Artificial intelligence-based career planning information processing method and system, electronic device and storage medium

Abstract

The application discloses a kind of based on artificial intelligence's career planning information processing method, system, electronic equipment and storage medium, is related to artificial intelligence and natural language processing technical field.The method includes: obtaining user input information and parsing generation structured user ability information;Based on post knowledge base, post matching candidate post is generated;From at least two evaluation dimensions, human post quantitative matching is generated to generate matching result;According to matching result, generate career path and stage action plan;According to preset template, generate career development report;And after report generation, based on the dialogue information supplemented by user, dynamically revise matching result and / or career path and / or stage action plan.The application improves the accuracy, explainability and executability of career planning matching by fusing real post data, standard post portrait and large language model reasoning.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and natural language processing, and in particular to a career planning information processing method, system, electronic device and storage medium based on artificial intelligence. Background Technology

[0002] With the continuous increase in the number of college graduates and increasingly fierce job competition, career planning has become an indispensable and important part of the higher education system. Job seekers, represented by college students, generally face multiple difficulties in career planning: unclear self-awareness, making it difficult to transform coursework, internship experiences, and skill combinations into a structured competency profile; scattered sources of job information, lacking a systematic reference to the actual requirements of corporate positions; limited university career guidance resources, making it difficult to meet the large-scale demand for personalized consultation; and planning schemes often remaining at the level of general suggestions, lacking implementable phased action plans and traceable matching evidence. These factors cause many students' career planning to become merely a formality, failing to effectively guide their job search practice.

[0003] Currently, there are three main types of career planning support tools for job seekers. First, traditional career assessment systems often use standardized questionnaires to evaluate personality and career inclinations. Their drawbacks include fixed questionnaire dimensions, inability to analyze personalized user experiences, and a disconnect between assessment results and specific job requirements. Second, rule-based resume analysis systems compare user experience with job requirements through keyword matching. However, keyword matching struggles to handle synonyms, semantic generalization, and cross-domain skill transfer, resulting in low accuracy and a lack of interpretable evidence for matching conclusions. Third, career counseling solutions based on large language models, while generating relatively fluent text suggestions, suffer from "illusion" problems such as inaccurate job recommendations, overgeneralized skills gap analysis, and a lack of industry evidence for career development paths due to the lack of real-world job data constraints and standard job profile benchmarks. The suggestions often remain vague. Furthermore, some existing solutions still focus on one-time information collection and report generation. After report generation, it's difficult to incorporate user-supplemented information to form subsequent evaluation suggestions, lacking the iterative optimization capabilities required in career counseling.

[0004] Therefore, how to integrate personalized user experience data, real job samples, and standard job profiles to achieve a career planning assistance solution with interpretable matching results, executable paths, and continuously optimized evaluation is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] To address these issues, this invention provides an artificial intelligence-based method, system, electronic device, and storage medium for processing career planning information. These solutions resolve technical problems in existing career planning schemes, such as inaccurate job matching, unenforceable generalized suggestions, and difficulty in incorporating user-supplemented information to form subsequent evaluation recommendations, all stemming from a lack of real job data constraints and dynamic interaction mechanisms.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a career planning information processing method based on artificial intelligence. This method schedules multiple processing nodes to execute via a state diagram workflow, including: Obtain user input information, which includes natural language descriptions and / or resume files; The user input information is parsed to generate structured user capability information; The user's career goal type is determined based on the structured user ability information, and job matching is performed based on the pre-established job knowledge base and the career goal type to generate candidate jobs; After receiving information from the user’s selection or confirmation of the target position, the structured user ability information is quantitatively matched with the confirmed target position from four evaluation dimensions: basic requirements, professional skills, professional qualities, and development potential, and a person-job matching result is generated. Based on the job matching results, a career path and phased action plan are generated. Generate a career development report according to a preset template; After the career development report is generated, supplementary dialogue information from the user is obtained. Based on the current career development report, structured user ability information, job matching results, and career path, supplementary evaluation results are generated. Upon receiving the user's report update instruction, the supplementary evaluation results are added to the career development report.

[0007] Preferably, parsing the user input information to generate structured user capability information includes: The resume file is parsed, and the parsed resume text is merged with the natural language description input by the user into a text to be processed. Based on the prompt template corresponding to the information extraction node, the large language model is invoked to extract structured information from the text to be processed, thereby obtaining initial capability information. Based on the rule compensation strategy, the missing fields in the initial capability information are supplemented and identified. The rule compensation strategy includes at least one of regular expression matching, keyword dictionary matching, and time information parsing. According to the preset data structure, the initial capability information and the supplementary identification results are merged and the structure is verified to generate the structured user capability information; The structured user capability information includes multiple aspects such as professional information, education level or grade level, job intention information, technical skills information, project experience information, internship experience information, certificate and honor information, learning ability information, communication ability information, innovation ability information, and stress resistance information.

[0008] Preferably, the job knowledge base includes a real job sample library, a standard job profile library, and an extended job reference library; The real job sample database contains job records composed of enterprise recruitment data, and each job record includes at least the job title, job description and job skill requirements. The standard job profile database includes job title, job alias, professional skill requirements, certificate requirements, professional ethics requirements, vertical development path information, and horizontal job transfer path information; The expanded job reference library contains job profiles that are not fully covered by the real job sample library, and records the source and confidence level of the profiles; The step of determining the user's career goal type based on the structured user ability information and performing job matching based on a pre-established job knowledge base and the career goal type includes: The user's career goal type is determined based on the structured user capability information; When a user has a specific career goal, that career goal will be used as the target for matching. When a user only has a job category or job field, candidate positions are generated within the corresponding job category; When a user does not have a target job, candidate jobs are generated based on their major, skills, project experience, internship experience, and the job intention information entered by the user. Perform alias matching, keyword matching, and / or semantic similarity matching on job titles to obtain a baseline job profile; Based on the benchmark job profile, keyword retrieval and / or vector semantic retrieval are performed in the real job sample database to recall relevant job samples. Based on the baseline job profile, relevant job samples, extended job reference profiles, and the confidence level of the job profiles, candidate jobs are generated, and information from the user to select or confirm the target job from the candidate jobs is received. Each candidate position should include at least the position name, matching score, confidence level, reason for recommendation, matched skills, skills to be added, data source identifier and / or position evidence information.

