Interview video generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an interview video generation method and device, electronic equipment and a storage medium, and relates to the technical field of online interview, and the method comprises the steps: in response to the detection of a resume delivery operation for a target post, if the target post starts an AI video interview function, outputting an AI interview invitation for the target post; in response to a confirmation operation for the AI interview invitation, displaying an interview page in the graphical user interface, and outputting an interview question for the target post in the interview page; and in response to the detection that the job hunting user completes the answer to all the interview questions, generating a first interview video for the target post, and sending the first interview video to the recruitment terminal to which the target post belongs, thereby shortening the recruitment period and improving the recruitment efficiency. Therefore, the processes of the job hunting user and the recruitment user are effectively optimized, and the efficiency of the job hunting user and the recruitment user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of online interviews, and in particular to a method for generating an interview video, a device for generating an interview video, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rise of online job search, recruiters can post corresponding job positions and job requirements on the Internet in order to recruit suitable job seekers; accordingly, job seekers can create their own resumes on the Internet, browse the job positions posted by recruiters, find suitable jobs for themselves, and then communicate with recruiters online to achieve two-way selection. However, in the process of online communication, it is often necessary to go through the process of recruiters posting positions-job seekers creating resumes-job seekers screening positions / recruiters screening job seekers-job seekers submitting resumes / recruiters actively initiating communication-job seekers and recruiters communicating online, etc. The online job search process is too cumbersome and can neither guarantee the job search efficiency of job seekers nor the recruitment efficiency of recruiters. Summary of the invention

[0003] The embodiments of the present invention provide a method, device, electronic device and computer-readable storage medium for generating an interview video, so as to solve or partially solve the problem of low efficiency in the online job search process.

[0004] The embodiment of the present invention discloses a method for generating an interview video, wherein a job-seeking terminal provides a graphical user interface, and the content displayed by the graphical user interface at least includes an application interface. The method comprises:

[0005] In response to detecting a resume submission operation for a target position, if the target position has an AI video interview function enabled, outputting an AI interview invitation for the target position;

[0006] In response to a confirmation operation on the AI ​​interview invitation, an interview page is displayed in the graphical user interface, and interview questions for the target position are output on the interview page;

[0007] In response to detecting that the job seeker has completed answering all the interview questions, a first interview video for the target position is generated, and the first interview video is sent to a recruitment terminal to which the target position belongs.

[0008] In some feasible implementations, after displaying the interview page in the graphical user interface, the method further includes:

[0009] If the interview video exists locally, the interview video is displayed on the interview page;

[0010] In response to a selection operation on the interview video, a second interview video matching the target position is determined, and the second interview video is sent to a recruitment terminal to which the target position belongs.

[0011] In some feasible implementations, displaying the interview video on the interview page includes:

[0012] The interview video and the video creation time and position identification corresponding to the interview video are displayed on the interview page.

[0013] Some possible implementations also include:

[0014] In response to the job search progress viewing operation, a job search management page is displayed in the graphical user interface, and at least one of a job application card, an interview invitation card, a browsing record card, and an interview feedback card is displayed in the job search management page. The interview feedback card includes a feedback status corresponding to the interview video, and the feedback status includes one of interview passed, interview failed, and video abnormality.

[0015] Some possible implementations also include:

[0016] In response to a confirmation operation on the interview invitation card, an interview page is displayed in the graphical user interface, and interview questions corresponding to the interview invitation card are output in the interview page.

[0017] In some feasible implementations, the method further includes:

[0018] In response to a deletion operation on the interview feedback card, a target interview feedback card corresponding to the deletion operation and a third interview video corresponding to the target interview feedback card are deleted, and a deletion message for the third interview video is generated;

[0019] The deletion message is synchronized to the target recruitment terminal that receives the third interview video, and the deletion message is used to instruct the target recruitment terminal to mark the third interview video as deleted and unavailable for browsing.

[0020] Some possible implementations also include:

[0021] If the interview video corresponding to the interview feedback card is in an abnormal video state and an interview instruction for the interview feedback card is detected, an interview page is displayed in the graphical user interface, and abnormal questions corresponding to the interview feedback card are output in the interview page.

[0022] Some possible implementations also include:

[0023] In response to receiving a marking message for the first interview video, displaying an interview result label for the first interview video according to the marking message;

[0024] The interview result label includes one of an interview passed label and an interview failed label.

[0025] In some feasible implementations, after outputting the interview questions for the target position on the interview page, the method further includes:

[0026] In response to the job seeker completing an answer to any interview question, determining whether the answer provided by the job seeker contains key information required by the interview question;

[0027] If it is determined that the answer content lacks any key information required by the interview question, constructing the interview question and the answer content as the first input data of the target large model;

[0028] Obtaining first prompt information, wherein the first prompt information is used to instruct the target large model to ask follow-up questions according to the interview question and the answer content in the input data, and the prompt information includes at least one of an interview question instance, an answer content instance, and a corresponding follow-up question instance;

[0029] Inputting the first input data and the prompt information into the target large model to perform question prediction, and generate follow-up questions corresponding to the interview questions;

[0030] The follow-up questions are displayed in the interview page to guide the job seeker to provide key information required by the interview questions.

[0031] In some feasible implementations, the determining whether the answer provided by the job seeker contains key information required for the interview question includes:

[0032] Obtaining answers provided by job seekers to the interview questions;

[0033] The target position, the interview question, and the answer content are constructed as second input data of the target macro model, and second prompt information is obtained, wherein the second prompt information is used to prompt the target macro model to extract key information from the answer content according to the interview question and the target position in the second input data, and the prompt information also includes at least one of an interview question instance, a position type instance, an answer content instance, and a corresponding key information instance;

[0034] The prompt information and the second input data are input into the target large model, and information is extracted from the answer content to obtain key information corresponding to the answer content.

[0035] The embodiment of the present invention further discloses a device for generating an interview video, wherein a job-seeking terminal provides a graphical user interface, and the content displayed by the graphical user interface at least includes an application interface. The device comprises:

[0036] An invitation output module, configured to respond to detecting a resume submission operation for a target position, and if the target position has an AI video interview function enabled, output an AI interview invitation for the target position;

[0037] An interview page display module, configured to display an interview page in the graphical user interface in response to a confirmation operation on the AI ​​interview invitation, and output interview questions for the target position on the interview page;

[0038] The video generation module is used to generate a first interview video for the target position in response to detecting that the job seeker has completed answering all the interview questions, and send the first interview video to the recruitment terminal to which the target position belongs.

[0039] In some feasible implementations, the device further includes:

[0040] A video display module, used to display the interview video on the interview page if the interview video exists locally;

[0041] The video sending module is used to determine a second interview video matching the target position in response to a selection operation on the interview video, and send the second interview video to a recruitment terminal to which the target position belongs.

[0042] In some feasible implementations, the video display module is specifically used for:

[0043] The interview video and the video creation time and position identification corresponding to the interview video are displayed on the interview page.

[0044] Some possible implementations also include:

[0045] The process viewing module is used to respond to the job search progress viewing operation, display a job search management page in the graphical user interface, and display at least one of a job application card, an interview invitation card, a browsing record card, and an interview feedback card in the job search management page, wherein the interview feedback card includes a feedback status corresponding to the interview video, and the feedback status includes one of interview passed, interview failed, and video abnormality.

[0046] Some possible implementations also include:

[0047] An interview processing module is used to display an interview page in the graphical user interface in response to a confirmation operation on the interview invitation card, and output interview questions corresponding to the interview invitation card in the interview page.

