A method, system, device and medium for simulating an interview scene based on a large model

Abstract

The application belongs to the technical field of large models and artificial intelligence, and particularly relates to a method, system, device and medium for simulating an interview scene based on a large model. The method comprises the following steps: obtaining input resume information through a visual interface; preprocessing the input resume information, performing semantic analysis on the input resume by using a large model, extracting key information of the resume in combination with recruitment information of a user company; generating corresponding interview questions based on the analysis result and the key information of the resume, and recording relevant parameters generated in real time; until a set number of question and answer is completed, calculating an interview evaluation index based on the reply information of the job seeker and the resume information; comparing the interview evaluation index with a preset threshold range to obtain an evaluation scheme corresponding to the interview evaluation index; and presenting the generated questions, the corresponding reply information of the job seeker and the evaluation scheme to the user in a visual form. When facing a job seeker, the interview success rate can be improved.

Description

Technical Field

[0001] This invention belongs to the field of large-scale model and artificial intelligence technology, specifically relating to a method, system, device and medium for simulating interview scenarios based on large-scale models. Background Technology

[0002] In the current recruitment process, interviews are a crucial step in assessing whether job seekers meet the requirements. Interviews not only test the thoroughness of a candidate's prepared answers but also assess their responsiveness and interviewing skills. However, traditional interviewing methods often rely on interviewers conducting individual interviews. With the increasing number of job seekers, this requires companies to expend significant time and energy on interviews. Selecting the best-performing and most suitable candidate from a large pool of applicants requires substantial human and material resources.

[0003] To address this issue, automated interview systems based on large models have emerged in recent years. These systems typically extract key information from resumes, generate interview questions, and conduct preliminary assessments based on applicants' responses. However, existing automated interview systems still have some shortcomings. For example, they often can only process simple text information and cannot deeply understand the semantic content of resumes; when generating interview questions, they lack close integration with job posting information, resulting in imprecise questions; and when evaluating applicants' responses, they lack comprehensiveness and accuracy, often offering little help to applicants. Summary of the Invention

[0004] To address the aforementioned problems with existing automated interview systems, this invention provides a method, system, device, and medium for simulating interview scenarios based on a large model.

[0005] In a first aspect, the technical solution of the present invention provides a method for simulating interview scenarios based on a large model, comprising the following steps:

[0006] Obtain the input resume information through a visual interface;

[0007] The input resume information is preprocessed, and a large model is used to perform semantic analysis on the input resume. Combined with the recruitment information of the user's company, key information of the resume is extracted.

[0008] Based on the analysis results and key information from resumes, combined with the recruitment information for the corresponding positions, corresponding interview questions are generated, and relevant parameters are recorded in real time.

[0009] Receive job seekers' responses to questions, and generate interview questions again based on the responses and key information from their resumes;

[0010] After completing a set number of questions and answers, an interview evaluation index is calculated based on the job seeker's responses and resume information.

[0011] The interview evaluation index is compared with a preset threshold range to obtain the evaluation scheme corresponding to the interview evaluation index.

[0012] The generated questions, along with the corresponding job seeker responses and evaluation plans, are presented to the user in a visual format.

[0013] As a preferred embodiment of the technical solution of the present invention, the method further includes:

[0014] Provide a feedback interface to receive user comments and suggestions on the generated questions and evaluation schemes, and optimize and fine-tune the large model based on user comments and suggestions.

[0015] As a preferred embodiment of the technical solution of this invention, the steps of preprocessing the input resume information, performing semantic analysis on the input resume using a large model, and extracting key information from the resume in conjunction with the user company's recruitment information include:

[0016] The resume information data was preprocessed by removing noise and segmenting words using a text preprocessing tool to obtain the preprocessed text data.

[0017] The TF-IDF algorithm is used to perform a preliminary analysis of the preprocessed data and calculate the importance value of each word in the text data.

[0018] Candidate keywords are selected from text data based on calculated importance values:

[0019] By combining the recruitment information of user companies, semantic analysis of candidate keywords is performed using a large model to obtain semantic analysis results;

[0020] Keywords for the resume are determined based on the semantic analysis results.

[0021] As a preferred embodiment of the technical solution of this invention, in the step of performing preliminary analysis on the preprocessed data using the TF-IDF algorithm to calculate the importance value of each word in the text data, the calculation formula is as follows:

[0022] Importance value = term frequency × inverse document frequency;

[0023] Word frequency = the number of times a word appears in an article / the total number of words in the article;

[0024] Inverse document frequency = log(total number of documents in the corpus / (number of documents containing the word + 1)).

[0025] As a preferred embodiment of the technical solution of the present invention, the step of calculating the interview evaluation index based on the job seeker's response information and resume information includes:

[0026] Based on the purpose and requirements of the interview, evaluation indicators are extracted from the job seeker's answers and resume. These evaluation indicators include professional skills, work experience, communication skills, teamwork, and problem-solving abilities.

