Artificial intelligence interview method, computing device, readable storage medium and computer program product

Abstract

The embodiment of the invention provides an artificial intelligence interview method, computing equipment, a readable storage medium and a computer program product. The artificial intelligence interview method comprises the following steps: acquiring an interview request sent by a client; determining a question list corresponding to the target position; judging whether the target user meets a question generation condition or not; under the condition that the target user meets the question generation condition, generating target question data from a question list by utilizing the target dialogue model and combining at least one round of historical dialogue data; judging whether the target problem data meets a corresponding constraint condition or not; under the condition that the target problem data meets the corresponding constraint condition, sending the target problem data to the client; and obtaining response data fed back by the client. According to the technical scheme provided by the embodiment of the invention, the processing pressure of the target dialogue model can be relieved, the training cost of the target dialogue model is reduced, and the performance of the target dialogue model on a specific task is improved.

Description

Technical Field

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

[0002] In today's digital age, artificial intelligence technology is increasingly widely used in the recruitment field. In particular, the AI (Artificial Intelligence) interview function has brought great convenience to both enterprises and job seekers.

[0003] AI interviews usually need to be implemented using a dialogue model. The dialogue model can ask questions to job seekers and, after obtaining the response data of the job seekers, continue to ask questions to the job seekers based on the response data to complete the interview through dialogue.

[0004] The inventors found during the process of implementing the concept of the present application that in actual application scenarios, more complex tasks need to be undertaken. These complex and diverse tasks make the amount of data that the dialogue model needs to process huge and the types of data complex. It not only needs to understand the semantics and grammar of natural language, but also needs to grasp the context and intention of the dialogue. Each additional function means that the model has to process more logical branches and judgment conditions. During the training process, a large amount of labeled data is required to support the learning of different functional modules. In order to optimize the model performance, it is also necessary to continuously adjust the hyperparameters and conduct multiple rounds of training and verification, which undoubtedly consumes a large amount of computing resources and time costs, resulting in relatively complex tasks for the dialogue model to process, high training pressure, and high training costs. Summary of the Invention

[0005] Embodiments of the present application provide an artificial intelligence interview method, a computing device, a readable storage medium, and a computer program product.

[0006] In a first aspect, an artificial intelligence interview method is provided in embodiments of the present application, which is applied to a server, and the method includes:

[0007] Obtain an interview request sent by a client; the interview request is generated by the client in response to an interview operation triggered by a target user for a target position;

[0008] Determine a question list corresponding to the target position; the question list includes a plurality of question data;

[0009] Combine at least one round of historical dialogue data of the target user to determine whether the target user meets the question generation condition;

[0010] When the target user meets the question generation condition, use the target dialogue model to generate target question data from the question list in combination with at least one round of historical dialogue data; the target dialogue model is trained based on at least one round of sample dialogue data;

[0011] Determine whether the target question data meets the corresponding constraint conditions;

[0012] When the target question data meets the corresponding constraint conditions, send the target question data to the client;

[0013] Obtain the response data fed back by the client, and return to the step of combining at least one round of historical dialogue data of the target user to determine whether the target user meets the question generation condition and continue to execute.

[0014] In a second aspect, an artificial intelligence interview device is provided in an embodiment of the present application, which is applied to a server, and the device includes:

[0015] A request acquisition module, configured to acquire an interview request sent by a client; the interview request is generated by the client in response to an interview operation triggered by a target user's target position;

[0016] A question list determination module, configured to determine a question list corresponding to the target position; the question list includes a plurality of question data;

[0017] A first judgment module, configured to determine whether the target user meets the question generation condition in combination with at least one round of historical dialogue data of the target user;

[0018] A question generation module, configured to use the target dialogue model to generate target question data from the question list in combination with at least one round of historical dialogue data when the target user meets the question generation condition; the target dialogue model is trained based on at least one round of sample dialogue data;

[0019] A second judgment module, configured to determine whether the target question data meets the corresponding constraint conditions;

[0020] A question sending module, configured to send the target question data to the client when the target question data meets the corresponding constraint conditions;

[0021] A response acquisition module, configured to acquire the response data fed back by the client, and return to the step of combining at least one round of historical dialogue data of the target user to determine whether the target user meets the question generation condition and continue to execute.

[0022] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component;

[0023] The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the artificial intelligence interview method provided by the embodiments of the present application.

[0024] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processing component, the artificial intelligence interview method provided by the embodiments of the present application is implemented.

[0025] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program / instructions. When the computer program / instructions are executed by the processing component, the artificial intelligence interview method provided by the embodiments of the present application is implemented.

[0026] In the embodiments of the present application, during the interview process, by combining at least one round of historical conversation data of the target user, it is determined whether the target user meets the question generation condition; when the target user meets the question generation condition, using the target dialogue model, combining at least one round of historical conversation data to generate target question data from the question list, and determining whether the target question data meets the corresponding constraint conditions; when the target question data meets the corresponding constraint conditions, sending the target question data to the client; obtaining the response data fed back by the client, and returning to the step of determining whether the target user meets the question generation condition by combining at least one round of historical conversation data of the target user and continuing to execute. The operations of determining whether the target user meets the question generation condition and determining whether the target question data meets the corresponding constraint conditions are split out from the target dialogue model. Therefore, the target dialogue model does not need to process these complex tasks, which can reduce the processing pressure of the target dialogue model, reduce the training cost of the target dialogue model, and improve its performance in specific tasks.

[0027] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0029] Figure 1 Shows a system architecture diagram to which a technical solution of an embodiment of the present application can be applied;

[0030] Figure 2Shows the flowchart of an artificial intelligence interview method provided by an embodiment of the present application;

[0031] Figure 3 Shows the schematic diagram of the artificial intelligence interview method provided by the embodiment of the present application;

[0032] Figure 4 Shows the flowchart of a training method for a dialogue model provided by an embodiment of the present application;

[0033] Figure 5 Shows the block diagram of an artificial intelligence interview device provided by an embodiment of the present application;

[0034] Figure 6 Shows the block diagram of a computing device provided by an embodiment of the present application. Detailed implementation manners

[0035] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0036] In some processes described in the specification, claims and above-mentioned drawings of the present application, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial 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 such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent the sequence, nor do they limit that "first" and "second" are of different types.