[0009] Preferably, the quantitative matching of personnel to positions includes: Scores are calculated based on the consistency of educational background, professional background, and job application intentions across the basic requirements dimensions. The professional skills dimension score is calculated based on the degree of overlap between technical skills, tool frameworks, project experience, and the core skills of the target position. Scores for the professional competence dimension are calculated based on learning ability, communication and collaboration skills, and resilience. A score for the development potential dimension is calculated based on learning ability, innovation ability, and job matching score. The overall matching score is calculated according to the preset dimension weights, where the sum of the weights of each dimension is 1; When any evaluation dimension lacks valid experience information, an insufficient evidence flag is set for that evaluation dimension, and a preset neutral value is used or the score of that evaluation dimension is limited. The job matching results include a comprehensive matching score, scores for each evaluation dimension, dimension explanation information, matching highlights, key gaps, matched skills, and skills to be supplemented.

[0010] Preferably, the career path includes a vertical development path and a horizontal job-changing path; The vertical development path generates a path from the target position to senior positions, technical expert positions, and / or management positions based on the job hierarchy in the standard job profile library. The horizontal job transfer path generates a path from the target job to a related technical field or a transferable job based on the skill association and ability transfer relationship between jobs. The career path also includes target positions, vertically developed positions, horizontally transferable positions, and corresponding skills enhancement suggestions. The phased action plan is generated based on the key gaps in the person-job matching results and includes short-term action plans, medium-term action plans, learning tasks, practical tasks, expected results, evaluation cycle, and evaluation indicators.

[0011] Preferably, the career development report includes chapters on career exploration and job matching, career goals and path planning, phased action plans, dynamic evaluation and adjustment, and personalized messages. In response to a user's report export request, a completeness check is performed on the career development report to be exported to determine whether the report includes key information, including target position, matching score, skills gap, phased action plan and evaluation cycle; When the key information is missing, output the integrity check result and corresponding information supplementation prompts; After the integrity check is passed, an editable and / or exportable career development report is output.

[0012] Preferably, the step of obtaining supplementary dialogue information from the user, and generating supplementary evaluation results based on the current career development report, structured user ability information, job-person matching results, and career path, includes: The current career development report, structured user ability information, job matching results, career path, and user-supplemented dialogue information are combined to form a follow-up question context, and a large language model is invoked based on the follow-up question context to generate natural follow-up question content. Obtain the user's answers to the natural follow-up questions, and perform intent recognition and information content evaluation on the user's answers; When the user's answer contains project responsibilities, internship responsibilities, technology stack usage, quantifiable results, job selection motivation, or other valid supplementary information, the answer is recorded; when the preset termination condition is met, a supplementary evaluation result is generated based on the recorded answer; when the preset termination condition is not met, the next natural follow-up question is generated. When the amount of information provided by the user's answer is lower than a preset threshold, alternative follow-up questions are generated to guide the user to supplement specific experiences, personal responsibilities, technical details, or quantitative results. When a user requests a change of question, an alternative follow-up question is generated. When no effective large language model output is obtained, a preset fallback strategy is used to generate alternative follow-up questions. When the preset number of follow-up questions is reached or when the user's instruction to end the follow-up questions is received, the follow-up questions are terminated and supplementary evaluation results are generated.

[0013] This invention also provides an artificial intelligence-based career planning information processing system, comprising: The system includes the following modules: an input parsing module for acquiring user input information, including natural language descriptions and / or resume files; a competency information processing module for parsing the user input information and generating structured user competency information; a job matching module for determining the user's career goal type based on the structured user competency information, performing job matching based on a pre-established job knowledge base and the career goal type, generating candidate jobs, and receiving the user's selection or confirmation of a target job; a person-job matching module for quantitatively matching the structured user competency information with the confirmed target job from four evaluation dimensions: basic requirements, professional skills, professional qualities, and development potential, generating a person-job matching result; a career path planning module for generating a career path and phased action plan based on the person-job matching result; and a report generation module for generating a career development report according to a preset template. The supplementary assessment module is used to obtain supplementary dialogue information from the user after the career development report is generated, generate supplementary assessment results based on the current career development report, structured user ability information, job matching results, and career path, and add the supplementary assessment results to the career development report after receiving the user's report update instruction.

[0014] This invention also provides an electronic device, which includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the aforementioned artificial intelligence-based career planning information processing method.

[0015] This invention also provides a computer storage medium storing a computer software product, the computer software product including several instructions to cause a computer device to execute the aforementioned artificial intelligence-based career planning information processing method.

[0016] As can be seen from the above technical solutions, this invention application has the following beneficial effects: First, it improves the accuracy and interpretability of job matching. This invention constructs a three-layer job knowledge base comprising a real job sample database, a standard job profile database, and an extended job reference database. Combined with a retrieval enhancement mechanism, it performs job matching, providing traceable evidence of real data sources for candidate job recommendations, skills gap analysis, and matching scores. This effectively reduces the risk of illusions caused by the lack of real job data constraints in large language models, and improves the accuracy and credibility of matching results.

[0017] Second, it enables quantifiable, multi-dimensional person-job matching assessment. This invention quantifies person-job matching from four dimensions: basic requirements, professional skills, professional qualities, and development potential. It generates matching scores, matching highlights, and key gap information for each dimension, allowing users to intuitively understand their degree of matching and specific gaps with the target position in various aspects. This avoids the problems of generalized matching results and lack of interpretability in traditional solutions.

