Interview method and device, storage medium and computer program product

Abstract

The embodiment of the invention provides an interview method and device, a storage medium and a computer program product. In the embodiment of the invention, after answer content provided by an interviewer for an interview question is obtained, the interview question, the answer content and a post type applied by the interviewer can be input into a first large model, so that the first large model extracts key information from the answer content according to preset first prompt information; and if the answer content is determined to be lack of any key information required by the interview question according to the extracted key information, constructing a question-asking question for the interview question so as to guide an interviewer to provide the key information required by the question-asking question by utilizing the question-asking question. According to the technical scheme of the invention, the answer content can be detected in real time, and when key information required by an interview question is not obtained, the interviewer can be timely asked, so that the accuracy and integrity of the collected key information can be effectively ensured, the interviewer can be conveniently and quickly screened, and the interview efficiency can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an interview method, device, storage medium and computer program product. Background Art

[0002] As companies continue to pursue recruitment efficiency and quality, and job seekers increasingly value interview experience, AI interviews have emerged as an innovative recruitment method. AI interviews simulate real interview scenarios and conduct intelligent assessments of job seekers, thereby providing companies with more efficient and accurate recruitment decision support.

[0003] At present, AI interviews usually present multiple preset interview questions to the interviewee in sequence, and collect the interviewee's answers and provide them to the recruiter for offline screening of the interviewee. With this interview method, the interview process is very mechanical, and the recruiter cannot evaluate the interviewee's answers in time, nor can they remedy the evaluation results in time, so the collected answers cannot represent the interviewee's ability, and the interviewee needs to be contacted again, resulting in poor interview efficiency. Summary of the invention

[0004] Multiple aspects of the present application provide an interview method, device, storage medium and computer program product to improve interview efficiency during the interview process.

[0005] The present application embodiment provides an interview method, including:

[0006] After issuing any interview question to the interviewee, obtaining the answer content provided by the interviewee to the interview question;

[0007] Determine the type of position for which the interviewee is applying;

[0008] The interview questions, the job types and the answer contents are constructed as input data of the first model;

[0009] Obtaining preset first prompt information, where the first prompt information is used to instruct the first large model to extract key information from the answer content according to the interview questions and job types in the input data, and the first prompt information also includes interview question examples, job type examples, answer content examples, and corresponding key information examples;

[0010] Providing the first prompt information and the input data to the first large model, so as to extract key information from the answer content provided by the interviewee by using the first large model;

[0011] If it is determined based on the extracted key information that any key information required for the interview question is missing from the answer content, a follow-up question is constructed for the interview question to guide the interviewee to provide the key information required for the follow-up question.

[0012] The embodiment of the present application also provides a computing device, including: a memory, a processor, and a communication component;

[0013] The memory is used to store one or more computer instructions;

[0014] The processor is coupled to the memory and the communication component, and is configured to execute the one or more computer instructions to perform the aforementioned interview method.

[0015] An embodiment of the present application also provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed by one or more processors, the one or more processors are caused to execute the aforementioned interview method.

[0016] An embodiment of the present application also provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, the processor is caused to execute the aforementioned interview method.

[0017] In an embodiment of the present application, after obtaining the answers provided by the interviewee to the interview questions, the interview questions, the answers and the type of position applied for by the interviewee can be input into the first large model, so that the first large model can extract key information from the answers according to the preset first prompt information. If it is determined that any key information required for the interview question is missing in the answers based on the extracted key information, follow-up questions are constructed for the interview questions to guide the interviewee to provide the key information required for the follow-up questions. By detecting the answer content, it can be determined in real time whether the key information required for the interview question is obtained, and if the required key information is not obtained, follow-up questions can be promptly initiated to the interviewee to effectively ensure the accuracy and completeness of the collected key information, facilitate rapid screening of the interviewee, and do not need to contact the interviewee again, thereby effectively improving the efficiency of the interview. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A system architecture diagram is provided for an exemplary embodiment of the present application;

[0020] Figure 2A flowchart of an interview method provided for an exemplary embodiment of the present application;

[0021] Figure 3 A schematic diagram of a flow chart for constructing follow-up questions provided for another exemplary embodiment of the present application;

[0022] Figure 4 A schematic diagram of a flow chart for generating interview questions provided by another exemplary embodiment of the present application;

[0023] Figure 5 A logic diagram of an interview in an exemplary application scenario provided for another exemplary embodiment of the present application;

[0024] Figure 6 A schematic diagram of the structure of a computing device is provided for yet another exemplary embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0026] In view of the technical problem of poor interview efficiency caused by the inability of the employer to timely evaluate the interviewee's answer content and timely remedy the evaluation results in the prior art, the embodiment of the present application provides a solution. The basic idea is: after obtaining the answer content provided by the interviewee to the interview question, the interview question, the answer content and the type of position applied for by the interviewee can be input into the first large model, so that the first large model can extract key information from the answer content according to the preset first prompt information. If it is determined that any key information required for the interview question is missing in the answer content based on the extracted key information, then a follow-up question is constructed for the interview question, so as to use the follow-up question to guide the interviewee to provide the key information required for the follow-up question. By detecting the answer content, it can be judged in real time whether the key information required for the interview question is obtained, and if the required key information is not obtained, the interviewee is promptly asked to effectively ensure the accuracy and completeness of the collected key information, so as to facilitate the rapid screening of the interviewee without contacting the interviewee again, thereby effectively improving the interview efficiency.