[0037] 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 for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. And the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0038] It should be noted that the technical solution of the embodiment of the present application is applicable to a network virtual environment. The users described generally refer to "virtual users". Real users can register user accounts on the server through the registration method to obtain user identities in the network environment. In the embodiment of the present application, the same user account can be logged in to the server through different types of clients, so that the server can identify the same user. Of course, different user accounts can also be logged in to the server through different types of clients. The server stores different user account binding relationships, so that different user accounts with binding relationships can be considered as the same user.

[0039] In today's digital age, the application of artificial intelligence technology in the recruitment field is becoming increasingly widespread, especially the AI (Artificial Intelligence) interview function, which brings great convenience to both enterprises and job seekers.

[0040] AI interviews usually need to be implemented using a dialogue model. The dialogue model can ask questions to job seekers and, after obtaining the response data of the job seekers, continue to ask questions to the job seekers based on the response data to complete the interview through dialogue.

[0041] The inventor found in the process of implementing the concept of the present application that in actual application scenarios, more complex tasks need to be undertaken. These complex and diverse tasks make the amount of data that the dialogue model needs to process huge and the types complicated. It not only needs to understand the semantics and grammar of natural language, but also needs to grasp the context and intention of the dialogue. Every time a function is added, it means that the model has to process more logical branches and judgment conditions. During the training process, a large amount of labeled data is required to support the learning of different functional modules. In order to optimize the model performance, it is also necessary to continuously adjust the hyperparameters and conduct multiple rounds of training and verification, which undoubtedly consumes a large amount of computing resources and time costs, resulting in relatively complex tasks for the dialogue model to process, high training pressure, and high training costs.

[0042] In order to solve the technical problems existing in the related art, in the embodiments of the present application, during the interview process, by combining at least one round of historical conversation data of the target user, it is determined whether the target user meets the question generation condition; when the target user meets the question generation condition, using the target dialogue model, combining at least one round of historical conversation data to generate target question data from the question list, and determining whether the target question data meets the corresponding constraint conditions; when the target question data meets the corresponding constraint conditions, sending the target question data to the client; obtaining the response data fed back by the client, and returning to the step of determining whether the target user meets the question generation condition by combining at least one round of historical conversation data of the target user and continuing to execute. The operations of determining whether the target user meets the question generation condition and determining whether the target question data meets the corresponding constraint conditions are split out from the target dialogue model. Thus, the target dialogue model does not need to process these complex tasks, which can reduce the processing pressure on the target dialogue model, reduce the training cost of the target dialogue model, and improve its performance in specific tasks.

[0043] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0044] Figure 1 A system architecture diagram to which a technical solution of an embodiment of the present application can be applied is shown. The system architecture may include a client 101 and a server 102.

[0045] Among them, a connection is established between the client 101 and the server 102 through a network. The network provides a medium for the communication link between the client 101 and the server 102. The network may include various connection types, such as wired, wireless communication links or fiber optic cables, etc. Optionally, the server can communicate with the client through a mobile network. Optionally, the client can also establish a communication connection with the server by means of Bluetooth, WiFi, infrared, etc.

[0046] The client 101 can interact with the server 102 through the network to receive or send messages, etc.

[0047] Among them, the client 101 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5) application, or 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 device or certain apps in the device to run, etc. The electronic device can, for example, have a display screen and support information browsing, etc., such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For ease of understanding, Figure 1 the client is mainly represented by the device image in Figure 1 . Various other types of applications can usually be configured in the electronic device, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. The electronic device can refer to a device used by a user and having functions such as computing, Internet access, and communication required by the user. For example, it can be a mobile phone, a tablet computer, a personal computer, a wearable device, etc. The electronic device usually can include at least one processing component and at least one storage component. The electronic device may also include basic configurations such as a network card chip, an IO bus, audio-video components, etc., which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as a keyboard, a mouse, an input pen, a printer, etc., which are not limited in this application.

[0048] The server 102 can include servers that provide various services.

[0049] It should be noted that the server 102 can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), as well as big data and artificial intelligence platforms, or an intelligent cloud computing server or an intelligent cloud host with artificial intelligence technology.

[0050] It should be noted that the artificial intelligence interview method provided in the embodiments of this application is generally executed by the server 102, and the corresponding artificial intelligence interview device is generally set in the server 102.

[0051] It should be understood that Figure 1 the number of user ends and server ends in Figure 1 is only illustrative. According to the implementation requirements, any number of user ends and server ends can be provided.

[0052] The implementation details of the technical solution of the embodiment of the present application will be elaborated in detail below.

[0053] Figure 2 The flowchart of an artificial intelligence interview method provided by an embodiment of the present application is shown. This method can be applied to the server side, such as Figure 2 As shown, the method may specifically include the following steps:

[0054] 201: Obtain an interview request sent by the client; the interview request is generated by the client in response to an interview operation triggered by a target user for a target position;

[0055] In the embodiment of the present application, the server side can detect the interview operation triggered by the client. When the target user triggers an interview operation for a certain target position on the display interface provided by the client, the client can generate an interview request. The interview operation may be, for example, that the target user clicks the "Start Interview" button, or selects to apply for an interview on a specific recruitment page, etc.

[0056] Then, the client can send this interview request to the server side. After the server side obtains this request, it can start the interview process. For example, on an online recruitment platform, after a user browses a certain desired waiter position and clicks the "Apply for Interview" button, the client will generate a corresponding interview request and send it to the server.

[0057] 202: Determine the question list corresponding to the target position; the question list includes multiple question data;

[0058] After the server side obtains the interview request, it can obtain a series of questions related to the target position. The server side can find the question list corresponding to the target position according to the internal database or configuration information. This question list contains multiple question data, and these question data can be prepared in advance according to the characteristics, requirements, and common examination points of the target position. For example, for a software engineer position, the question list may contain questions in dimensions such as programming language knowledge, project experience, and algorithm understanding.

