, leading to discrepancies between job recommendations and users' actual development potential.

[0004] Furthermore, existing technologies define the costs of inter-occupational transfer in a rather crude manner, typically based solely on the similarity of occupational names or industry classifications, ignoring the quantitative differences in specific skill requirements and failing to incorporate the real-time capacity of the labor market into transfer decisions. This results in generated career paths that are detached from market realities and are difficult to effectively guide users. Simultaneously, existing solutions lack analysis of the supplementary skills required at intermediate nodes along the career migration path, failing to provide specific directions for phased skill enhancement. Summary of the Invention

[0005] The purpose of this invention is to provide a career planning auxiliary analysis system to solve the above-mentioned technical problems.

[0006] To achieve the above objectives, the embodiments of this application provide the following technical solutions: This application provides a career planning auxiliary analysis system, comprising: a career profile construction module, used to receive user-input personal basic data, ability assessment data, and interest assessment data, and output a user ability vector representing the user's multidimensional ability level and a user interest vector representing the user's multidimensional interest tendency; a market analysis module, used to acquire real-time labor market occupational data, extract the skill demand vector, average salary, number of job openings, and number of job openings for each occupation, and calculate the market capacity index for that occupation, wherein the skill demand vector is a vector representation of the various skills required for that occupation and their importance, and the market capacity index reflects the supply and demand tension in the labor market for that occupation; and a graph construction module, connected to the market analysis module, used to determine the transfer difficulty index of directed edges based on the difference between the skill demand vectors of any two occupations, using occupations as nodes, and correcting the transfer difficulty index using the market capacity index of the target occupation node, thereby obtaining... The system calculates the transfer cost and then constructs a career transfer graph. A fitness calculation module, connected to the career profile construction module, market analysis module, and graph construction module, is used to perform nonlinear synthesis on each career node in the career transfer graph, considering the matching degree between the user's ability vector and skill demand vector, the fit between the user's interest vector and the preset interest tags for that career, and the average salary of that career, to generate the initial fitness of that career node. A path planning module, connected to the fitness calculation module and the graph construction module, is used to search for the career migration path that maximizes the ratio of cumulative fitness to cumulative transfer cost, starting from the user's current career node and based on the initial fitness of each career node and the transfer cost on the edges, under preset constraints. This path is designated as the optimal career migration path. A report generation module, connected to the path planning module, is used to generate a career planning report based on the node sequence and node attributes on the optimal career migration path.

[0007] Optionally, the market analysis module calculates the market capacity index for occupation j. The method is as follows: ; Where k is the preset steepness coefficient. The number of people needed for occupation j The number of people supplying occupation j.

[0008] Optionally, the map construction module calculates the transition cost from occupation i to occupation j. for: ; in, Let ρ be the transfer difficulty index determined by the cosine distance between the skill demand vectors of occupation i and occupation j, and let ρ be the preset market penalty coefficient. The market capacity index of occupation j is output by the market analysis module.

[0009] Optionally, the fitness calculation module generates the initial fitness of occupation node j. The formula for calculation is: ; in, Skill demand vector With user capability vector cosine similarity, For average salary The value after normalization to the maximum and minimum values, User interest vector With the preset interest label vector of occupation j cosine similarity, Adjust the weights for preferences.

[0010] Optionally, the path planning module adopts the A* search algorithm, whose cost function is the actual cumulative transfer cost from the starting point to the current node, and the heuristic function is the estimated value of the ratio of the maximum possible remaining fitness to the minimum possible remaining transfer cost from the current node to the target node set. The preset constraints include: the total transfer cost does not exceed the maximum investment budget set by the user, and the number of path nodes does not exceed the preset maximum number of career jumps.

[0011] Optionally, the report generation module is further configured to mark intermediate occupational nodes in the optimal occupational migration path, excluding the starting point and the ending point, as transitional occupations, calculate the difference vector between the user's ability vector and the skill requirement vector of the transitional occupation, and output a list of skills to be supplemented corresponding to each transitional occupation.

[0012] Optionally, the professional profile building module includes a pre-trained word embedding model for converting the user's input work experience text and online assessment results into a fixed-dimensional ability score vector, which serves as the user's ability vector.

[0013] The beneficial effects of this invention are as follows: This invention constructs a career transfer map that integrates a market capacity index. The transfer difficulty is determined by calculating the differences in skill demand vectors between occupations, and this difficulty is then adjusted using a market capacity index calculated based on real-time supply and demand data, thus forming a transfer cost. This definition ensures that the career transfer cost not only reflects skill gaps but also the ease of entry into the target occupation. The generated career migration paths are more aligned with the actual labor market situation, improving the feasibility of the planning.