[0027] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0028] Figure 1 A system architecture diagram is provided for an exemplary embodiment of the present application. The system architecture may include a client 101 and a server 102. A communication connection is established between the client 101 and the server 102. The communication connection method includes but is not limited to wired, wireless communication links or optical fiber cables.

[0029] Among them, the client 101 can be an APP (Application), a web application, a light application (also known as a mini-program, a lightweight application) or a cloud application, etc. The client 101 can be deployed in an electronic device and needs to rely on the electronic device to run. The electronic device may include but is not limited to mobile phones, tablet computers, personal computers, desktop computers, smart speakers, smart watches, etc. The server 102 may include servers that provide various services, such as a server for background training that supports the model used on the client 101, and a server that processes the interactive information sent by the client, etc. The server 102 can be implemented as a single server, a distributed server cluster consisting of multiple servers, a server or cloud server combined with blockchain, etc.

[0030] It should be noted that the interview method provided in the embodiment of the present application is generally executed by the server 102, and the corresponding data processing device is generally set in the server 102. However, in other embodiments of the present application, the client 101 may also have similar functions as the server 102, so as to execute the interview method provided in the embodiment of the present application. In other embodiments, the interview method provided in the embodiment of the present application may also be jointly executed by the client 101 and the server 102.

[0031] The implementation details of the technical solution of the embodiment of the present application are elaborated in detail below.

[0032] Figure 2 A flowchart of an interview method provided by an exemplary embodiment of the present application. The method can be executed by a data processing device, which can be implemented as a combination of software and / or hardware, and the data processing device can be integrated in a computing device. Figure 2 , the method comprising:

[0033] Step 200, after issuing any interview question to the interviewee, obtaining the answer content provided by the interviewee to the interview question;

[0034] Step 201, determining the type of position applied for by the interviewee;

[0035] Step 202, constructing the interview questions, job types and answer contents as input data of the first model;

[0036] Step 203, obtaining preset first prompt information, where the first prompt information is used to instruct the first large model to extract key information from the answer content according to the interview questions and job types in the input data;

[0037] The first prompt information also includes interview question examples, job type examples, answer content examples, and corresponding key information examples;

[0038] Step 204, providing the first prompt information and the input data to the first large model, so as to use the first large model to extract key information from the answer content provided by the interviewee;

[0039] Step 205: If it is determined based on the extracted key information that the answer lacks any key information required for the interview question, a follow-up question is constructed for the interview question to guide the interviewee to provide the key information required for the follow-up question.

[0040] The interview method provided in the embodiment of the present application can be applied to various scenarios where intelligent interviews are required, such as scenarios of recruiting job seekers, providing psychological counseling to visitors, and conducting admission interviews for students. Of course, these are only exemplary, and the present embodiment is not limited thereto.

[0041] Prior to step 200, natural language processing and machine learning technologies may be used to quickly browse and screen a large number of resumes, screen out interviewees that meet the job requirements, and send interview invitations to the interviewees to interview them using preset interview questions or interview questions generated for the interviewees. Alternatively, in response to the interview invitation initiated by the interviewee, preset interview questions or interview questions generated for the interviewee may be sent to the interviewee to interview the interviewee. The technical details related to generating interview questions for the interviewee will be described in detail below.

[0042] In step 200, after any interview question is sent to the interviewee, the answer content provided by the interviewee to the interview question can be obtained, and the answer content can include text, pictures, etc. Among them, after the interview question is sent to the interviewee, the interviewee's answer status to the interview question can be monitored, and different operation actions can be performed according to the monitored answer status. The monitored answer status may include but is not limited to the answered status and the unanswered status. When the answer status is monitored as the answered status, the answer content provided by the interviewer to the interview question can be obtained; when the unanswered status is monitored, the duration of the unanswered status is recorded. If the duration of the monitored answer status in the unanswered status exceeds the preset waiting threshold, the interview question can be resent to the interviewer, or follow-up questions can be constructed for the interviewer to guide the interviewer to provide key information required for the follow-up questions through follow-up questions.

[0043] In this embodiment, real-time monitoring of the interviewee's answer status can help the interviewer respond to the interviewee's answer in a timely manner. By repeatedly sending interview questions, the interviewee can be given more time to think and prepare, so as to understand the questions more deeply and give more comprehensive answers. Of course, excessive repetition may cause the interview process to become tedious and even cause the interviewee's disgust. Therefore, a repetition threshold can be preset. When the number of times the interview question is repeatedly sent to the interviewee exceeds the repetition threshold, a follow-up question can be constructed for the interview question, so that the interviewee can understand the interview intention more accurately and give a more accurate answer.

[0044] In step 201, the type of position applied for by the interviewee may be determined. Position types may be used to describe different job categories divided according to work factors, including but not limited to the nature of work, work content, work environment, scope of responsibilities, etc. Among them, according to the nature of work, the position types may include management positions, technical positions, sales positions, administrative positions, etc.; according to the work content, the position types may include front-end engineers, test engineers, back-end engineers, project managers, etc.; according to the work environment, the position types may include workshop positions, office positions, outdoor positions, etc.; according to the scope of responsibilities, the position types may include employees, team leaders, store managers, managers, etc.