[0059] 203: Combine at least one round of historical conversation data of the target user to determine whether the target user meets the question generation condition;

[0060] 204: When the target user meets the question generation condition, use the target dialogue model to generate target question data from the question list in combination with at least one round of historical conversation data; the target dialogue model is trained based on at least one round of sample dialogue data;

[0061] If the target user meets the problem generation conditions, use the target dialogue model, combined with at least one round of historical dialogue data, to generate target problem data from the problem list.

[0062] Among them, at least one round of historical dialogue data contains previous interview interaction information, and the previous interview interaction information can be used to help the target dialogue model determine whether new problem data needs to be generated. If new problem data needs to be generated, that is, the target dialogue model can be used to generate target problem data from the problem list in combination with at least one round of historical dialogue data.

[0063] The target dialogue model can be obtained by migrating the knowledge of the second dialogue model to the first dialogue model; the first dialogue model is used as the student model, and the second dialogue model is used as the teacher model; the student model is used to adjust based on the difference information between the first probability distribution and the second probability distribution of different element data generated by reasoning; the first probability distribution is generated by the student model based on the second sample data; the second probability distribution is generated by the teacher model based on the second sample data; the second sample input model is obtained by splicing the first sample data with the target element data; the target element data is generated by the student model based on the first sample data.

[0064] The training process of the target dialogue model will be specifically described in the following embodiments.

[0065] The target dialogue model can generate target problem data from the problem list according to at least one round of historical dialogue data. These historical dialogue data record the content that has been communicated during the previous interview process. The target dialogue can screen and generate the most suitable target problem data for the current interview stage from the problem list by analyzing these historical dialogue data and the problem list.

[0066] Among them, the problem list contains multiple pre-set problem data, and these problems can be arranged in a certain logical order. The target dialogue model can be trained to have the ability to generate target problem data from the problem list following the predefined problem order.

[0067] The target dialogue model can combine its own training results and determine which question should be output as the target problem data in sequence from the problem list according to the input historical dialogue data.

[0068] 205: Determine whether the target problem data meets the corresponding constraint conditions;

[0069] 206: When the target problem data meets the corresponding constraint conditions, send the target problem data to the client;

[0070] In some embodiments, determining whether the target problem data meets the corresponding constraint conditions can be specifically implemented as:

[0071] Determine whether the pre - information of the target question data is included in at least one round of historical dialogue data;

[0072] If so, determine that the constraint conditions are met; if not, determine that the constraint conditions are not met.

[0073] Among them, in the question list, at least one question data can be configured with constraint conditions. A question data configured with constraint conditions means that the raising of this question data needs to be based on certain pre - information. When the pre - information appears in at least one round of historical dialogue data, it can be judged that the target question data meets the constraint conditions; otherwise, it does not meet the constraint conditions. For example, in an interview scenario, for the question data "Please elaborate on the specific problems and solutions you encountered when using Python for data analysis", its pre - information can be that in the previous historical dialogue, the target user mentioned that they have experience in using Python.

[0074] After selecting the target question data configured with constraint conditions, the target dialogue model can check at least one round of historical dialogue data to see if there is pre - information related to the target question data. If it exists, it indicates that the target question data meets the constraint conditions because it is a natural extension based on the previous dialogue content and conforms to the logical coherence of the dialogue. For example, if the applicant mentioned in the previous dialogue "I often use Python to process data at work", then the above question about Python data analysis has a reasonable pre - condition and meets the constraint conditions.

[0075] When the target question data meets the constraint conditions, the server can send it to the client. This can ensure that the questions received by the client are relevant and reasonable to the previous dialogue, which helps the smooth progress of the dialogue. If the target question data does not meet the constraint conditions, it may return to perform the operation of generating the target question data from the question list by using the target dialogue model combined with at least one round of historical dialogue data.

[0076] In actual application scenarios, different groups of people, such as those with differences in age, occupation, educational background, etc., and people with different experiences, need to be asked different questions in the dialogue scenario. For example, in a recruitment interview, the focus of attention of the interviewer for fresh graduates and job seekers with many years of work experience is different, and the questions asked are naturally different. Under different recruitment positions, the questions to be asked are also different.

[0077] By defining pre-constraints for the question data, it's like setting a "switch" for the question. Only when specific conditions are met will the corresponding question be asked. When new categories need to be expanded, such as adding new job categories in recruitment, one only needs to define all the questions to be asked for that category and clarify under what conditions different questions are to be asked. Based on these settings, the target dialogue model can automatically ask appropriate questions according to the actual situation in the new category dialogue scenario, thus achieving the ability to automate the support for new category conversations without the need to massively modify the overall architecture or logic of the dialogue system, reducing development and maintenance costs and improving the flexibility and scalability of the interview.

[0078] 207: Obtain the response data fed back by the client, and return and combine at least one round of historical conversation data of the target user to determine whether the target user meets the question generation condition and continue to execute the steps.

[0079] The client can collect the response data given by the target user for the target question and feed it back to the server. After the server obtains this response data, it will return to step 204 again, that is, use the target dialogue model to combine the new at least one round of historical conversation data (the historical conversation data at this time includes the user's just-given response) to generate new target question data from the question list. This process will loop continuously until the interview ends, and in this way, a dynamic interview process that progresses based on the user's answers is achieved.

[0080] In the embodiments of the present application, by adopting the technical solution of, during the interview process, combining at least one round of historical conversation data of the target user to determine whether the target user meets the question generation condition; in the case where the target user meets the question generation condition, using the target dialogue model to combine at least one round of historical conversation data to generate target question data from the question list and determine whether the target question data meets the corresponding constraints; in the case where the target question data meets the corresponding constraints, sending the target question data to the client; obtaining the response data fed back by the client, and returning and combining at least one round of historical conversation data of the target user to determine whether the target user meets the question generation condition and continue to execute the steps, the operations of determining whether the target user meets the question generation condition and determining whether the target question data meets the corresponding constraints are split out from the target dialogue model. Thus, the target dialogue model does not need to handle these complex tasks, which can relieve the processing pressure of the target dialogue model, reduce the training cost of the target dialogue model, and improve its performance in specific tasks.