[0048] In some feasible implementations, the device further includes:

[0049] A deletion module, configured to, in response to a deletion operation on the interview feedback card, delete the target interview feedback card corresponding to the deletion operation and the third interview video corresponding to the target interview feedback card, and generate a deletion message for the third interview video;

[0050] A synchronization module is used to synchronize the deletion message to a target recruitment terminal that has received the third interview video, wherein the deletion message is used to instruct the target recruitment terminal to mark the third interview video as deleted and unavailable for browsing.

[0051] Some possible implementations also include:

[0052] The abnormal prompt module is used to display the interview page in the graphical user interface and output the abnormal questions corresponding to the interview feedback card in the interview page if the interview video corresponding to the interview feedback card is in an abnormal video state and an interview instruction for the interview feedback card is detected.

[0053] Some possible implementations also include:

[0054] a marking message receiving module, configured to, in response to receiving a marking message for the first interview video, display an interview result label for the first interview video according to the marking message;

[0055] The interview result label includes one of an interview passed label and an interview failed label.

[0056] In some feasible implementations, the device further includes:

[0057] A key information detection module, configured to determine, in response to a job seeker completing an answer to any interview question, whether the answer provided by the job seeker contains the key information required by the interview question;

[0058] A data construction module, for constructing the interview question and the answer content as the first input data of the target large model if it is determined that the answer content lacks any key information required by the interview question;

[0059] An information acquisition module, used to acquire first prompt information, wherein the first prompt information is used to instruct the target macro model to ask follow-up questions according to the interview question and the answer content in the input data, and the prompt information includes at least one of an interview question instance, an answer content instance, and a corresponding follow-up question instance;

[0060] A question generation module, used for inputting the first input data and the prompt information into the target large model to perform question prediction and generate follow-up questions corresponding to the interview questions;

[0061] The question display module is used to display the follow-up questions in the interview page to guide the job seeker to provide key information required by the interview questions.

[0062] In some feasible implementations, the key information detection module is specifically used to:

[0063] Obtaining answers provided by job seekers to the interview questions;

[0064] The target position, the interview question, and the answer content are constructed as second input data of the target macro model, and second prompt information is obtained, wherein the second prompt information is used to prompt the target macro model to extract key information from the answer content according to the interview question and the target position in the second input data, and the prompt information also includes at least one of an interview question instance, a position type instance, an answer content instance, and a corresponding key information instance;

[0065] The prompt information and the second input data are input into the target large model, and information is extracted from the answer content to obtain key information corresponding to the answer content.

[0066] The embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0067] The memory is used to store computer programs;

[0068] The processor is used to implement the method described in the embodiment of the present invention when executing the program stored in the memory.

[0069] The embodiment of the present invention further discloses a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, enables the processors to execute the method described in the embodiment of the present invention.

[0070] The embodiments of the present invention include the following advantages:

[0071] In an embodiment of the present invention, a job seeker can realize online job search through an application. During the online job search process, the job seeker can submit a resume for a desired target position. When the terminal detects the resume submission operation for the target position, it can detect the target position to determine whether the AI ​​video interview function is enabled for the target position. If the AI ​​video interview function is enabled for the target position, an AI interview invitation for the target position is output. The recruiting user turns on the AI ​​video interview function corresponding to the target position, so that when a resume submission is detected, the system can automatically trigger an invitation to the job seeker for a video interview, effectively simplifying the recruitment process of the recruiting user and improving the recruitment efficiency. For the job seeker, he can accept the AI ​​interview invitation, and the terminal will respond based on the job seeker input. The job seeker performs a confirmation operation for the AI ​​interview invitation, displays the interview page in the graphical user interface, and outputs interview questions for the target position in the interview page. The job seeker can conduct an interview based on the interview questions. Then, in response to detecting that the job seeker has completed answering all the interview questions, a first interview video for the target position is generated, and the first interview video is sent to the recruitment terminal to which the target position belongs, thereby effectively simplifying the interview process of the job seeker through online video interviews. The job seeker can present relevant information about himself through the interview video, saving commuting time and cost. At the same time, the recruitment user can understand the relevant information of the job seeker based on the interview video, shortening the recruitment cycle, thereby effectively optimizing the processes of both the job seeker and the recruitment user and improving the efficiency of both parties. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 It is a flowchart of the steps of a method for generating an interview video provided in an embodiment of the present invention;

[0073] Figure 2 is a schematic diagram of an application interface provided in an embodiment of the present invention;

[0074] Figure 3 is a schematic diagram of an application interface provided in an embodiment of the present invention;

[0075] Figure 4 is a schematic diagram of an application interface provided in an embodiment of the present invention;

[0076] Figure 5 is a schematic diagram of an application interface provided in an embodiment of the present invention;

[0077] Figure 6 It is a structural block diagram of a device for generating an interview video provided in an embodiment of the present invention;

[0078] Figure 7 It is a block diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0080] As an example, in the process of online communication, it is often necessary to go through the following steps: recruiters post jobs - job seekers create resumes - job seekers screen jobs / recruiters screen job seekers - job seekers submit resumes / recruiters actively initiate communication - job seekers and recruiters communicate online. The online job search process is too cumbersome and can neither guarantee the job search efficiency of job seekers nor the recruitment efficiency of recruiters.

[0081] In this regard, in the present invention, by combining AI (Artificial Intelligence) technology, the online job search process is optimized. Specifically, job seekers can submit resumes to their desired target positions. When the terminal detects the resume submission operation for the target position, it can detect the target position to determine whether the AI ​​video interview function is enabled for the target position. If the AI ​​video interview function is enabled for the target position, the AI ​​interview invitation for the target position is output. The recruiting user turns on the AI ​​video interview function corresponding to the target position, so that when the resume submission is detected, the system can automatically trigger the job seeker to conduct a video interview, which effectively simplifies the recruitment process of the recruiting user and improves the recruitment efficiency. For the job seeker, he can accept the AI ​​interview invitation, and the terminal can select the target position based on the job seeker input. The confirmation operation of the AI ​​interview invitation displays the interview page in the graphical user interface, and outputs the interview questions for the target position in the interview page. The job seeker can conduct the interview based on the interview questions. Then, in response to detecting that the job seeker has completed answering all the interview questions, a first interview video for the target position is generated, and the first interview video is sent to the recruitment terminal to which the target position belongs, thereby effectively simplifying the interview process of the job seeker through online video interviews. The job seeker can show his or her relevant information through the interview video, saving commuting time and cost. At the same time, the recruitment user can understand the relevant information of the job seeker based on the interview video, shortening the recruitment cycle, thereby effectively optimizing the processes of both the job seeker and the recruitment user, and improving the efficiency of both parties.

[0082] Reference Figure 1 , shows a flowchart of the steps of a method for generating an interview video provided in an embodiment of the present invention, wherein a graphical user interface is provided through a job search terminal, and the content displayed by the graphical user interface includes at least an application interface, and specifically may include the following steps:

[0083] Step 101, in response to detecting a resume submission operation for a target position, if the target position has an AI video interview function enabled, outputting an AI interview invitation for the target position;

[0084] Optionally, the job-seeking terminal may be a terminal device corresponding to the job-seeking user, and corresponding applications, applets, browser pages, etc. may be run in the job-seeking terminal, and corresponding online job-seeking functions may be provided to the job-seeking user through the applications, applets, browser pages, etc. It should be noted that in the embodiment of the present invention, an exemplary description is given by taking the job-seeking terminal running a recruitment application as an example, the terminal runs the recruitment application, and displays the corresponding application interface through a graphical user interface, so that the job-seeking user can perform corresponding operations in the application interface, such as editing a resume, browsing positions, submitting a resume, online conversation, etc., and the present invention does not limit this.

