Employment ability evaluation method and device based on resume document, equipment and medium

Abstract

The invention discloses an employment ability assessment method, device and equipment based on a resume document and a medium, and the method comprises the steps: obtaining a personal resume document of a target object, and carrying out the natural language processing of the personal resume document, and obtaining personal ability data; obtaining target post information of a target object, and performing structured extraction and capability dimension classification according to the target post information to obtain target post data; and performing semantic association on the personal ability data and a preset ability dimension to obtain a preliminary evaluation result, and comparing the preliminary evaluation result with target post data to obtain an employment ability evaluation result. According to the invention, the employment ability evaluation result of the job seeker is generated based on the personal resume document of the job seeker and the target post information, and compared with the common evaluation based on the personal information of the job seeker in the prior art, the employment ability evaluation result obtained by the method is more targeted and accurate.

Description

Technical Field

[0001] The present invention relates to the field of human resource management, and in particular to a resume-based employability assessment method, device, equipment and medium. Background Art

[0002] In today's society, the employment issues of citizens have attracted much attention, because this is not only related to the personal development of citizens, but also of great significance to social stability and economic development. With the improvement of education level and increasingly fierce competition in the employment market, job seekers need more accurate and personalized employment ability assessment methods and employment ability improvement suggestions, so as to provide job seekers with a direction for ability improvement to improve their employment success rate.

[0003] Existing employability assessment methods utilize a pre-set weighting system to quantify and score applicants based on their educational background, work experience, and skills certifications. Applicants are then ranked based on their overall scores to aid employers in decision-making. Clearly, existing employability assessment methods focus solely on individual applicants' abilities, failing to consider the competencies required for their desired positions. This results in a lack of direct connection between the assessment process and the applicant's desired position, leading to a lack of relevance and accuracy in the results. Summary of the Invention

[0004] The present invention provides a resume-based employability assessment method, device, equipment, and medium, which can improve the pertinence and accuracy of employability assessment.

[0005] In a first aspect, an embodiment of the present invention provides a method for assessing employability based on a resume document, comprising:

[0006] Obtain the target subject's resume document, perform natural language processing on the resume document to extract key fields from the resume document, and obtain personal ability data; wherein the key fields include educational background, project experience, internship experience, skill keywords, certificates, and achievements;

[0007] Obtain target position information of the target object, and perform structured extraction and capability dimension classification based on the target position information to obtain target position data;

[0008] The personal ability data is semantically associated with the preset ability dimensions to generate ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result, and the preliminary assessment result is compared with the target position data to obtain the employability assessment result.

[0009] The embodiment of the present invention obtains personal ability data based on the personal resume document of the target object, providing evaluable data for subsequent employability assessment; obtains target position data based on the target position information of the target object, providing reference data for subsequent employability assessment; and obtains employability assessment results by comparing the preliminary assessment results of the target object's personal ability with the target position data. This can improve the pertinence of the employability assessment results, and compared with the prior art that only assesses employability from the perspective of the job seeker's personal ability, the employability assessment results obtained by the embodiment of the present invention are more accurate. Compared with the prior art, the present invention can improve the pertinence and accuracy of employability assessment.

[0010] Furthermore, the target subject's resume document is obtained, and natural language processing is performed on the resume document to extract key fields in the resume document to obtain personal ability data, specifically:

[0011] Obtaining a personal resume document of a target subject, performing natural language processing on the personal resume document, and extracting key fields from the personal resume document, so as to convert the personal resume document into a standard structured format according to the key fields, and obtain personal ability data;

[0012] The standard structured format includes a JSON structure.

[0013] The embodiment of the present invention obtains the personal ability data of the target object based on the personal resume document of the target object, thereby providing evaluable data for subsequent employment ability assessment.