[0045] Optionally, multiple recruitment information may be displayed to the interviewer, and in response to an interview request initiated for the target recruitment information, the position type associated with the target recruitment information may be used as the position type applied for by the interviewer. For example, in actual applications, multiple recruitment information may be displayed on the recruitment interface, and the recruitment information may include but is not limited to the company name, company address, position name, position description, job requirements, salary and benefits, etc.; each recruitment information is associated with a position type, and in response to the interviewer clicking on the application button corresponding to the recruitment information, the position type associated with the recruitment information corresponding to the application button may be obtained as the position type applied for by the interviewer.

[0046] Based on this, interview questions, job types and answer content can be constructed as input data for the first large model. The first large model is an artificial intelligence large model used to extract key information from the answer content. Artificial intelligence large models refer to machine learning models with ultra-large-scale parameters and complex computing structures. These models can process large-scale data sets and complete various complex tasks, such as natural language processing, image recognition, speech recognition, etc. through deep learning and neural network technology.

[0047] Continue to refer Figure 2 In step 203, a preset first prompt information may be obtained, and the first prompt information is used to instruct the first large model to extract key information from the answer content according to the interview questions and job types in the input data. The first prompt information may include interview question examples, job type examples, answer content examples, and corresponding key information examples. The first prompt information is a prompt template (promt template) preset for the first large model. The prompt template is a text template used to guide the large model to generate specific outputs or perform specific tasks. The prompt template can guide the model to generate specific outputs that meet the requirements by providing detailed context, instructions or questions to the model.

[0048] For example, the first prompt information preset for the first large model may be:

[0049] "You now need to extract the key information from the interviewee's response. Please extract the corresponding key information from the answer based on the question (interview question) and type (interview position type) in the input."

[0050] "Requirements: 1. Output in json format. Only output the two fields of key (type of interview question) and value (value of key information), in the format of {"key":"","value":"};

[0051] 2. The results should be normalized;

[0052] 3. If the extracted result does not conform to common sense, the output value is an empty string. "

[0053] "Please complete the parsing of the input according to the following case examples and requirements, and output it in JSON format: {"key":"","value":""}.'+"Other irrelevant results are not allowed to be output"."

[0054] “case1:'input:{"question":"What kind of work have you done before?","type":"General worker","answer":"I worked as a machine tool worker for 2 years. Supplementary information: No more, next question"}'

[0055] 'output:{"key":"Work experience","value":"Machine tool worker"}'"

[0056] “case2:'input:{"question":"Have you done this before? How many years did you do it?","type":"General worker / operator","answer":"No, next question."}'

[0057] 'output:{"key":"Work experience","value":"No experience"}'"

[0058] "case3:'input:{"question":"What kind of working hours do you accept?","type":"General worker / operator","answer":"I can do six days on and one day off, answer complete."}'

[0059] 'output:{"key":"working hours","value":"work six days and rest one day"}'"

[0060] "Please complete the parsing of the input according to the above case examples and requirements, and output it in JSON format: {"key":"","value":""}." + "Output of other irrelevant results is not allowed."

[0061] On this basis, the first prompt information and the input data can be provided to the first large model, so as to use the first large model to extract key information from the answer content provided by the interviewee. The specific implementation process of extracting key information using the first large model will be described in detail below and will not be elaborated here. Based on the extracted key information, it can be determined whether any key information required for the interview question is missing in the answer content.

[0062] In one case, if it is determined based on the extracted key information that the answer content contains all the key information required for the interview question, a target transition phrase is selected from at least one preset transition phrase to be presented to the interviewee, and a new interview question is presented to the interviewee. The interview question can be presented to the interviewee in the form of a dialogue, and the transition phrase is used to transition between the dialogues corresponding to the two interview questions. The transition phrase may be “The current question ends, and we will move on to the next interview question”, “A new interview question will be presented to you next”, etc. The target transition phrase is used to prompt the interviewee to move on to a new interview question. Using a transition phrase to transition between two interview questions can prevent the question-and-answer process from being too abrupt, thereby improving the interviewer's interview experience.

[0063] In this case, the corresponding job type can be associated with the transition phrase in advance, and based on the job type applied for by the interviewee, the transition phrase associated with the job type is obtained as the target transition phrase. Alternatively, a transition phrase can be randomly selected from at least one preset transition phrase as the target transition phrase. In this embodiment, the method for determining the target transition phrase is not limited.

[0064] In another case, if it is determined based on the extracted key information that the answer lacks any key information required for the interview question, a follow-up question is constructed for the interview question to guide the interviewee to provide the key information required for the follow-up question. The follow-up question is a new interview question, and the follow-up question has the same interview intention as its corresponding interview question.

[0065] In this case, if the time consumed by the interview question for extracting key information does not exceed the preset time threshold, a follow-up question is directly constructed for the interview question to guide the interviewee to provide the key information required for the follow-up question; if the extraction time exceeds the preset time threshold, a new interview question is displayed to the interviewee or the interview is ended.