[0018] Third, it supports dynamic iteration and optimization of assessment results. After the career development report is generated, this invention obtains supplementary dialogue information from the user, generates supplementary assessment results, and adds the supplementary assessment results to the career development report upon receiving the user's report update instruction, significantly improving the continuous optimization capability and user acceptance of career planning assessment. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Referring to the drawings will make the features and advantages of the present invention clearer. The drawings are illustrative and should not be construed as limiting the present invention in any way. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a flowchart of a career planning information processing method based on artificial intelligence provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating the generation of structured user capability information in an embodiment of the present invention; Figure 3 This is a flowchart of a process for matching structured user competency information with job requirements based on a pre-established job knowledge base, as described in an embodiment of the present invention. Figure 4 This is a flowchart of the dynamic supplementary evaluation process in an embodiment of the present invention; Figure 5 This is a block diagram of a career planning information processing system based on artificial intelligence, provided 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 embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Example 1: To address the technical problems in existing career planning schemes, such as inaccurate job matching, unenforceable generalized suggestions, and difficulty in incorporating user-supplemented information to form subsequent evaluation recommendations, due to the lack of real-world job data constraints and dynamic interaction mechanisms, this invention proposes an artificial intelligence-based career planning information processing method. For example... Figure 1 As shown, the method schedules multiple processing nodes to execute through a state diagram workflow, including the following steps S1 to S7.

[0022] In step S1, user input information is obtained.

[0023] In this step, the system obtains user input information. This user input information includes natural language descriptions and / or resume files. Natural language descriptions refer to free text entered by the user through the dialog interface. For example, a user could directly enter descriptive statements such as, "I am a third-year computer science and technology student, proficient in Python and Java, and hope to work in backend development." Resume files can be electronic files in PDF, DOCX, TXT, or Markdown formats. The system supports users uploading resume files in the above formats through the front-end interface, and also supports users describing their personal information in natural language in the dialog input box. Users can provide information using one of these methods alone, or simultaneously using both methods—for example, uploading a resume file and then supplementing it with details about their job objective or latest project experience through the dialog.

[0024] After receiving user input, the system performs text parsing on PDF, DOCX, TXT, or Markdown format files, extracts the text content from the files, and merges the parsed text with the content input by the user through natural language to form a unified text to be processed, which is then used for structured information extraction in subsequent steps.

[0025] In step S2, the user input information is parsed to generate structured user capability information.

[0026] In this step, the system parses the merged user input information from step S1 and transforms it into structured user capability information. Specifically, as follows... Figure 2 As shown, this step includes the following sub-steps S21 to S24.

[0027] S21: Perform text parsing on the resume file, and merge the parsed resume text with the natural language description input by the user into a text to be processed.

[0028] S22: Based on the prompt template corresponding to the information extraction node, the large language model is invoked to perform structured information extraction on the text to be processed, obtaining initial ability information. The system is pre-configured with an information extraction prompt template, which instructs the large language model to extract various ability information related to career planning from the user input information. The large language model performs semantic understanding and information extraction on the user input information according to the prompt template, and outputs initial structured ability information. This initial ability information includes, but is not limited to, professional information, education or grade information, job intention information, technical skills information, project experience information, internship experience information, certificate and honor information, as well as soft quality information such as learning ability, communication ability, innovation ability, and stress resistance. It should be noted that when the large language model extracts information, for information fields not explicitly mentioned in the user input information, the corresponding fields can be empty or marked as missing.

[0029] S23: Based on a rule-based compensation strategy, missing fields in the initial capability information are supplemented and identified. The rule-based compensation strategy includes at least one of regular expression matching, keyword dictionary matching, and time information parsing. Since information extraction from a large language model may miss certain key fields due to factors such as the way user input is expressed, its format, or the completeness of its content, this step introduces a rule-based compensation strategy as a supplementary means. This rule-based compensation strategy adopts a rule-based information identification method. Specifically, the rule-based compensation strategy is used to identify at least one of the following fields from the user input information: education level or grade information (e.g., identifying education keywords such as "undergraduate," "master's," and "doctoral," as well as grade expressions such as "junior year" and "second year of graduate school," and time expressions such as "enrolled in 20XX" and "graduated in 20XX"), graduation time information (e.g., identifying expressions such as "expected to graduate in 20XX" and "will graduate in June 20XX"), internship experience information (e.g., identifying keywords such as "internship," "intern," and "served at a certain company" and their context), certificate information (e.g., identifying expressions such as "passed CET-6" and "obtained a Level 2 Computer Proficiency Certificate"), and major information (e.g., identifying majors such as "Computer Science and Technology" and "Software Engineering"). The rule-based compensation strategy identifies each of the above fields one by one. If a field in the initial capability information is missing, and the rule-based compensation strategy successfully identifies the corresponding content of the field from the original input information, then the identification result is filled into the field as supplementary information; if the rule-based compensation strategy also fails to identify the corresponding content of the field, then the field remains missing.

[0030] For example, when the user input includes information such as start and end dates, school name, major, and academic level, the rule-based compensation strategy can infer the user's academic status (e.g., currently enrolled, graduating, or already graduated) or grade level based on the current year and academic system information. When the user input includes the internship company name, internship position, and job description, the rule-based compensation strategy will add these to the internship experience information field.

[0031] S24: The initial capability information and supplementary identification results are merged and structurally verified according to a preset data structure to generate the structured user capability information. The system merges the initial capability information from step S22 with the fields obtained after supplementation and identification by the rule compensation strategy in step S23—for fields successfully identified and supplemented by the rule compensation strategy, the corresponding missing fields in the initial capability information are replaced or filled with the supplementary identification results; for fields that already exist in the initial capability information and have not been modified by the rule compensation strategy, the content in the initial capability information is retained; for fields that are not identified by either the initial capability information or the rule compensation strategy, they remain missing. After the above merging process and structural verification, complete structured user capability information is obtained.

[0032] In this embodiment of the invention, the structured user capability information includes multiple items from the following: professional information, educational background or grade level, job intention information, technical skills information, project experience information, internship experience information, certificate and honor information, learning ability information, communication ability information, innovation ability information, and stress resistance information. It is understood that the specific content of the above fields depends on the amount of information contained in the user input; for information not provided by the user, the corresponding fields can be left blank or marked as missing.