[0081] In some embodiments, combining at least one round of historical conversation data to determine whether the target user meets the question generation condition can be specifically implemented as:

[0082] Determine the previous round of question data and the previous round of response data in the previous round of conversation data;

[0083] Determine whether the previous round of response data matches the previous round of question data; if so, determine that the target user meets the question generation condition, otherwise the question generation condition is not met.

[0084] In a possible implementation, a first recognition model can be used to determine whether the previous round of response data matches the previous round of question data. The first recognition model can be a trained large model. A large model refers to a machine learning model with a large number of parameters and a complex structure, which can process massive amounts of data and complete various complex tasks, such as natural language processing, computer vision, speech recognition, etc., and is an AI (Artificial Intelligence) model. Among them, the large model can be implemented, for example, using a large language model (LLM) or a multimodal large model (MLM), etc. For example, it can use GPT-3 (Generative Pre-Trained Transformer-3, the third generation of generative pre-trained model), GPT-4 (Generative Pre-Trained Transformer-4, the fourth generation of generative pre-trained model), BERT (Bidirectional Encoder Representation from Transformers, a bidirectional encoder model based on Transformers), Turing NLG (Turing Natural language Generation), and so on. This application does not limit this. Such large models can perform well in various natural language processing tasks.

[0085] The first recognition model can be trained based on the sample dialogue data and the matching labels between the sample question data and the sample response data in the sample dialogue data. For example: for the sample dialogue data, it may contain multiple sets of sample question data and sample response data, as well as corresponding matching labels (indicating whether the response matches the question), such as "Question: Please list the programming languages you master. Response: I master Java and Python. Matching label: Yes". By training on a large amount of such sample data, the first recognition model learns how to determine whether a response reasonably answers the corresponding question.

[0086] When the previous round of question data and response data are received, they can be input into the first recognition model. The first recognition model can, based on the knowledge it has learned through training, evaluate whether the previous round of response data is a reasonable answer to the previous round of question data.

[0087] In the case where the first recognition model determines that the previous round of response data matches the previous round of question data, it means that more questions need to be asked to further understand the user's situation, or enter the next interview session. Thus, it can be indicated that the target user meets the question generation condition.

[0088] In the case where the first recognition model determines that the previous round of response data does not match the previous round of question data, it may mean that the user's answer is inaccurate or the question is not understood, and the current question needs to be asked again. At this time, it can be determined that the target user does not meet the question generation condition.

[0089] In some embodiments, the method further includes:

[0090] If the target user does not meet the question generation condition, use the previous round of question data as the target question data.

[0091] In some embodiments, if the target user does not meet the question generation condition, using the previous round of question data as the target question data can be specifically implemented as:

[0092] If the target user does not meet the question generation condition, determine whether the retry count of the previous round of question data meets the limit condition;

[0093] If not, use the previous round of question data as the target question data and accumulate the retry count;

[0094] If so, use the target dialogue model, in combination with at least one round of historical dialogue data, to generate the target question data from the question list.

[0095] Among them, the retry count can refer to the number of times of repeatedly asking the same question data to the target user, and the limit condition can be a preset number threshold for controlling the upper limit of the number of times of asking the same question data. For example, in an interview scenario, the limit condition can be set to a maximum of 3 retries for each question. If it is the first or second time to ask a certain question to the target user, then it is necessary to determine whether the current retry count has reached 3 times. If it has not reached 3 times, the limit condition is not met, and the question can be asked again; if it has reached 3 times, the limit condition is met.

[0096] If it is determined that the retry count of the previous round of question data does not meet the limit condition, then use the previous round of question data as the target question data again and send it to the target user. In the case where the previous round of response data does not match the previous round of question data, it may be that the target user does not understand the question or answers incorrectly for a moment. By asking again, a more appropriate answer may be obtained.

[0097] At the same time, after sending the previous round of question data as the target question data, it is necessary to accumulate the retry count of this question.

[0098] When it is determined that the number of retries of the previous round of question data has met the limit condition, it indicates that after multiple inquiries about this question, the target user still has not given a suitable answer. At this time, in order not to get stuck in this question data and prevent the interview or conversation from proceeding, this question data can be temporarily skipped to ensure the smooth progress of the interview or conversation.

[0099] In some embodiments, if the target user does not meet the question generation condition, taking the previous round of question data as the target question data can be specifically implemented as:

[0100] If the target user does not meet the question generation condition, determine whether the previous round of response data is a question data;

[0101] If not, take the previous round of question data as the target question data;

[0102] If so, use the conversation model to generate response data corresponding to the question data and send the response data to the client.

[0103] In a possible implementation manner, a second recognition model can be used to determine whether the previous round of response data is a question data. The second recognition model can be a trained large model.

[0104] If the second recognition model determines that the previous round of response data is not a question data, it means that the user is answering the question, but the answer may not meet the requirements, resulting in the target user not meeting the question generation condition. In this case, the previous round of question data can be taken as the target question data.

[0105] When the second recognition model determines that the previous round of response data is a question data, it indicates that the target user has asked a question. At this time, the conversation model needs to be used to generate response data for this question data according to the position information of the target position.

[0106] In a possible implementation manner, the conversation model can be implemented as a target dialogue model.

[0107] In some embodiments, combining at least one round of historical conversation data to determine whether the target user meets the question generation condition can be specifically implemented as:

[0108] Determine the previous round of question data and the previous round of response data in the previous round of conversation data;

[0109] Determine whether the previous round of response data is a question data; if so, determine that the target user meets the question generation condition.

[0110] In some embodiments, the method further includes:

[0111] If the target user does not meet the question generation condition, take the previous round of question data as the target question data.

[0112] In some embodiments, if the historical conversation data meets the question generation condition, using the target conversation model, combining at least one round of historical conversation data to generate target question data from the question list can be specifically implemented as follows:

[0113] If the target user meets the question generation condition, use the conversation model to generate a response data corresponding to the question data, and send the response data to the client;

[0114] Use the target conversation model, combine the historical conversation data to generate target question data from the question list.

