AI-based recruitment interaction service method, device, and storage medium

Abstract

Embodiments of the present application provide an AI-based recruitment interaction service method and device and a storage medium. In the embodiments of the present application, if it is detected that a job seeker initiates an interaction request for a target recruitment position and no response is given to the interaction request within a set time, instead of asking the job seeker whether he or she has the intention to understand the target recruitment position, based on the confirmation information fed back by the job seeker, the job seeker is output with recruitment position introduction information corresponding to the target recruitment position. If the historical AI conversation record corresponding to the job seeker and the target recruitment position is obtained, a plurality of question and answer pairs are extracted from the historical AI conversation record, and based on the plurality of question and answer pairs, a confirmation question for inquiring whether the plurality of question and answer pairs are valid is generated. Based on the reply information fed back by the job seeker in response to the confirmation question, a new AI conversation record is generated, so as to guide the recruiter and the job seeker to carry out subsequent recruitment-related interactions based on the new AI conversation record, thereby improving the recruitment efficiency.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to an AI-based recruitment interaction service method, device, and storage medium. Background Technology

[0002] Currently, recruitment platforms allow recruiters to post job openings and job seekers to upload their resumes. Employers can proactively contact qualified candidates, and platforms can also recommend positions to job seekers. However, this process requires recruiters to manage communication with a large number of job seekers and utilize their resources, resulting in significant time wasted on identifying and contacting potential candidates, leading to low recruitment efficiency. Summary of the Invention

[0003] This application provides several aspects of an AI-based recruitment interaction service method, device, and storage medium to provide recruiters with AI recruitment interaction services, thereby improving recruitment efficiency.

[0004] This application also provides an AI-based recruitment interaction service method, applied to an AI interaction service module corresponding to a recruiter. The AI ​​interaction service module provides recruitment interaction services between the recruiter and job seekers. The method includes: If an interaction request initiated by a job seeker for a target job posting is detected, and the recruiter does not respond to the interaction request within a set time, the recruiter is simulated to output an AI inquiry card to the job seeker in the instant messaging chat interface with the job seeker. The AI ​​inquiry card is used to ask the job seeker whether they are willing to learn about the target job posting. Based on the confirmation information from the job seeker regarding the AI ​​inquiry card, the job description information corresponding to the target job position is output to the job seeker in the instant messaging chat interface; If the historical AI conversation records corresponding to the job seeker and the target job position are obtained, multiple question-answer pairs are extracted from the historical AI conversation records, and a confirmation question is generated based on the multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid. The confirmation question is output to the job seeker in the instant messaging chat interface. The multiple question-answer pairs consist of multiple reference questions corresponding to the target job position and the job seeker's response information to the multiple reference questions. The multiple reference questions are used to reflect the matching situation between the job seeker and the target job position. Based on the job seeker's response to the confirmation question, a new AI conversation record is generated between the job seeker and the target job posting. This new AI conversation record guides the recruiter and the job seeker to conduct subsequent recruitment-related interactions.

[0005] This application embodiment also provides a recruitment interaction service device, located in the AI ​​interaction service module corresponding to the recruiter. The device includes: a detection module, an output module, an extraction module, and a generation module. The detection module is used to simulate the recruiter if it detects an interaction request initiated by a job seeker for a target job posting and the recruiter does not respond to the interaction request within a set time. The AI ​​inquiry card is used to ask the job seeker whether they are willing to learn about the target job posting. The output module is used to output the job description information corresponding to the target job position to the job seeker in the instant messaging chat interface based on the confirmation information of the job seeker in response to the AI ​​inquiry card. An extraction module is used to extract multiple question-answer pairs from historical AI conversation records corresponding to the job seeker and the target job posting if such records are obtained. Based on these multiple question-answer pairs, a confirmation question is generated to inquire whether the multiple question-answer pairs are valid. The confirmation question is then output to the job seeker in the instant messaging chat interface. Each multiple question-answer pair consists of multiple reference questions corresponding to the target job posting and the job seeker's responses to these reference questions. The multiple reference questions reflect the matching status between the job seeker and the target job posting. The generation module is used to generate a new AI conversation record corresponding to the job seeker and the target job position based on the job seeker's response information to the confirmation question, so as to guide the recruiter and the job seeker to conduct subsequent recruitment-related interactions based on the new AI conversation record.

[0006] This application also provides an electronic device, including: a memory and a processor; the memory for storing a computer program; and the processor, coupled to the memory, for executing the computer program to implement the steps in the AI-based recruitment interactive service method provided in this application.

[0007] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to implement the steps of the AI-based recruitment interactive service method provided in this application.

[0008] In the AI-based recruitment interaction service solution provided in this application embodiment, when a job seeker initiates an interaction request for a target job posting, and the recruiter is offline or too busy to respond promptly, the system can proactively interact with the job seeker on their behalf. This involves displaying an AI inquiry card in the instant messaging chat interface to inquire whether the job seeker is interested in learning about the target job posting. If the job seeker is interested, they can provide confirmation information in response to the AI ​​inquiry card. Based on this confirmation, the system displays the job description information corresponding to the target job posting in the instant messaging chat interface. Subsequently, the system retrieves the job seeker's historical AI conversation records related to the target job posting to determine whether the job seeker has engaged in an AI conversation regarding the target job posting. If the job seeker has engaged in an AI conversation regarding the target job posting, multiple question-and-answer pairs are extracted from the historical AI conversation records. A confirmation question is generated based on these pairs to verify their validity, and this confirmation question is displayed to the job seeker in the instant messaging chat interface. Each question-and-answer pair consists of multiple reference questions corresponding to the target job posting and the job seeker's responses to these reference questions. These reference questions reflect the match between the job seeker and the target job posting. Finally, based on the job seeker's responses to the confirmation question, a new AI conversation record corresponding to the target job posting is generated. This new AI conversation record guides the recruiter and job seeker in subsequent recruitment-related interactions.