[0033] Furthermore, the system can generate an information completeness score based on the completeness of the aforementioned fields. This information completeness score is used to quantitatively assess the completeness of the user's competency information. If the information completeness score is below a preset threshold, for example, if the user has not provided information about the target position or key experience information is missing, the system can guide the user to supplement relevant information through interactive dialogue, avoiding the direct generation of unreliable matching results and career planning suggestions when information is insufficient.

[0034] In step S3, the user's career goal type is determined based on the structured user ability information, and job matching is performed based on the pre-established job knowledge base and the career goal type to generate candidate jobs.

[0035] In this step, the system performs job matching on the structured user competency information generated in step S2 based on a pre-established job knowledge base. First, the construction of the job knowledge base involved in this step will be explained.

[0036] The job knowledge base includes a database of real job samples, a database of standard job profiles, and a database of extended job references.

[0037] The real job sample database contains job records comprised of corporate recruitment data. Specifically, this database may consist of approximately 10,000 job postings. Each job record includes at least the following fields: job title, work address, salary range, company information, industry, and job description. The job description includes the required skills. The real job sample database provides data source evidence for job matching; that is, when the system recommends a particular job, it can extract the corresponding job record from this database as evidence for the recommendation.

[0038] The standard job profile database includes job title, job alias, professional skill requirements, certification requirements, professional ethics requirements, vertical career development path information, and lateral job transfer path information. For common jobs, the system has pre-built standardized job profiles as stable benchmarks for job competency, used for rapid matching and four-dimensional scoring.

[0039] The expanded job reference library includes job profiles not fully covered by the real job sample library, and records the source and confidence level of each profile. For emerging jobs with insufficient coverage by real job data (such as job types newly emerging due to technological development), the system can generate reference profiles for these jobs using a large language model, which are then manually reviewed and stored in the expanded job reference library. Compared to job records in the real job sample library, the confidence level of the profile information in the expanded job reference library is relatively low, and users need to be prompted to verify it when it is displayed later.

[0040] Based on the above job knowledge base, such as Figure 3 As shown, step S3 specifically includes the following sub-steps S31 to S37.

[0041] S31: Determine the user's career goal type based on the structured user competency information. The system reads the job intention field from the structured user competency information and determines which of the following types the user's career goal type belongs to: the user has a specific career target position, the user only has a job category or job field, or the user has no career target position.

[0042] S32: When a user has a specific career goal, that career goal will be used as the target for matching. If the user specifies a particular job title, such as "AI Algorithm Engineer" or "Java Backend Engineer," that job title will be directly identified as the target for matching, and the process will proceed to the subsequent standard profile matching process.

[0043] S33: When a user only has a job category or job field, candidate positions are generated within the corresponding job category. For example, if a user enters "I want to work in software development" or "I am interested in the field of artificial intelligence," the system will filter and generate candidate positions within that category based on the scope of the job category or field, combined with the user's professional skills and project experience in the structured competency information.

[0044] S34: When a user does not have a target job, candidate jobs are generated based on their major, skills, project experience, internship experience, and the user's input career intention information. If the structured user competency information does not include job intention information or does not specify a particular job name or category, the system recommends one or more possible job directions to the user based on their existing professional background, technical skills, project experience, and internship experience, combined with job requirement data in the job knowledge base.

[0045] S35: Perform alias matching, keyword matching, and / or semantic similarity matching on the job title to obtain a baseline job profile. In practical applications, the target job title entered by the user may differ from the standard job titles in the standard job profile database. For example, the user might say "AI Engineer," while the standard profile database records it as "Artificial Intelligence Algorithm Engineer," or the user might say "Backend Developer," while the standard profile database records it as "Backend Development Engineer." Therefore, the system first performs alias matching, mapping the user-entered job title to a standard job title using a pre-defined job alias mapping table. If alias matching fails, keyword matching is performed, calculating the keyword overlap between the user-entered job title and each job title in the standard job profile database. If the keyword similarity is still below a pre-defined threshold, semantic similarity matching is performed, converting the user-entered job title into a vector representation and calculating its cosine similarity with the vector representations of each job title in the standard job profile database. The standard job profile with the highest similarity is selected as the matching result. The above three matching methods can be used in an "AND / OR" relationship—that is, one method can be used alone, or multiple methods can be combined, dynamically selected based on the reliability of the matching results. After matching is completed, the matched standard job profile will be used as the baseline job profile.

[0046] S36: Based on the benchmark job profile, the system performs keyword and / or vector semantic retrieval in the real job sample database to recall relevant job samples. The system uses job titles, skill requirements, and other information from the benchmark job profile as search criteria to search the real job sample database. The search can employ text-based keyword retrieval, vector-based semantic retrieval, or a combination of both. Specifically, the system can combine the job title and skill requirement fields from the benchmark job profile into search query conditions, and match them against the job title, job description, and job skill requirement fields in the real job sample database to recall several job sample records with the highest relevance to the target job. The recalled job sample records record the recruitment requirements of real companies, providing real data support for subsequent job recommendations.

[0047] S37: Based on the baseline job profile, relevant job samples, extended job reference profiles, and the confidence level of the job profiles, candidate jobs are generated, and information from the user selecting or confirming a target job from the candidate jobs is received. The system integrates the baseline job profile (providing job competency benchmarks), relevant job samples (providing real data evidence), and extended job reference profiles (providing supplementary references when real samples are insufficient), and considers the confidence level of each profile source to generate candidate jobs. In this embodiment of the invention, the system can generate multiple candidate jobs (e.g., 5), each candidate job including at least a job name, matching score, confidence level, recommendation reason, matched skills, skills to be supplemented, and data source identifier and / or job evidence information. The system provides the following information: Job title (the standard name of the candidate job); matching score (quantifying the degree of match between the user and the job); confidence level (indicating the credibility of the recommendation result; e.g., a higher confidence level for candidate jobs generated based on real job samples, and a lower confidence level for candidate jobs generated based on an expanded job reference library, requiring the user to verify); recommendation reason (explaining the main reasons for recommending the job); matched skills list (skills the user already possesses and that meet the job requirements); skills to be supplemented list (skills the user does not yet possess but are required for the job); and data source identifier and / or job evidence information (showing the specific data source on which the candidate job was generated, such as which real job sample records or which expanded job profile it came from). The system displays the above candidate jobs to the user and receives information from the user selecting or confirming the target job. This confirmation information will serve as the execution trigger condition for step S4.