[0085] In an embodiment of the present invention, for full-time positions posted online by recruiting users, in order to reduce the recruitment pressure of recruiting users and simplify the recruitment process, recruiting users can enable the AI ​​video interview function for full-time positions after posting the full-time positions. After enabling this function, when the system (backend server, etc.) detects the submission of a resume for a full-time position, it can automatically trigger the sending of an AI interview invitation to the job-seeking terminal of the job-seeking user who submitted the resume, so as to invite the job-seeking user to an AI interview through the AI ​​interview invitation. Through online AI interviews, the commuting time and cost of job-seeking users can be effectively reduced, and the interview process of job-seeking users can be effectively simplified. Job-seeking users can present relevant information about themselves through interview videos.

[0086] Assuming that a job seeker has submitted his resume to a target position, and the system detects that the AI ​​video interview function has been enabled for the target position, a user session can be created between the job seeker and the recruiter, and corresponding session messages and AI interview invitations can be sent in the user session, such as, "I'm glad to receive your resume. I'm not online now. You can enter the AI ​​interview room for an interview. The AI ​​interviewer is waiting for you" (session message). At the same time, the corresponding AI interview invitation is output in the form of a message card, and an entry interface for the AI ​​interview room is provided in the message card, so that the job seeker can enter the corresponding AI interview room through the interface and conduct an online AI interview.

[0087] Optionally, for AI interview invitations, it may include session messages output from the user session between the recruiting user and the job-seeking user, as well as invitation message records displayed during the job-seeking process, etc. For the former, when the job-seeking user successfully submits the corresponding user resume to the target position, the job-seeking terminal may create a user session between the recruiting user and the job-seeking user, and send a session message indicating the successful resume submission in the user session. At the same time, when the AI ​​video interview function is enabled for the target position, the corresponding AI interview invitation message is output in the user session, and the job-seeking user is invited to an AI interview through the AI ​​interview invitation; for the latter, it may include the AI ​​interview invitation actively initiated by the recruiting user or the aforementioned AI interview invitation message received The corresponding AI interview invitation, that is, the invitation message record may include the AI ​​interview invitation triggered by the job seeker actively submitting his resume, and the AI ​​interview invitation initiated by the recruiting user, etc. The job seeker can judge whether to accept the corresponding AI interview invitation based on his own needs. Therefore, the job seeker can choose to accept the online AI interview immediately when the AI ​​interview invitation is triggered by submitting his resume, or he can conduct the AI ​​interview in other scenarios (such as conducting centralized online interviews with one or more of the favorite ones after receiving multiple AI interview invitations). By providing users with multiple methods, the online interview scenarios are enriched, so that job seekers can flexibly arrange the job search process according to their own needs, thereby improving the flexibility of online job search.

[0088] Step 102, in response to a confirmation operation on the AI ​​interview invitation, displaying an interview page in the graphical user interface, and outputting interview questions for the target position on the interview page;

[0089] For AI interview invitations, job seekers can choose to accept or reject. If they do not accept the AI ​​interview invitation, they can reject it explicitly or implicitly. For example, job seekers can enter a corresponding rejection message in the user session, such as "Sorry, this position is not suitable for me and I will not consider it for the time being"; or they can simply not do anything with the AI ​​interview invitation (implicit rejection).

[0090] If the job seeker accepts the AI ​​interview invitation, the terminal can respond to the confirmation operation of the AI ​​interview invitation, display the interview page in the graphical user interface, and output interview questions for the target position in the interview page, so as to obtain relevant information of the job seeker through the corresponding interview questions.

[0091] Optionally, the interview questions can be questions set for the target position, which can be questions generated by a big data model. The recruiting user enters relevant information such as job requirements and skill requirements into the big data model, and then the big data model constructs corresponding interview questions. In order to trigger the AI ​​video interview, the job seeker can be interviewed online through the interview questions.

[0092] For example, a recruiting user can enter the corresponding job description as follows:

[0093] Position: Marketing Manager;

[0094] Responsibilities: Responsible for formulating and implementing marketing strategies, managing marketing teams, analyzing market data, and enhancing brand awareness;

[0095] Skill requirements: market analysis, team management, brand promotion, data analysis.

[0096] Next, the recruiting user can input prompt information for the big data model, and through the prompt information, instruct the big data model to generate corresponding interview questions according to the input job description, as shown below:

[0097] Prompt A: Please generate 5 behavioral interview questions for the marketing manager position.

[0098] The generated results of the big data model can include:

[0099] 1. Please describe a time when you successfully developed and implemented a marketing strategy.

[0100] 2. How do you handle disagreements with team members?

[0101] 3. Please share an experience in which you optimized a marketing campaign through data analysis.

[0102] 4. How do you motivate and manage the marketing team?

[0103] 5. Please describe a time when you faced a market challenge and successfully overcame it.

[0104] Prompt B: Please generate 5 situational interview questions for the marketing manager position.

[0105] The generation results of the big data model:

[0106] 1. What would you do if you find that the results of market data analysis do not match your expectations?

[0107] 2. Please describe a time when you needed to learn a new marketing tool in a short period of time.

[0108] 3. If you discovered that a competitor had launched a very successful marketing campaign, how would you respond?

[0109] 4. Please describe a time when you needed to complete a marketing task with limited resources.

[0110] 5. If you find that a team member is inefficient, how would you solve the problem?

[0111] Hint C: Please generate 5 skills testing questions for the Marketing Manager position.

[0112] The generation results of the big data model:

[0113] 1. Please explain the tools and techniques you use in market analysis.

[0114] 2. How do you ensure the quality and effectiveness of marketing activities?

[0115] 3. Please describe an experience in which you successfully increased brand awareness.

[0116] 4. How do you evaluate the ROI of your marketing campaigns?

[0117] 5. Please share an experience in which you successfully managed a marketing team.

[0118] Through the above process, interview questions matching the target position can be constructed so that when the AI ​​video interview is triggered, the job seeker can be interviewed online through the interview questions.

[0119] In some feasible implementations, in the process of asking job seekers questions through interview questions, job seekers can answer the interview questions. In the process of answering, the answers may be too general or vague, making it impossible for the terminal to extract key information that meets the interview questions from the job seekers' answers. In this regard, the terminal can determine whether to trigger follow-up questions based on the job seekers' answers, and further ask the job seekers follow-up questions to guide the job seekers to answer in a targeted manner, thereby ensuring the effectiveness of the answers and improving the effectiveness of AI video interviews.

[0120] In the process of a job seeker answering interview questions, the terminal can respond to the job seeker completing the answer to any interview question and determine whether the answer content provided by the job seeker contains key information required for the interview question. If it is determined that the answer content lacks any key information required for the interview question, the interview question and the answer content are constructed as the first input data of the target large model. Then the terminal can obtain the first prompt information, and the first prompt information is used to instruct the target large model to ask follow-up questions according to the interview question and the answer content in the input data. The prompt information includes at least one of an interview question instance, an answer content instance, and a corresponding follow-up question instance. Then the first input data and the prompt information can be input into the target large model for question prediction, and follow-up questions corresponding to the interview question are generated, and the follow-up questions are displayed on the interview page to guide the job seeker to provide the key information required for the interview question. Therefore, for each interview question, the terminal can perform corresponding key information extraction and completeness judgment, and ask questions based on the judgment result. By extracting matching key information from the job seeker's answer content, it is ensured that each interview question can have corresponding key information, and the comprehensiveness and effectiveness of information collection are ensured.