[0014] Secondly, this invention uses a nonlinear synthesis method to generate the initial fitness of occupation nodes. It combines the matching degree of user ability vector, the fit of user interest vector, and average salary logarithmically and weighted, overcoming the shortcomings of simple linear weighting in reflecting the synergistic or saturation effects between factors. This makes the fitness value more realistically reflect the comprehensive attractiveness and suitability of the occupation to the user.

[0015] Secondly, this invention uses the ratio of cumulative fitness to cumulative transfer cost as the optimization objective and applies a path search algorithm to find the optimal career migration path under preset constraints. Compared to methods that only maximize the fitness of the final career or independently optimize single-step transitions, this solution can automatically balance long-term returns and migration costs, outputting a step-by-step development sequence that includes intermediate transitional careers. This upgrades career planning from a static "point-to-point" recommendation to a dynamic "trajectory" optimization.

[0016] Furthermore, when generating reports, this invention automatically provides a list of skills that need to be supplemented by calculating the difference between the user's ability vector and the transitional career skill requirement vector, thus providing users with clear directions for phased ability improvement and further enhancing the practical guidance value of career planning.

[0017] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the structure of a career planning auxiliary analysis system as described in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0021] Example:

[0022] like Figure 1 As shown in the figure, this embodiment provides a career planning auxiliary analysis system, the system including: The professional profile building module receives user-inputted basic personal data, ability assessment data, and interest assessment data, and generates user ability vectors and user interest vectors accordingly. Basic personal data includes, but is not limited to, age, education, current occupation, and years of work experience; ability assessment data originates from standardized vocational skills test scores or online evaluation results; and interest assessment data is obtained through a career interest scale. This module integrates a pre-trained word embedding model, which transforms unstructured work experience text such as resumes and project descriptions into dense numerical vectors. Specifically, key terms and vocational skills vocabulary in the work experience are mapped to a high-dimensional semantic space, and the weighted average of the word vectors is taken as the semantic vector of the text. This is then adjusted through a linear mapping layer to form a fixed-dimensional ability score vector. Simultaneously, structured assessment scores are directly filled into the corresponding ability dimensions. The fusion of these two results in a comprehensive user ability vector, with each dimension representing the quantitative level of a specific ability item. The user interest vector is composed of the projection combination of interest assessment scores into a multi-dimensional interest space, with each dimension corresponding to a type of career interest.

[0023] Optionally, the learning efficiency coefficient of the user can be further extracted in the career profile construction module described in this embodiment. This coefficient can be calculated by comprehensively considering the user's educational background, historical training records, cognitive ability assessment scores, and actual time spent on past career transitions. When calculating the transfer difficulty index, the graph construction module no longer directly applies the cosine distance of the skill demand vector, but instead first performs personalized scaling on the difference in the skill demand vector. Specifically, for each skill dimension, if the user already has a strong foundation or a high learning efficiency coefficient, the difference in that dimension is multiplied by a decay factor less than 1, which means that the user can quickly make up for it through short-term learning, and the actual transfer difficulty is reduced. Conversely, the difference weight of skill dimensions with low learning efficiency remains unchanged or is amplified. The norm or cosine distance of the scaled difference vector is then calculated to obtain the personalized transfer difficulty index. Finally, the transfer cost is combined with the market capacity index to realize the migration cost estimation from "group average" to "individualized", which greatly improves the fit between path planning and individual actual situation.

[0024] The market analysis module connects to an external labor market database to acquire real-time labor market occupational data at set intervals. For each occupation, this module extracts its skill demand vector, average salary, number of openings, and number of job seekers. The skill demand vector is a multi-dimensional vector, with dimensions consistent with the user's ability vector. The value of each dimension represents the intensity of the requirement for that skill in that occupation, typically obtained based on the frequency and weight of skill keywords in job postings. The number of openings represents the number of job vacancies posted by employers for that occupation within the statistical period, while the number of job seekers represents the number of active job seekers in that occupational field during the same period.