[0027] Assign a weight to each evaluation indicator;

[0028] Each evaluation metric is scored based on the job seeker's responses and resume information.

[0029] The score for each indicator is multiplied by its corresponding weight to obtain a weighted score.

[0030] Sum all the weighted scores to get the total interview score.

[0031] The overall evaluation score is converted into an interview evaluation index according to the set index range.

[0032] As a preferred embodiment of the technical solution of the present invention, the method further includes:

[0033] Analyze job seekers' resumes and interview responses to identify problems.

[0034] As a preferred embodiment of the technical solution of the present invention, the steps of analyzing job seekers' resumes and job seekers' questions to identify problems in job seekers' resumes and / or interview responses include:

[0035] Collect and organize job seekers' resume information and interview response data;

[0036] Based on the composition of the interview evaluation index, key analytical indicators are set, and the evaluation criteria and thresholds for each analytical indicator are determined.

[0037] The job seeker's resume information and interview answers are compared and analyzed with preset evaluation standards and thresholds;

[0038] Analytical indicators that identify job seekers who fall below the evaluation standards;

[0039] Text mining is performed on job seekers' resumes and interview responses to extract key information and keywords;

[0040] The extracted information is interpreted by combining the identified analytical indicators and evaluation criteria;

[0041] The problems identified in the analysis will be summarized and compiled into a problem report;

[0042] Based on the problem report, provide job seekers with specific improvement suggestions, and then return the problem report and improvement suggestions to the job seekers.

[0043] When conducting mock interviews, job seekers upload their resumes and desired positions. The large-scale simulation platform then accurately simulates the interview scenario based on the information provided. Typically, there are 5-6 rounds of questions. After each question, the job seeker inputs their answer via voice or text. The platform provides a brief evaluation before moving on to the next round. At the end of the mock interview, the platform, acting as the interviewer, summarizes the interview, including the job seeker's strengths and weaknesses, the match between the resume and the position, and offers suggestions for improvement. This helps job seekers identify their shortcomings and develop targeted improvement plans. Through these repeated mock interviews, job seekers master the interviewer's questioning logic and answering techniques, enabling them to better handle various questions in real interviews and increase their chances of success.

[0044] Secondly, the technical solution of the present invention also provides a system based on a large model to simulate an interview scenario, including a resume acquisition module, a processing and analysis module, a question generation module, an interview evaluation index calculation module, an evaluation scheme acquisition module, and an interview result feedback module;

[0045] The resume retrieval module is used to obtain the input resume information through a visual interface;

[0046] The processing and analysis module is used to preprocess the input resume information, perform semantic analysis on the input resume using a large model, and extract key information from the resume by combining it with the recruitment information of the user company.

[0047] The question generation module is used to generate corresponding interview questions based on the analysis results, key information from the resume, and recruitment information for the corresponding position, and to record the relevant parameters in real time; it receives the job seeker's response to the question, and generates interview questions again based on the response and key information from the resume.

[0048] The interview evaluation index calculation module is used to calculate the interview evaluation index based on the job seeker's answers and resume information after a set number of questions and answers have been completed.

[0049] The evaluation scheme acquisition module is used to compare the interview evaluation index with a preset threshold range and obtain the evaluation scheme corresponding to the interview evaluation index.

[0050] The interview result feedback module is used to present the generated questions, corresponding job seeker responses, and evaluation plans to users in a visual format.

[0051] As a preferred embodiment of the technical solution of the present invention, the system further includes a model fine-tuning module, which provides a feedback interface to receive user comments and suggestions on the generated problems and evaluation schemes, and optimizes and fine-tunes the large model based on the user comments and suggestions.

[0052] As a preferred embodiment of the technical solution of the present invention, the processing and analysis module includes a preprocessing unit, an analysis and calculation unit, a candidate word screening unit, a semantic analysis unit, and a keyword determination unit;

[0053] The preprocessing unit is used to perform noise removal and word segmentation on the resume information data using text preprocessing tools to obtain preprocessed text data.

[0054] The analysis and calculation unit is used to perform preliminary analysis on the preprocessed data using the TF-IDF algorithm, and to calculate the importance value of each word in the text data.

[0055] The candidate keyword filtering unit is used to filter candidate keywords from text data based on calculated importance values.

[0056] The semantic analysis unit is used to combine the user company's recruitment information and perform semantic analysis on candidate keywords through a large model to obtain semantic analysis results.

[0057] The keyword determination unit is used to determine the keywords for a resume based on the results of semantic analysis.

[0058] As a preferred embodiment of the technical solution of the present invention, the analysis and calculation unit performs preliminary analysis on the preprocessed data using the TF-IDF algorithm, and the calculation formula for calculating the importance value of each word in the text data is as follows:

[0059] Importance value = term frequency × inverse document frequency;

[0060] Word frequency = the number of times a word appears in an article / the total number of words in the article;

[0061] Inverse document frequency = log(total number of documents in the corpus / (number of documents containing the word + 1)).