[0121] Among them, in the process of judging the answer content provided by the job seeker, the terminal can first obtain the answer content provided by the job seeker to the interview questions based on the voice information input by the job seeker, and construct the target position, interview questions and answer content as the second input data of the target big model, and obtain the second prompt information, the second prompt information is used to prompt the target big model to extract key information from the answer content according to the interview questions and target positions in the second input data, the prompt information also includes at least one of the interview question instance, the position type instance, the answer content instance and the corresponding key information instance, and then input the prompt information and the second input data into the target big model, extract information from the answer content, and obtain the key information corresponding to the answer content, so that for each interview question, the terminal can perform corresponding key information extraction and completeness judgment, and extract matching key information from the job seeker's answer content to ensure that each interview question can have corresponding key information, thereby ensuring the comprehensiveness and effectiveness of information collection.

[0122] In some examples, the first prompt information preset for the large model may be:

[0123] "You are an AI interviewer. After the user has answered, you need to ask follow-up questions for unclear or illogical responses. When the user clearly answers the question, output an empty string."

[0124] "Where the question in input is your question, and the answer is the user's answer."

[0125] “Requirements: 1. The questions you output must be reliable, compliant, and objective. Content that violates laws and regulations is not allowed.

[0126] 2. Output of other irrelevant results is not allowed. "

[0127] Please output the corresponding questions according to the following case examples and requirements:

[0128] “case1:'input:{"question":"When can I start work at the earliest?","answer":"I haven't done it yet. What are your requirements?"}'

[0129] 'output: Our job requirements are detailed in the recruitment post. When can I start work at the earliest? '"

[0130] “case2:'input:{"question":"What type of truck have you driven before?","answer":"4.2 meters."}'

[0131] 'output: For this question, you can answer flatbed trucks and box trucks. What type of trucks have you driven before? '"

[0132] “case3:'input:{"question":"Have you ever worked in this field before? How many years did you work there?","answer":"Hotel service industry, right?"}'

[0133] 'output: May I ask how many years you have worked in this industry? '"

[0134] "Please complete your inquiry according to the above case examples and requirements. No other irrelevant results are allowed."

[0135] On this basis, the first prompt information and input data can be provided to the target macro model, so as to use the target macro model to generate follow-up questions for the interview questions, and the follow-up questions are a new interview question. The follow-up questions are sent to the job seeker to guide the job seeker to provide key information required for the new interview question.

[0136] Accordingly, in this embodiment, after obtaining the answer content provided by the job seeker to the interview question, the answer content can be detected. If it is detected that the answer content lacks any key information required for the interview question, the interview question and the answer content are provided to the target macro model, so that the target macro model can generate follow-up questions for the interview question according to the first prompt information, and send the follow-up questions to the job seeker to guide the job seeker to provide the key information required for the follow-up questions. Among them, when the answer content provided by the job seeker is not sufficient to answer the interview intention of the interview question, a new interview question is regenerated for the interview intention, and the new interview question is used to ask the job seeker, so that the job seeker can supplement the information in time, so that the employer can quickly and accurately obtain more effective information for the job seeker, thereby improving the employer's recruitment experience.

[0137] In the above or following embodiments, multiple implementations may be used to generate follow-up questions for interview questions. In an optional implementation, the step of generating follow-up questions for interview questions by the target large model may include: performing a semantic extraction operation on the interview question to obtain the semantic information of the interview question, and searching for a target inspection dimension that is adapted to the semantic information of the interview question from the inspection dimension associated with the job type applied for by the job seeker. Performing a semantic extraction operation on the answer content to obtain the semantic information of the answer content, and searching for the target semantic information that is adapted to the target inspection dimension from the semantic information of the answer content. For the target inspection dimension that does not have the target semantic information adapted thereto, follow-up questions are generated for the interview question according to the follow-up question generation knowledge learned from the first prompt information. In this way, only generating follow-up questions for the interview questions that have not been answered in the interview questions can not only reduce the workload of generating follow-up questions, but also improve the interview efficiency. It can also avoid asking repeated questions to job seekers, and improve the interview experience of job seekers.

[0138] The same method can be used to perform semantic extraction on interview questions / answers. Semantic extraction can include the following steps: obtaining text data corresponding to interview questions / answers, performing word segmentation on the text data, and obtaining multiple specific entities contained in the text data as semantic information of the interview questions / answers. Specific entities are meaningful, interview-related concepts and relationships in text data. Specific entities include but are not limited to names, positions, place names, contact information, etc.

[0139] In this embodiment, at least one assessment dimension is pre-configured for each position type. According to the position type applied by the job seeker, the assessment dimension associated with the position type applied by the job seeker can be obtained, and the target assessment dimension that is adapted to the semantic information of the interview question can be found from the assessment dimensions associated with the position type; the target semantic information that is adapted to the target assessment dimension can be found from the semantic information of the answer content. If there is any target assessment dimension for which the target semantic information that is adapted cannot be found from the semantic information of the answer content, a follow-up question is generated for the interview question with respect to the target assessment dimension.

[0140] For example, an interview question is "What type of truck have you driven before?", and the answer is "4.2 meters", the semantic information extracted from the interview question is "which type of truck", and the semantic information extracted from the answer is "4.2 meters". The assessment dimensions associated with the job type applied for by the job seeker include age, education, work experience, working hours, etc. Based on this, the target assessment dimension found from the assessment dimensions associated with the job type that is adapted to the semantic information of the interview question is "work experience". The semantic information of the answer content is not compatible with the target assessment dimension. Therefore, a follow-up question can be generated for the interview question based on the assessment dimension of "work experience". The generated follow-up question can be "For this question, the answers can be flatbed trucks and box trucks. What type of truck have you driven before?"

[0141] Of course, other implementations may be used to generate follow-up questions. For example, at least one follow-up question may be generated for an interview question by manual configuration, which is not limited in this embodiment.

[0142] After sending follow-up questions to job seekers, the answers submitted by job seekers to the follow-up questions can be obtained, and key information can be extracted from the answers corresponding to the follow-up questions to detect the answers corresponding to the follow-up questions. If, based on the extracted key information, it is determined that the answers corresponding to the follow-up questions lack any key information required for the follow-up questions, the follow-up questions are reconstructed for the interview questions until the answers to the follow-up questions contain all the key information required for the interview questions or the number of follow-up questions constructed exceeds a preset question threshold. Based on this, when all the key information required for the interview questions is obtained based on the interview questions and / or one or more follow-up questions constructed for the interview questions, new interview questions can be displayed to the job seekers or the interview can be ended.

[0143] Furthermore, if the number of follow-up questions constructed for the interview question exceeds the preset follow-up threshold and all the key information required for the interview question is still not obtained, a new interview question may be displayed to the job seeker or the interview may be ended. Before displaying a new interview question or ending the interview, it may be determined whether the current interview question is the last interview question. If the current interview question is not the last interview question, a transition statement may be sent to the job seeker to prompt the job seeker to enter a new interview question; if the current interview question is the last interview question, a closing statement may be provided to the job seeker to end the interview.

[0144] As mentioned above, for any target assessment dimension corresponding to the interview question, if the target semantic information that matches the target assessment dimension cannot be found from the semantic information of the answer content, a follow-up question is generated for the interview question for the target assessment dimension. That is, when generating follow-up questions for the interview question, only follow-up questions are asked for the unanswered target assessment dimensions, and there is no need to ask follow-up questions for all target assessment dimensions corresponding to the interview question.