[0009] In the above solution, when an interaction request initiated by a job seeker regarding a target job posting is detected, and the job seeker fails to respond within a set time, the system can inquire about relevant information about the target job posting on behalf of the recruiter. This allows the recruiter to understand the job seeker's basic information related to the target position, thereby improving the recruiter's recruitment efficiency. Furthermore, when inquiring about job-related questions on behalf of the recruiter, it first determines whether the current AI conversation is a secondary trigger for the target job posting. If historical AI conversation records corresponding to the job seeker and the target job posting are obtained, confirming that this is a secondary trigger, a confirmation question is generated to verify the validity of multiple question-and-answer pairs in the historical AI conversation records. This eliminates the need for job seekers to repeatedly answer the same or similar questions, making the entire question-and-answer process simpler and faster. This increases job seeker cooperation with the AI ​​conversation, allows recruiters to gain a more comprehensive understanding of the job seeker's basic information, and enables subsequent interactions with the job seeker based on the AI ​​conversation records, saving time and improving recruitment efficiency. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating an AI-based recruitment interaction service method provided for an exemplary embodiment of this application; Figure 2 A flowchart illustrating a process for generating a confirmation question based on multiple question-answer pairs to determine whether the multiple question-answer pairs are valid, provided as an exemplary embodiment of this application; Figure 3 This is a flowchart illustrating an exemplary embodiment of the present application, which generates a new AI conversation record between a job seeker and a target job posting based on the job seeker's response to a confirmation question. Figure 4 An application illustration of displaying a question card corresponding to a target reference question in an instant messaging chat interface, provided as an exemplary embodiment of this application; Figure 5 A schematic diagram illustrating a process for guiding recruiters and job seekers to conduct subsequent recruitment-related interactions based on new AI conversation records, provided as an exemplary embodiment of this application; Figure 6 An application diagram illustrating an AI-based recruitment interaction service method provided as an exemplary embodiment of this application; Figure 7 A schematic diagram of a device for providing recruitment interactive services is provided as an exemplary embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0012] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0013] To address the aforementioned technical issues, this application provides an AI-based recruitment interaction service solution. When a job seeker initiates an interaction request for a target job posting, and the recruiter is offline or too busy to respond promptly, the system can simulate the recruiter's initiative to interact with the job seeker, proactively gathering the job seeker's basic information. This improves the interaction efficiency between recruiters and job seekers, thereby increasing the recruiter's recruitment efficiency.

[0014] Furthermore, when gathering basic information about job seekers and asking them questions for the target job on behalf of recruiters, the system can first determine if the job seeker has previously engaged in an AI conversation related to the same target job. If so, the system can confirm the validity of multiple question-and-answer pairs in the historical AI conversation records. Based on the job seeker's responses, a new AI conversation record corresponding to the target job is generated. This new record guides the recruiter and job seeker in subsequent recruitment-related interactions. Job seekers no longer need to repeatedly answer the same or similar questions, making the entire question-and-answer process simpler and faster. This increases job seeker cooperation with the AI ​​conversation, provides recruiters with more comprehensive information about the job seeker, saves recruiters initial research and data mining, and allows for direct interaction with job seekers based on the AI ​​conversation record, thereby improving recruitment efficiency.

[0015] The following describes in detail a solution provided by an embodiment of this application, with reference to the accompanying drawings.

[0016] Figure 1 A flowchart illustrating an AI-based recruitment interaction service method provided as an exemplary embodiment of this application; see attached document. Figure 1 As shown, this method can be applied to the AI ​​interaction service module corresponding to recruiters. The AI ​​interaction service module is used to provide recruitment interaction services between recruiters and job seekers. Specifically, the method may include: 101. If an interaction request initiated by a job seeker for a target job posting is detected, and the recruiter does not respond to the interaction request within a set time, the recruiter will simulate the recruiter and output an AI inquiry card to the job seeker in the instant messaging chat interface. The AI ​​inquiry card is used to ask the job seeker whether they are willing to learn about the target job posting.

[0017] 102. Based on the job seeker's confirmation information in response to the AI ​​inquiry card, output the job description information corresponding to the target job to the job seeker in the instant messaging chat interface.

[0018] 103. If the historical AI conversation records corresponding to the job seeker and the target job are obtained, multiple question-answer pairs are extracted from the historical AI conversation records, and confirmation questions are generated based on the multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid. The confirmation questions are output to the job seeker in the instant messaging chat interface. The multiple question-answer pairs consist of multiple reference questions corresponding to the target job and the job seeker's reply information to the multiple reference questions. The multiple reference questions are used to reflect the matching situation between the job seeker and the target job.

[0019] 104. Based on the job seeker's response to the confirmation question, generate a new AI conversation record corresponding to the job seeker and the target job posting, and use the new AI conversation record to guide the recruiter and job seeker to conduct subsequent recruitment-related interactions.

[0020] In practical applications, recruiters often spend a significant amount of time identifying and contacting potential candidates during the recruitment process. They frequently fail to respond promptly to job seekers' interactive requests, potentially missing out on candidates who are a perfect fit for the target position. Alternatively, when a job seeker initiates an interactive request, the recruiter may be offline. By the time the recruiter returns online, the job seeker may already be offline, requiring them to wait for the job seeker to come online before interacting with the recruiter. This process is lengthy and inefficient, resulting in low interaction efficiency between recruiters and job seekers.

[0021] Therefore, in this embodiment, it is possible to detect whether the recruiter responds to the interaction request initiated by each job seeker for the target job within a predetermined time. If an interaction request is detected and the recruiter does not respond within the set time, the interaction between the recruiter and the job seeker can be simulated, improving the efficiency of the interaction. Furthermore, during the simulated interaction, questions related to the target job can be asked on behalf of the recruiter to understand the match between the job seeker and the target job, as well as the job seeker's job intentions. This saves the recruiter significant consultation and communication time, thereby improving recruitment efficiency.

[0022] Specifically, if an interaction request initiated by a job seeker for a target job posting is detected, and the recruiter does not respond to the request within a set time, the recruiter simulates an AI inquiry card and outputs it to the job seeker in an instant messaging chat interface. The AI ​​inquiry card is used to ask the job seeker if they are interested in learning about the target job posting. For example, the content of the AI ​​inquiry card might be: "Hi + [User Name] + We are recruiting for a [Level 3] position. To better understand your information, I have a few important questions I'd like to discuss with you in advance." Or, the AI ​​inquiry card might include: "Hi + [User Name] + We are recruiting for a [Level 3] position. Would it be convenient to chat?". In this embodiment, the content of the AI ​​inquiry card is not limited and can be adapted accordingly.

[0023] In addition, the AI ​​inquiry card can include multiple controls, allowing job seekers to respond to the AI ​​inquiry card displayed in the instant messaging chat interface by triggering these controls. These controls can include: a "Let's chat" control, a "Not needed right now" control, etc. For example, ... Figure 2 As shown, a simulated recruiter outputs an AI inquiry card to a job seeker in an instant messaging chat interface. The AI ​​inquiry card reads: "Hi + [User Name] + We are recruiting for a [Level 3] position, would you mind chatting?". The AI ​​inquiry card includes "Let's chat" and "Not needed at the moment" controls. When the job seeker triggers the "Let's chat" control, the AI ​​responds by outputting the corresponding text "Let's chat" in the instant messaging chat interface, indicating that the job seeker is interested in learning about the target job and has provided confirmation of the AI ​​inquiry card's response.