[0048] In step S4, after receiving the user's selection or confirmation information for the target position, the structured user ability information is quantitatively matched with the confirmed target position from four evaluation dimensions: basic requirements, professional skills, professional qualities, and development potential, to generate a person-job matching result.

[0049] In this step, after receiving information from the user that they have selected or confirmed a target position from the candidate positions, the system triggers the quantitative matching process between the candidate and the job. The system performs quantitative matching between the structured user competency information generated in step S2 and the target position confirmed by the user, based on four evaluation dimensions: basic requirements, professional skills, professional qualities, and development potential.

[0050] The matching criteria for the basic requirements dimension include educational background, professional background, and consistency of job application intention. The system compares the educational background or grade information in the structured user's ability information with the educational requirements of the target position, such as undergraduate, master's, or doctoral requirements; it compares the professional information with the disciplinary background requirements of the target position, such as computer science, electronic information, and other related majors; and it compares the user's job application intention with the direction of the target position to determine whether they are consistent. Based on the above comparison results, a score is calculated for the basic requirements dimension.

[0051] The matching criteria for the professional skills dimension include the degree of overlap between technical skills, tool frameworks, project experience, and the core skills of the target position. The system compares the technical skills information in the structured user competency information with the skill requirements of the target position item by item, calculating the proportion of the user's mastered skills among the core skills of the target position. Simultaneously, the system also performs correlation analysis between the user's project experience information and the job responsibilities of the target position to determine whether the user's project experience is relevant to the job content. Based on the above analysis results, a score for the professional skills dimension is calculated.

[0052] The matching criteria for the professional competence dimension include learning ability, communication and collaboration skills, and resilience. The system extracts information on these soft skills from structured user competence information and assesses the sufficiency of evidence for each soft skill. For example, if a user demonstrates teamwork in their project experience, the evidence for communication and collaboration skills is relatively strong; if a user demonstrates performance under high-pressure conditions in their internship experience, the evidence for resilience is relatively strong. Based on the matching degree and sufficiency of evidence for the soft skills, a score for the professional competence dimension is calculated.

[0053] The matching criteria for the development potential dimension include learning ability, innovation ability, and job matching score. The system evaluates the user's learning and innovation abilities and calculates the development potential dimension score by combining the development space of the target position (such as the growth trend and promotion path of the industry in which the position is located).

[0054] The system calculates a comprehensive matching score according to preset dimension weights, where the sum of the weights of each dimension is 1. When any evaluation dimension lacks valid experience information, an insufficient evidence flag is set for that evaluation dimension, and a preset neutral value is used or the score of that evaluation dimension is limited.

[0055] The job matching results include a comprehensive matching score, scores for each evaluation dimension, dimension explanation information, matching highlights, key gaps, matched skills, and skills to be improved. Dimension explanation information summarizes the matching situation for that dimension; matching highlights indicate the user's outstanding strengths in a particular dimension; and key gaps indicate the user's main weaknesses in a particular dimension.

[0056] In step S5, a career path and phased action plan are generated based on the job matching results.

[0057] In this step, the system generates a career path and phased action plan for the user based on the job matching results generated in step S4.

[0058] The career path includes vertical development paths and lateral job transfer paths. The vertical development path generates a path from the target position to senior, technical expert, and / or management positions based on the hierarchical relationships in a standard job profile database. Specifically, the system generates a description of the direction from the currently matched target position to a higher-level or higher-ranking position based on the vertical development path information in the standard job profile database, such as from junior engineer to senior engineer, technical expert, or technical leader. The lateral job transfer path generates a path from the target position to related technical fields or transferable positions based on the skill associations and ability transfer relationships between positions. Specifically, the system generates a description of the direction from the currently matched target position to related technical fields or similar positions based on the lateral job transfer path information in the standard job profile database, such as from Java backend engineer to big data development engineer, Go / Python backend engineer, or full-stack engineer. The career path also includes the target position, vertical development positions, laterally transferable positions, and corresponding skill enhancement suggestions.

[0059] The phased action plan is generated based on key gaps identified in the person-job matching results and includes short-term action plans, medium-term action plans, learning tasks, practical tasks, expected outcomes, evaluation cycles, and evaluation indicators. Short-term plans may include specific action items such as acquiring key skills, project restructuring, resume optimization, and interview preparation. Medium-term plans may include specific action items such as internship applications, project launches, accumulation of certificates or competition results, and phase reviews. Each phase has an evaluation cycle and corresponding evaluation indicators to allow users to execute the plan and periodically assess its effectiveness.

[0060] In step S6, a career development report is generated according to a preset template.

[0061] In this step, the system generates a career development report according to a preset template. The career development report includes sections on career exploration and job matching, career goals and path planning, phased action plans, dynamic evaluation and adjustment, and personalized messages. Specifically, the career exploration and job matching section presents the job matching results generated in step S4, including matching scores for each dimension, matching highlights, and key gaps; the career goals and path planning section presents the career path generated in step S5; the phased action plans section presents the phased action plans generated in step S5; the dynamic evaluation and adjustment section explains how the user can adjust their plans based on subsequent changes; and the personalized messages section outputs encouraging and guiding messages generated by AI based on the user's overall situation.

[0062] In response to a user's report export request, the system performs a completeness check on the career development report to be exported, determining whether the report includes key information, such as the target position, matching score, skills gap, phased action plan, and assessment cycle. If the key information is missing, the system outputs the completeness check results and corresponding supplementary information suggestions. After the completeness check passes, an editable and / or exportable career development report is output. Export formats support Word and PDF, and the exported version can include layout elements such as a title page, project name, generation date, table styles, and headers and footers.

[0063] In step S7, after the career development report is generated, the user's supplementary dialogue information is obtained, and a supplementary evaluation result is generated based on the current career development report, structured user ability information, job matching results, and career path. After receiving the user's report update instruction, the supplementary evaluation result is added to the career development report.