[0014] Furthermore, the target position information of the target object is obtained, and structured extraction and capability dimension classification are performed based on the target position information to obtain target position data, specifically:

[0015] Obtain target position information of the target object, and perform semantic interpretation on the target position information to obtain three key capability data, namely capability attribution dimension, capability requirement element, and capability requirement intensity, from the target position information, and match the three key capability data one by one to obtain a plurality of structured capability requirement ternary data;

[0016] According to the capability attribution dimension in the structured capability requirement ternary data, the structured capability requirement ternary data are classified to obtain target position data.

[0017] The embodiment of the present invention obtains target position data based on the target position information of the target object, thereby providing reference data for subsequent employability assessment.

[0018] Furthermore, the personal ability data is semantically associated with the preset ability dimensions to generate ability scores and explanatory comments under each ability dimension to obtain preliminary evaluation results, specifically:

[0019] The key fields in the personal ability data are semantically pre-associated with the preset ability dimensions, and the key fields associated under each ability dimension are semantically parsed in turn, and the ability scores and explanatory comments under each ability dimension of the target object are generated according to the preset scoring criteria, and the ability scores and explanatory comments under each ability dimension are integrated to obtain a preliminary evaluation result.

[0020] The embodiment of the present invention performs capability assessment on the target object's personal capability data under each capability dimension to obtain preliminary capability assessment results under each dimension, thereby providing data preparation for subsequent employability capability assessment.

[0021] Furthermore, the preliminary assessment results are compared with the target position data to obtain the employability assessment results, specifically:

[0022] Establishing a semantic mapping relationship between the preliminary assessment result and the target position data based on the capability dimension in the preliminary assessment result and the capability attribution dimension in the target position data;

[0023] Calculating the semantic similarity between the preliminary assessment result and the target position data based on the semantic mapping relationship to obtain a semantic similarity assessment result under each capability dimension, and generating an employability assessment result based on the semantic similarity assessment result;

[0024] Among them, the employment ability assessment results include job requirements, resume ability reflection and matching degree.

[0025] The embodiment of the present invention compares the target job requirements with the target object's personal ability data under the corresponding dimensions to obtain an employment ability assessment result based on the target job requirements as the evaluation criteria, making the employment assessment result more accurate.

[0026] Furthermore, the matching degree in the employability assessment result is obtained based on the corresponding ability score under the corresponding ability dimension and the semantic similarity assessment result, and the matching degree includes three results: matching, partial matching and mismatching.

[0027] The embodiment of the present invention obtains the job matching degree of the ability dimension based on the ability score of the target object under the same ability dimension and the semantic similarity with the target job requirements, provides an intuitive conclusion for the target object, and provides data preparation for the subsequent generation of ability improvement suggestions.

[0028] Furthermore, after evaluating each capability dimension of the target object based on the semantic similarity evaluation result and obtaining the employability evaluation result, if the employability evaluation result includes an capability dimension with a matching degree or a partial matching degree, capability improvement suggestions under the capability dimension will be generated.

[0029] The embodiment of the present invention provides a reference direction for employment efforts for the target object by providing ability improvement suggestions, so as to improve the employability of the target object.

[0030] In a second aspect, an embodiment of the present invention provides an employability assessment device based on a resume document, comprising a resume parsing module, a job data acquisition module, and an employability assessment module, wherein:

[0031] The resume parsing module is used to obtain the target subject's resume document, perform natural language processing on the resume document, extract key fields from the resume document, and obtain personal ability data; wherein the key fields include educational background, project experience, internship experience, skill keywords, certificates, and achievements;

[0032] The job data acquisition module is used to acquire target job information of a target object, and perform structured extraction and capability dimension classification based on the target job information to obtain target job data;

[0033] The employability assessment module is used to semantically associate the personal ability data with preset ability dimensions, generate ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result, and compare the preliminary assessment result with the target position data to obtain an employability assessment result.

[0034] The embodiment of the present invention generates corresponding personal ability data based on the personal resume document of the target object through a personal resume parsing module, providing evaluable data for subsequent employment ability assessment; generates target position data based on the target position information of the target object through a position data acquisition module, providing comparable data for subsequent employment ability assessment; and compares the personal ability data of the target object under various ability dimensions with the requirements of its target position, thereby analyzing the degree of fit between the personal ability of the target object and the requirements of its target position, obtaining an employment ability assessment result, and thus improving the pertinence and accuracy of the ability assessment result.