[0062] As a preferred embodiment of the technical solution of this invention, the interview evaluation index calculation module is specifically used to extract evaluation indicators from the job seeker's answers and resume according to the purpose and requirements of the interview. The evaluation indicators include professional skills, work experience, communication skills, teamwork, and problem-solving abilities; assign a weight to each evaluation indicator; score each evaluation indicator based on the job seeker's answers and resume information; multiply the score of each indicator by its corresponding weight to obtain a weighted score; sum all the weighted scores to obtain the total interview evaluation score; and convert the total evaluation score into an interview evaluation index according to a set index range.

[0063] As a preferred embodiment of the technical solution of the present invention, the system further includes a job seeker question feedback module, which is used to analyze the job seeker's resume and job seeker questions and point out the problems in the job seeker's resume and / or interview answers.

[0064] As a preferred embodiment of the technical solution of this invention, the job seeker feedback module is specifically used to collect and organize job seekers' resume information and interview response data; based on the composition of the interview evaluation index, key analysis indicators are set, and the evaluation standards and thresholds for each analysis indicator are determined; the job seeker's resume information and interview responses are compared and analyzed with the preset evaluation standards and thresholds; analysis indicators in which the job seeker falls below the evaluation standards are identified; text mining is performed on the job seeker's resume and interview responses to extract key information and keywords; the extracted information is interpreted in conjunction with the identified analysis indicators and evaluation standards; the problems obtained from the analysis are summarized and compiled into a problem report; based on the problem report, specific improvement suggestions are provided to the job seeker, and the problem report and improvement suggestions are fed back to the job seeker.

[0065] Thirdly, the present invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing computer program instructions executable by the at least one processor, the computer program instructions being executed by the at least one processor to enable the at least one processor to perform the method for simulating interview scenarios based on a large model as described in the first aspect.

[0066] Fourthly, the present invention also provides a non-transitory computer-readable storage medium that stores computer instructions that cause the computer to execute the method for simulating interview scenarios based on a large model as described in the first aspect.

[0067] As can be seen from the above technical solutions, this invention has the following advantages: By utilizing a large model to perform semantic analysis on the input resume and combining it with the user company's recruitment information, key information from the resume can be extracted, enabling a deeper understanding of the job seeker's background and experience, providing strong support for generating accurate interview questions. Generating corresponding interview questions based on the analysis results and key information from the resume ensures a high degree of relevance between the questions and the recruitment information and the job seeker's background, thereby improving the relevance and effectiveness of the interview. After completing a set number of question-and-answer sessions, an interview evaluation index is calculated based on the job seeker's responses and resume information, and compared with a preset threshold range to obtain the corresponding evaluation scheme. This method comprehensively considers multiple aspects of the job seeker's performance, improving the accuracy and comprehensiveness of the evaluation. Presenting the generated questions, corresponding job seeker responses, and evaluation schemes to the user in a visual format allows the user to intuitively understand the interview process and results, improving the efficiency of the job seeker's interview. Attached Figure Description

[0068] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0069] Figure 1 This is a schematic flowchart of a method according to an embodiment of the present invention.

[0070] Figure 2 This is a schematic block diagram of a system according to an embodiment of the present invention. Detailed Implementation

[0071] In simulated interview scenarios, Prompt engineering technology offers significant advantages. Traditional simulated interview systems often rely on pre-set question and answer databases, lacking flexibility and adaptability. However, Prompt engineering technology based on a large model can dynamically generate interview questions based on the user's actual resume and the requirements of the applied position, evaluate the applicant's answers, and even provide intelligent guidance based on the interviewee's responses, achieving a more realistic and natural interview experience. To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions in the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0072] like Figure 1 As shown, this embodiment of the invention provides a method for simulating interview scenarios based on a large model, including the following steps:

[0073] Step 1: Obtain the input resume information through a visual interface;

[0074] Step 2: Preprocess the input resume information, use a large model to perform semantic analysis on the input resume, and extract key information from the resume by combining it with the recruitment information of the user company;

[0075] Step 3: Based on the analysis results and key information from the resumes, combined with the recruitment information for the corresponding positions, generate corresponding interview questions and record the relevant parameters in real time;

[0076] Step 4: Receive the job seeker's responses to the questions, and generate interview questions again based on the responses and key information from the resume;

[0077] Step 5: After completing the set number of questions and answers, calculate the interview evaluation index based on the job seeker's responses and resume information;

[0078] Step 6: Compare the interview evaluation index with a preset threshold range to obtain the evaluation scheme corresponding to the interview evaluation index;

[0079] Step 7: Present the generated questions, corresponding job seeker responses, and evaluation plans to the user in a visual format.