[0064] In this step, after the system generates the career development report in step S6, it initiates a dynamic supplementary assessment mechanism. Unlike questionnaire-style interactions with a pre-set fixed list of questions, the dynamic supplementary assessment in this step generates natural follow-up questions in real time based on the current context, and dynamically generates supplementary assessment results based on the user's answers. Specifically, as follows... Figure 4 As shown, this step includes the following sub-steps S71 to S72.

[0065] S71: The system constructs a follow-up question context from the current career development report, structured user competency information, job-person matching results, career path, and user-supplemented dialogue information. Based on this context, it calls a large language model to generate natural follow-up questions. The system organizes the above information into contextual prompts, inputs them into the large language model, and the large language model dynamically generates natural follow-up questions related to the current context. These natural follow-up questions are not from a pre-set fixed question list, but are dynamically generated by the large language model based on the user's previous answer and the current context, making the dialogue process more flexible and closer to real career consultation scenarios. For example, if the user's previous answer involved a project experience, the system can ask follow-up questions about the specific responsibilities, technology stack, or achievements of that project; if the user's previous answer involved the motivation for choosing a job, the system can ask follow-up questions about the user's career interests and long-term goals.

[0066] S72: Obtain the user's response to the natural follow-up question, and perform intent recognition and information content evaluation on the user's response. Based on the recognition results, the system executes the following processing logic: When the user's answer includes project responsibilities, internship responsibilities, technology stack usage, quantifiable results, job selection motivation, or other valid supplementary information, the answer is recorded. When a preset convergence condition is met, a supplementary evaluation result is generated based on the recorded answer. When the preset convergence condition is not met, the next natural follow-up question is generated. The preset convergence condition can be that the collected supplementary information covers all preset key supplementary fields, such as all key fields such as project responsibilities, technology stack, quantifiable results, and job motivation having obtained valid information.

[0067] When the amount of information provided by a user's answer is below a preset threshold, alternative follow-up questions are generated to guide the user to supplement specific experiences, personal responsibilities, technical details, or quantitative results. For example, if the user's answer is too general (such as "I have done projects"), the system can generate more specific follow-up questions (such as "Please describe your main responsibilities and technology choices in the project") to guide the user to provide more valuable supplementary content.

[0068] When a user requests a change of question, the system generates alternative follow-up questions. For example, if a user indicates they do not want to answer the current question or requests a different question, the system can generate a lighter, more nuanced question, such as shifting from a technical detail question to one about career interests or preferences.

[0069] When no valid large language model output is obtained, a preset fallback strategy is used to generate alternative follow-up questions. For example, if the large language model fails to generate valid follow-up questions due to abnormal input format or inference failure, the system can use a preset fallback question template as an alternative to ensure that the dialogue flow is not interrupted.

[0070] When the preset number of follow-up questions is reached or when the user's instruction to end the follow-up questions is received, the follow-up questions are terminated and supplementary evaluation results are generated.

[0071] After generating supplementary assessment results, the system will temporarily store the supplementary assessment results and, upon receiving the user's report update instruction, will add the supplementary assessment results to the career development report, thereby supplementing and iteratively optimizing the original report content.

[0072] Through the dynamic follow-up questioning and supplementary evaluation mechanisms described in S71 to S72, the system can continue to engage in multiple rounds of dialogue with the user after the report is generated, gradually refining the evaluation basis and planning suggestions. This makes the career planning results more aligned with the user's actual situation, improving the accuracy of the evaluation and the feasibility of the suggestions. After reviewing the report, users can decide whether to initiate the supplementary evaluation process and whether to merge the supplementary evaluation results into the original report, fully respecting the user's wishes.

[0073] In summary, the AI-based career planning information processing method provided in Embodiment 1 of this invention separates tasks such as user information organization, job matching, path planning, and report generation through a state diagram workflow, avoiding the mismatch risk caused by a single prompt word undertaking multiple tasks. Through a three-layer job knowledge base including a real job sample library, a standard job profile library, and an extended job reference library, along with a retrieval-enhanced job matching mechanism, traceable data sources are provided to support job recommendations and skills gap analysis, reducing the risk of large language models generating illusions in job matching due to a lack of real data constraints. By requiring users to confirm their target job before entering the four-dimensional quantitative matching process, it ensures that the evaluation object is a job that the user truly cares about, improving the relevance of the matching results and user satisfaction. By performing quantitative matching of people and jobs from four dimensions—basic requirements, professional skills, professional qualities, and development potential—explainable matching results are generated, including scores for each dimension, matching highlights, and key gaps, enabling users to understand the reasons for recommending specific jobs and their own shortcomings. By initiating a dynamic, natural follow-up question module after report generation, the interactive burden on users caused by fixed questionnaires is avoided. This makes the supplementary assessment process closer to a continuous dialogue in real career counseling, and can generate supplementary assessment results based on supplementary information provided by the user and add them to the report. Through templated report generation and integrity check mechanisms, the presentation and applicability of career planning results are improved, making it easy for users to export them for presentations or personal archiving.

[0074] Example 2: Embodiment 2 of the present invention provides an artificial intelligence-based career planning information processing system, which is used to implement the artificial intelligence-based career planning information processing method of Embodiment 1 above. For example... Figure 5 As shown, the system specifically includes the following modules.

[0075] The input parsing module is used to acquire user input information, including natural language descriptions and / or resume files. The module supports users inputting natural language descriptions through a dialog interface, and also supports users uploading resume files in PDF, DOCX, TXT, or Markdown formats. For uploaded resume files, the module performs text parsing and content extraction.

[0076] The capability information processing module is used to parse the user input information and generate structured user capability information. This module parses the resume file, merges the parsed resume text with the user's input natural language description into a text to be processed, and uses a large language model to extract initial capability information from the text based on the prompt template corresponding to the information extraction node. It then uses a rule-based compensation strategy to supplement and identify missing fields in the initial capability information, and performs field merging and structure verification on the initial capability information and the supplemented identification results according to a preset data structure to generate structured user capability information. For a detailed description of the implementation of this module, please refer to step S2 in Embodiment 1; it will not be repeated here.