[0035] In a third aspect, an embodiment of the present invention provides a terminal device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0036] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operations of any one of the above-mentioned employability assessment methods based on resume documents.

[0037] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device / apparatus where the computer-readable storage medium is located is controlled to execute the employment ability assessment method based on resume documents as described in any one of the above.

[0038] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to more clearly understand the technical means of the embodiments of the present invention, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of an employability assessment method based on resume documents provided by an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of an ability indicator system of a six-factor employability evaluation model provided by an embodiment of the present invention;

[0041] Figure 3 This is a structural diagram of an employability assessment device based on resume documents provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0043] Example 1:

[0044] like Figure 1 As shown, an employability assessment method based on a resume document provided by an embodiment of the present invention includes the following steps:

[0045] S11, obtaining a personal resume document of a target subject, performing natural language processing on the personal resume document to extract key fields in the personal resume document to obtain personal ability data; wherein the key fields include educational background, project experience, internship experience, skill keywords, certificates, and achievements;

[0046] S12, obtaining target position information of the target object, and performing structured extraction and capability dimension classification based on the target position information to obtain target position data;

[0047] S13, semantically associate the personal ability data with preset ability dimensions, generate ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result, and compare the preliminary assessment result with the target position data to obtain an employability assessment result.

[0048] In this embodiment, the target object's resume document is obtained, and natural language processing is performed on the resume document to extract key fields in the resume document to obtain personal ability data, specifically:

[0049] Obtaining a personal resume document of a target subject, performing natural language processing on the personal resume document, and extracting key fields from the personal resume document, so as to convert the personal resume document into a standard structured format according to the key fields, and obtain personal ability data;

[0050] The standard structured format includes a JSON structure.

[0051] In a specific implementation, the formats supported by the personal resume document include PDF format, DOCX format, DOC format, etc.

[0052] In this embodiment, the target position information of the target object is obtained, and structured extraction and ability dimension classification are performed based on the target position information to obtain target position data, specifically:

[0053] Obtain target position information of the target object, and perform semantic interpretation on the target position information to obtain three key capability data, namely capability attribution dimension, capability requirement element, and capability requirement intensity, from the target position information, and match the three key capability data one by one to obtain a plurality of structured capability requirement ternary data;

[0054] According to the capability attribution dimension in the structured capability requirement ternary data, the structured capability requirement ternary data are classified to obtain target position data.

[0055] In a specific implementation, the target position information includes the position title and the position responsibilities description, wherein the position responsibilities description serves as a reference for subsequent comparative analysis.

[0056] Furthermore, based on the job description input by the user, the system prompts the engineering department to call a large language model to structure the job capability information.

[0057] In an optional embodiment, the system uses prompt engineering technology to drive a large language model to perform semantic analysis on the job description and extract structured capability requirement triples. The triples are in the following form:

[0058] Triple format: (ability attribution dimension, capability requirement element, capability requirement intensity).

[0059] In a specific embodiment, the triplet is presented as follows:

[0060] ("Knowledge and Skills", "Proficiency in Python Programming", "Required");

[0061] ("Self-management skills", "ability to organize time effectively in a multi-tasking environment", "prioritized").

[0062] In an optional embodiment, the three key capability data of capability attribution dimension, capability requirement element and capability requirement intensity are obtained from the target position information, and the key capability data extracted are as follows:

[0063] Ability attribution factors (first-level ability dimension): six dimensions: knowledge and skills, competence, self-management ability, career planning ability, leadership, and social adaptability;

[0064] Competency requirements (competency behavior items): such as "proficient in SQL tuning", "experience in cross-departmental collaboration", "ability to plan career paths", etc.

[0065] Strength of capability requirements (such as "must", "priority", "optional"): used for subsequent adaptability comparison.