[0080] In some embodiments, the method further includes:

[0081] Provide a feedback interface to receive user comments and suggestions on the generated questions and evaluation schemes, and optimize and fine-tune the large model based on user comments and suggestions.

[0082] First, design the feedback interface. Specifically, design an intuitive and user-friendly layout to ensure users can easily find the entry point to submit comments and suggestions. Provide input fields such as text boxes, radio buttons, and checkboxes to facilitate users entering different types of feedback. Set a clear submit button to ensure users can easily submit feedback. Clearly inform users on the interface how their privacy will be protected and obtain necessary privacy authorization.

[0083] Next, user comments and suggestions are collected through the feedback interface. The collected feedback data is stored in a secure database to ensure data integrity and traceability. The collected data is then cleaned to remove invalid or duplicate feedback.

[0084] The third step involves textual analysis of user comments to extract key information and opinions. Sentiment analysis techniques are then used to determine user satisfaction with the issues and evaluation solutions. User feedback is categorized into different types, such as inaccurate question generation or unreasonable evaluation solutions. Based on the analysis results, problems in the large-scale model regarding question generation and evaluation solution formulation are identified. Specific optimization strategies are then developed for these identified problems, such as adjusting model parameters and improving the algorithm. These optimization strategies are prioritized according to the severity and urgency of the problems.

[0085] The fourth step is to train and adjust the large model according to the optimization strategy. After training, the newly generated problems and evaluation schemes are evaluated to ensure that the optimization effect meets expectations. Based on the evaluation results, the optimization strategy is continuously adjusted and iteratively improved. The optimized problems and evaluation schemes are then presented to the user, informing them of the optimization results.

[0086] In some embodiments, the steps of preprocessing the input resume information, performing semantic analysis on the input resume using a large model, and extracting key information from the resume in conjunction with the user company's recruitment information include:

[0087] Step 21: Use a text preprocessing tool to preprocess the resume information data by removing noise and segmenting words to obtain the preprocessed text data;

[0088] Step 22: Perform preliminary analysis on the preprocessed data using the TF-IDF algorithm to calculate the importance value of each word in the text data;

[0089] Step 23: Select candidate keywords from the text data based on the calculated importance values:

[0090] Step 24: Combine the user company's recruitment information and use a large model to perform semantic analysis on the candidate keywords to obtain the semantic analysis results;

[0091] Step 25: Determine the keywords for the resume based on the semantic analysis results. The resume should include information related to the position being applied for.

[0092] It should be noted that in the step of performing preliminary analysis of the preprocessed data using the TF-IDF algorithm to calculate the importance value of each word in the text data, the calculation formula is as follows:

[0093] Importance value = term frequency × inverse document frequency;

[0094] Word frequency = the number of times a word appears in an article / the total number of words in the article;

[0095] Inverse document frequency = log(total number of documents in the corpus / (number of documents containing the word + 1)).

[0096] In some embodiments, the step of calculating the interview evaluation index based on the job seeker's responses and resume information includes:

[0097] Step 51: Based on the purpose and requirements of the interview, extract evaluation indicators from the job seeker's answers and resume. Evaluation indicators include professional skills, work experience, communication skills, teamwork, and problem-solving skills.

[0098] Step 52: Assign a weight to each evaluation indicator;

[0099] Step 53: Based on the job seeker's responses and resume information, score each evaluation indicator;

[0100] Step 54: Multiply the score of each indicator by its corresponding weight to obtain the weighted score;

[0101] Step 55: Sum all the weighted scores to get the total interview score;

[0102] Step 56: Convert the total evaluation score into an interview evaluation index according to the set index range.

[0103] It should be noted that the specific process for calculating the interview evaluation index is as follows:

[0104] First, organize the job seekers' responses and resume information, ensuring consistent data formats for easier subsequent processing. Standardize key information in the responses and resumes, such as converting textual responses into numerical scores, or quantifying work experience and educational background in resumes according to uniform standards.

[0105] Based on the purpose and requirements of the interview, extract key evaluation indicators from the candidate's responses and resume. These indicators may include professional skills, work experience, communication skills, teamwork, and problem-solving abilities. Assign a weight to each evaluation indicator, reflecting its importance in the overall evaluation. The weighting can be determined based on company needs, job requirements, industry standards, and other factors. Score each evaluation indicator based on the candidate's responses and resume information. Scoring can use a five-point rating system (e.g., 1-5 points), a percentage system, or other suitable methods. Multiply each indicator's score by its corresponding weight to obtain a weighted score. Sum all weighted scores to obtain the overall interview evaluation score.

[0106] The overall evaluation score is converted into an interview evaluation index. This can be achieved by mapping the overall score to a specific index range, such as 0-100. The interview evaluation index reflects the candidate's overall performance level during the interview. The interview evaluation index is compared with a preset threshold range, and an appropriate evaluation plan is generated based on the comparison results. The evaluation plan may include recommendations such as recommended hiring, pending further evaluation, or not recommended hiring.