[0066] Accordingly, in this embodiment, after obtaining the answers provided by the interviewee to the interview questions, the interview questions, the answers and the type of position applied for by the interviewee can be input into the first large model, so that the first large model can extract key information from the answers according to the preset first prompt information. If it is determined that any key information required for the interview question is missing in the answers based on the extracted key information, follow-up questions are constructed for the interview questions, so as to use the follow-up questions to guide the interviewee to provide the key information required for the follow-up questions. By detecting the answer content, it can be determined in real time whether the key information required for the interview question is obtained, and if the required key information is not obtained, follow-up questions can be promptly initiated to the interviewee, so as to effectively ensure the accuracy and completeness of the collected key information, facilitate rapid screening of the interviewee, and do not need to contact the interviewee again, thereby effectively improving the efficiency of the interview.

[0067] In the above or following embodiments, a variety of implementation methods may be used to extract key information from the answer content. In an optional implementation method, the step of extracting key information from the answer content by the first 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 dimensions associated with the job type. Perform a semantic extraction operation on the answer content to obtain the semantic information of the answer content, and search for target semantic information adapted to any target inspection dimension from the semantic information of the answer content. Combine the found target semantic information and the target inspection dimension to which it is adapted as the key information extracted from the answer content.

[0068] The same method can be used to perform semantic extraction on the interview questions / answers. The semantic extraction can include the following steps: the text data corresponding to the interview questions / answers can be obtained, and the text data can be segmented to obtain multiple phrases contained in the text data. The specific entities in the multiple phrases are used as the semantic information of the interview questions / answers. The specific entities are meaningful concepts and relationships related to the interview in the text data. The specific entities include but are not limited to names, positions, place names, contact information, etc.

[0069] In this embodiment, at least one assessment dimension is pre-configured for each position type. After receiving the interviewee's answer, the assessment dimension associated with the position type applied by the interviewee can be obtained according to the position type applied by the interviewee, and the target assessment dimension adapted to the semantic information of the interview question can be found from the assessment dimension associated with the position type, and the target semantic information adapted to any target assessment dimension can be found from the semantic information of the answer content. For example, the interview question is "What kind of work have you done before?", and the answer content is "I have worked as a machine tool worker for 2 years." The semantic information of the interview question extracted is "What kind of work", and the semantic information of the answer content extracted is "I have worked as a machine tool worker." The position type applied by the interviewee is a technical position, and the assessment dimensions associated with the technical position include age, education, work experience, working hours, etc. Based on this, the target assessment dimension adapted to the semantic information of the interview question found from the assessment dimension associated with the technical position is "work experience", and the target semantic information adapted to the target assessment dimension found from the semantic information of the answer content is "machine tool worker". Based on this, the target assessment dimensions and target semantic information are combined in the form of key-value pairs, and the key information extracted from the answer content can be determined as {key: "work experience", value: "machine tool worker"}.

[0070] Of course, other implementations may also be used to extract key information from the answer content, which is not limited in this embodiment.

[0071] As mentioned above, the key information extracted from the answer content includes the target assessment dimensions and target semantic information. If the target assessment dimensions contained in the key information do not cover all the assessment dimensions required for the interview question, it is determined that the answer content lacks any key information required for the interview question. In this way, judging the validity of the answer content from the perspective of the assessment dimensions provides a clear judgment standard for judging whether the answer content lacks any key information required for the interview question, which can effectively improve the efficiency and accuracy of the judgment of the answer content, thereby further improving the efficiency and accuracy of the interview.

[0072] Among them, the target assessment dimensions corresponding to the interview questions can be one or more.

[0073] In the case where the assessment dimension corresponding to the interview question is a single one, if the target assessment dimension included in the key information does not include the assessment dimension corresponding to the interview question, it is determined that the answer lacks any key information required for the interview question. For example, in the case where the assessment dimension corresponding to the interview question is "work experience", if the target assessment dimension included in the key information does not include "work experience", it is determined that the answer lacks any key information required for the interview question.

[0074] In the case where there are multiple assessment dimensions corresponding to the interview question, if the target assessment dimension included in the key information lacks any of the multiple assessment dimensions corresponding to the interview question, it is determined that any key information required for the interview question is missing in the answer. For example, in the case where the assessment dimensions corresponding to the interview question are "work experience", "age" and "working hours", if the target assessment dimension included in the key information lacks any of the above three assessment dimensions, it is considered that any key information required for the interview question is missing in the answer.

[0075] In addition, the same assessment dimension can also be associated with one or more job types. After extracting key information from the answers to the interview questions, the target assessment dimension and the target semantic information corresponding to the target assessment dimension in the key information can be extracted. At least one job type associated with the target assessment dimension is obtained, and at least one job type is traversed based on the target semantic information corresponding to the target assessment dimension to determine the target job type that matches the target semantic information from at least one job type. If the target job type is different from the job type applied for by the interviewee, it is determined that any key information required for the interview question is missing from the answer content.