[0115] In some embodiments, using the target conversation model to combine at least one round of historical conversation data to generate target question data from the question list can be specifically implemented as follows:

[0116] Use the target conversation model to combine at least one round of historical conversation data to generate candidate question data from the unmarked question data in the question list, and determine whether there is response data corresponding to the candidate question data in at least one round of historical conversation data. If so, mark the candidate question data and regenerate the candidate question data. If not, use the candidate question data as the target question data and mark the target question data.

[0117] Among them, the unmarked question data means that these question data have not been used in the previous conversation process. The target conversation model can generate candidate question data from these unmarked question data according to the information provided by the historical conversation data.

[0118] If there is already a relevant answer to a certain question data, then it may not be necessary to ask this question data again. Therefore, when generating candidate question data, search in at least one round of historical conversation data to check whether there is already response data for this candidate question.

[0119] If the response data corresponding to the candidate question data is found in the historical conversation data, then mark the candidate question data. By marking this question data, it can be indicated that this question already has relevant information in the current conversation and cannot be used as the current valid question. Then, candidate question data can be regenerated, and a suitable question can be found again from the unmarked questions in the question list, repeating the above judgment process.

[0120] If the response data corresponding to the candidate question data is not found in the historical conversation data, this means that this question has not been involved in the current conversation and is a new question that can be asked. At this time, the candidate question data can be used as the target question data and the target question data is marked. Marking the target question data is to record that this question has been used and will not be misselected again in subsequent conversations.

[0121] In some embodiments, using the target dialogue model in combination with at least one round of historical dialogue data to generate target question data from the question list can be specifically implemented as follows:

[0122] Using the target dialogue model in combination with at least one round of historical dialogue data, and generating target question data from the question list according to at least one question output requirement;

[0123] The at least one question output requirement includes one or more of the following options:

[0124] The response data in the previous round of historical dialogue data matches the question data;

[0125] The retry count of the question data in the previous round of historical dialogue data exceeds the limit condition;

[0126] There is no response data in at least one round of historical dialogue data that matches the target question data;

[0127] And,

[0128] The target question data meets its corresponding constraint conditions.

[0129] As mentioned in the above embodiments, in the embodiments of the present application, the first recognition model, the second recognition model, and the third recognition model can be used to identify whether the response data matches the question data, whether the retry count exceeds the limit condition, and whether the constraint conditions are met. Thus, these complex tasks that the target dialogue model needs to handle can be split out, thereby reducing the processing pressure on the target dialogue model and lowering the training cost of the target dialogue model. Moreover, for each recognition model, more targeted data can be used for training, enabling different recognition models to be more focused on their respective tasks. Through specialized training and optimization, their performance in specific tasks can be improved.

[0130] In some embodiments, after obtaining the response data fed back by the client, the method may further include:

[0131] Determine whether there is unselected question data in the question list;

[0132] If so, continue to execute the step of selecting question data from the question list; if not, generate an interview end prompt message.

[0133] If there is no unselected question data in the question list after checking the question list, that is, all questions have been asked, this indicates that the interview has covered all the pre-set aspects of the examination, and the interview can end. At this time, the server can generate an interview end prompt message. This prompt message will be sent to the client to inform the applicant that the interview has ended. For example, the client may display "This interview has ended. Thank you for your participation!"

[0134] In some embodiments, the method may further include:

[0135] Receiving a resume submission operation from the client for a target position;

[0136] In response to the resume submission operation, sending an interview invitation notice to the client;

[0137] Obtaining an interview request sent by the client includes:

[0138] Obtaining an interview request sent by the client by triggering the interview invitation notice.

[0139] Figure 3 The figure shows a schematic diagram of the artificial intelligence interview method provided by an embodiment of the present application.

[0140] In Figure 3 301 may represent the server, and 302 may represent the client. The target dialogue model 3011 may be deployed in the server 301, and the first recognition model 3012, the second recognition model 3013, and the third recognition model 3014 may be deployed in the server 301.

[0141] After the server 301 receives the response data sent by the client 302 for the target question data, the at least one-round historical dialogue data can be respectively input into the first recognition model 3012, the second recognition model 3013, and the third recognition model 3014, so that the first recognition model 3012 can identify whether the response data of the target user matches the target question data, and whether there is a question in the response data of the target user; the second recognition model 3013 can be used to identify the target question data of this round of question and answer, and the retry times of the target question data; the third recognition model 3014 can be used to identify whether the target question data meets the constraint conditions.

[0142] The first recognition model 3012, the second recognition model 3013, and the third recognition model 3014 can respectively output recognition results, and then the recognition results can be input into the target dialogue model, so that the target dialogue model can generate the question data to be asked in the next round of dialogue according to the recognition results. The question data to be asked in the next round of dialogue can be to repeat the target question data, or to re-select question data from the question list.

[0143] In an embodiment of the present application, in order to improve the interaction experience, after determining the target question data, the server can convert the target question data into voice data, so that the digital human can use the generated voice data to orally broadcast the target question data. Oral broadcasting by the digital human can create an atmosphere closer to real face-to-face communication for the target user.

[0144] Figure 4 The flowchart of a method for training a dialogue model provided by an embodiment of the present application is shown, as Figure 4 shown, and the method may specifically include the following steps:

[0145] 401: Determine a first dialogue model and a second dialogue model, where the number of parameters of the second dialogue model is greater than that of the first dialogue model.

[0146] 402: Use the first dialogue model as the student model and the second dialogue model as the teacher model.

[0147] Among them, the first dialogue model can be a model with relatively few parameters and more focused on specific dialogue tasks. In an embodiment of the present application, the specific dialogue task may include a dialogue task in an interview scenario.

[0148] The second dialogue model can have a large number of parameters. Thus, the second dialogue model can be a more complex and more powerful model, which can be trained on a wider dataset, have more abundant knowledge and stronger processing capabilities.

[0149] In an embodiment of the present application, the Knowledge Distillation technology can be used to train the first dialogue model. In the framework of knowledge distillation, the first dialogue model can be regarded as the student model, and the student model can learn knowledge and skills from another more powerful model, that is, the teacher model. In an embodiment of the present application, the second dialogue model with a large number of parameters can be used as the teacher model.