[0066] Marking standards:

[0067] The aforementioned musts are core requirements for the position and are indispensable; the aforementioned priority considerations are not hard requirements, but possessing this ability will add points and enhance the candidate's competitiveness; the aforementioned optionals are bonus points, and candidates with this ability can better adapt to the position, but they are not the decisive factors in the recruitment decision.

[0068] Furthermore, the model automatically identifies and generates multiple structured capability triples based on the prompts, and stores them in a standard JSON structure for subsequent processing.

[0069] Furthermore, the system clusters and classifies the triples according to the "Capability Dimension" field. The program classifies the "Capability Elements + Strengths" under each dimension into different categories.

[0070] In an optional embodiment, the target position data is finally presented in the form of:

[0071] {

[0072] "Knowledge and Skills":[

[0073] {"Ability Elements":"Proficiency in Python and data analysis tools","Requirement Strength":"Required"},

[0074] {"Ability element":"Experience in interdisciplinary project collaboration","Requirement strength":"Priority"}

[0075] ],

[0076] "Self-management ability":[

[0077] {"Ability element":"Ability to maintain stable execution under high-pressure environment","Required strength":"Required"},

[0078] {"Ability Elements":"Good time management and task prioritization skills","Requirement Strength":"Priority"}

[0079] ],

[0080] "Competence":[

[0081] {"Ability element":"Ability to independently complete data analysis and report writing","Requirement strength":"Required"},

[0082] {"Ability element":"Proficient in problem solving and making quick decisions in complex environments","Requirement strength":"Priority"}

[0083] ],

[0084] "Career planning ability":[

[0085] {"Ability Elements":"Ability to set career growth goals based on personal development and job requirements","Requirement Strength":"Required"},

[0086] {"Ability Elements":"Ability to continuously learn and iterate skills","Requirement Strength":"Priority"}

[0087] ],

[0088] "Leadership":[

[0089] {"Ability Elements":"Ability to manage teams and coordinate projects","Requirement Strength":"Required"},

[0090] {"Ability element":"Ability to motivate team members to achieve common goals","Requirement strength":"Priority"}

[0091] ],

[0092] "Social adaptability":[

[0093] {"Ability Elements":"Have good communication skills","Requirement Strength":"Required"},

[0094] {"Ability element":"Ability to adapt to a cross-cultural collaborative environment","Requirement strength":"Priority"} ]

[0096] }.

[0097] In this embodiment, the personal ability data is semantically associated with the preset ability dimensions to generate ability scores and explanatory comments under each ability dimension to obtain preliminary evaluation results, specifically:

[0098] The key fields in the personal ability data are semantically pre-associated with the preset ability dimensions, and the key fields associated under each ability dimension are semantically parsed in turn, and the ability scores and explanatory comments under each ability dimension of the target object are generated according to the preset scoring criteria, and the ability scores and explanatory comments under each ability dimension are integrated to obtain a preliminary evaluation result.

[0099] In its specific implementation, the system is based on the resume information uploaded and structured by the user, combined with the 27 secondary ability indicator system defined by the "Six-Factor Employment Competency Evaluation Model", and performs multiple rounds of semantic parsing and scoring tasks through the Large Language Model (LLM) to generate ability scores and explanatory comments, providing support for subsequent job matching and ability gap analysis.

[0100] It should be noted that the first-level capability dimensions for obtaining capability requirement triples and the 27 second-level capability indicator systems for generating capability scores and explanatory comments can be found in Figure 2 shown.

[0101] In the specific implementation, the structured resume fields + large language model Prompt (prompt word engineering) are combined to achieve multi-dimensional intelligent evaluation.

[0102] In an optional embodiment, the system semantically pre-associates different fields with secondary indicators based on the structured parsing results (such as education experience, project experience, skill list, certificates, competitions, etc.). The pre-association form can be as follows:

[0103] Project experience → problem-solving ability, innovation ability, and cooperation ability.

[0104] Skills → Master your own skills and digital tool capabilities.

[0105] Certificates / Achievements → Professional knowledge, foreign language proficiency, and continuous learning ability.