[0076] For example, when the job type applied by the interviewee is driver, and the assessment dimension corresponding to the interview question is "work experience", if the target assessment dimension contained in the key information is "work experience" and the target semantic information is "working as a waiter for 2 years", the job types such as waiter, driver, and shopping guide associated with the target assessment dimension can be obtained. Based on the target semantic information, the target job type that matches the target semantic information can be determined to be "waiter". At this time, although the key information contains the assessment dimension corresponding to the interview question, the semantic information corresponding to the assessment dimension does not match the job type applied by the interviewee, and it is still considered that the answer content lacks the key information required for the interview question. This can ensure the comprehensiveness of the answer content while further ensuring the accuracy of the answer content, which helps to more accurately understand and evaluate the interviewee's ability, thereby effectively improving the efficiency of the interview.

[0077] In the above or below embodiments, various implementations may be used to construct follow-up questions for interview questions.

[0078] Figure 3 A flowchart of constructing a follow-up question is provided for another exemplary embodiment of the present application. Figure 3 As shown, in an optional implementation, the interview questions and answers can be constructed as input data of the second largest model to obtain the preset second prompt information. The input data and the second prompt information are provided to the second largest model to generate follow-up questions for the interview questions using the second largest model.

[0079] Among them, the second prompt information is used to instruct the second largest model to ask follow-up questions based on the interview questions and answers in the input data. The second prompt information also includes interview question examples, answer content examples, and corresponding follow-up question examples. The second largest model is an artificial intelligence large model for generating follow-up questions for interview questions. The second prompt information is a prompt template (promt template) preset for the second largest model, which is used to instruct the second largest model to generate follow-up questions for interview questions based on interview questions and answer contents.

[0080] Of course, other implementations may also be used to construct follow-up questions. For example, at least one follow-up question may be constructed for the interview question by manual configuration, which is not limited in this embodiment.

[0081] In this embodiment, when the answer provided by the interviewee is not sufficient to answer the interview intention of the interview question, a new interview question is regenerated for the interview intention, and the interviewee is asked follow-up questions using the new interview question so that the interviewee can supplement the information in a timely manner, so that the employer can quickly and accurately obtain more effective information for the interviewee, thereby improving the employer's recruitment experience.

[0082] In the above or below embodiments, multiple implementations may be used to generate interview questions for the interviewer.

[0083] Figure 4 A flowchart of generating interview questions is provided for another exemplary embodiment of the present application. Figure 4 In an optional implementation, before any interview question is sent to the interviewee, the type of position applied for by the interviewee can be determined in response to the interview request initiated by the interviewee. The assessment dimensions required for the position type are obtained, the resume data and historical interview data of the interviewee are obtained, and the assessment dimensions, resume data and historical interview data are constructed as input data of the third model. The preset third prompt information is obtained, and the input data and the third prompt information are provided to the third model, so as to generate interview questions for the interview request using the third model.

[0084] Among them, the third prompt information is used to instruct the third model to generate interview questions adapted to the inspection dimension based on the resume data and historical interview data in the input data. The third prompt information also includes resume data examples, historical interview data examples, inspection dimension examples, and corresponding interview question examples. The third model is an artificial intelligence large model for generating interview questions for interviewers. The third prompt information is a preset prompt template (promt template) for the third model, which is used to instruct the third model to generate interview questions adapted to the inspection dimension based on resume data and historical interview data.

[0085] Of course, other implementations may also be used to generate interview questions. For example, interview questions may be generated for the interviewer by manual configuration, which is not limited in this embodiment.

[0086] In this embodiment, the assessment dimensions that need to be paid attention to under the job type are obtained according to the job type applied for by the interviewee, and the obtained assessment dimensions are the assessment dimensions for the interviewee. Based on the assessment dimensions for the interviewee, the interviewee's resume data, and the interviewee's historical interview data, at least one interview question adapted to the assessment dimensions is generated for the interviewee in real time, so as to guide the interviewee to provide key information under each assessment dimension corresponding to the job type through the interview questions. In this way, according to the actual situation of each interviewee, corresponding interview questions are customized for each interviewee, which can effectively reduce the occurrence of mismatches between interview questions and the interviewee's actual experience or skills, so that the interview questions provided to the interviewee are more in line with the interviewee's actual situation, thereby effectively improving the interview experience of the interviewee.

[0087] It should be noted that, in this embodiment, the form of the interview with the interviewee includes but is not limited to text form and voice form. If the interview process is in voice form, the interview questions, follow-up questions, and follow-up words can be converted from text form to voice form after the interview questions and follow-up questions are generated, or before the follow-up words are sent, and the converted voice is used to interact with the interviewee. Among them, the text form can be converted into voice form by using text-to-speech (TTS) technology. The form conversion of interview questions and follow-up questions is real-time conversion, and the interview questions and follow-up questions are converted into voice in real time, and sent directly to the interviewer after conversion; the form conversion of the follow-up words is cache conversion, and the follow-up words can be converted into voice in advance and continue to be cached so that they can be directly called when needed.