[0024] Then, based on the job seeker's confirmation of the AI ​​inquiry card, the system can output the job description information corresponding to the target recruitment position to the job seeker in the instant messaging chat interface. This job description information mainly explains the work location, work experience requirements, education requirements, monthly salary range, age requirements, and various benefits of the recruitment position.

[0025] In practical applications, keywords can be extracted from job descriptions to generate the corresponding job introduction information. Alternatively, job introduction scripts can be pre-configured. When it's necessary to deliver the desired job introduction information to job seekers, keywords can be extracted from the job description and inserted into the corresponding script. For example, a job introduction script could be: "Let me introduce the job to you first. The work location is in {city + district + business area}, work experience {specific years required}, education {specific education requirement}, monthly salary range {salary range}, age {specific age range}, {benefits 1}, {benefits 2}, {benefits 3}…". The extracted keywords are then inserted into the corresponding positions to generate the job introduction information for the target position, which is then displayed to job seekers in the instant messaging chat interface. Note that if the job description does not include the content corresponding to a particular item, that item can be hidden.

[0026] After providing job seekers with the job description information for the target position, the system can ask them questions related to the position to further understand the match between the job seeker and the target job, as well as the job seeker's interest in the position. However, in practice, if a job seeker has already engaged in similar question-and-answer sessions with the AI ​​interaction service module multiple times, they may become annoyed and uncooperative when asked similar questions again, thus affecting the questioning results. This prevents the system from providing recruiters with more comprehensive basic information about the job seeker, ultimately impacting the recruiter's hiring outcome.

[0027] Therefore, in this embodiment, when conducting AI Q&A sessions with job seekers related to the target job posting, historical AI conversation records between the job seeker and the target job posting can be obtained to determine whether the job seeker has previously conducted AI Q&A sessions related to the same target job posting. This determines whether the current AI Q&A session triggered on the job seeker is the first time such a session has been initiated. If it is determined that this is the first AI Q&A session triggered on the job seeker regarding the target job posting, questions can be asked sequentially according to the information the recruiter might want to know, guiding the job seeker to respond with work experience related to the target job posting. If it is determined that this is not the first AI Q&A session triggered on the job seeker regarding the target job posting, historical AI conversation records between the job seeker and the target job posting can be obtained. The responses to multiple reference questions related to the target job posting in the historical conversation records can be confirmed. For completed and confirmed reference questions, there is no need to repeat the questions; questions can be asked sequentially.

[0028] Specifically, if historical AI conversation records between the job seeker and the target job are obtained, multiple question-and-answer pairs are extracted from these records. Confirmation questions are then generated based on these pairs to verify their validity, and these confirmation questions are displayed to the job seeker in the instant messaging chat interface. Each question-and-answer pair consists of multiple reference questions corresponding to the target job and the job seeker's responses to these reference questions. These reference questions reflect the match between the job seeker and the target job.

[0029] Furthermore, for this target job posting, the job seeker may have initiated interaction requests with different recruiters, resulting in multiple AI conversations related to the position, triggering two or more AI Q&A sessions. Therefore, retrieving the historical AI conversation records for this job seeker and the target job posting may yield multiple records. Since the job seeker's work experience or job requirements may change over time, the most recent historical AI conversation record can be retrieved. For the question-and-answer pairs in the latest historical AI conversation record, the job seeker can be asked whether they wish to update their responses to multiple reference questions. To reduce the amount of data stored, when a new AI conversation occurs, the historical conversation records for this job seeker regarding the target job posting stored in the database can be updated to the latest AI conversation record; that is, the database can retain only the most recent AI conversation record.

[0030] Additionally, if historical AI conversation records corresponding to the target job posting are obtained, it indicates that the job seeker has previously engaged in AI Q&A for the same target job posting. The question-and-answer pairs in the historical conversation records need to be confirmed. Since historical conversation records typically contain multiple question pairs, confirming each pair sequentially would be extremely tedious. Therefore, in this embodiment, multiple question pairs from the historical AI conversation records can be concatenated to generate a single confirmation question, which the job seeker can then simply reply to.

[0031] After job seekers respond to the confirmation questions, a new AI conversation record can be generated between the job seeker and the target job posting based on the job seeker's response. This new AI conversation record can then guide recruiters and job seekers to conduct subsequent recruitment-related interactions.

[0032] The generated confirmation question is primarily used to verify the validity of multiple question pairs in the historical AI conversation record. If the job seeker confirms that all question pairs in the historical conversation record are valid, they can provide feedback that all are valid and no updates are needed. In this case, the current AI conversation can be ended, and a new AI conversation record can be generated based on the historical AI conversation record. If the job seeker confirms that a certain question pair needs updating, they can provide feedback that some question pairs are invalid and need updating. In this case, the invalid question pair can be asked again to obtain new feedback from the job seeker, ending the current AI conversation, and a new AI conversation record can be generated based on the new feedback.

[0033] In addition, different recruiters may have different questions and focuses for the same target job. That is, there may be multiple reference questions to ask the job seeker for the same target job. After confirming all the questions in the historical AI conversation records, it is determined whether the job seeker has any other questions. If the job seeker has other questions, they can continue to ask.

[0034] In the AI-based recruitment interaction service solution provided in this application embodiment, when an interaction request initiated by a job seeker for a target job posting is detected, and the job seeker fails to respond to the interaction request within a set time, the system can inquire about relevant information about the target job posting on behalf of the recruiter. This allows the recruiter to understand the job seeker's basic information related to the target job posting, thereby improving the recruiter's recruitment efficiency. Furthermore, when inquiring about job-related questions on behalf of the recruiter, it first determines whether the current AI session is a secondary trigger for the target job posting. If historical AI session records corresponding to the job seeker and the target job posting are obtained, confirming that this is a secondary trigger, a confirmation question is generated to verify the validity of multiple question-and-answer pairs in the historical AI session records. This eliminates the need for job seekers to repeatedly answer the same or similar questions, making the entire question-and-answer process simpler and faster. This increases the job seeker's cooperation with the AI ​​session, allowing the recruiter to gain a more comprehensive understanding of the job seeker's basic information. The recruiter can then use the AI ​​session records to interact with the job seeker further, saving recruitment time and improving recruitment efficiency.

[0035] To facilitate understanding of the specific implementation process of generating a confirmation question based on multiple question-answer pairs to determine the validity of these pairs in the above embodiments, combined with... Figure 2 An exemplary description is provided of the specific implementation process for generating a confirmation question based on multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid.