[0106] Furthermore, the system constructs 27 sets of scoring prompts based on Prompt Engineering, and each ability is analyzed independently. In an optional embodiment, the prompts are as follows:

[0107] Based on the following resume information, please rate this candidate on a scale of 1-5 based on their "cross-cultural and remote collaboration skills" and provide your reasons. Please assess whether they possess the following experience: international collaboration, remote collaboration, and cross-cultural communication, as reflected in their communication style, adaptability, and collaborative achievements.

[0108]

Resume Content

[0109] -Project: Participate in cross-school online research projects and communicate and collaborate with overseas mentors...

[0110] -Skills: Master English, familiar with collaboration tools such as Zoom / Slack

[0111] Please output:

[0112] Score (1–5) + Comments (be concise and clear, indicating the basis for the rating)

[0113] LLM (Big Data Model) automatically parses the resume semantics, extracts elements such as behavioral evidence, description level, scenario complexity, etc. related to the ability, and returns the results.

[0114] Furthermore, a capability score and explanatory comments are generated. In an optional embodiment, the capability score and explanatory comments are presented in the following form:

[0115] Output for each capability dimension:

[0116] Score (1-5): Based on the model's pre-defined scoring criteria (whether it is reflected, the degree of reflection, and the specificity of the evidence)

[0117] Comments: Briefly explain the basis for scoring, indicate the areas where your abilities are demonstrated and the sources of supporting evidence (e.g., project descriptions, internship experience, certificates, etc.).

[0118] It should be noted that the score may be based on the following scoring system:

[0119] Definition of rating scale (1–5 points):

[0120] 1 point: Not reflected or completely lacking

[0121] 2 points: Slightly reflected, but not fully

[0122] 3 points: general manifestation, with basic evidence

[0123] 4 points: relatively comprehensive and specific examples

[0124] 5 points: Demonstrates outstanding performance, with significant achievements or leadership experience

[0125] This scoring system takes into account both subjective evaluation and factual support, and emphasizes the specificity, relevance and verifiability of ability performance.

[0126] In this embodiment, the preliminary assessment results are compared with the target position data to obtain the employability assessment results, specifically:

[0127] Establishing a semantic mapping relationship between the preliminary assessment result and the target position data based on the capability dimension in the preliminary assessment result and the capability attribution dimension in the target position data;

[0128] Calculating the semantic similarity between the preliminary assessment result and the target position data based on the semantic mapping relationship to obtain a semantic similarity assessment result under each capability dimension, and generating an employability assessment result based on the semantic similarity assessment result;

[0129] Among them, the employment ability assessment results include job requirements, resume ability reflection and matching degree.

[0130] Furthermore, the matching degree in the employability assessment result is obtained based on the corresponding ability score under the corresponding ability dimension and the semantic similarity assessment result, and the matching degree includes three results: matching, partial matching and mismatching.

[0131] Furthermore, after evaluating each capability dimension of the target object based on the semantic similarity evaluation result and obtaining the employability evaluation result, if the employability evaluation result includes an capability dimension with a matching degree or a partial matching degree, capability improvement suggestions under the capability dimension will be generated.

[0132] In specific implementation, the system conducts a multi-dimensional semantic comparison between job competency requirements (from target job data) and actual candidate performance (from preliminary assessment results), and outputs competency matching, competency gap analysis, and personalized improvement suggestions to assist users in clearly identifying their own compatibility and shortcomings with the target job.