[0088] Figure 5 This is a schematic diagram of an interview logic in an exemplary application scenario provided by another exemplary embodiment of the present application. Figure 5 As shown, the interview logic in this exemplary application scenario includes the following steps:

[0089] Step 501, displaying multiple recruitment information to the interviewer;

[0090] Step 502, in response to an interview request initiated by the interviewer for the target recruitment information, the position type associated with the target recruitment information may be used as the position type applied for by the interviewer;

[0091] Step 503, obtaining the assessment dimensions required for the position type, the interviewee's resume data, and the interviewee's historical interview data;

[0092] Step 504, inputting the inspection dimension, the resume data and the historical interview data into the third model, so that the third model generates interview questions adapted to the inspection dimension according to the resume data and the historical interview data and the third prompt information;

[0093] Step 505, sending the interview question to the interviewee, and obtaining the answer provided by the interviewee to the interview question; wherein, if the interview question is the first interview question sent to the interviewee, the opening remarks of this interview may be shown to the interviewee before sending the first interview question;

[0094] Step 506, inputting the interview questions, answer content and job type into the first large model, so that the first large model extracts key information from the answer content according to the interview questions and job type and the first prompt information;

[0095] Step 507, judging whether the answer lacks any key information required for the interview question based on the extracted key information;

[0096] If it is determined in step 507 that the answer contains all the key information required for the interview question, then jump to step 508 to determine whether the current interview question is the last interview question;

[0097] If the current interview question is not the last interview question, then jump to step 509 and send the target follow-up words to the interviewee to prompt him to enter a new interview question;

[0098] If the current interview question is the last interview question, then jump to step 510 to provide the interviewee with a closing statement to end the interview;

[0099] If it is determined in step 507 that the answer lacks any key information required for the interview question, then jump to step 511 to determine whether the key information extraction time exceeds a preset time threshold;

[0100] If the preset time threshold is exceeded, the process jumps back to step 508 .

[0101] If the preset time threshold is not exceeded, the process jumps to step 512 to input the interview questions and answers into the second largest model, so that the second largest model can generate follow-up questions for the interviewee according to the interview questions and answers and the second prompt information.

[0102] Step 513, sending follow-up questions to the interviewee, and obtaining answers provided by the interviewee to the follow-up questions;

[0103] Step 514, determining whether the answer provided for the follow-up question lacks any key information required for the follow-up question;

[0104] If the answer provided for the follow-up question contains all the key information required for the follow-up question, then jump to step 508;

[0105] If the answer provided for the follow-up question lacks any key information required for the follow-up question, then jump to step 515 to determine whether the number of follow-up questions constructed for the interview question exceeds a preset follow-up threshold;

[0106] If it exceeds the preset inquiry threshold, jump to step 508;

[0107] If the preset inquiry threshold is not exceeded, the process jumps to step 512 .

[0108] Accordingly, in the embodiments of the present application, interview questions can be customized for each interviewee based on the interviewee's actual situation, and the answers returned by the interviewee can be detected in real time, so that when the answers lack any key information required for the interview questions, follow-up questions can be generated in time for the interview questions to guide the interviewee to provide the missing key information. This can provide the interviewee with a more realistic interview experience and a faster and more accurate understanding of the interviewee's abilities; and, corresponding response measures are provided for various situations that may arise during the interview process, so that the interview process can proceed smoothly, thereby effectively improving the interview experience and efficiency of both parties.

[0109] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 200 to 203 can be device A; for another example, the execution subject of steps 201 and 202 can be device A, and the execution subject of step 203 can be device B; and so on.

[0110] In addition, in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel, and the sequence numbers of the operations, such as 201, 202, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0111] Figure 6 A schematic diagram of a computing device provided as another exemplary embodiment of the present application is shown in FIG. Figure 6 As shown, the computing device includes: a memory 60 , a processor 61 , and a communication component 62 .

[0112] The processor 61 is coupled to the memory 60 and the communication component 62, and is used to execute the computer program in the memory 60, so as to:

[0113] After any interview question is sent to the interviewee, the answer content provided by the interviewee to the interview question is obtained through the communication component 62;

[0114] Determine the type of position the interviewee is applying for;

[0115] Interview questions, job types, and answer content are constructed as input data for the first model;

[0116] Obtaining preset first prompt information, the first prompt information is used to instruct the first large model to extract key information from the answer content according to the interview questions and job types in the input data, and the first prompt information also includes interview question examples, job type examples, answer content examples, and corresponding key information examples;

[0117] Providing the first prompt information and the input data to the first large model, so as to extract key information from the answer content provided by the interviewee by using the first large model;

[0118] If, based on the extracted key information, it is determined that the answer lacks any key information required for the interview question, a follow-up question is constructed for the interview question to guide the interviewee to provide the key information required for the follow-up question.

[0119] In an optional embodiment, in the process of extracting key information from the answer content provided by the interviewer using the first large model, the processor 61 is further used to:

[0120] Use the first model to perform semantic extraction operations on interview questions to obtain semantic information of interview questions;

[0121] Use the first model to find the target assessment dimension that matches the semantic information of the interview question from the assessment dimensions associated with the job type;

[0122] Using the first model to perform semantic extraction on the answer content, obtaining semantic information of the answer content;

[0123] Using the first model, search for target semantic information suitable for any target inspection dimension from the semantic information of the answer content;

[0124] The first model is used to combine the found target semantic information and the target examination dimension to which it is adapted as the key information extracted from the answer content.

[0125] In an optional embodiment, the processor 61 is further configured to:

[0126] If the target assessment dimensions contained in the key information extracted from the answer content do not cover all the assessment dimensions corresponding to the interview questions, it is determined that the answer content lacks any key information required for the interview questions.