[0107] The generated questions, job seekers' responses, interview evaluation indices, and corresponding assessment plans are presented to users in a visual format to help them make decisions.

[0108] In some embodiments, the method further includes:

[0109] Analyze job seekers' resumes and interview responses to identify problems. Specifically, this includes:

[0110] Step 81: Collect and organize job seekers' resume information and interview response data;

[0111] Step 82: Based on the composition of the interview evaluation index, set key analysis indicators and determine the evaluation criteria and thresholds for each analysis indicator.

[0112] Step 83: Compare and analyze the job seeker's resume information and interview answers with the preset evaluation criteria and thresholds;

[0113] Step 84: Identify analytical indicators that job seekers fall below the evaluation criteria;

[0114] Step 85: Perform text mining on job seekers' resumes and interview responses to extract key information and keywords;

[0115] Step 86: Interpret the extracted information by combining the identified analytical indicators and evaluation criteria;

[0116] Step 87: Summarize and conclude the problems identified in the analysis, and form a problem report;

[0117] Step 88: Based on the problem report, provide specific improvement suggestions to the job seeker, and then return the problem report and improvement suggestions to the job seeker.

[0118] Based on the steps described above for analyzing job seekers' resumes and answering questions to identify problems in their resumes and / or interview responses, another application of this application includes:

[0119] Job seekers input their resumes and the positions they are applying for, or their resumes include the applied-for position. Guided by prompts, the large-scale model generates multiple highly relevant interview questions based on the job requirements and resume. After the job seeker answers the questions, the model professionally evaluates their responses, summarizing their strengths and weaknesses, and proceeds to the next round of questions. Once all questions are asked, the model provides an overall professional assessment of the job seeker's performance, pointing out strengths and weaknesses, and offering suggestions for improvement. Through multiple rounds of dialogue with job seekers, this highly realistic interview practice platform significantly improves their interview skills, increases their chances of success, and boosts their confidence, ultimately contributing to a higher employment rate.

[0120] Choosing a suitable large model requires the ability to provide prompts for project implementation. This can be an open-source or self-developed large model. Larger models generally yield better results. After selecting a base model, the large model environment needs to be set up. This includes configuring the GPU server based on the chosen model, installing the GPU server, installing and deploying the base model, and configuring the environment. After setting up the large model environment, test data needs to be collected and constructed for subsequent algorithm debugging and optimization. This primarily involves the candidate's resume and the job posting. Resumes should include age, gender, education, major, skill set, work experience, skills training, and job objective. Job postings should include company name, business scope, job responsibilities, skill requirements, education and major requirements. The more detailed the information provided, the better the mock interview will be.

[0121] Prompt Project Development - Job Role Assessment: Based on the above plan, you need to develop a prompt project according to actual needs. According to the requirements and format specifications of the prompt project, refine the instructions for each step the large model needs to complete, forming text content that the large model can accurately understand.

[0122] 1) Resume Prompt: Write a function to determine if the user's input is a properly formatted resume. If it is, return true, and the main model continues to the next step. If not, return false, prompting the user to re-enter their resume. Example instruction:

[0123] isResume: You are an interview material assessment expert. You need to determine whether the user input is resume information. The following principles must be followed: 1. Output false if the input is information unrelated to the resume; 2. Output true if the input is a resume; 3. You must output one of these two answers, and other answers are prohibited. User input: {userInput}.

[0124] 2) Job Requirements Prompt: Please provide a text file. I will determine whether this text contains content related to the job requirements. The criteria are as follows: 1. If the text is unrelated to the job requirements, output "False"; 2. If the text contains content related to the job requirements, even if not all of the text is relevant, output "True"; 3. I will only output "True" or "False" and will not provide other options. Text: {userInput}.

[0125] 3) Generate Interview Question Prompt: You are an interview expert. You can generate 6 different interview questions based on the input job requirements and user resume. Output format: "Question 1: Based on your resume, I have a question I'd like to know..."; "Question 2: Next, I'd like to know..."; "Question 3: Next, I'd like to know..."; "Question 4: Next, I'd like to know..."; "Question 5: Next, I'd like to know..."; "Question 6: The last question...". The following principles must be followed: 1. Do not give questions beyond the scope of the resume. You can give some detailed questions about the technologies mentioned in the resume; 2. You must strictly follow the output format. Do not use other formats. Ensure that the output includes Questions 1, 2, 3, 4, 5, and 6. Do not omit any; 3. The questions should cover the resume as comprehensively as possible. Job Requirements: {demands}. User Resume: {resume}.