[0150] Through knowledge distillation, the teacher model can use its rich parameters and extensive training knowledge to provide guidance for the student model, thereby improving the performance of the student model on specific tasks while maintaining the advantage of a relatively simple structure itself, such as faster inference speed and lower resource consumption.

[0151] 403: Obtain first sample data; the first sample data includes at least one round of sample dialogue data.

[0152] Among them, in the first sample data, at least one round of sample dialogue data can be included, and the at least one round of sample dialogue data can be arranged in the dialogue order.

[0153] In a possible implementation, at least one round of sample conversation data can be obtained by collecting the conversation data generated during at least one historical interview process. The sample conversation data can record the conversation situation between the interviewer and the job-seeking user in a real interview scenario.

[0154] In an actual conversation scenario, the order of the conversation affects the understanding of semantics and the coherence of logic. For example, in an interview scenario, the interviewer may further ask relevant questions based on the previous answers of the job-seeking user, or adjust the direction and depth of the questions according to the progress of the interview. This sequentiality enables the first conversation model to learn the natural flow of the conversation and the relevance of the context.

[0155] 404: Input the first sample data into the student model to enable the student model to perform an inference operation based on the first sample data, calculate the first probability distribution of different element data, and select the target element data according to the first probability distribution; the element data is the smallest data unit.

[0156] After obtaining the first sample data, the first sample data can be input into the student model.

[0157] After receiving the first sample data, the student model can perform an inference operation. In the embodiments of the present application, the inference operation may refer to the process in which the student model processes the first sample data based on its internal neural network structure and training parameters to calculate the first probability distribution of different element data.

[0158] In the embodiments of the present application, the element data may be the smallest data unit. For example, in a natural language processing task, the element data may be a single character, word, morpheme, or other smallest semantic unit. The student model can calculate the first probability distribution of these element data.

[0159] Among them, the first probability distribution can represent the possibility of each element data appearing under the current input. For example, for a conversation generation task, if the element data is a word, the student model can calculate the probability distribution of the next possible word according to the first sample data. For example, assuming the input of the student model is "Please describe your experience in the project", the student model may calculate the probability distribution of a series of words, such as the probability of "experience" being 0.3, the probability of "role" being 0.25, the probability of "contribution" being 0.2, etc. This probability distribution is obtained based on the language patterns and semantic relationships learned by the student model during the training process, and reflects what the student model thinks the next element data may be under the current input.

[0160] Based on the calculated first probability distribution, the student model can select the target element data. When the student model selects the target element data from different element data, it can adopt selection strategies such as the greedy strategy, random sampling strategy, etc. In the greedy strategy, the student model can select the element data with the highest probability as the target element data. For example, in the above example, if the greedy strategy is adopted, the student model can select "experience" as the target element data because it has the highest probability of 0.3; in the random sampling strategy, the student model can perform random sampling according to the probability distribution, which can increase the diversity of the generated content.

[0161] 405: Concatenate the target element data with the first sample data to obtain the second sample data.

[0162] By concatenating the target element data with the first sample data, a continuous conversation process can be simulated. In natural language processing tasks, especially in scenarios involving dialogue generation, the model needs to continuously update its input based on the previous content in order to continue generating subsequent content.

[0163] For example, the process of concatenating the target element data with the first sample data to obtain the second sample data can be as follows:

[0164] Suppose the first sample data is a dialogue sequence. For example, in an interview scenario, the first sample data may be "Interviewer: Please describe your experience in the project. Job applicant: I have participated in a software project,". According to the previous reasoning operation, the target element data that the student model can select from the calculated first probability distribution may be "development". Through the concatenation operation, the target element data is added to the end of the first sample data to obtain the second sample data. At this time, the second sample data becomes "Interviewer: Please describe your experience in the project. Applicant: I have participated in a software project, development".

[0165] By adding the newly generated element data to the original sample data to form a new input (i.e., the second sample data), updated information can be provided to the model, enabling it to continue learning and reasoning based on the updated input.

[0166] After generating the second sample data, the second sample data can be re - input into the student model and the teacher model, allowing the model to further calculate the probability distribution based on the updated information and perform new reasoning operations. This helps the model learn the coherence and logic of the dialogue or text, enabling the model to gradually improve its performance in the continuous iteration process, better master the structure and semantics of the language, and provide a basis for transferring the knowledge of the teacher model to the student model and generating high - quality dialogue or text.

[0167] 406: Input the second sample data into the student model and the teacher model respectively, so that the student model performs inference operations based on the second sample data to calculate the first probability distribution of different element data, and the teacher model performs inference operations based on the second sample data to calculate the second probability distribution of different element data.

[0168] By inputting the second sample data into the student model and the teacher model respectively, the student model and the teacher model can process and analyze the input second sample data according to their respective parameters and structures, so as to calculate the probability distribution of different element data.

[0169] 407: Determine the difference information between the first probability distribution and the second probability distribution corresponding to different element data.

[0170] After inputting the second sample data, the student model and the teacher model may calculate the probability distribution of the next word respectively. By comparing these two probability distributions, the differences in the predictions of the student model in some cases and the teacher model can be found, and then the parameters of the student model can be adjusted to make it more accurate in predicting the next word. In this way, the student model can learn more accurate language patterns and knowledge from the teacher model, improving the quality and accuracy of the generated text.

[0171] 408: Adjust the student model based on the difference information to transfer the knowledge of the second dialogue model to the first dialogue model, obtaining a target dialogue model; the target dialogue model is used to generate target question data from the question list corresponding to the target position in combination with at least one round of historical dialogue data.

[0172] After determining the difference information, the training parameters of the student model can be adjusted with the goal of making the first probability distribution output by the student model closer to the second probability distribution output by the teacher model. Thus, the student model can continuously learn the performance of the teacher model when processing the same input, learn better knowledge and experience from the teacher model, and thereby transfer the knowledge of the teacher model to the student model.