[0025] Optionally, the market analysis module in this embodiment also includes a time-series forecasting submodule. The time-series forecasting submodule continuously collects time-series data on the number of people demanding and supplying each occupation, and uses time-series forecasting algorithms (such as trend- and seasonal decomposition-based forecasting models, or neural network forecasters) to generate forecasts of demand and supply for a preset future time period. Based on this, it calculates the expected market capacity index for each occupation. The formula is formally the same as the original market capacity index, but replaces the real-time demand and supply with the expected demand and supply at the end of the forecast period. During path planning, the graph construction module can use the expected market capacity index to adjust the transfer cost. Specifically, the market capacity index in the transfer cost calculation formula is replaced with a weighted fusion value of the current market capacity index and the expected market capacity index, with the weight determined by the user-defined planning forward-looking coefficient. Therefore, when the target occupation is predicted to become saturated in the future, even if the current market is still relatively healthy, the transfer cost will be appropriately increased, thereby guiding users to avoid occupational nodes that are about to become crowded, enhancing the predictability of the planning.

[0026] The core of the market analysis module lies in calculating the market absorption index for each occupation, which quantifies the occupation's potential to absorb new workers. The market absorption index uses a logistic function to non-linearly map the supply-demand ratio; the market absorption index for occupation j... The calculation formula is: ; Where k is a preset steepness coefficient, a positive constant used to adjust the sensitivity of the index near the supply-demand equilibrium point. The number of people needed for occupation j The number of people supplying occupation j.

[0027] When demand exceeds supply, (demand / supply - 1) is positive, the index approaches 1, indicating a labor shortage and low entry barriers for the occupation. When demand is less than supply, the difference is negative, the index approaches 0, indicating intense competition and difficulty in entry. When the two are equal, the index is 0.5. Thus, the market capacity index continuously and smoothly reflects the tightness of supply and demand in the labor market.

[0028] The market absorption index quantifies the potential of a particular occupation to absorb new workers. This formula uses a logistic function to non-linearly map the supply-demand ratio, with the independent variable being the ratio of demand to supply minus 1, representing the degree to which supply and demand deviate from the equilibrium point. When demand exceeds supply, the independent variable is positive, and the index approaches 1, indicating a low entry barrier; when demand is less than supply, the independent variable is negative, and the index approaches 0, indicating intense competition. This function is continuous and smooth, avoiding abrupt changes caused by hard threshold judgments, and can delicately reflect continuous changes in market supply and demand tension. The steepness coefficient controls the sensitivity of the function near the equilibrium point; the larger the coefficient, the sharper the index's response to changes in supply and demand.

[0029] The graph construction module uses all available professions as nodes to build a fully connected directed profession transition graph. The directed edges between nodes represent possible paths for a profession transition from the starting profession to the target profession. Each edge carries a transition cost, which is used to measure the overall difficulty of the transition step.

[0030] Determining the transfer cost involves two steps. First, calculate the transfer difficulty index between any two occupations. Taking occupations i and j as an example, calculate the cosine distance between their skill requirement vectors, which is 1 minus the cosine similarity. The cosine similarity is the ratio of the dot product of two vectors to the product of their magnitudes. The cosine distance ranges from 0 to 2; a larger value indicates a greater difference in the skills required by the two occupations, and thus a higher transfer difficulty. Second, adjust the transfer difficulty index using the market capacity index of the target occupation j to obtain the transfer cost from occupation i to occupation j. The calculation formula is: ; in, Let ρ be the transfer difficulty index determined by the cosine distance between the skill demand vectors of occupation i and occupation j, and let ρ be the preset market penalty coefficient. The market capacity index of occupation j is output by the market analysis module.

[0031] The market penalty coefficient is positive, used to amplify the obstacles caused by market saturation in the target occupation. When the market capacity index of occupation j is close to 1, the term in parentheses is close to 1, the transfer cost is approximately equal to the transfer difficulty index, and there is almost no market penalty. When the market capacity index is close to 0, the term in parentheses is 1 + the market penalty coefficient, the transfer cost is significantly amplified, indicating that even if the skill difference is not significant, entering a saturated occupation still requires a high switching cost. Thus, the transfer cost simultaneously incorporates information on both ability gaps and market conditions.

[0032] The transfer cost measures the overall difficulty of migrating from one occupation to another. This formula includes two factors: the first is a transfer difficulty index, determined by the cosine distance between the skill requirement vectors of the two occupations, measuring the objective difference in required abilities; the second is a market penalty factor, expressed as "1 plus the market penalty coefficient multiplied by (1 minus the target occupation market capacity index)," adjusting the transfer difficulty upwards. When the target occupation market capacity index is low, the penalty factor increases, indicating that even with similar skill differences, entering a saturated market requires a higher cost. The market penalty coefficient controls the strength of market influence. This formula integrates ability gaps and market conditions through a product, achieving a unified quantification of dual constraints.