[0126] 4) Evaluation prompt for each interview question's answer: You need to act as an interview coach and provide feedback based on the provided interview questions and answers. For each answer, you need to choose one of the following three options to output: 1. If the answer is significantly off-topic, reply directly: "Please answer the interview question, do not give irrelevant answers." 2. If the respondent requests a different question or indicates that they cannot answer, reply: "A different question has been provided for you." 3. If the answer provides specific content related to the question, even if it is not comprehensive, you should provide a brief evaluation. Feedback should be one or two sentences, evaluating the answer, using the second person "you," pointing out the strengths of the answer, but avoiding asking for more information or raising new questions. Question: {question}. Answer: {answer}.

[0127] 5) Post-interview summary prompt: You are an interview expert. You need to provide an overall evaluation of the interview process based on the job requirements, user resume, questions, and answers. The following principles should be followed: 1. Evaluation format requirements: In the interview, your performance was... (strengths), in xx aspect... (strengths), in xx aspect... (strengths), but there is room for improvement in... (weaknesses). I suggest you... (suggestions for improvement). 2. Evaluation must consider both the fit between the user's resume and the job requirements, and the user's responses. 3. The presence of "I don't know" in questions and answers indicates a lack of knowledge on the subject; this can be addressed in the section on areas of weakness within the template. 4. Provide personalized suggestions for the user's interview responses to facilitate improvement and enhance their interview skills. 5. Do not include the user's name or names from their resume; use the second-person pronoun "you" for the overall interview evaluation. 6. Evaluation must be detailed and not generic; it must consider both the user's resume and responses, providing an overall assessment of all responses. Do not evaluate individual answers; provide a holistic evaluation of all responses. 7. If a user's responses contain four or more "I don't know," the mandatory overall evaluation output should be: "During today's interview, you seemed to encounter some difficulties answering questions, failing to provide specific answers. This may be due to communication issues, insufficient preparation, or the challenge of coping with interview pressure. Nevertheless, I still appreciate your participation and effort today. Due to the lack of specific answers, I cannot directly assess your professional abilities and suitability for the position." We suggest you strengthen your preparation for future interviews and improve your performance under pressure. Job Requirements: {demands}. User Resume: {resume}. Questions and Answers: {q&a}.

[0128] Based on the above solution, call the prompt-related interfaces provided by the large model, execute the above content in sequence, and output the returned content of the large model at each step.

[0129] like Figure 2 As shown, this embodiment of the invention also provides a system for simulating interview scenarios based on a large model, including a resume acquisition module, a processing and analysis module, a question generation module, an interview evaluation index calculation module, an evaluation scheme acquisition module, and an interview result feedback module;

[0130] The resume retrieval module is used to obtain the input resume information through a visual interface;

[0131] The processing and analysis module is used to preprocess the input resume information, perform semantic analysis on the input resume using a large model, and extract key information from the resume by combining it with the recruitment information of the user company.

[0132] The question generation module is used to generate corresponding interview questions based on the analysis results, key information from the resume, and recruitment information for the corresponding position, and to record the relevant parameters in real time; it receives the job seeker's response to the question, and generates interview questions again based on the response and key information from the resume.

[0133] The interview evaluation index calculation module is used to calculate the interview evaluation index based on the job seeker's answers and resume information after a set number of questions and answers have been completed.

[0134] The evaluation scheme acquisition module is used to compare the interview evaluation index with a preset threshold range and obtain the evaluation scheme corresponding to the interview evaluation index.

[0135] The interview result feedback module is used to present the generated questions, corresponding job seeker responses, and evaluation plans to users in a visual format.

[0136] In some embodiments, the system also includes a model fine-tuning module that provides a feedback interface to receive user comments and suggestions on the generated problems and evaluation schemes, and to optimize and fine-tune the large model based on the user comments and suggestions.

[0137] In some embodiments, the processing and analysis module includes a preprocessing unit, an analysis and calculation unit, a candidate word screening unit, a semantic analysis unit, and a keyword determination unit;

[0138] The preprocessing unit is used to perform noise removal and word segmentation on the resume information data using text preprocessing tools to obtain preprocessed text data.

[0139] The analysis and calculation unit is used to perform preliminary analysis on the preprocessed data using the TF-IDF algorithm, and to calculate the importance value of each word in the text data.

[0140] The candidate keyword filtering unit is used to filter candidate keywords from text data based on calculated importance values.

[0141] The semantic analysis unit is used to combine the user company's recruitment information and perform semantic analysis on candidate keywords through a large model to obtain semantic analysis results.

[0142] The keyword determination unit is used to determine the keywords for a resume based on the results of semantic analysis.

[0143] In some embodiments, the analysis and calculation unit performs preliminary analysis on the preprocessed data using the TF-IDF algorithm. The formula for calculating the importance value of each word in the text data is as follows:

[0144] Importance value = term frequency × inverse document frequency;

[0145] Word frequency = the number of times a word appears in an article / the total number of words in the article;

[0146] Inverse document frequency = log(total number of documents in the corpus / (number of documents containing the word + 1)).