[0133] As can be seen from the above steps, in an optional embodiment, the final presentation form of the target position data is:

[0134] {

[0135] "Knowledge and Skills":[

[0136] {"Ability Elements":"Proficiency in Python and data analysis tools","Requirement Strength":"Required"},

[0137] {"Ability element":"Experience in interdisciplinary project collaboration","Requirement strength":"Priority"}

[0138] ],

[0139] "Self-management ability":[

[0140] {"Ability element":"Ability to maintain stable execution under high-pressure environment","Required strength":"Required"},

[0141] {"Ability Elements":"Good time management and task prioritization skills","Requirement Strength":"Priority"}

[0142] ]}

[0143] The performance structure of the preliminary assessment results generated by the system is ability score + explanatory comments, as shown below:

[0144] {

[0145] "Knowledge and skills":{

[0146] "Skills":{"score":5,"comment":"Proficient in using Python and Pandas for data processing"},

[0147] "Interdisciplinary knowledge integration ability": {"score":3,"comment":"The project involves basic data analysis and bioinformatics integration, which is generally good."}

[0148] },

[0149] "Self-management ability":{

[0150] "Time Management and Task Prioritization":{"score":2,"comment":"No experience demonstrating clear time management and prioritization"}

[0151] }

[0152] }

[0153] Furthermore, the system uses the prompt word project combined with the big data model to evaluate the semantic similarity of each target position information with the preliminary assessment results of the corresponding first-level ability, and drives the prompt word project to perform semantic comparison. Finally, a threshold is set based on the ability score to obtain the employment ability assessment result. The comparison logic of the semantic comparison of the prompt word project can be seen in the following example:

[0154] {Job requirements: Proficiency in Python and data analysis tools

[0155] Resume skills demonstrated: Candidates using Python / Pandas for data preprocessing and visualization in two projects will be scored 5 points

[0156] Please determine whether it matches (match / partial match / no match) and briefly explain the reason.

[0157] Furthermore, for "mismatched" or "partially matched" competency items, the system automatically generates gap descriptions and competency improvement suggestions: the gap descriptions are based on the semantic requirements in the target job description and the missing content in the resume, pointing out the unmet needs; the competency improvement suggestions are the system's recommended improvement paths. By comparing the scores of each competency in the resume with the strength of the job requirements, the system determines which competencies need to be further improved. For example, supplementing experience, taking courses in certain areas, adding project training in certain areas, etc. The specific presentation of the gap descriptions and competency improvement suggestions can refer to the following example:

[0158] {

[0159] "Self-management ability":{

[0160] "Match Status": "Partial Match",

[0161] "Gap Description":"The position requires good task prioritization, but the resume lacks specific descriptions of time management or task sequencing.",

[0162] "Improvement suggestion": "It is recommended to add project management timelines and experience using tools (such as Trello / Gantt charts) to your resume, or to participate in a time management training camp."

[0163] }

[0164] }.

[0165] Furthermore, the employability assessment result is outputted. The employability assessment result can refer to the following example.

[0166]

[0167] Furthermore, the system generates a visual capability assessment report, which includes a six-dimensional capability radar chart, first-level indicator capability scores and explanatory comments, matching degree with the position, and capability improvement suggestions.

[0168] The embodiment of the present invention obtains personal ability data based on the personal resume document of the target object, providing evaluable data for subsequent employability assessment; obtains target position data based on the target position information of the target object, providing reference data for subsequent employability assessment; and obtains employability assessment results by comparing the preliminary assessment results of the target object's personal ability with the target position data. This can improve the pertinence of the employability assessment results, and compared with the prior art that only assesses employability from the perspective of the job seeker's personal ability, the employability assessment results obtained by the embodiment of the present invention are more accurate. Compared with the prior art, the present invention can improve the pertinence and accuracy of employability assessment.

[0169] Example 2:

[0170] like Figure 3 As shown, this embodiment provides an employment ability assessment device based on resume documents, including a resume parsing module 001, a job data acquisition module 002 and an employment ability assessment module 003, wherein:

[0171] The resume parsing module 001 is used to obtain the target subject's resume document, perform natural language processing on the resume document, extract key fields from the resume document, and obtain personal ability data; wherein the key fields include educational background, project experience, internship experience, skill keywords, certificates, and achievements;

[0172] The job data acquisition module 002 is used to acquire target job information of a target object, and perform structured extraction and capability dimension classification based on the target job information to obtain target job data;

[0173] The employability assessment module 003 is used to semantically associate the personal ability data with preset ability dimensions, generate ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result, and compare the preliminary assessment result with the target position data to obtain an employability assessment result.