[0145] Accordingly, when regenerating follow-up questions for interview questions, the interview questions sent to job seekers and the target assessment dimensions that have not received a response after the previous follow-up questions are obtained, and only the target assessment dimensions that have not received a response need to be followed up. This can not only reduce the burden of generating follow-up questions and improve interview efficiency, but also avoid repeatedly asking the same questions to job seekers, thereby avoiding causing disgust among job seekers and effectively improving the interview experience of job seekers.

[0146] Through the above process, the job search terminal can conduct online interviews with job seekers by asking interview questions corresponding to the target positions. During the online AI interview, based on the job seekers' answers to the interview questions, key information matching the interview questions is collected to ensure that each interview question has corresponding key information, thereby ensuring the comprehensiveness and effectiveness of information collection.

[0147] Step 103, in response to detecting that the job seeker has completed answering all the interview questions, generating a first interview video for the target position, and sending the first interview video to the recruitment terminal to which the target position belongs.

[0148] During an online AI interview, job seekers need to answer multiple interview questions. When the job seekers have completed answering all the interview questions, the job seeker terminal can generate a first interview video for the target position in response to detecting that the job seekers have completed answering all the interview questions, and send the first interview video to the recruitment terminal to which the target position belongs. The recruitment user corresponding to the recruitment terminal can screen the job seekers by browsing the first interview video to select suitable candidates who meet the job requirements, thereby effectively simplifying the interview process of the job seekers through online video interviews. Job seekers can present their relevant information through interview videos, saving commuting time and costs. At the same time, recruitment users can understand the relevant information of the job seekers based on the interview videos, shortening the recruitment cycle, thereby effectively optimizing the processes of both job seekers and recruitment users and improving the efficiency of both parties.

[0149] Optionally, before starting the AI ​​video interview, the job search terminal can detect local data to see if a corresponding interview video already exists. If so, the job seeker can directly use the existing interview video without having to conduct an AI video interview. For example, for a target position, it may include positions of the same type posted by different companies. In the job search process for similar positions, in the case of the first application, the job seeker can record the corresponding interview video through an AI video interview. In the case of a non-first application and an interview video for a similar position already exists, the job seeker can directly use the already recorded interview video, thereby simplifying the job search process for job seekers, reducing repeated recordings, and improving job search efficiency.

[0150] In one example, before entering an online AI interview, the job search terminal can detect local data. If an interview video exists locally, the interview video can be displayed on the interview page so that the job seeker can select an existing interview video. After the job seeker selects the corresponding interview video, the terminal can respond to the selection operation on the interview video, determine a second interview video that matches the target position, and send the second interview video to the recruitment terminal to which the target position belongs. After the job seeker has participated in the corresponding online AI interview, by storing the interview video corresponding to the online AI interview, the job seeker can directly "submit a video resume" based on the existing interview video when conducting an online AI interview for the same type of position, thereby simplifying the job search process for the job seeker, reducing repeated recordings, and improving job search efficiency.

[0151] Optionally, the terminal can display the interview video and the video creation time and position identification corresponding to the interview video on the interview page. The creation time can effectively identify the creation time corresponding to different interview videos. At the same time, the position identification can enable job seekers to intuitively and quickly identify the position types corresponding to different interview videos. For example, assuming that interview video ①, interview video ② and interview video ③ exist locally on the job search terminal, the job search terminal can display the corresponding creation time and position identification in the video card while displaying the video cards corresponding to interview video ①, interview video ② and interview video ③, such as 2024-06-28 (salesperson), 2024-06-29 (sales supervisor), 2024-06-30 (sales manager), etc., and provide a corresponding sending control in each video card, so that job seekers can directly send the corresponding interview video to the recruitment terminal based on the sending control, avoiding online AI interviews for the same type of position again, reducing repeated recording, and improving job search efficiency.

[0152] It should be noted that when the job seeker answers the interview questions and has answered all the interview questions, the terminal will record the corresponding interview video based on the entire question-and-answer process. The job seeker can upload the interview video. After successful uploading, the system can first review the interview video. After the review is successful, the interview video will be sent to the recruitment terminal corresponding to the recruiting user who posted the target position, so that the recruiting user can understand the relevant information of the job seeker based on the interview video, thereby shortening the recruitment cycle.

[0153] Optionally, the review of the interview video can include content compliance, video quality, interview process and specifications, technical compliance and other aspects. For example, the system can review whether there is inappropriate language, discriminatory remarks or expressions that disrespect others in the interview video, and can also review whether the video picture is clear, whether the audio is clear, etc. It can also review whether the online AI interview is conducted according to the predetermined process, whether the interview time meets the requirements (timeout or insufficient time, etc.), and whether the data storage or transmission meets security standards. By reviewing the interview videos sent by job seekers, the compliance of the online AI interview process and the video quality can be effectively ensured, thereby providing a reliable basis for the recruitment users' recruitment decisions.

[0154] When the interview video is reviewed and approved, the job search terminal can receive the corresponding review pass letter message and output the corresponding session message in the user session between the job seeker and the recruiting user. For example, the terminal can automatically send reminder messages such as "Hello, I have completed the AI ​​video interview for the #position name you posted, and look forward to your reply" as the job seeker. At the same time, the corresponding video delivery card can be displayed in the user session. The video delivery card can include the job seeker's name, age, years of work experience, education, and position title, and provide a video playback entrance for playing the interview video, so that the recruiting user can intuitively and quickly perceive the job seeker's basic information through the video delivery card, and browse the corresponding interview video through the video playback entrance, thereby understanding the job seeker's relevant information based on the interview video, shortening the recruitment cycle.

[0155] In addition, after watching the interview video, the recruiting user can mark the interview video, including marking the interview passed or failed. Based on the marking result of the recruiting user, the recruiting terminal can generate a corresponding marking message, and then send the marking message to the job-seeking terminal. The job-seeking terminal can respond to receiving the marking message for the first interview video and display the interview result label for the first interview video according to the marking message. Among them, the interview result label includes one of the interview passed label or the interview failed label, so that based on the marking of the interview video, the job-seeking user can timely understand the interview result of the "video resume delivery" so as to adjust the job-seeking strategy in time.

[0156] In some feasible implementations, the job search terminal can provide a corresponding management interface for "video resume delivery", processed AI interview invitations, unprocessed AI interview invitations, etc., so that job seekers can manage them uniformly and view the job search progress so as to adjust the job search strategy in time. Specifically, the terminal can display a job search management page in a graphical user interface in response to the job search progress viewing operation, and different label controls can be provided in the job search management page, and different label controls can trigger the display of different cards in the job search management page.

[0157] Among them, the job search management page may include a delivery label control, a browsing record control, an invitation record control and an interview feedback control. The delivery label control can trigger the display of a job delivery card in the job search management page, the browsing record control can trigger the display of recruiting users who have browsed the job seeker in the job search management page, the invitation record control can trigger the display of received AI interview invitations in the job search management page, and the interview feedback control can trigger the display of feedback records corresponding to the job applied for by the job seeker in the job search management page, etc. Therefore, through different label controls, job seekers can manage the delivery records, browsing records, AI interview invitations and interview feedback involved in the job search process, and can also view the corresponding AI interview invitations so as to adjust the corresponding job search strategies in time.