[0147] In some embodiments, the interview evaluation index calculation module is specifically used to extract evaluation indicators from the job seeker's answers and resume according to the purpose and requirements of the interview. The evaluation indicators include professional skills, work experience, communication skills, teamwork, and problem-solving skills; assign a weight to each evaluation indicator; score each evaluation indicator based on the job seeker's answers and resume information; multiply the score of each indicator by its corresponding weight to obtain a weighted score; sum all the weighted scores to obtain the total interview evaluation score; and convert the total evaluation score into an interview evaluation index according to a set index range.

[0148] In some embodiments, the system also includes a job seeker question feedback module, which is used to analyze the job seeker's resume and job seeker questions and point out problems in the job seeker's resume and / or interview answers when the interview evaluation index is lower than the re-interview threshold.

[0149] In some embodiments, the job seeker feedback module is specifically used to collect and organize job seekers' resume information and interview response data; set key analysis indicators based on the composition of the interview evaluation index, and determine the evaluation criteria and thresholds for each analysis indicator; compare and analyze the job seeker's resume information and interview responses with the preset evaluation criteria and thresholds; identify analysis indicators in which the job seeker's performance falls below the evaluation criteria; perform text mining on the job seeker's resume and interview responses to extract key information and keywords; interpret the extracted information in conjunction with the identified analysis indicators and evaluation criteria; summarize and conclude the analyzed problems to form a problem report; provide specific improvement suggestions to the job seeker based on the problem report, and provide feedback on the problem report and improvement suggestions to the job seeker.

[0150] This invention also provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other via the communication bus. The communication bus can be used for information transmission between the electronic device and sensors. The processor can call logical instructions in the memory to execute the following method: Step 1: Obtain input resume information through a visual interface; Step 2: Preprocess the input resume information, perform semantic analysis on the input resume using a large model, and extract key information from the resume in conjunction with the recruitment information of the user's company; Step 3: Generate corresponding interview questions based on the analysis results and the key information of the resume, combined with the recruitment information of the corresponding position, and record the relevant parameters generated in real time; Step 4: Receive the job seeker's response information based on the questions, and generate interview questions again based on the response information and the key information of the resume; Step 5: After completing a set number of question-and-answer sessions, calculate the interview evaluation index based on the job seeker's response information and resume information; Step 6: Compare the interview evaluation index with a preset threshold range to obtain the evaluation scheme corresponding to the interview evaluation index; Step 7: Present the generated questions, the corresponding job seeker's response information, and the evaluation scheme to the user in a visual form.

[0151] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0152] This invention provides a non-transitory computer-readable storage medium storing computer instructions that cause a computer to execute the method provided in the above-described method embodiments, including, for example, the following steps: Step 1: Obtaining input resume information through a visual interface; Step 2: Preprocessing the input resume information, performing semantic analysis on the input resume using a large model, and extracting key information from the resume in conjunction with the user company's recruitment information; Step 3: Generating corresponding interview questions based on the analysis results and the key information in the resume, combined with the recruitment information for the corresponding position, and recording the relevant parameters generated in real time; Step 4: Receiving the job seeker's response information based on the questions, and generating interview questions again based on the response information and the key information in the resume; Step 5: Calculating an interview evaluation index based on the job seeker's response information and resume information after completing a set number of question-and-answer sessions; Step 6: Comparing the interview evaluation index with a preset threshold range to obtain an evaluation scheme corresponding to the interview evaluation index; Step 7: Presenting the generated questions, the corresponding job seeker's response information, and the evaluation scheme to the user in a visual form.

[0153] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0154] The embodiments of the present invention provide an embodiment of a system based on a large model simulating an interview scenario. This system and the methods based on a large model simulating an interview scenario described in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the system based on a large model simulating an interview scenario, please refer to the embodiments of the methods based on a large model simulating an interview scenario described above.

[0155] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A method for simulating interview scenarios based on a large model, characterized in that, include: Obtain the input resume information through a visual interface; The input resume information is preprocessed, and a large model is used to perform semantic analysis on the input resume. Combined with the recruitment information of the user's company, key information in the resume is extracted. Based on the analysis results and key information from resumes, combined with the recruitment information for the corresponding positions, corresponding interview questions are generated, and relevant parameters are recorded in real time. Receive job seekers' responses to questions, and generate interview questions again based on the responses and key information from their resumes; After completing a set number of questions and answers, an interview evaluation index is calculated based on the job seeker's responses and resume information. The interview evaluation index is compared with a preset threshold range to obtain the evaluation scheme corresponding to the interview evaluation index. The generated questions, along with the corresponding job seeker responses and evaluation plans, are presented to users in a visual format. The steps involved in preprocessing the input resume information, performing semantic analysis on the input resume using a large model, and extracting key information from the resume by combining it with the user company's recruitment information include: The resume information data was preprocessed by removing noise and segmenting words using a text preprocessing tool to obtain the preprocessed text data. The TF-IDF algorithm is used to perform a preliminary analysis of the preprocessed data and calculate the importance value of each word in the text data. Candidate keywords are selected from text data based on calculated importance values; By combining the user company's recruitment information, semantic analysis of candidate keywords is performed using a large model to obtain semantic analysis results; Keywords for the resume are determined based on the semantic analysis results; The method also includes: Provide a feedback interface to receive user comments and suggestions on the generated questions and evaluation schemes, and optimize and fine-tune the large model based on user comments and suggestions.