[0077] The job matching module is used to determine the user's career goal type based on the structured user ability information, perform job matching based on a pre-established job knowledge base and the career goal type, generate candidate jobs, and receive the user's selection or confirmation of the target job. The job matching module executes different candidate job generation strategies based on three scenarios: whether the user has a specific career goal, only a job category or field, or no career goal. It obtains a baseline job profile through alias matching, keyword matching, and / or semantic similarity matching, retrieves relevant job samples through keyword retrieval and / or vector semantic retrieval in a real job sample database, generates candidate jobs based on the baseline job profile, relevant job samples, extended job reference profiles, and confidence levels, and receives the user's selection or confirmation. For a detailed description of the implementation of this module, please refer to step S3 in Embodiment 1, which will not be repeated here.

[0078] The job matching module, upon receiving a user's selection or confirmation of a target job, performs a quantitative match between the structured user's competency information and the confirmed target job from four evaluation dimensions: basic requirements, professional skills, professional qualities, and development potential, generating a job matching result. The module calculates a comprehensive matching score according to preset dimension weights and sets an insufficient evidence flag if any evaluation dimension lacks valid experience information. For a detailed description of the job matching module's implementation, please refer to step S4 in Embodiment 1; it will not be repeated here.

[0079] The career path planning module is used to generate career paths and phased action plans based on the person-job matching results. The career paths include vertical development paths and lateral job-changing paths. For a detailed description of the implementation of the career path planning module, please refer to step S5 in Embodiment 1; it will not be repeated here.

[0080] The report generation module is used to generate career development reports according to preset templates. The module generates career development reports that include chapters such as career exploration and job matching, career goals and path planning, phased action plans, dynamic evaluation and adjustments, and personalized messages. In response to a user's report export request, it performs a completeness check and outputs an editable and / or exportable report after the check passes. For a detailed description of the implementation of the report generation module, please refer to step S6 in Embodiment 1; it will not be repeated here.

[0081] The supplementary assessment module is used to obtain supplementary dialogue information from the user after the career development report is generated, generate supplementary assessment results based on the current career development report, structured user ability information, job matching results, and career path, and append the supplementary assessment results to the career development report upon receiving the user's report update instruction. The supplementary assessment module combines the current report, user ability information, matching results, career path, and supplementary dialogue information to form a follow-up question context, calls a large language model to generate natural follow-up question content, performs intent recognition and information content evaluation on the user's answer, and executes corresponding processing logic based on different situations such as whether the answer contains valid supplementary information, whether the information content is below a preset threshold, whether a request to change the question has been received, whether a valid large language model output has been obtained, and whether a preset number of follow-up question rounds has been reached. Supplementary assessment results are generated when the termination condition is met. For a detailed description of the supplementary assessment module, please refer to step S7 in Embodiment 1, which will not be repeated here.

[0082] The AI-based career planning information processing system provided in Embodiment 2 of this invention adopts a modular design, with the data flow between modules corresponding to the method steps in Embodiment 1. The system acquires and structures user information through an input parsing module and a competency information processing module; generates candidate positions, confirms target positions, and conducts four-dimensional quantitative assessments through a job matching module and a person-job matching module; outputs planning schemes and reports through a career path planning module and a report generation module; and performs dynamic supplementary assessments and iterative optimizations after report generation through a supplementary evaluation module. All modules work collaboratively to achieve a complete process from user information input to career development report generation and dynamic supplementation.

[0083] The AI-based career planning information processing system of this embodiment is used to implement the AI-based career planning information processing method of the aforementioned embodiment 1. Therefore, the specific implementation of each module in the system can be found in the corresponding steps in the method embodiment above. To avoid redundancy, they will not be described one by one here.

[0084] Example 3: This invention provides an electronic device, which includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the above-mentioned artificial intelligence-based career planning information processing method.

[0085] Example 4: This invention provides a computer storage medium storing a computer software product, which includes several instructions to cause a computer device to execute the aforementioned artificial intelligence-based career planning information processing method.

[0086] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0089] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A career planning information processing method based on artificial intelligence, characterized in that, The method schedules multiple processing nodes to execute through a state graph workflow, including: Obtain user input information, which includes natural language descriptions and / or resume files; The user input information is parsed to generate structured user capability information; The user's career goal type is determined based on the structured user ability information, and job matching is performed based on the pre-established job knowledge base and the career goal type to generate candidate jobs; After receiving information from the user’s selection or confirmation of the target position, the structured user ability information is quantitatively matched with the confirmed target position from four evaluation dimensions: basic requirements, professional skills, professional qualities, and development potential, and a person-job matching result is generated. Based on the job matching results, a career path and phased action plan are generated. Generate a career development report according to a preset template; After the career development report is generated, supplementary dialogue information from the user is obtained. Based on the current career development report, structured user ability information, job matching results, and career path, supplementary evaluation results are generated. Upon receiving the user's report update instruction, the supplementary evaluation results are added to the career development report.

2. The career planning information processing method based on artificial intelligence according to claim 1, characterized in that, The step of parsing the user input information to generate structured user capability information includes: The resume file is parsed, and the parsed resume text is merged with the natural language description input by the user into a text to be processed. Based on the prompt template corresponding to the information extraction node, the large language model is invoked to extract structured information from the text to be processed, thereby obtaining initial capability information. Based on the rule compensation strategy, the missing fields in the initial capability information are supplemented and identified. The rule compensation strategy includes at least one of regular expression matching, keyword dictionary matching, and time information parsing. According to the preset data structure, the initial capability information and the supplementary identification results are merged and the structure is verified to generate the structured user capability information; The structured user capability information includes multiple aspects such as professional information, education level or grade level, job intention information, technical skills information, project experience information, internship experience information, certificate and honor information, learning ability information, communication ability information, innovation ability information, and stress resistance information.