[0173] After multiple adjustments and optimizations, the finally obtained student model can be the target dialogue model. This target dialogue model combines the structure of the student model and some knowledge of the teacher model. When processing tasks such as interview conversations, it can utilize the knowledge advantages of the teacher model while maintaining the characteristics of the student model itself. For example, the target dialogue model may inherit the teacher model's capabilities in language patterns, semantic understanding, and logical reasoning, while also having certain advantages in resource utilization and computational efficiency like the student model, making it suitable for application in actual dialogue systems, such as intelligent interview systems, which can generate more appropriate and fluent target question data from the question list corresponding to the target position according to at least one round of historical dialogue data.

[0174] In some embodiments, the method may further include:

[0175] Obtaining pre-training data, where the pre-training data includes third sample data and sample question data corresponding to the third sample data; the third sample data includes at least one round of sample dialogue data; each round of sample dialogue data includes sample question data and sample response data corresponding to the question data;

[0176] Pre-training the first dialogue model and the second dialogue model respectively using the pre-training data.

[0177] By inputting the obtained pre-training data into the first dialogue model and the second dialogue model, the first dialogue model and the second dialogue model can learn the language pattern, semantic understanding, and dialogue logical relationship according to the sample question data and the sample response data corresponding to the question data in the pre-training data. For example, it will learn the common answer patterns corresponding to different questions and how to make reasonable responses according to the context. By continuously processing and learning the pre-training data, the first dialogue model and the second dialogue model can gradually adjust their own parameters to meet the requirements of this dialogue task, thereby enhancing their capabilities in dialogue-related tasks.

[0178] In the application embodiments, first, determine a first dialogue model and a second dialogue model with different numbers of parameters, use the first dialogue model as the student model, and the second dialogue model as the teacher model. Then, obtain first sample data including at least one round of sample dialogue data, input it into the student model for inference operations, calculate the first probability distribution of different element data and select target element data, splice the target element data with the first sample data to obtain second sample data. Then, input the second sample data into the student model and the teacher model respectively, calculate the first probability distribution and the second probability distribution of different element data respectively, and then determine the difference information between the first probability distribution and the second probability distribution of different element data. Finally, adjust the student model based on the difference information to transfer the knowledge of the second dialogue model to the first dialogue model to obtain the target dialogue model. By comparing the difference information between the outputs of the student model and the teacher model after the student model already has its own output and guiding the student model to adjust in a better direction according to the difference information, the training difficulty of the student model is reduced, and the performance of the target dialogue model generated by training is improved.

[0179] In some embodiments, pre-training the first dialogue model and the second dialogue model respectively using the pre-training data can be specifically implemented as:

[0180] For any one of the first dialogue model and the second dialogue model, use the third sample data as the input data of the model and the sample question data as the training label;

[0181] Train the model using the input data and training labels.

[0182] When either the first dialogue model or the second dialogue model receives the input third sample data, the third sample data can perform forward propagation in the neural network structure of the model. Thus, the model can perform operations such as feature extraction and semantic understanding on the input data according to its own parameters and structure, and finally generate an output. This output can include a prediction of the next possible dialogue content or a preliminary answer to a related question.

[0183] After the model generates an output, the output of the model can be compared with the training labels to calculate the difference between the output of the model and the training labels using a loss function. The loss function can, for example, include a cross-entropy loss function, etc. The loss function can be used to measure the distance between the probability distribution of the model output and the true labels. If the output of the model is significantly different from the training labels, the loss value will be high; otherwise, it will be low.

[0184] According to the loss value calculated using the loss function, the backpropagation algorithm can be used to calculate the gradient of the loss function with respect to the model parameters. The gradient represents the direction and degree of the impact of parameter changes on the loss value. Then, through an optimization algorithm (such as stochastic gradient descent, Adam, etc.), the model parameters are updated according to the gradient, so that when the model encounters a similar input next time, it can generate an output closer to the training labels. This process will be repeated continuously. Through multiple iterative trainings, the model parameters are gradually adjusted to continuously improve the performance of the model, and finally it can better handle dialogue-related tasks.

[0185] In some embodiments, obtaining the first sample data can be specifically implemented as:

[0186] Determine at least one round of sample dialogue data and the requirements for question output;

[0187] Generate the first sample data based on at least one round of sample dialogue data and the requirements for question output.

[0188] Among them, the requirements for question output can be the specifications and expectations for the model output, used to clarify the conditions that the output generated by the model after processing the sample dialogue data needs to meet. In the scenario of generating interview questions, the requirements for question output can, for example, include the language style of the questions (formal, concise, etc.), the types of questions (technical, behavioral, etc.), the relevance of the questions to the interview position, the difficulty level of the questions, etc. In addition, the requirements for question output can also include the requirements for the model's capabilities. For example, the model can be required to select a question from a preset list of questions in sequence and output it.

[0189] Among them, the first sample data can be implemented as a prompt. A prompt is a form of input used to prompt or guide the model to give an expected output. A prompt is a natural language input, similar to a command or instruction, to let the model know what it needs to do.

[0190] In the embodiments of the present application, to facilitate the generation of prompt information, a prompt template can be pre-configured. By adding at least one round of sample dialogue data and question output requirements to the prompt template, the corresponding prompt can be generated.

[0191] Among them, the prompt template can include the following parts:

[0192] At least one round of sample dialogue data: Interviewer: "Please share the work content you were responsible for in the recent project."

[0193] Job-seeking user: "I mainly XXXX."

[0194] Question output requirement: Generate a formal and professional question regarding the technical capabilities of the job-seeking user.

[0195] In some embodiments, the second sample data is respectively input into the student model and the teacher model, so that the student model performs an inference operation based on the second sample data to calculate the first probability distribution of different element data, which can be specifically implemented as:

[0196] The second sample data is respectively input into the student model and the teacher model, so that the student model performs an inference operation based on the second sample data and selects the target element data according to the first probability distribution;

[0197] In some embodiments, the method may further include:

[0198] The target element data is concatenated with the second sample data to update the second sample data, and the step of respectively inputting the second sample data into the student model and the teacher model is returned to continue execution.