[0036] Figure 2A flowchart illustrating a process for generating a confirmation question based on multiple question-answer pairs to determine their validity, provided as an exemplary embodiment of this application; see attached diagram. Figure 2 As shown, the method may include: 201. Generate multiple structured information from multiple question-answer pairs, each structured information including the question and answer information of the corresponding question-answer pair.

[0037] 202. Combine multiple structured information.

[0038] 203. Confirmation of the generated spliced ​​result containing multiple structured information.

[0039] The historical AI conversation records mainly consist of multiple question-and-answer pairs. These pairs are composed of several reference questions corresponding to the target job posting and the job seeker's responses to those reference questions. The reference questions reflect the match between the job seeker and the target job. Therefore, upon obtaining the historical AI conversation records corresponding to the target job posting, multiple question-and-answer pairs can be extracted. Since these pairs include the job seeker's responses to the reference questions, it's possible to directly inquire whether these responses are valid. If valid, there's no need to ask the job seeker the reference questions again.

[0040] In practical applications, multiple question pairs are extracted from historical AI conversation records. In order to improve the interaction efficiency between the AI ​​interaction service module and job seekers and enhance the job seeker's experience, in this embodiment of the application, multiple question pairs can be spliced ​​together to generate a confirmation question. Confirming this confirmation question can achieve simultaneous confirmation of multiple question pairs, effectively improving the efficiency of AI question answering.

[0041] Specifically, multiple structured information is generated based on multiple question-answer pairs. Each structured information includes the question and answer information of the corresponding question-answer pair. The multiple structured information are then concatenated to generate a confirmation question containing the concatenated result of the multiple structured information.

[0042] In practice, for example, if the target job posting is chef, the historical AI conversation records might include question pairs like, "Do you have any chef-related experience? I have five years of chef experience," "Okay, do you have a health certificate? Yes," and "Great, what type of restaurants have you worked in? Chain restaurants, star-rated restaurants." After extracting multiple question pairs, several structured pieces of information are generated: "Do you have any chef-related experience? I have five years of chef experience," "Do you have a health certificate? Yes," and "What type of restaurants have you worked in? Chain restaurants, star-rated restaurants." These structured pieces of information are then concatenated to obtain the concatenated result: "I have five years of chef experience, a health certificate, and have worked in chain restaurants and star-rated restaurants." Finally, based on the concatenated result of the multiple structured pieces of information, a confirmation question is generated: "Do you have five years of chef experience, and have worked in chain restaurants and star-rated restaurants for these five years, and have a health certificate, correct?"

[0043] In this embodiment of the application, multiple structured information is generated based on multiple question-answer pairs, and the multiple structured information is spliced ​​together to generate a confirmation question containing the spliced ​​result of multiple structured information. In this way, the information in multiple question pairs can be confirmed at the same time during a single question-asking process, which can simplify the AI ​​question-answering process, improve job seeker experience and cooperation, and improve the efficiency of interaction with job seekers.

[0044] The above embodiments describe how to generate a confirmation question based on multiple questions in historical AI conversation records, allowing job seekers to confirm multiple question pairs using this confirmation question. If the job seeker confirms that updating multiple question-answer pairs is not required, the current AI conversation can end, and a new AI conversation record is determined based on the historical AI conversation record. This new AI conversation record is then output in the instant messaging chat interface, allowing recruiters to determine whether to continue interacting with the job seeker. If the job seeker confirms that updating certain question-answer pairs is necessary, the corresponding question card for that reference question is displayed in the instant messaging chat interface, allowing the job seeker to re-respond to these reference questions. The following describes a method in conjunction with... Figure 3 The specific implementation process of generating a new AI conversation record corresponding to the target job posting based on the job seeker's response to the confirmation question is illustrated by an example.

[0045] Figure 3 A flowchart illustrating an exemplary embodiment of this application is provided, illustrating the process of generating a new AI conversation record between a job seeker and a target job posting based on the job seeker's response to a confirmation question; see attached diagram. Figure 3 As shown, the method may include: 301. If the reply message indicates that multiple question-answer pairs are valid, then the new AI conversation record is determined to be the same as the historical AI conversation record.

[0046] 302. If the reply message indicates that at least one of the multiple question-answer pairs is invalid, then output at least one reference question corresponding to at least one question-answer pair in the instant messaging chat interface, obtain the job seeker's new reply information to at least one reference question, and generate a new AI conversation record.

[0047] If the job seeker's response to the confirmation question indicates that multiple question-answer pairs in the historical AI conversation record are valid, then the new AI conversation record is determined to be the same as the historical AI conversation record. If the job seeker's response to the confirmation question indicates that at least one question-answer pair is invalid, then at least one reference question corresponding to at least one question-answer pair is output in the instant messaging chat interface so that the job seeker can reply to the reference question again. Then, the job seeker's new response to at least one reference question is obtained, and a new AI conversation record is generated based on the new response and the confirmation question.

[0048] In one optional embodiment, the specific implementation of outputting at least one reference question corresponding to at least one question-answer pair in the instant messaging chat interface and obtaining the job seeker's new response information to at least one reference question can be as follows: displaying a question card corresponding to the target reference question in the instant messaging chat interface, the question card including the target reference question and multiple candidate answer controls, the target reference question being any one of the at least one reference question; responding to the job seeker's selection operation of the target candidate answer control, setting the target candidate answer control to the selected state, and displaying the text content corresponding to the target candidate answer control as the reply text corresponding to the target reference question in the instant messaging chat interface.

[0049] In this AI interaction service module, after outputting the question card corresponding to the target reference question in the instant messaging chat interface, multiple candidate answer controls corresponding to the target reference question can be displayed simultaneously. By triggering each candidate answer control, the corresponding reply information can be selected, allowing job seekers to quickly and conveniently complete AI Q&A. Furthermore, in this embodiment, after the job seeker triggers the selection operation of the target candidate answer control, the system responds by placing the target candidate answer control in a selected state and automatically outputting the corresponding text content in the instant messaging chat interface. That is, this text content is determined as the reply text corresponding to the target reference question. For example, after the job seeker selects the target candidate answer control, the target candidate answer control is displayed in gray in the instant messaging chat interface, and the corresponding text content is automatically displayed.

[0050] Since the text content corresponding to the target candidate answer can be automatically displayed after the job seeker triggers the selection operation of the target candidate answer control, the AI ​​conversation record can only include multiple reference questions and the corresponding reply information of each reference question, and the multiple candidate answer options displayed can be removed to reduce the amount of data.