[0127] In an optional embodiment, the processor 61 is further configured to:

[0128] In the case where the assessment dimension corresponding to the interview question is single, if the target assessment dimension included in the key information does not include the single assessment dimension corresponding to the interview question, it is determined that the answer content lacks any key information required for the interview question;

[0129] When there are multiple assessment dimensions corresponding to an interview question, if the target assessment dimension included in the key information lacks any one of the multiple assessment dimensions corresponding to the interview question, it is determined that any key information required for the interview question is missing in the answer content.

[0130] In an optional embodiment, the same assessment dimension is associated with one or more job types, and the processor 61 is further configured to:

[0131] Extract the target inspection dimension in the key information and the target semantic information corresponding to the target inspection dimension;

[0132] Obtain at least one position type associated with the target assessment dimension;

[0133] Based on the target semantic information corresponding to the target inspection dimension, traverse at least one job type to determine a target job type that matches the target semantic information from the at least one job type;

[0134] If the target position type is different from the position the interviewee is applying for, make sure that the answer is missing any key information required by the interview question.

[0135] In an optional embodiment, the processor 61 is further configured to:

[0136] If it is determined that the answer includes all the key information required for the interview question based on the extracted key information, a target transition phrase is selected from at least one preset transition phrase and displayed to the interviewee, and the target transition phrase is used to prompt the interviewee to proceed to a new interview question;

[0137] Present new interview questions to the interviewee.

[0138] In an optional embodiment, the processor 61 is further configured to:

[0139] In the case that the answer lacks any key information required for the interview question, if the time consumed by the interview question to extract the key information does not exceed the preset time threshold, a follow-up question is constructed for the interview question to guide the interviewee to provide the key information required for the follow-up question;

[0140] If the extraction time exceeds the preset time threshold, new interview questions are presented to the interviewee or the interview is ended.

[0141] In an optional embodiment, in the process of obtaining the answer content provided by the interviewer to the interview question, the processor 61 is further used to:

[0142] Monitor the status of the interviewee's responses to interview questions;

[0143] When it is detected that the answer status is answered, the answer content provided by the interviewer to the interview question is obtained;

[0144] If it is monitored that the answer status remains unanswered for a period exceeding a preset waiting threshold, a follow-up question is constructed for the interviewer to guide the interviewer to provide key information required for the follow-up question.

[0145] In an optional embodiment, during the process of constructing follow-up questions for interview questions, the processor 61 is further configured to:

[0146] The interview questions and answers were used as input data for the second largest model;

[0147] Obtaining preset second prompt information, the second prompt information is used to instruct the second largest model to ask follow-up questions based on the interview questions and answers in the input data, and the second prompt information also includes interview question examples, answer content examples, and corresponding follow-up question examples;

[0148] The input data and the second prompt information are provided to the second largest model to generate follow-up questions for the interview questions using the second largest model.

[0149] In an optional embodiment, before issuing any interview question to the interviewer, the processor 61 is further configured to:

[0150] In response to an interview request initiated by an interviewer, determine the type of position the interviewer is applying for;

[0151] Obtain the assessment dimensions that need to be focused on under the position type;

[0152] Obtain the interviewee's resume data and historical interview data;

[0153] The assessment dimensions, resume data, and historical interview data are constructed as input data for the third model;

[0154] Obtaining preset third prompt information, the third prompt information is used to instruct the third model to generate interview questions adapted to the examination dimension according to the resume data and historical interview data in the input data, the third prompt information also including resume data examples, historical interview data examples, examination dimension examples, and corresponding interview question examples;

[0155] The input data and the third prompt information are provided to the third model to generate interview questions for the interview request using the third model.

[0156] Further, if Figure 6 As shown, the computing device also includes: a display 63, a power component 64, an audio component 65 and other components. Figure 6 Only some components are shown schematically, and it does not mean that the computing device only includes Figure 6 Components shown.

[0157] It is worth noting that the technical details in the above-mentioned embodiments of the computing device can refer to the relevant descriptions of the actions of the computing device in the aforementioned embodiments of the interview method. In order to save space, they will not be repeated here, but this should not cause any loss of the protection scope of this application.

[0158] The embodiment of the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps in the above-mentioned interview method can be implemented. It should be noted that the technical solution of the computer program and the technical solution of the above-mentioned interview method belong to the same concept, and the details of the technical solution of the computer program that are not described in detail can be found in the description of the technical solution of the above-mentioned interview method.

[0159] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement the steps that can be executed by a computing device in the above method embodiment.

[0160] Above Figure 6 The memory in the computer is used to store computer programs and can be configured to store various other data to support operations on the computing platform. Examples of such data include instructions for any application or method operating on the computing platform, contact data, phone book data, messages, pictures, videos, etc. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0161] Above Figure 6 The communication component in is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0162] Above Figure 6The display in the embodiment includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0163] Above Figure 6 The power supply component in the device provides power to various components of the device where the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply component is located.

[0164] Above Figure 6 The audio component in can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting an audio signal.