[0158] Optionally, the interview feedback card may include a feedback status corresponding to the interview video, the feedback status including one of interview passed, interview failed, and video abnormal, so that the job seeker can intuitively perceive the processing results corresponding to each interview video through the feedback status, which is convenient for the job seeker to process the interview video. For example, for an interview video that failed the interview, the job seeker can delete it. For an interview video that passed the interview, it may represent a video that can highlight the job seeker's ability, or a video with good question and answer effects. The job seeker can choose to keep it so that when encountering other job interviews of the same type, the interview video can be directly sent. For an interview video with an abnormal video, it may be that the review failed, so the job seeker can delete it or re-record it.

[0159] For example, when a job seeker deletes an interview feedback card, the job seeker terminal can respond to the deletion operation on the interview feedback card, delete the target interview feedback card corresponding to the deletion operation, and the third interview video corresponding to the target interview feedback card, and generate a deletion message for the third interview video. The job seeker terminal can then synchronize the deletion message to the target recruitment terminal that has received the third interview video. The deletion message is used to instruct the target recruitment terminal to mark the third interview video as deleted and unbrowsable. By sending the corresponding deletion message to the recruitment terminal, the recruitment user can promptly perceive the corresponding status of the interview video. On the one hand, the personal privacy of the job seeker can be effectively guaranteed. On the other hand, although the recruitment user cannot watch the corresponding interview video, he can browse the corresponding delivery record, so that the recruitment user can judge whether to actively initiate an interview invitation to the job seeker according to his own needs to avoid missing the corresponding talent.

[0160] In a specific implementation, for interview invitation cards, each interview invitation card can correspond to an AI video interview invitation for a position, then the job seeker can select one of the interview invitation cards and conduct an online AI interview through the interview entrance provided in the interview invitation card. Specifically, the terminal can respond to the confirmation operation for the interview invitation card, display the interview page in the graphical user interface, and output the interview questions corresponding to the interview invitation card in the interview page. It should be noted that the process of the relevant online AI interview can refer to the description in the aforementioned embodiment, which will not be repeated here.

[0161] In addition, for interview videos that are in an abnormal state, job seekers can also choose to re-take the online AI interview. Specifically, if the interview video corresponding to the interview feedback card is in an abnormal video state and an interview instruction for the interview feedback card is detected, the job search terminal can display the interview page in the graphical user interface and output the abnormal questions corresponding to the interview feedback card in the interview page, so that job seekers can adjust the corresponding job search strategies in time according to the abnormal questions prompted.

[0162] It should be noted that the embodiments of the present invention include but are not limited to the above examples. It is understandable that those skilled in the art can also make settings according to actual needs under the guidance of the ideas of the embodiments of the present invention, and the present invention is not limited to this.

[0163] In an embodiment of the present invention, a job seeker can realize online job search through an application. During the online job search process, the job seeker can submit a resume for a desired target position. When the terminal detects the resume submission operation for the target position, it can detect the target position to determine whether the AI ​​video interview function is enabled for the target position. If the AI ​​video interview function is enabled for the target position, an AI interview invitation for the target position is output. The recruiting user turns on the AI ​​video interview function corresponding to the target position, so that when a resume submission is detected, the system can automatically trigger an invitation to the job seeker for a video interview, effectively simplifying the recruitment process of the recruiting user and improving the recruitment efficiency. For the job seeker, he can accept the AI ​​interview invitation, and the terminal will respond based on the job seeker input. The job seeker performs a confirmation operation for the AI ​​interview invitation, displays the interview page in the graphical user interface, and outputs interview questions for the target position in the interview page. The job seeker can conduct an interview based on the interview questions. Then, in response to detecting that the job seeker has completed answering all the interview questions, a first interview video for the target position is generated, and the first interview video is sent to the recruitment terminal to which the target position belongs, thereby effectively simplifying the interview process of the job seeker through online video interviews. The job seeker can present relevant information about himself through the interview video, saving commuting time and cost. At the same time, the recruitment user can understand the relevant information of the job seeker based on the interview video, shortening the recruitment cycle, thereby effectively optimizing the processes of both the job seeker and the recruitment user and improving the efficiency of both parties.

[0164] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the following examples are used for exemplary description:

[0165] Reference Figure 2 , showing a schematic diagram of an application interface provided in an embodiment of the present invention, when a job seeker submits a user resume for a corresponding target position (the position has the AI ​​video interview function enabled), triggering the system to automatically initiate an interview invitation, or when receiving an interview invitation initiated by a recruiting user, the system can create a user session between the recruiting user and the job seeker, and output a corresponding interview invitation message in the user session, such as Figure 2 As shown, the interview invitation message can be displayed in the user conversation interface in the form of a message card, and a corresponding interview control 210 can be provided in the card. The interview control 210 can trigger an AI video interview of the job seeker, so as to effectively simplify the interview process of the job seeker through the online video interview. The job seeker can present his or her relevant information through the interview video, saving commuting time and cost.

[0166] When the job seeker accepts the interview invitation request, the job seeker terminal can jump to the interview page, and the corresponding welcome message can be output on the interview homepage. At the same time, the job seeker terminal can detect the local area. If the corresponding historical interview video is detected, the corresponding video card can be displayed at the bottom of the homepage, so that the job seeker can directly complete the video interview through the recorded interview video when interviewing for the same type of position, reducing the video recording process. If there is no corresponding interview video, the job seeker can conduct this video interview through the "Start Interview" control provided on the interview page. After entering the formal recording page, the corresponding interview questions can be displayed on the interview page. The job seeker can answer the interview questions and trigger the answer to the next interview question after completing the answer to the interview question. When all the interview questions are completed, the corresponding recording results of this video interview can be submitted. At the same time, the corresponding prompt message and the corresponding interview record viewing control can be displayed on the end page so that the job seeker can view the corresponding job search progress.

[0167] It should be noted that for Figure 3 It only shows the partial process of video interview. Figure 3 There is no restriction on the actual video recording process. In the actual video interview process, job seekers need to answer multiple interview questions, and there can also be corresponding follow-up questions. Figure 3 It is not shown in the figure, and the related process can be referred to the description in the aforementioned embodiment, which will not be repeated here.

[0168] Accordingly, when a job seeker views the job search progress through the interview record viewing control, the job search terminal can display the corresponding progress page, such as Figure 4As shown, different controls can be displayed in the process page, such as "My Submission", "Who Viewed Me", "AI Interview Invitation" and "AI Interview Feedback", etc. Different spaces can display different sub-pages, among which "My Submission" can be used to display the submission record actively submitted by the job seeker; "Who Viewed Me" can be used to display the visit record of the recruiting user who browsed the user resume of the job seeker; "AI Interview Invitation" can be used to display the interview invitation received by the job seeker; "AI Interview Feedback" can be used to display the feedback result of the interview video submission based on the online AI video interview by the job seeker. For example, when the job seeker selects "AI Interview Invitation", the job seeker terminal can display the received interview invitation card on the page, and each interview invitation card can at least include the corresponding position name, salary, user avatar of the recruiting user, name, company name, receiving time and interview control, etc. If the job seeker believes that the corresponding position is more in line with his own needs, he can trigger the online AI video interview through the "Interview Now" control, thereby effectively simplifying the interview process of the job seeker through the online video interview, and the job seeker can show his relevant information through the interview video, saving commuting time and cost.