[0051] During the AI ​​question-and-answer process, job seekers cannot modify question cards that have already submitted answers. If modifications are needed, they can be made by entering text content to change the answer. Furthermore, in practical applications, job seekers may have multiple target answers for a single reference question. Therefore, in this embodiment, job seekers can select one or more answers from a set of candidate answers, meaning they can choose one or more candidate answer controls as the final answer corresponding to the target reference question.

[0052] The system can determine whether a single-choice or multiple-choice target answer control is used, depending on the nature of the reference question. For single-choice reference questions, after a job seeker selects a target answer control, the corresponding text content is directly displayed in the instant messaging chat interface; repeated selection is not currently supported. For multiple-choice reference questions, the instant messaging chat interface can also display selected controls. After a job seeker selects one target answer control, that control is set to selected. When the job seeker selects all target answer controls, the selected controls are combined and displayed in the instant messaging chat interface. Simultaneously, job seekers can freely input text to reply to the corresponding target reference question. The AI ​​interaction service module then recognizes the output free text content to determine the reply text corresponding to the target reference question.

[0053] For example, such as Figure 4As shown, the instant messaging chat interface displays a question card corresponding to the target reference question, such as "Do you have any chef-related experience?" The job seeker can directly enter the reply "I have five years of chef experience" in the corresponding text input box. In response to the job seeker's reply, the instant messaging chat interface displays the reply "I have five years of chef experience." Next, the instant messaging chat interface continues to ask the job seeker questions, displaying a question card corresponding to the target reference question, such as "Okay, do you have a health certificate?" and multiple candidate answer controls "Yes" and "No health certificate." The job seeker can directly select the corresponding target candidate answer control "Yes" in the instant messaging chat interface. In response to the job seeker's selection of the target candidate answer control, the target candidate answer control is selected, and the text content corresponding to the target candidate answer control is displayed as the reply text corresponding to the target reference question, i.e., the reply text "I have a health certificate" is displayed in the instant messaging chat interface. Then, the system continues to ask questions of the job seeker, displaying a question card corresponding to the target reference question in the instant messaging chat interface. The question card includes the target reference question, "Great! What type of restaurant have you worked in?", along with multiple candidate answer controls: "Chinese breakfast shop," "chain restaurant," "starred restaurant," "high-end restaurant," "Western restaurant," "None," and a "selected" control. The job seeker can select the corresponding target candidate answer controls, such as "chain restaurant" or "starred restaurant," in the instant messaging chat interface. In response to the job seeker's selection, the corresponding text content of the selected target candidate answer control is displayed as the reply text corresponding to the target reference question, i.e., the reply text "chain restaurant, starred restaurant" is displayed in the instant messaging chat interface.

[0054] During the Q&A session with job seekers, structured information from multiple question-and-answer pairs can be collected and automatically updated into the corresponding resumes of the job seekers. This helps to improve the resumes and facilitates better recommendations to suitable recruiters in the future. If the collected structured information matches the information in the resume, no update is needed. If the update is successful, a notification will be displayed in the instant messaging chat interface after the AI ​​session ends: "Friendly reminder: Some information you submitted during the inquiry has been updated into your resume." Furthermore, after the AI ​​session ends, the generated new AI session record can be updated in the database storing the AI ​​session records corresponding to the job seeker and the target job opening.

[0055] In practical applications, job seekers often voluntarily exit the AI ​​session midway. If a job seeker exits midway, a pop-up window will display the message, "Completing the job Q&A will increase the chances of being contacted by the recruiter. Are you sure you want to give up?" Both "Continue Answering" and "Confirm Exit" controls will be displayed to remind the job seeker. If a job seeker exits the AI ​​session before even starting to answer a question, the Q&A session is considered invalid, and the AI ​​session record will not be saved. However, if a job seeker has already sent a reply but exited the AI ​​session before completing it, the AI ​​session record will be saved.

[0056] In this embodiment, if the reply information indicates that multiple question-answer pairs are valid, then the new AI conversation record is determined to be the same as the historical AI conversation record. If the reply information indicates that at least one of the multiple question-answer pairs is invalid, then at least one reference question corresponding to at least one question-answer pair is output in the instant messaging chat interface to obtain the job seeker's new reply information to at least one reference question, thereby generating a new AI conversation record. This allows for the rapid completion of AI conversations and the rapid generation of corresponding new AI conversation records.

[0057] In practical applications, after generating a new AI conversation record, it can be integrated and sent to recruiters. This allows recruiters to clearly see all the information within the instant messaging chat interface. Specifically, the new AI conversation record is displayed as a card in the instant messaging chat interface, titled: "My Job Application Q&A Record." The card's display area shows the content of the 2nd, 3rd, and 4th messages in the new AI conversation record, giving recruiters a general understanding of the AI ​​conversation content. If recruiters want to view the complete conversation record, they can click on the card to display the full conversation messages.

[0058] Once recruiters learn about job seekers' basic information directly through the new AI conversation records, if they feel the candidate is a good fit for the target position, they can directly contact the candidate by phone to schedule an interview, significantly improving recruitment efficiency and preventing them from missing out on suitable talent. Furthermore, to facilitate further interaction between recruiters and job seekers, this embodiment can also guide them through subsequent recruitment-related interactions based on the new AI conversation records. For example, recruiters can be guided to initiate phone conversations with job seekers, and job seekers can be guided to submit resumes, exchange WeChat contacts (or any third-party communication software), or proactively call recruiters. Combined with... Figure 5 This paper provides an exemplary description of the specific implementation process of guiding recruiters and job seekers to conduct subsequent recruitment-related interactions based on new AI conversation records.

[0059] Figure 5 A schematic diagram illustrating a process for guiding recruiters and job seekers to conduct subsequent recruitment-related interactions based on new AI conversation records, as provided in an exemplary embodiment of this application; see attached diagram. Figure 5 As shown, the method may include: 501. Based on the job seeker's responses to reference questions in the new AI conversation records, determine the match between the job seeker and the recruiter.

[0060] 502. If the matching degree meets the preset threshold, an interaction channel is established for job seekers and recruiters to interact based on the interaction channel.

[0061] In this embodiment, after a new AI conversation record is generated, the recruiter and job seeker can be guided to further interact based on the new AI conversation record. Specifically, the matching degree between the job seeker and recruiter is determined based on the job seeker's response to the reference question in the new AI conversation record. If the matching degree meets a preset threshold, an interaction channel is established between the job seeker and recruiter, enabling them to interact through this channel. This improves the interaction efficiency between the recruiter and job seeker, thereby increasing the recruiter's recruitment efficiency.