[0033] The fitness calculation module calculates the initial fitness of each occupation node in the occupational transfer graph for the user, representing the overall attractiveness of the occupation as an independent goal. To overcome the drawback of simple linear weighting which easily ignores the nonlinear relationships between factors, this module adopts a logarithmic-weighted nonlinear synthesis strategy.

[0034] Specifically, first, the ability matching degree is calculated, which is the cosine similarity between the user's ability vector and the skill requirement vector of occupation j, resulting in a value between 0 and 1. Next, the average salary is normalized by applying maximum and minimum values ​​to eliminate dimensional differences, resulting in a normalized salary, also between 0 and 1. Then, the interest fit degree is calculated, which is the cosine similarity between the user's interest vector and the preset interest label vector of occupation j, again with a value between 0 and 1. The preset interest label vector is determined based on the typical interest distribution of practitioners in this occupation. Finally, the above three indicators are synthesized using the following formula: ; in, Skill demand vector With user capability vector cosine similarity, For average salary The value after normalization to the maximum and minimum values, User interest vector With the preset interest label vector of occupation j cosine similarity, The preference adjustment weight is an adjustable constant between 0 and 1, which can be specified by the user or defaulted to by the system, and is used to express the relative importance that the user attaches to salary and interests.

[0035] In the formula, the logarithmic term ln(1 + ability matching degree) = ( The non-linear compression of ability matching reflects the diminishing marginal returns of ability improvement: when the ability matching is high, the contribution of further ability improvement to fitness tends to level off, and the guiding algorithm will not excessively favor jobs that perfectly match current abilities, but will also consider growth potential. The values ​​in square brackets represent a weighted combination of salary and interest, dynamically adjusted through preference weights. Multiplying these two factors allows the ability dimension to play an overall regulatory role in fitness: even for high-paying, highly interesting jobs, fitness will be suppressed if the user's abilities do not match.

[0036] Initial fitness represents the overall attractiveness of a particular profession to a user. This formula consists of two multipliers: the first multiplier is the logarithm of the natural logarithm term "1 plus the logarithm of ability matching," which non-linearly compresses the ability matching degree. As the ability matching degree increases, the growth of this term gradually slows down, reflecting the diminishing marginal returns of ability improvement and preventing the algorithm from excessively favoring professions that perfectly match the user's current abilities, thus preserving some room for growth. The second multiplier is a linearly weighted combination of salary and interest, expressing the user's relative emphasis on these two factors through preference weights. Multiplying these two factors allows ability factors to play a global moderating role in fitness: even with high salaries and matching interests, if the ability gap is too large, fitness will still be suppressed, ensuring the comprehensiveness and rationality of the evaluation results.

[0037] Optionally, in the above basic fitness formula, the logarithmic compression coefficient of ability matching is fixed, without distinguishing between different occupations and ability types. This embodiment further introduces a skill scarcity factor and a user age influence factor to dynamically adjust the fitness synthesis. Specifically, when the market analysis module statistically analyzes the skill demand for each occupation, it also calculates the scarcity index of each skill dimension, i.e., the rarity of the skill among the total number of people in the market. When calculating the ability matching degree, the fitness calculation module multiplies each dimension value in the skill demand vector by the corresponding scarcity index and then performs a similarity calculation with the user ability vector, so that occupations with scarce skills contribute more to the user's fitness, encouraging users to migrate to high-barrier, high-value directions. At the same time, an age influence factor is introduced, which is used in the form of a natural index or a linear piecewise function to adjust the relative proportion of salary and interest in the preference weights. For example, the younger the age, the higher the weight of interest matching, encouraging early exploration; the higher the age, the greater the weight of salary and stability-related factors, and the preference weights in the fitness formula dynamically and adaptively change with the user's age. This design dynamically matches career planning with the user's current career stage, resulting in more reasonable recommendations.

[0038] The path planning module receives the career transfer graph and the transfer cost of each edge output by the graph construction module, as well as the initial fitness of each node output by the fitness calculation module. By solving a constrained optimization problem, it determines the optimal career migration path from the user's current career node to the potential target node.