[0169] In addition, when a job seeker selects "AI Interview Feedback" to view the feedback results corresponding to the submitted interview video, the terminal can jump to the corresponding sub-page, such as Figure 5 As shown, the job search terminal can display the corresponding delivery record card, in which the video preview page corresponding to the interview video, the job title, salary, the user name of the recruiting user, the company name and the video status corresponding to the interview video can be displayed. The video status can include "video under review", "failed", "passed" and "video to be viewed", etc. "Video under review" indicates the interview video processing review stage; "failed" indicates that the video interview failed; "passed" indicates that the video interview passed; "video to be viewed" indicates that the recruiting user has not viewed the interview video yet, etc., so that based on different video statuses, job seekers can intuitively manage each interview video, such as deleting the interview video, re-recording, etc.

[0170] Through the above process, job seekers can accept AI interview invitations. Based on the confirmation operation input by the job seekers for the AI ​​interview invitation, the terminal displays the interview page in the graphical user interface and outputs interview questions for the target position in the interview page. The job seekers can conduct interviews based on the interview questions. Then, in response to detecting that the job seekers have completed answering all interview questions, a first interview video for the target position is generated and sent to the recruitment terminal to which the target position belongs. The interview process of job seekers is effectively simplified through online video interviews. Job seekers can show their relevant information through interview videos, saving commuting time and costs. At the same time, recruitment users can understand the relevant information of job seekers based on the interview videos, shortening the recruitment cycle, thereby effectively optimizing the processes of both job seekers and recruitment users and improving the efficiency of both parties.

[0171] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0172] Reference Figure 6 , shows a structural block diagram of a device for generating an interview video provided in an embodiment of the present invention, wherein a graphical user interface is provided through a job-seeking terminal, and the content displayed by the graphical user interface includes at least an application interface, which may specifically include the following modules:

[0173] An invitation output module 601 is used to respond to detecting a resume submission operation for a target position, and if the target position has an AI video interview function enabled, output an AI interview invitation for the target position;

[0174] An interview page display module 602 is used to display an interview page in the graphical user interface in response to a confirmation operation on the AI ​​interview invitation, and output interview questions for the target position on the interview page;

[0175] The video generation module 603 is used to generate a first interview video for the target position in response to detecting that the job seeker has completed answering all the interview questions, and send the first interview video to the recruitment terminal to which the target position belongs.

[0176] In some feasible implementations, the device further includes:

[0177] A video display module, used to display the interview video on the interview page if the interview video exists locally;

[0178] The video sending module is used to determine a second interview video matching the target position in response to a selection operation on the interview video, and send the second interview video to a recruitment terminal to which the target position belongs.

[0179] In some feasible implementations, the video display module is specifically used for:

[0180] The interview video and the video creation time and position identification corresponding to the interview video are displayed on the interview page.

[0181] Some possible implementations also include:

[0182] The process viewing module is used to respond to the job search progress viewing operation, display a job search management page in the graphical user interface, and display at least one of a job application card, an interview invitation card, a browsing record card, and an interview feedback card in the job search management page, wherein the interview feedback card includes a feedback status corresponding to the interview video, and the feedback status includes one of interview passed, interview failed, and video abnormality.

[0183] Some possible implementations also include:

[0184] An interview processing module is used to display an interview page in the graphical user interface in response to a confirmation operation on the interview invitation card, and output interview questions corresponding to the interview invitation card in the interview page.

[0185] In some feasible implementations, the device further includes:

[0186] A deletion module, configured to, in response to a deletion operation on the interview feedback card, delete the target interview feedback card corresponding to the deletion operation and the third interview video corresponding to the target interview feedback card, and generate a deletion message for the third interview video;

[0187] A synchronization module is used to synchronize the deletion message to a target recruitment terminal that has received the third interview video, wherein the deletion message is used to instruct the target recruitment terminal to mark the third interview video as deleted and unavailable for browsing.

[0188] Some possible implementations also include:

[0189] The abnormal prompt module is used to display the interview page in the graphical user interface and output the abnormal questions corresponding to the interview feedback card in the interview page if the interview video corresponding to the interview feedback card is in an abnormal video state and an interview instruction for the interview feedback card is detected.

[0190] Some possible implementations also include:

[0191] a marking message receiving module, configured to, in response to receiving a marking message for the first interview video, display an interview result label for the first interview video according to the marking message;

[0192] The interview result label includes one of an interview passed label and an interview failed label.

[0193] In some feasible implementations, the device further includes:

[0194] A key information detection module, configured to determine, in response to a job seeker completing an answer to any interview question, whether the answer provided by the job seeker contains the key information required by the interview question;

[0195] A data construction module, for constructing the interview question and the answer content as the first input data of the target large model if it is determined that the answer content lacks any key information required by the interview question;

[0196] An information acquisition module, used to acquire first prompt information, wherein the first prompt information is used to instruct the target macro model to ask follow-up questions according to the interview question and the answer content in the input data, and the prompt information includes at least one of an interview question instance, an answer content instance, and a corresponding follow-up question instance;

[0197] A question generation module, used for inputting the first input data and the prompt information into the target large model to perform question prediction and generate follow-up questions corresponding to the interview questions;

[0198] The question display module is used to display the follow-up questions in the interview page to guide the job seeker to provide key information required by the interview questions.

[0199] In some feasible implementations, the key information detection module is specifically used to:

[0200] Obtaining answers provided by job seekers to the interview questions;

[0201] The target position, the interview question, and the answer content are constructed as second input data of the target macro model, and second prompt information is obtained, wherein the second prompt information is used to prompt the target macro model to extract key information from the answer content according to the interview question and the target position in the second input data, and the prompt information also includes at least one of an interview question instance, a position type instance, an answer content instance, and a corresponding key information instance;

[0202] The prompt information and the second input data are input into the target large model, and information is extracted from the answer content to obtain key information corresponding to the answer content.

[0203] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0204] In addition, an embodiment of the present invention further provides an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned interview video generation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0205] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above-mentioned interview video generation method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. The computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0206] Figure 7 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0207] The electronic device 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709, a processor 710, and a power supply 711. Those skilled in the art will appreciate that the electronic device structure involved in the embodiments of the present invention does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently. In the embodiments of the present invention, the electronic device includes but is not limited to a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted terminal, a wearable device, and a pedometer.

[0208] It should be understood that in the embodiment of the present invention, the radio frequency unit 701 can be used for receiving and sending signals during information transmission or communication. Specifically, after receiving downlink data from the base station, it is sent to the processor 710 for processing; in addition, uplink data is sent to the base station. Generally, the radio frequency unit 701 includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc. In addition, the radio frequency unit 701 can also communicate with the network and other devices through a wireless communication system.

[0209] The electronic device provides users with wireless broadband Internet access through the network module 702, such as helping users to send and receive emails, browse web pages, and access streaming media.

[0210] The audio output unit 703 can convert the audio data received by the RF unit 701 or the network module 702 or stored in the memory 709 into an audio signal and output it as sound. Moreover, the audio output unit 703 can also provide audio output related to a specific function performed by the electronic device 700 (for example, a call signal reception sound, a message reception sound, etc.). The audio output unit 703 includes a speaker, a buzzer, a receiver, etc.

[0211] The input unit 704 is used to receive audio or video signals. The input unit 704 may include a graphics processor (GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The processed image frame can be displayed on the display unit 706. The image frame processed by the graphics processor 7041 can be stored in the memory 709 (or other storage medium) or sent via the radio frequency unit 701 or the network module 702. The microphone 7042 can receive sound and can process such sound into audio data. The processed audio data can be converted into a format output that can be sent to a mobile communication base station via the radio frequency unit 701 in the case of a telephone call mode.