[0062] This allows for the establishment of interactive channels between recruiters and job seekers, corresponding to specific connection methods. These methods can include: exchanging WeChat contacts, making two-way calls, submitting resumes, exchanging phone numbers, and exchanging third-party instant messaging application accounts.

[0063] In one optional embodiment, the specific implementation of establishing an interaction channel between job seekers and recruiters may include: determining the job seeker's job intention for the target job posting; determining the target channel mode corresponding to the interaction channel based on the job intention; and establishing the interaction channel between the job seeker and recruiter using the target channel mode. That is, when the match between the job seeker and recruiter is high, before establishing the interaction channel between them, in order to improve the recruiter's recruitment efficiency, the job seeker's job intention for the target job posting can be determined first, and then the corresponding target channel mode can be determined based on the job intention.

[0064] For example, when job seekers have a strong desire to apply for the target job, the target channel mode can be a phone call; when job seekers have a moderate desire to apply for the target job, the target channel mode can be guiding them to chat on WeChat; and when job seekers have a low desire to apply for the target job, the target channel mode can be guiding them to submit a resume.

[0065] In one optional embodiment, determining a job seeker's intention to apply for the target position can be achieved by: determining the job seeker's intention to apply for the target position based on at least one of the following: the number of reference questions answered by the job seeker in the new AI conversation record; the job seeker's delay in answering the reference questions; or keywords in the conversation information output by the job seeker in the instant messaging chat interface. The conversation information includes responses to the reference questions, and the keywords refer to keywords used to reflect the job seeker's intention.

[0066] Additionally, information actively input by job seekers during AI conversations can be used to determine their interest in the target position. For example, questions asked and expressions of interest regarding the target position can help determine their job intentions.

[0067] After determining the job seeker's interest in the target position, a corresponding target channel mode is determined based on this interest, and an interaction channel is established between the job seeker and the recruiter using this target channel mode. Specifically, if the determined target channel mode is a telephone call mode, the encrypted phone number of the recruiter or job seeker is obtained, and the recruiter's encrypted phone number is filled into a preset AI-guided outbound call script template to obtain the AI-guided outbound call script information. This AI-guided outbound call script information is then sent to the job seeker or recruiter to guide them to make a telephone call to the other party.

[0068] In an alternative embodiment, if the determined target channel mode is a telephone call mode, new AI conversation records can be obtained, analyzed, and processed to obtain text information related to the job seeker and the target job posting. This text information is then converted into voice information, and an outbound call request is initiated to the recruiter based on the recruiter's encrypted phone number. The voice information is then played to the recruiter, allowing the recruiter to obtain the job seeker's basic information in a timely manner without having to review complex conversation records, and to interact with the job seeker further in a timely manner.

[0069] If the target channel mode is resume submission mode, a submission guidance message will be generated. The submission guidance message includes multiple submission controls, which job seekers can use to trigger the corresponding submission behavior. The submission guidance message will be sent to the job seeker to guide them to trigger the submission operation.

[0070] In this embodiment of the application, the matching degree between job seekers and recruiters is determined based on the job seeker's response to reference questions in the new AI conversation record. If the matching degree meets a preset threshold, an interaction channel is established between the job seeker and the recruiter so that they can interact based on the interaction channel. This allows the recruiter to interact with the job seeker as soon as possible, improving the interaction efficiency between the recruiter and the job seeker, and thus improving the recruiter's recruitment efficiency.

[0071] The detailed implementation methods and beneficial effects of each step in the embodiments of this application have been described in detail in the foregoing embodiments, and will not be elaborated here.

[0072] The above embodiments describe the specific implementation process of how the AI ​​interaction service module simulates the interaction between the recruiter and the job seeker when the recruiter fails to respond to the job seeker's interaction request for the target job within a set time. The AI ​​interaction service module asks the job seeker questions about job matching related to the target job on behalf of the recruiter, so as to understand the job seeker's basic information in advance and guide the interaction between the recruiter and the job seeker. In order to facilitate the understanding of the above implementation process, it is illustrated with examples in conjunction with application scenarios.

[0073] like Figure 6 As shown, suppose job seeker A initiates an interaction request to recruiter B for the target job of chef. Recruiter B does not respond to the interaction request within a set time. Simulate the recruiter asking job seeker questions related to the target job and generate a new AI conversation record corresponding to the target job based on the AI ​​question-answering results. The recruiter will then guide the recruiter and job seeker to conduct subsequent interactions related to recruitment based on the new AI conversation record.

[0074] In practical application, if it is detected that job seeker A initiates an interaction request to recruiter B for the target position of chef, and recruiter B fails to respond to the interaction request within a set time, then the system simulates recruiter B and outputs an AI inquiry card to job seeker A in the instant messaging chat interface: "Hi + [Job Seeker A] + We are recruiting for the position of [Chinese Restaurant Chef]. To better understand your information, I have a few important questions I would like to discuss with you in advance." The system also displays "Not Needed at the Moment" and "Let's Chat" controls. Job seeker A triggers the "Let's Chat" control and provides confirmation information regarding the AI ​​inquiry card. Next, the instant messaging chat interface outputs the job description information for the target chef position to job seeker A: "Let me introduce it to you first. The work location is in Chaoyang District, Beijing. 5 years of work experience is required. A college degree or above is required. The monthly salary is 5000-10000 yuan. The age is 18-35 years old. The working hours are 8:00 am to 6:00 pm. There is a shuttle bus and an annual bonus."

[0075] Then, the historical AI conversation records between job seeker A and the target job are obtained. Assuming that the historical AI conversation records between job seeker A and the target job are obtained, multiple question-answer pairs are extracted from the historical AI conversation records, and a confirmation question is generated based on the multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid. That is, the generated confirmation question is: "Do you have five years of chef experience, have worked in chain restaurants and star-rated restaurants in these 5 years, and have a health certificate?", and the confirmation question is output to the job seeker in the instant messaging chat interface.

[0076] Then, after the job seeker provides multiple valid responses to the confirmation question, the AI ​​conversation ends, and a closing message is displayed in the instant messaging chat: "Received. We will contact you by phone if you are a suitable candidate. Please keep your phone accessible." The historical AI conversation record is then directly designated as the new AI conversation record. Based on this new AI conversation record, the match between the job seeker and the recruiter is determined. If the match meets a preset threshold, the recruiter can be guided to engage in subsequent recruitment-related interactions with the job seeker.

[0077] It should be noted that the execution subject of each step of the method provided in the above embodiments can be the same device, or the method can be executed by different devices. For example, the execution subject of steps 101 to 103 can be device A; or the execution subject of steps 101 and 102 can be device A, and the execution subject of step 103 can be device B, etc.