3. The career planning information processing method based on artificial intelligence according to claim 1, characterized in that, The job knowledge base includes a real job sample library, a standard job profile library, and an extended job reference library; The real job sample database contains job records composed of enterprise recruitment data, and each job record includes at least the job title, job description and job skill requirements. The standard job profile database includes job title, job alias, professional skill requirements, certificate requirements, professional ethics requirements, vertical development path information, and horizontal job transfer path information; The expanded job reference library contains job profiles that are not fully covered by the real job sample library, and records the source and confidence level of the profiles; The step of determining the user's career goal type based on the structured user ability information and performing job matching based on a pre-established job knowledge base and the career goal type includes: The user's career goal type is determined based on the structured user capability information; When a user has a specific career goal, that career goal will be used as the target for matching. When a user only has a job category or job field, candidate positions are generated within the corresponding job category; When a user does not have a target job, candidate jobs are generated based on their major, skills, project experience, internship experience, and the job intention information entered by the user. Perform alias matching, keyword matching, and / or semantic similarity matching on job titles to obtain a baseline job profile; Based on the benchmark job profile, keyword retrieval and / or vector semantic retrieval are performed in the real job sample database to recall relevant job samples. Based on the baseline job profile, relevant job samples, extended job reference profiles, and the confidence level of the job profiles, candidate jobs are generated, and information from the user to select or confirm the target job from the candidate jobs is received. Each candidate position should include at least the position name, matching score, confidence level, reason for recommendation, matched skills, skills to be added, data source identifier and / or position evidence information.

4. The career planning information processing method based on artificial intelligence according to claim 1, characterized in that, The quantitative matching of personnel to positions includes: Scores are calculated based on the consistency of educational background, professional background, and job application intentions across the basic requirements dimensions. The professional skills dimension score is calculated based on the degree of overlap between technical skills, tool frameworks, project experience, and the core skills of the target position. Scores for the professional competence dimension are calculated based on learning ability, communication and collaboration skills, and resilience. A score for the development potential dimension is calculated based on learning ability, innovation ability, and job matching score. The overall matching score is calculated according to the preset dimension weights, where the sum of the weights of each dimension is 1; When any evaluation dimension lacks valid experience information, an insufficient evidence flag is set for that evaluation dimension, and a preset neutral value is used or the score of that evaluation dimension is limited. The job matching results include a comprehensive matching score, scores for each evaluation dimension, explanatory information for each dimension, matching highlights, key gaps, matched skills, and skills to be supplemented.

5. The method according to claim 1, characterized in that, The career paths include vertical development paths and horizontal job-changing paths; The vertical development path generates a path from the target position to senior positions, technical expert positions, and / or management positions based on the job hierarchy in the standard job profile library. The horizontal job transfer path generates a path from the target job to a related technical field or a transferable job based on the skill association and ability transfer relationship between jobs. The career path also includes target positions, vertically developed positions, horizontally transferable positions, and corresponding skills enhancement suggestions. The phased action plan is generated based on the key gaps in the person-job matching results and includes short-term action plans, medium-term action plans, learning tasks, practical tasks, expected results, evaluation cycle, and evaluation indicators.

6. The career planning information processing method based on artificial intelligence according to claim 1, characterized in that, The career development report includes chapters on career exploration and job matching, career goals and path planning, phased action plans, dynamic evaluation and adjustment, and personalized messages. In response to a user's report export request, a completeness check is performed on the career development report to be exported to determine whether the report includes key information, including target position, matching score, skills gap, phased action plan and evaluation cycle; When the key information is missing, output the integrity check result and corresponding information supplementation prompts; After the integrity check is passed, an editable and / or exportable career development report is output.

7. The career planning information processing method based on artificial intelligence according to claim 1, characterized in that, The process of obtaining supplementary dialogue information from users, based on the current career development report, structured user competency information, job-person matching results, and career path, generates supplementary assessment results, including: The current career development report, structured user ability information, job matching results, career path, and user-supplemented dialogue information are combined to form a follow-up question context, and a large language model is invoked based on the follow-up question context to generate natural follow-up question content. Obtain the user's answers to the natural follow-up questions, and perform intent recognition and information content evaluation on the user's answers; When the user's answer contains project responsibilities, internship responsibilities, technology stack usage, quantifiable results, job selection motivation, or other valid supplementary information, the answer is recorded; when the preset termination condition is met, a supplementary evaluation result is generated based on the recorded answer; when the preset termination condition is not met, the next natural follow-up question is generated. When the amount of information provided by the user's answer is lower than a preset threshold, alternative follow-up questions are generated to guide the user to supplement specific experiences, personal responsibilities, technical details, or quantitative results. When a user requests a change of question, an alternative follow-up question is generated. When no effective large language model output is obtained, a preset fallback strategy is used to generate alternative follow-up questions. When the preset number of follow-up questions is reached or the user's instruction to end the follow-up questions is received, the follow-up questions are terminated and supplementary evaluation results are generated.

8. A career planning information processing system based on artificial intelligence, characterized in that, include: The input parsing module is used to obtain user input information, which includes natural language descriptions and / or resume files; The capability information processing module is used to parse the user input information and generate structured user capability information; The job matching module is used to determine the user's career goal type based on the structured user ability information, perform job matching based on the pre-established job knowledge base and the career goal type, generate candidate jobs, and receive the user's selection or confirmation information for the target job. The job matching module is used to quantitatively match the structured user ability information with the confirmed target job from four evaluation dimensions: basic requirements, professional skills, professional qualities and development potential, after receiving the user's selection or confirmation information of the target job, and generate job matching results. The career path planning module is used to generate career paths and phased action plans based on the job matching results. The report generation module is used to generate career development reports according to preset templates. The supplementary assessment module is used to obtain supplementary dialogue information from the user after the career development report is generated, generate supplementary assessment results based on the current career development report, structured user ability information, job matching results, and career path, and add the supplementary assessment results to the career development report after receiving the user's report update instruction.

9. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a bus system. The processor and the memory are connected through the bus system. The memory is used to store instructions, and the processor is used to execute the instructions stored in the memory to implement the artificial intelligence-based career planning information processing method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The computer storage medium stores a computer software product, which includes several instructions to cause a computer device to execute the artificial intelligence-based career planning information processing method according to any one of claims 1 to 7.

Images