2. The method for simulating interview scenarios based on a large model according to claim 1, characterized in that, The TF-IDF algorithm is used to perform preliminary analysis of the preprocessed data. The formula for calculating the importance value of each word in the text data is as follows: Importance value = term frequency × inverse document frequency; Word frequency = the number of times a word appears in an article / the total number of words in the article; Inverse document frequency = log(total number of documents in the corpus / (number of documents containing the word + 1)).

3. The method for simulating interview scenarios based on a large model according to claim 2, characterized in that, The steps for calculating the interview evaluation index based on the job seeker's responses and resume information include: Based on the purpose and requirements of the interview, evaluation indicators are extracted from the job seeker's answers and resume. These evaluation indicators include professional skills, work experience, communication skills, teamwork, and problem-solving abilities. Assign a weight to each evaluation indicator; Each evaluation metric is scored based on the job seeker's responses and resume information. The score for each indicator is multiplied by its corresponding weight to obtain a weighted score. Sum all the weighted scores to get the total interview score. The overall evaluation score is converted into an interview evaluation index according to the set index range.

4. The method for simulating interview scenarios based on a large model according to claim 3, characterized in that, The method also includes: Analyze job seekers' resumes and interview responses to identify problems.

5. The method for simulating interview scenarios based on a large model according to claim 4, characterized in that, The steps for analyzing job seekers' resumes and interview responses to identify problems include: Collect and organize job seekers' resume information and interview response data; Based on the composition of the interview evaluation index, key analytical indicators are set, and the evaluation criteria and thresholds for each analytical indicator are determined. The job seeker's resume information and interview answers are compared and analyzed with preset evaluation standards and thresholds; Analytical indicators that identify job seekers who fall below the evaluation standards; Text mining is performed on job seekers' resumes and interview responses to extract key information and keywords; The extracted information is interpreted by combining the identified analytical indicators and evaluation criteria; The problems identified in the analysis will be summarized and compiled into a problem report; Based on the problem report, provide job seekers with specific improvement suggestions, and then return the problem report and improvement suggestions to the job seekers.

6. A system for simulating interview scenarios based on a large model, characterized in that, It includes modules for resume acquisition, processing and analysis, question generation, interview evaluation index calculation, assessment scheme acquisition, and interview result feedback. The resume retrieval module is used to obtain the input resume information through a visual interface; The processing and analysis module is used to preprocess the input resume information, perform semantic analysis on the input resume using a large model, and extract key information from the resume by combining it with the recruitment information of the user company. The question generation module is used to generate corresponding interview questions based on the analysis results, key information from resumes, and recruitment information for the corresponding positions, and to record the relevant parameters generated in real time. Receive job seekers' responses to questions, and generate interview questions again based on the responses and key information from their resumes; The interview evaluation index calculation module is used to calculate the interview evaluation index based on the job seeker's answers and resume information after a set number of questions and answers have been completed. The evaluation scheme acquisition module is used to compare the interview evaluation index with a preset threshold range and obtain the evaluation scheme corresponding to the interview evaluation index. The interview result feedback module is used to present the generated questions, corresponding job seeker responses, and evaluation plans to users in a visual format. The steps involved in preprocessing the input resume information, performing semantic analysis on the input resume using a large model, and extracting key information from the resume by combining it with the user company's recruitment information include: The resume information data was preprocessed by removing noise and segmenting words using a text preprocessing tool to obtain the preprocessed text data. The TF-IDF algorithm is used to perform a preliminary analysis of the preprocessed data and calculate the importance value of each word in the text data. Candidate keywords are selected from text data based on calculated importance values: By combining the user company's recruitment information, semantic analysis of candidate keywords is performed using a large model to obtain semantic analysis results; Keywords for the resume are determined based on the semantic analysis results; The system is also configured to perform the following steps: Provide a feedback interface to receive user comments and suggestions on the generated questions and evaluation schemes, and optimize and fine-tune the large model based on user comments and suggestions.

7. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; the memory stores computer program instructions executable by the at least one processor, the computer program instructions being executed by the at least one processor to enable the at least one processor to perform the method based on a large model simulating an interview scenario as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the method for simulating interview scenarios based on a large model as described in any one of claims 1 to 5.

Images