[0078] Furthermore, some processes described in the above embodiments and accompanying drawings include multiple operations appearing in a specific order. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or they may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Additionally, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first" and "second" in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0079] Figure 7 A schematic diagram of a device for providing recruitment interactive services is provided as an exemplary embodiment of this application, such as... Figure 7 As shown, the device includes: a detection module 701, an output module 702, an extraction module 703, and a generation module 704.

[0080] The detection module 701 is used to simulate the recruiter if it detects an interaction request initiated by a job seeker for a target job posting and the recruiter does not respond to the interaction request within a set time. The AI ​​inquiry card is used to ask the job seeker whether they are willing to learn about the target job posting.

[0081] The output module 702 is used to output the job description information corresponding to the target job position to the job seeker in the instant messaging chat interface based on the confirmation information of the job seeker's feedback on the AI ​​inquiry card.

[0082] The extraction module 703 is used to extract multiple question-and-answer pairs from the historical AI conversation records corresponding to the job seeker and the target job position if the historical AI conversation records corresponding to the job seeker are obtained, and to generate a confirmation question based on the multiple question-and-answer pairs to inquire whether the multiple question-and-answer pairs are valid. The confirmation question is then output to the job seeker in the instant messaging chat interface. The multiple question-and-answer pairs consist of multiple reference questions corresponding to the target job position and the job seeker's response information to the multiple reference questions. The multiple reference questions are used to reflect the matching situation between the job seeker and the target job position.

[0083] The generation module 704 is used to generate a new AI conversation record corresponding to the job seeker and the target job position based on the job seeker's response information to the confirmation question, so as to guide the recruiter and the job seeker to conduct subsequent recruitment-related interactions based on the new AI conversation record.

[0084] In an optional embodiment, the extraction module 703 is specifically used to: generate multiple structured information based on the multiple question-answer pairs, each structured information including the question and answer information in the corresponding question-answer pair; concatenate the multiple structured information; and generate the confirmation question containing the concatenation result of the multiple structured information.

[0085] In an optional embodiment, the generation module 704 is specifically configured to: if the reply information indicates that all of the multiple question-answer pairs are valid, then determine that the new AI conversation record is the same as the historical AI conversation record; if the reply information indicates that at least one of the multiple question-answer pairs is invalid, then output at least one reference question corresponding to the at least one question-answer pair in the instant messaging chat interface, obtain the job seeker's new reply information to the at least one reference question, and generate the new AI conversation record.

[0086] In an optional embodiment, the generation module 704 is specifically configured to: display a question card corresponding to the target reference question in the instant messaging chat interface, the question card including the target reference question and multiple candidate answer controls, the target reference question being any one of the at least one reference question; in response to the job seeker's selection operation on the target candidate answer control, setting the target candidate answer control to a selected state, and displaying the text content corresponding to the target candidate answer control as reply text corresponding to the target reference question in the instant messaging chat interface.

[0087] In an optional embodiment, the generation module 704 is specifically used to: determine the matching degree between the job seeker and the recruiter based on the job seeker's response information to the reference question in the new AI session record; if the matching degree meets a preset threshold, then establish an interaction channel for the job seeker and the recruiter so that the job seeker and the recruiter can interact based on the interaction channel.

[0088] In an optional embodiment, the generation module 704 is specifically used to: determine the job seeker's job intention for the target job posting; determine the target channel mode corresponding to the interaction channel based on the job seeker's job intention; and establish an interaction channel for the job seeker and the recruiter based on the target channel mode.

[0089] In an optional embodiment, the generation module 704 is specifically configured to: determine the job seeker's job intention for the target recruitment position based on at least one of the following: the number of reference questions answered by the job seeker contained in the new AI conversation record, the job seeker's delay in answering the reference questions, or keywords in the dialogue information output by the job seeker in the instant messaging chat interface; wherein, the dialogue information includes response information to the reference questions, and the keywords refer to keywords used to reflect job intention.

[0090] In an optional embodiment, the generation module 704 is specifically used to: if the target channel mode is a telephone call mode, obtain the encrypted phone number of the recruiter or the job seeker; fill the encrypted phone number of the recruiter into a preset AI-guided outbound call script template to obtain AI-guided outbound call script information; and send the AI-guided outbound call script information to the job seeker or the recruiter to guide the job seeker or the recruiter to make a telephone call to the other end.

[0091] Regarding the embodiments provided in this application Figure 7 The detailed implementation methods and beneficial effects of each step in the apparatus shown have been described in detail in the foregoing embodiments, and will not be elaborated here.

[0092] Figure 8A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application, such as... Figure 8 As shown, the device includes a memory 84 and a processor 85.

[0093] Memory 84 is used to store computer programs and can be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device.

[0094] Processor 85, coupled to memory 84, is used to execute computer programs in memory 84 for: If an interaction request initiated by a job seeker for a target job posting is detected, and the recruiter does not respond to the interaction request within a set time, the recruiter is simulated to output an AI inquiry card to the job seeker in the instant messaging chat interface with the job seeker. The AI ​​inquiry card is used to ask the job seeker whether they are willing to learn about the target job posting. Based on the confirmation information from the job seeker regarding the AI ​​inquiry card, the job description information corresponding to the target job position is output to the job seeker in the instant messaging chat interface; If the historical AI conversation records corresponding to the job seeker and the target job position are obtained, multiple question-answer pairs are extracted from the historical AI conversation records, and a confirmation question is generated based on the multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid. The confirmation question is output to the job seeker in the instant messaging chat interface. The multiple question-answer pairs consist of multiple reference questions corresponding to the target job position and the job seeker's response information to the multiple reference questions. The multiple reference questions are used to reflect the matching situation between the job seeker and the target job position. Based on the job seeker's response to the confirmation question, a new AI conversation record is generated between the job seeker and the target job posting. This new AI conversation record guides the recruiter and the job seeker to conduct subsequent recruitment-related interactions.

[0095] Regarding the embodiments provided in this application Figure 8 The detailed implementation methods and beneficial effects of each step in the device shown have been described in detail in the foregoing embodiments, and will not be elaborated here.

[0096] Furthermore, such as Figure 8 As shown, the electronic device also includes other components such as a communication component 86, a display 87, a power supply component 88, and an audio component 89. Figure 8 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 8 The components shown. Additionally... Figure 8 The components within the dashed box are optional, not mandatory, and their specific requirements depend on the product form of the electronic device. The electronic device in this embodiment can be a terminal device such as a desktop computer, laptop computer, smartphone, or IoT device, or a server-side device such as a conventional server, cloud server, or server array. If the electronic device in this embodiment is a terminal device such as a desktop computer, laptop computer, or smartphone, it may include... Figure 8 The components within the dashed box; if the electronic device in this embodiment is implemented as a conventional server, cloud server, or server array, it may be omitted. Figure 8 The component within the dashed box.