[0212] The electronic device 700 also includes at least one sensor 705, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor includes an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 7061 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 7061 and / or the backlight when the electronic device 700 is moved to the ear. As a kind of motion sensor, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary, which can be used to identify the posture of the electronic device (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; the sensor 705 can also include a fingerprint sensor, a pressure sensor, an iris sensor, a molecular sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., which will not be repeated here.

[0213] The display unit 706 is used to display information input by the user or information provided to the user. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.

[0214] The user input unit 707 can be used to receive input digital or character information, and to generate key signal input related to user settings and function control of the electronic device. Specifically, the user input unit 707 includes a touch panel 7071 and other input devices 7072. The touch panel 7071, also known as a touch screen, can collect the user's touch operation on or near it (such as the user's operation on the touch panel 7071 or near the touch panel 7071 using any suitable object or accessory such as a finger, stylus, etc.). The touch panel 7071 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the contact point coordinates, and then sends it to the processor 710, receives the command sent by the processor 710 and executes it. In addition, the touch panel 7071 can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic waves. In addition to the touch panel 7071, the user input unit 707 may also include other input devices 7072. Specifically, other input devices 7072 may include but are not limited to a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which are not described in detail here.

[0215] Further, the touch panel 7071 may be covered on the display panel 7061. When the touch panel 7071 detects a touch operation on or near it, it is transmitted to the processor 710 to determine the type of the touch event, and then the processor 710 provides a corresponding visual output on the display panel 7061 according to the type of the touch event. It can be understood that in one embodiment, the touch panel 7071 and the display panel 7061 are used as two independent components to implement the input and output functions of the electronic device, but in some embodiments, the touch panel 7071 and the display panel 7061 can be integrated to implement the input and output functions of the electronic device, which is not limited here.

[0216] The interface unit 708 is an interface for connecting an external device to the electronic device 700. For example, the external device may include a wired or wireless headset port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, etc. The interface unit 708 may be used to receive input (e.g., data information, power, etc.) from an external device and transmit the received input to one or more elements within the electronic device 700 or may be used to transmit data between the electronic device 700 and an external device.

[0217] The memory 709 can be used to store software programs and various data. The memory 709 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 709 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0218] The processor 710 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 709, and calling data stored in the memory 709, so as to monitor the electronic device as a whole. The processor 710 may include one or more processing units; preferably, the processor 710 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 710.

[0219] The electronic device 700 may also include a power supply 711 (such as a battery) for supplying power to each component. Preferably, the power supply 711 may be logically connected to the processor 710 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system.

[0220] In addition, the electronic device 700 includes some functional modules not shown, which will not be described in detail here.

[0221] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0222] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0223] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

[0224] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the embodiments of the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0225] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0226] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0227] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0228] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0229] If the functions are implemented in the form of software functional units and sold or used as independent products, they 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 the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0230] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for generating an interview video, characterized in that: A graphical user interface is provided by a job-seeking terminal, wherein the content displayed by the graphical user interface at least includes an application interface, and the method includes: In response to detecting a resume submission operation for a target position, if the target position has an AI video interview function enabled, outputting an AI interview invitation for the target position; In response to a confirmation operation on the AI ​​interview invitation, an interview page is displayed in the graphical user interface, and interview questions for the target position are output on the interview page; In response to detecting that the job seeker has completed answering all the interview questions, a first interview video for the target position is generated, and the first interview video is sent to a recruitment terminal to which the target position belongs.

2. The method according to claim 1, characterized in that After displaying the interview page in the graphical user interface, the method further includes: If the interview video exists locally, the interview video is displayed on the interview page; In response to a selection operation on the interview video, a second interview video matching the target position is determined, and the second interview video is sent to a recruitment terminal to which the target position belongs.

3. The method according to claim 2, characterized in that The displaying of the interview video on the interview page includes: The interview video and the video creation time and position identification corresponding to the interview video are displayed on the interview page.

4. The method according to claim 1, characterized in that Also includes: In response to the job search progress viewing operation, a job search management page is displayed in the graphical user interface, and at least one of a job application card, an interview invitation card, a browsing record card, and an interview feedback card is displayed in the job search management page. The interview feedback card includes a feedback status corresponding to the interview video, and the feedback status includes one of interview passed, interview failed, and video abnormality.

5. The method according to claim 4, characterized in that Also includes: In response to a confirmation operation on the interview invitation card, an interview page is displayed in the graphical user interface, and interview questions corresponding to the interview invitation card are output in the interview page.

6. The method according to claim 4, characterized in that The method further comprises: In response to a deletion operation on the interview feedback card, a target interview feedback card corresponding to the deletion operation and a third interview video corresponding to the target interview feedback card are deleted, and a deletion message for the third interview video is generated; The deletion message is synchronized to the target recruitment terminal that receives the third interview video, and the deletion message is used to instruct the target recruitment terminal to mark the third interview video as deleted and unavailable for browsing.

7. The method according to claim 4, characterized in that Also includes: If the interview video corresponding to the interview feedback card is in an abnormal video state and an interview instruction for the interview feedback card is detected, an interview page is displayed in the graphical user interface, and abnormal questions corresponding to the interview feedback card are output in the interview page.

8. The method according to claim 1, characterized in that Also includes: In response to receiving a marking message for the first interview video, displaying an interview result label for the first interview video according to the marking message; The interview result label includes one of an interview passed label and an interview failed label.

9. The method according to claim 1, characterized in that: After outputting the interview questions for the target position in the interview page, the method further includes: In response to the job seeker completing an answer to any interview question, determining whether the answer provided by the job seeker contains key information required by the interview question; If it is determined that the answer content lacks any key information required by the interview question, constructing the interview question and the answer content as the first input data of the target large model; Obtaining first prompt information, wherein the first prompt information is used to instruct the target large model to ask follow-up questions according to the interview question and the answer content in the input data, and the prompt information includes at least one of an interview question instance, an answer content instance, and a corresponding follow-up question instance; Inputting the first input data and the prompt information into the target large model to perform question prediction, and generate follow-up questions corresponding to the interview questions; The follow-up questions are displayed in the interview page to guide the job seeker to provide key information required by the interview questions.

10. The method according to claim 9, characterized in that The determining whether the answer provided by the job seeker contains key information required for the interview question includes: Obtaining answers provided by job seekers to the interview questions; The target position, the interview question, and the answer content are constructed as second input data of the target macro model, and second prompt information is obtained, wherein the second prompt information is used to prompt the target macro model to extract key information from the answer content according to the interview question and the target position in the second input data, and the prompt information also includes at least one of an interview question instance, a position type instance, an answer content instance, and a corresponding key information instance; The prompt information and the second input data are input into the target large model, and information is extracted from the answer content to obtain key information corresponding to the answer content.

11. A device for generating an interview video, characterized in that: A graphical user interface is provided by a job-seeking terminal, wherein the content displayed by the graphical user interface at least includes an application interface, and the device includes: An invitation output module, configured to respond to detecting a resume submission operation for a target position, and if the target position has an AI video interview function enabled, output an AI interview invitation for the target position; An interview page display module, configured to display an interview page in the graphical user interface in response to a confirmation operation on the AI ​​interview invitation, and output interview questions for the target position on the interview page; The video generation module is used to generate a first interview video for the target position in response to detecting that the job seeker has completed answering all the interview questions, and send the first interview video to the recruitment terminal to which the target position belongs.

12. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; The memory is used to store computer programs; The processor is used to implement the method according to any one of claims 1 to 10 when executing the program stored in the memory.

13. A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 10.

Images