[0039] The path planning employs a heuristic graph search algorithm (such as the A* search algorithm). Taking the current job node as the starting point, the optimization objective for any path is defined as "maximizing the ratio of cumulative fitness to cumulative transition cost". Cumulative fitness is the sum of the initial fitnesss of the job nodes traversed by the path, and cumulative transition cost is the sum of the transition costs of all directed edges on the path. For efficient searching, the algorithm calculates an evaluation function for each state node, which consists of the cost already paid and the estimated remaining potential. The cost already paid is the actual cumulative transition cost from the starting point to the current node, while the estimated remaining potential is heuristically estimated, for example, using the ratio of the minimum lower bound of the transition cost from the current node to a potentially reachable high-fitness region as the denominator and the maximum remaining fitness as the numerator as a heuristic value. During the search process, a priority queue is maintained, prioritizing the expansion of nodes with the optimal evaluation function until the preset target node set is reached or the search is completed.

[0040] The search is also subject to preset constraints: first, the total transfer cost cannot exceed the user's maximum investment budget, which can be converted into input by the user in the system in the form of time or economic costs; second, the number of nodes in the path cannot exceed the preset maximum number of career jumps, in order to avoid excessively long migration chains that increase real-world uncertainty. By adjusting the maximum number of jumps and the investment budget, career planning strategies of varying degrees of aggressiveness can be generated.

[0041] Optionally, the above scheme uses the ratio of cumulative fitness to cumulative migration cost as a single optimization objective. In actual decision-making, users often need to consider the robustness and risk of the path. This embodiment can also upgrade path planning to a multi-objective optimization framework. In addition to the original ratio objective, a path stability index is introduced, defined as the variance of the market capacity index of each occupation on the path or the negative value of the information entropy, used to measure the degree of market environment fluctuation during migration. The path planning module uses a Pareto optimal multi-objective search algorithm (such as multi-objective A* or non-dominated ranking evolutionary algorithm) to generate a set of non-dominated occupation migration path solutions. Each path achieves different trade-offs between maximizing returns, minimizing costs, and stability. The system presents the Pareto front to the user through a graphical interface. The user can drag the slider or click on the area to select the preferred trade-off scheme in real time, and the system will immediately highlight the corresponding optimal path. This mechanism incorporates the user's subjective preferences into the final decision of multi-dimensional optimization, avoiding the uniformity caused by preset weights, and significantly improving the applicability of the planning scheme and user satisfaction.

[0042] Ultimately, the algorithm outputs a sequence of nodes that satisfies the constraints and maximizes the target ratio, representing the optimal career migration path. This path may contain several intermediate career nodes, serving as transitional careers before reaching the ideal career.

[0043] After obtaining the optimal career migration path, the report generation module parses the node sequence into a highly readable career planning report. The report lists the target careers for each stage in sequence, indicating the average salary, expected market conditions, and required key skills for each career.

[0044] Meanwhile, the report generation module marks all occupational nodes in the path, excluding the starting and ending points, as transitional occupations. For each transitional occupation, it calculates the difference vector between the user's ability vector and the skill requirement vector for that occupation. Positive components in the difference vector represent skills that the user currently lacks or has not yet met the requirements for. The module extracts these skills and sorts them according to the magnitude of the difference, generating a list of skills that need to be supplemented for each transitional occupation. Users can then use this list to conduct targeted learning and training in stages to reduce resistance during actual migration.

[0045] In addition, the report can include the total transfer cost and cumulative fitness value for the entire path, serving as a quantitative reference for horizontal comparison between different planning schemes and assisting users in making decisions.

[0046] Through the synergy among the modules mentioned above, this method organically integrates career interests, ability structure, salary incentives, and external market demand, and quantifies the real obstacles to career transition by using transfer costs. This generates a progressive optimal trajectory from the current career to the ideal career, achieving an upgrade from static recommendation to dynamic path planning.

[0047] This embodiment constructs an occupational transfer map that integrates a market capacity index. The transfer difficulty is determined by calculating the differences in skill demand vectors between occupations, and this difficulty is then adjusted using a market capacity index calculated based on real-time supply and demand data, thus forming the transfer cost. This definition ensures that the occupational transfer cost not only reflects skill gaps but also the ease of entry into the target occupation. The generated occupational migration paths are more consistent with the actual labor market situation, improving the feasibility of the plan.

[0048] Secondly, this invention uses a nonlinear synthesis method to generate the initial fitness of occupation nodes. It combines the matching degree of user ability vector, the fit of user interest vector, and average salary logarithmically and weighted, overcoming the shortcomings of simple linear weighting in reflecting the synergistic or saturation effects between factors. This makes the fitness value more realistically reflect the comprehensive attractiveness and suitability of the occupation to the user.