[0097] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed, can perform the steps that can be executed by the recruitment interaction service device in the above-described method embodiments.

[0098] The aforementioned 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 storage, flash memory, magnetic disk, or optical disk.

[0099] The aforementioned communication components are configured to facilitate wired or wireless communication between the device containing the communication components and other devices. The device containing the communication components can access wireless networks based on communication standards, such as WiFi, 2G, 3G, 4G / LTE, 5G, or combinations thereof. In one exemplary embodiment, the communication components receive broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication components also include a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wide Band (UWB), Bluetooth (BT), and other technologies.

[0100] The aforementioned display 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 can be implemented as a touchscreen to receive input signals from the user. The Touch Panel includes one or more touch sensors to sense touches, swipes, and gestures on the Touch Panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation.

[0101] The aforementioned power supply components provide power to various components within the device in which they reside. These power supply components may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device in which they reside.

[0102] The aforementioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC) configured to receive external audio signals when the device containing the audio component is in an operating mode, such as call mode, recording mode, or voice recognition mode. The received audio signals can be further stored in memory or transmitted via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0103] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, compact disc read-only memory (CD-ROM), optical storage, etc.) containing computer-usable program code.

[0104] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interfaces, network interfaces, and memory.

[0108] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0109] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. 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 random access 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 technologies, CD-ROM, Digital Video Disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0111] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An AI-based recruitment interaction service method, characterized in that, An AI interaction service module is applied to recruiters, the module providing recruitment interaction services between recruiters and job seekers, the method comprising: If an interaction request initiated by a job seeker for a target job posting is detected, and the recruiter does not respond to the interaction request within a set time, the recruiter is simulated to output an AI inquiry card to the job seeker in the instant messaging chat interface with the job seeker. The AI ​​inquiry card is used to ask the job seeker whether they are willing to learn about the target job posting. Based on the confirmation information from the job seeker regarding the AI ​​inquiry card, the job description information corresponding to the target job position is output to the job seeker in the instant messaging chat interface; If historical AI conversation records corresponding to the job seeker and the target job position are obtained, multiple question-answer pairs are extracted from the historical AI conversation records, and a confirmation question is generated based on the multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid. The confirmation question is then output to the job seeker in the instant messaging chat interface. The multiple question-answer pairs consist of multiple reference questions corresponding to the target job position and the job seeker's responses to the multiple reference questions. The multiple reference questions are used to reflect the matching situation between the job seeker and the target job position. The historical AI conversation records are determined from the AI ​​conversation records of different recruiters corresponding to the target job position. Based on the job seeker's response to the confirmation question, a new AI conversation record is generated corresponding to the job seeker and the target job position. This new AI conversation record guides the recruiter and the job seeker to conduct subsequent recruitment-related interactions. Different recruiters may have different reference questions for the target job position.

2. The method according to claim 1, characterized in that, The step of generating a confirmation question based on the multiple question-answer pairs to inquire whether the multiple question-answer pairs are valid includes: Multiple structured information items are generated based on the multiple question-answer pairs, and each structured information item includes the question and answer information of the corresponding question-answer pair; The multiple structured information items are spliced ​​together; The confirmation question is used to generate a spliced ​​result containing the multiple structured information.

3. The method according to claim 1, characterized in that, The step of generating a new AI conversation record between the job seeker and the target job posting based on the job seeker's response to the confirmation question includes: If the response information indicates that all of the multiple question-answer pairs are valid, then the new AI session record is determined to be the same as the historical AI session record; If the reply information indicates that at least one of the multiple question-answer pairs is invalid, then at least one reference question corresponding to the at least one question-answer pair is output in the instant messaging chat interface to obtain the job seeker's new reply information to the at least one reference question, so as to generate the new AI conversation record.

4. The method according to claim 3, characterized in that, The step of outputting at least one reference question corresponding to at least one question-answer pair in the instant messaging chat interface, and obtaining the job seeker's new response information to the at least one reference question, includes: The instant messaging chat interface displays a question card corresponding to the target reference question. The question card includes the target reference question and multiple candidate answer controls. The target reference question is any one of the at least one reference question. In response to the job seeker's selection of the target candidate answer control, the target candidate answer control is selected, and the text content corresponding to the target candidate answer control is displayed as the reply text corresponding to the target reference question in the instant messaging chat interface.

5. The method according to any one of claims 1 to 4, characterized in that, The process of guiding the recruiter and job seeker to conduct subsequent recruitment-related interactions based on the new AI session record includes: Based on the job seeker's response to the reference questions in the new AI conversation record, the matching degree between the job seeker and the recruiter is determined; If the matching degree meets a preset threshold, an interaction channel is established for the job seeker and the recruiter so that the job seeker and the recruiter can interact based on the interaction channel.

6. The method according to claim 5, characterized in that, The establishment of an interaction channel between the job seeker and the recruiter includes: Determine the job seeker's job intention for the target recruitment position; Determine the target channel mode corresponding to the interaction channel based on the job seeker's intention; An interactive channel is established for the job seeker and the recruiter using the target channel mode.

7. The method according to claim 6, characterized in that, Determining the job seeker's job intention for the target recruitment position includes: The job seeker's job intention for the target recruitment position is determined based on at least one of the following: the number of reference questions answered by the job seeker in the new AI conversation record; the job seeker's delay in answering the reference questions; or the keywords in the dialogue information output by the job seeker in the instant messaging chat interface; wherein, the dialogue information includes response information to the reference questions, and the keywords refer to keywords used to reflect job intention.

8. The method according to claim 6, characterized in that, The establishment of an interaction channel for the job seeker and the recruiter using the target channel mode includes: If the target channel mode is a telephone call mode, then obtain the encrypted phone number of the recruiter or the job seeker; The recruiter's encrypted phone number is filled into a preset AI-guided outbound call script template to obtain AI-guided outbound call script information; The AI-guided outbound call script information is sent to the job seeker or the recruiter to guide them to make a phone call to the other party.

9. An electronic device, characterized in that, include: Memory and processor; The memory is used to store a computer program; the processor, coupled to the memory, is used to execute the computer program to implement the steps of the AI-based recruitment interaction service method according to any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it causes the processor to perform the steps in the AI-based recruitment interaction service method according to any one of claims 1-8.

Images