[0165] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0166] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0167] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0168] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0169] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0170] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0171] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0172] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0173] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. An interview method, characterized in that: include: After issuing any interview question to the interviewee, obtaining the answer content provided by the interviewee to the interview question; Determine the type of position for which the interviewee is applying; The interview questions, the job types and the answer contents are constructed as input data of the first model; Obtaining preset first prompt information, where the first prompt information is used to instruct the first large model to extract key information from the answer content according to the interview questions and job types in the input data, and the first prompt information also includes interview question examples, job type examples, answer content examples, and corresponding key information examples; Providing the first prompt information and the input data to the first large model, so as to extract key information from the answer content provided by the interviewee by using the first large model; If it is determined based on the extracted key information that any key information required for the interview question is missing from the answer content, a follow-up question is constructed for the interview question to guide the interviewee to provide the key information required for the interview question.

2. The method according to claim 1, characterized in that The first model is used to extract key information from the answer provided by the interviewee, including: Using the first large model to perform a semantic extraction operation on the interview question to obtain semantic information of the interview question; Using the first model, from the assessment dimensions associated with the position type, a target assessment dimension that is adapted to the semantic information of the interview question is searched; Using the first large model to perform a semantic extraction operation on the answer content to obtain semantic information of the answer content; Using the first large model, searching for target semantic information suitable for any target inspection dimension from the semantic information of the answer content; The first large model is used to combine the found target semantic information and the target examination dimension to which it is adapted, as key information extracted from the answer content.

3. The method according to claim 2, characterized in that Also includes: If the target assessment dimensions contained in the key information extracted from the answer content do not cover all assessment dimensions corresponding to the interview question, it is determined that the answer content lacks any key information required for the interview question.

4. The method according to claim 3, characterized in that Also includes: In the case where the examination dimension corresponding to the interview question is single, if the target examination dimension included in the key information does not include the single examination dimension corresponding to the interview question, it is determined that the answer content lacks any key information required for the interview question; In the case where there are multiple examination dimensions corresponding to the interview question, if the target examination dimension included in the key information lacks any one of the multiple examination dimensions corresponding to the interview question, it is determined that the answer content lacks any key information required for the interview question.

5. The method according to claim 2, characterized in that: The same assessment dimension is associated with one or more job types, and the method further includes: Extracting target inspection dimensions from the key information and target semantic information corresponding to the target inspection dimensions; Obtain at least one position type associated with the target assessment dimension; Based on the target semantic information corresponding to the target inspection dimension, traverse the at least one position type to determine a target position type that matches the target semantic information from the at least one position type; If the target position type is different from the position type applied for by the interviewee, it is determined that the answer lacks any key information required for the interview question.

6. The method according to claim 1, characterized in that Also includes: If it is determined that the answer includes all the key information required for the interview question based on the extracted key information, a target connecting phrase is selected from at least one preset connecting phrase and displayed to the interviewee, wherein the target connecting phrase is used to prompt the interviewee to proceed to a new interview question; The new interview question is presented to the interviewer.

7. The method according to claim 1, characterized in that Also includes: In the case where the answer lacks any key information required for the interview question, if the time consumed by the interview question to extract the key information does not exceed the preset time threshold, then construct a follow-up question for the interview question to guide the interviewee to provide the key information required for the follow-up question; If the extraction time exceeds the preset time threshold, new interview questions are presented to the interviewee or the interview is ended.

8. The method according to claim 1, characterized in that Obtaining the answers provided by the interviewee to the interview questions, including: Monitoring the interviewee's answer status to the interview questions; When it is detected that the answer status is answered, obtaining the answer content provided by the interviewer to the interview question; If it is monitored that the duration of the unanswered state exceeds a preset waiting threshold, a follow-up question is constructed for the interviewer to guide the interviewer to provide key information required for the follow-up question.

9. The method according to claim 1, characterized in that: Construct follow-up questions for the interview questions, including: The interview questions and the answers are constructed as input data for the second largest model; Obtaining preset second prompt information, where the second prompt information is used to instruct the second large model to ask follow-up questions based on the interview questions and answers in the input data, and the second prompt information also includes interview question examples, answer content examples, and corresponding follow-up question examples; The input data and the second prompt information are provided to the second large model to generate follow-up questions for the interview question using the second large model.

10. The method according to claim 1, characterized in that Before asking the candidate any interview questions, include: In response to an interview request initiated by an interviewer, determining the type of position applied for by the interviewer; Obtain the assessment dimensions that need to be focused on under the position type; Obtaining resume data and historical interview data of the interviewee; The inspection dimension, the resume data and the historical interview data are constructed as input data of the third model; Obtaining preset third prompt information, wherein the third prompt information is used to instruct the third model to generate interview questions adapted to the examination dimension according to the resume data and the historical interview data in the input data, wherein the third prompt information also includes resume data examples, historical interview data examples, examination dimension examples, and corresponding interview question examples; The input data and the third prompt information are provided to the third large model to generate interview questions for the interview request using the third large model.

11. A computing device, characterized in that: Includes memory, processor, and communication components; The memory is used to store one or more computer instructions; The processor is coupled to the memory and the communication component, and is configured to execute the one or more computer instructions to execute the interview method according to any one of claims 1 to 10.

12. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed by one or more processors, the one or more processors are caused to execute the interview method according to any one of claims 1 to 10.

13. A computer program product, characterized in that The invention comprises a computer program, wherein when the computer program is executed by a processor, the processor is caused to execute the interview method according to any one of claims 1 to 10.

Images