[0049] Secondly, this embodiment uses the ratio of cumulative fitness to cumulative transfer cost as the optimization objective and applies a path search algorithm to find the optimal career migration path under preset constraints. Compared to methods that only maximize the fitness of the final career or independently optimize single-step transitions, this solution can automatically balance long-term returns and migration costs, outputting a step-by-step development sequence that includes intermediate transitional careers. This upgrades career planning from a static "point-to-point" recommendation to a dynamic "trajectory" optimization.

[0050] Furthermore, when generating the report, this embodiment automatically provides a list of skills that need to be supplemented by calculating the difference between the user's ability vector and the transitional career skill requirement vector, providing users with clear directions for phased ability improvement and further enhancing the practical guidance value of career planning.

[0051] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A career planning auxiliary analysis system, characterized in that, The system includes: The professional profile building module is used to receive basic personal data, ability assessment data and interest assessment data input by users, and output user ability vectors that represent the user's multidimensional ability level and user interest vectors that represent the user's multidimensional interest tendencies. The market analysis module is used to acquire real-time labor market occupational data, extract the skill demand vector, average salary, number of job openings and supply for each occupation, and calculate the market capacity index for that occupation. The skill demand vector is a vector representation of the various skills required for that occupation and their importance, and the market capacity index reflects the supply and demand tension in the labor market for that occupation. The graph construction module, connected to the market analysis module, is used to determine the transfer difficulty index of directed edges based on the difference between the skill demand vectors of any two occupations, with occupations as nodes, and to correct the transfer difficulty index using the market capacity index of the target occupation node to obtain the transfer cost, thereby constructing an occupation transfer graph. The fitness calculation module is connected to the occupational profile construction module, the market analysis module, and the graph construction module, respectively. It is used to perform nonlinear synthesis of the matching degree between the user's ability vector and skill demand vector, the fit between the user's interest vector and the preset interest tags of the occupation, and the average salary of the occupation for each occupational node in the occupational transfer graph, to generate the initial fitness of the occupational node. The path planning module, connected to the fitness calculation module and the graph construction module, is used to search for the career migration path that maximizes the ratio of cumulative fitness to cumulative transfer cost, starting from the user's current career node and based on the initial fitness of each career node and the transfer cost on the edges, under preset constraints, as the optimal career migration path. The report generation module, connected to the path planning module, is used to generate a career planning report based on the node sequence and node attributes on the optimal career migration path.

2. The career planning auxiliary analysis system according to claim 1, characterized in that, The market analysis module calculates the market tolerance index for occupation j. The method is as follows: ； Where k is the preset steepness coefficient. The number of people needed for occupation j The number of people supplying occupation j.

3. The career planning auxiliary analysis system according to claim 2, characterized in that, The map construction module calculates the transfer cost from occupation i to occupation j. for: ； in, Let ρ be the transfer difficulty index determined by the cosine distance between the skill demand vectors of occupation i and occupation j, and let ρ be the preset market penalty coefficient. The market capacity index of occupation j is output by the market analysis module.

4. The career planning auxiliary analysis system according to claim 3, characterized in that, The fitness calculation module generates the initial fitness of occupational node j. The formula for calculation is: ； in, Skill demand vector With user capability vector cosine similarity, For average salary The value after normalization to the maximum and minimum values, User interest vector With the preset interest label vector of occupation j cosine similarity, Adjust the weights for preferences.

5. The career planning auxiliary analysis system according to claim 4, characterized in that, The path planning module uses the A* search algorithm, whose cost function is the actual cumulative transfer cost from the starting point to the current node, and the heuristic function is the estimated ratio of the maximum possible remaining fitness to the minimum possible remaining transfer cost from the current node to the target node set. The preset constraints include: the total transfer cost does not exceed the maximum investment budget set by the user, and the number of path nodes does not exceed the preset maximum number of career jumps.

6. The career planning auxiliary analysis system according to claim 5, characterized in that, The report generation module is also used to mark intermediate career nodes in the optimal career migration path, excluding the starting point and the ending point, as transitional careers, and to calculate the difference vector between the user's ability vector and the skill requirement vector of the transitional career, and output a list of skills to be supplemented for each transitional career.

7. The career planning auxiliary analysis system according to claim 6, characterized in that, The professional profile building module includes a pre-trained word embedding model, which is used to transform the user's input work experience text and online assessment results into a fixed-dimensional ability score vector, which serves as the user's ability vector.

Images