[0174] In this embodiment, the resume parsing module 001 obtains the resume document of the target object, performs natural language processing on the resume document to extract key fields in the resume document, and obtains personal ability data. Specifically, the resume parsing module 001 obtains the resume document of the target object, performs natural language processing on the resume document, and extracts key fields in the resume document to convert the resume document into a standard structured format according to the key fields to obtain personal ability data; wherein, the standard structured format includes a JSON structure.

[0175] In this embodiment, the job data acquisition module 002 acquires the target job information of the target object, and performs structured extraction and capability dimension classification based on the target job information to obtain the target job data. Specifically, the job data acquisition module 002 acquires the target job information of the target object, and performs semantic interpretation on the target job information to obtain three key capability data, namely capability attribution dimension, capability requirement element and capability requirement intensity, from the target job information, and matches the three key capability data one by one to obtain a number of structured capability requirement ternary data; according to the capability attribution dimension in the structured capability requirement ternary data, the structured capability requirement ternary data is classified to obtain the target job data.

[0176] In this embodiment, the employment ability assessment module 003 semantically associates the personal ability data with the preset ability dimensions, generates ability scores and explanatory comments under each ability dimension, and obtains a preliminary assessment result. Specifically, the employment ability assessment module 003 semantically pre-associates the key fields in the personal ability data with the preset ability dimensions, and semantically analyzes the associated key fields under each ability dimension in turn, and generates ability scores and explanatory comments under each ability dimension of the target object according to the preset scoring criteria, and integrates the ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result.

[0177] Furthermore, the employment ability assessment module 003 compares the preliminary assessment result with the target position data to obtain the employment ability assessment result, specifically: the employment ability assessment module 003 establishes a semantic mapping relationship between the preliminary assessment result and the target position data based on the ability dimension in the preliminary assessment result and the ability attribution dimension in the target position data; calculates the semantic similarity between the preliminary assessment result and the target position data based on the semantic mapping relationship, obtains the semantic similarity assessment result under each ability dimension, and generates the employment ability assessment result based on the semantic similarity assessment result; wherein, the employment ability assessment result includes job requirements, resume ability reflection and matching degree.

[0178] Furthermore, the matching degree in the employability assessment result is obtained based on the corresponding ability score under the corresponding ability dimension and the semantic similarity assessment result, and the matching degree includes three results: matching, partial matching and mismatching.

[0179] Furthermore, the employability assessment module 003 assesses each capability dimension of the target object based on the semantic similarity assessment result. After obtaining the employability assessment result, if the employability assessment result includes capability dimensions with a matching degree or a partial matching degree, the employability assessment module 003 will generate capability improvement suggestions under the capability dimensions.

[0180] In the embodiment of the present invention, the personal resume parsing module 001 generates corresponding personal ability data based on the personal resume document of the target object, thereby providing evaluable data for subsequent employment ability assessment; the job data acquisition module 002 generates target job data based on the target job information of the target object, thereby providing comparable data for subsequent employment ability assessment; the employment ability assessment module 003 compares the personal ability data of the target object under each ability dimension with the requirements of its target job, thereby analyzing the degree of fit between the personal ability of the target object and the requirements of its target job, obtaining an employment ability assessment result, and thereby improving the pertinence and accuracy of the ability assessment result.

[0181] Example 3:

[0182] This embodiment provides a terminal device, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0183] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operations of any one of the above-mentioned employability assessment methods based on resume documents.

[0184] Example 4:

[0185] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program. When the computer program is executed, the device / apparatus where the computer-readable storage medium is located is controlled to execute any one of the above-described methods for assessing employability based on resume documents.

[0186] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-monitorable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0187] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that 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 for those skilled in the art.

Claims

1. A method for assessing employability based on resume documents, characterized in that: include: Obtain the target subject's resume document, perform natural language processing on the resume document to extract key fields from the resume document, and obtain personal ability data; wherein the key fields include educational background, project experience, internship experience, skill keywords, certificates, and achievements; Obtain target position information of the target object, and perform structured extraction and capability dimension classification based on the target position information to obtain target position data; The personal ability data is semantically associated with the preset ability dimensions to generate ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result, and the preliminary assessment result is compared with the target position data to obtain the employability assessment result.

2. The employability assessment method based on resume documents according to claim 1, characterized in that: The target object's resume document is obtained, and natural language processing is performed on the resume document to extract key fields in the resume document to obtain personal ability data, specifically: Obtaining a personal resume document of a target subject, performing natural language processing on the personal resume document, and extracting key fields from the personal resume document, so as to convert the personal resume document into a standard structured format according to the key fields, and obtain personal ability data; The standard structured format includes a JSON structure.

3. The employability assessment method based on resume documents according to claim 2, characterized in that: The target position information of the target object is obtained, and structured extraction and ability dimension classification are performed based on the target position information to obtain target position data, specifically: Obtain target position information of the target object, and perform semantic interpretation on the target position information to obtain three key capability data, namely capability attribution dimension, capability requirement element, and capability requirement intensity, from the target position information, and match the three key capability data one by one to obtain a plurality of structured capability requirement ternary data; According to the capability attribution dimension in the structured capability requirement ternary data, the structured capability requirement ternary data are classified to obtain target position data.

4. The employability assessment method based on resume documents according to claim 3, characterized in that: The personal ability data is semantically associated with the preset ability dimensions to generate ability scores and explanatory comments under each ability dimension to obtain preliminary evaluation results, specifically: The key fields in the personal ability data are semantically pre-associated with the preset ability dimensions, and the key fields associated under each ability dimension are semantically parsed in turn, and the ability scores and explanatory comments under each ability dimension of the target object are generated according to the preset scoring criteria, and the ability scores and explanatory comments under each ability dimension are integrated to obtain a preliminary evaluation result.

5. The employability assessment method based on resume documents according to claim 4, characterized in that: The preliminary assessment results are compared with the target position data to obtain the employability assessment results, specifically: Establishing a semantic mapping relationship between the preliminary assessment result and the target position data based on the capability dimension in the preliminary assessment result and the capability attribution dimension in the target position data; Calculating the semantic similarity between the preliminary assessment result and the target position data based on the semantic mapping relationship to obtain a semantic similarity assessment result under each capability dimension, and generating an employability assessment result based on the semantic similarity assessment result; Among them, the employment ability assessment results include job requirements, resume ability reflection and matching degree.

6. The employability assessment method based on resume documents according to claim 5, characterized in that: The matching degree in the employability assessment result is obtained based on the corresponding ability score under the corresponding ability dimension and the semantic similarity assessment result, and the matching degree includes three results: matching, partial matching and non-matching.

7. The employability assessment method based on resume documents according to claim 6, characterized in that: After evaluating each capability dimension of the target object based on the semantic similarity evaluation result and obtaining the employability evaluation result, if the employability evaluation result includes an capability dimension with a matching degree or a partial matching degree, capability improvement suggestions under the capability dimension will be generated.

8. An employability assessment device based on resume documents, characterized in that: It includes resume parsing module, job data acquisition module and employment ability assessment module, among which, The resume parsing module is used to obtain the target subject's resume document, perform natural language processing on the resume document, extract key fields from the resume document, and obtain personal ability data; wherein the key fields include educational background, project experience, internship experience, skill keywords, certificates, and achievements; The job data acquisition module is used to acquire target job information of a target object, and perform structured extraction and capability dimension classification based on the target job information to obtain target job data; The employability assessment module is used to semantically associate the personal ability data with preset ability dimensions, generate ability scores and explanatory comments under each ability dimension to obtain a preliminary assessment result, and compare the preliminary assessment result with the target position data to obtain an employability assessment result.

9. A terminal device, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the employability assessment method based on resume documents as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device / apparatus where the computer-readable storage medium is located is controlled to execute the employability assessment method based on resume documents according to any one of claims 1 to 7.

Images