[0199] In the embodiments of the present application, after the concatenation is completed, the updated second sample data is input into the student model and the teacher model again, and the above steps are repeated, realizing an iterative training process. By continuously updating the sample data and letting the model process it, the model can gradually learn how to generate more reasonable and coherent text or dialogue, and can continuously optimize its calculation of the probability distribution of element data and the selection of target element data, which helps to improve the performance of the model and make it perform better in tasks such as dialogue generation and text continuation.

[0200] In practical applications, this iterative training process can continue for multiple times until a certain stopping condition is met. The stopping condition can, for example, include reaching a predetermined number of iterations, the generated text length meeting the requirements, or the generated content meeting a certain evaluation metric (such as the generated dialogue conforming to human language habits and logic). Through this iterative approach, the student model can continuously learn from the input data and gradually adjust its own parameters and prediction capabilities, ultimately achieving learning and absorbing knowledge from the teacher model to achieve better performance. At the same time, the teacher model can also provide a reference for the student model to help the student model adjust its prediction of the element data in each iteration, enabling the student model to gradually approach the performance of the teacher model.

[0201] Figure 5 The block diagram of an artificial intelligence interview device provided by an embodiment of the present application is shown. This device can be applied to a server side, such as Figure 5 as shown, the device may include:

[0202] A request acquisition module 501, configured to acquire an interview request sent by a client; the interview request is generated by the client in response to an interview operation triggered by a target user for a target position;

[0203] A question list determination module 502, configured to determine a question list corresponding to the target position; the question list includes a plurality of question data;

[0204] A first judgment module 503, configured to combine at least one round of historical dialogue data of the target user to judge whether the target user meets the question generation condition;

[0205] A question generation module 504, configured to, when the target user meets the question generation condition, use the target dialogue model to generate target question data from the question list in combination with at least one round of historical dialogue data; the target dialogue model is trained based on at least one round of sample dialogue data;

[0206] A second judgment module 505, configured to judge whether the target question data meets the corresponding constraint conditions;

[0207] A question sending module 506, configured to send the target question data to the client when the target question data meets the corresponding constraint conditions;

[0208] A response acquisition module 507, configured to acquire the response data fed back by the client and return to continue executing the step of judging whether the target user meets the question generation condition in combination with at least one round of historical dialogue data of the target user.

[0209] In some embodiments, the second judgment module 505 is specifically configured to:

[0210] Determine whether the pre-information of the target question data is included in at least one round of historical conversation data;

[0211] If so, determine that the constraint condition is satisfied; if not, determine that the constraint condition is not satisfied.

[0212] In some embodiments, the first judgment module 503 is specifically configured to:

[0213] Determine the previous round of question data and the previous round of response data in the previous round of conversation data;

[0214] Judge whether the previous round of response data matches the previous round of question data; if so, determine that the target user meets the question generation condition, otherwise the question generation condition is not met;

[0215] In some embodiments, the device may further include:

[0216] The first question determination module is configured to use the previous round of question data as the target question data if the target user does not meet the question generation condition.

[0217] In some embodiments, the question determination module is specifically configured to:

[0218] If the target user does not meet the question generation condition, judge whether the retry times of the previous round of question data meet the limit condition;

[0219] If not, use the previous round of question data as the target question data and accumulate the retry times;

[0220] If so, use the target dialogue model, combine at least one round of historical conversation data, and generate the target question data from the question list.

[0221] In some embodiments, the question determination module is specifically configured to:

[0222] If the target user does not meet the question generation condition, judge whether the previous round of response data is question data;

[0223] If not, use the previous round of question data as the target question data;

[0224] If so, generate a reply data corresponding to the question data using the session model and send the reply data to the client.

[0225] In some embodiments, the first judgment module 503 is specifically configured to:

[0226] Determine the previous round of question data and the previous round of response data in the previous round of conversation data;

[0227] Judge whether the previous round of response data is question data; if so, determine that the target user meets the question generation condition;

[0228] In some embodiments, the apparatus may further include:

[0229] A second problem determination module, configured to use the previous round of problem data as the target problem data if the target user does not meet the problem generation condition;

[0230] In some embodiments, the problem generation module 504 may specifically be configured to:

[0231] If the target user meets the problem generation condition, use the session model to generate response data corresponding to the question data, and send the response data to the client;

[0232] Use the dialogue model to generate target problem data from the question list in combination with the historical dialogue data.

[0233] In some embodiments, the problem generation module 504 may specifically be configured to:

[0234] Use the target dialogue model in combination with at least one round of historical dialogue data to generate candidate problem data from the unmarked problem data in the question list, and determine whether there is response data corresponding to the candidate problem data in at least one round of historical dialogue data. If so, mark the candidate problem data and regenerate the candidate problem data. If not, use the candidate problem data as the target problem data and mark the target problem data.

[0235] In some embodiments, the problem generation module 504 may specifically be configured to:

[0236] Use the target dialogue model in combination with at least one round of historical dialogue data to generate target problem data from the question list according to at least one question output requirement;

[0237] The at least one question output requirement includes one or more of the following options:

[0238] The response data in the previous round of historical dialogue data matches the question data;

[0239] The retry count of the question data in the previous round of historical dialogue data exceeds the limit condition;

[0240] There is no response data in at least one round of historical dialogue data that matches the target problem data;

[0241] And,

[0242] The target problem data meets its corresponding constraint conditions.

[0243] In some embodiments, the apparatus may further include:

[0244] A third problem determination module, configured to determine whether there is unselected problem data in the question list;

[0245] A third judgment module, configured to, when there is unselected question data in the question list, continue to execute the step of selecting question data from the question list; otherwise, generate an interview end prompt message.

[0246] In some embodiments, the device may further include:

[0247] A delivery operation receiving module, configured to receive a resume delivery operation of a client for a target position;

[0248] A notification sending module, configured to send an interview invitation notification to the client in response to the resume delivery operation;

[0249] In some embodiments, the request acquisition module 501 may specifically be configured to:

[0250] Acquire an interview request sent by the client by triggering the interview invitation notification.

[0251] Figure 5 The described artificial intelligence interview device may execute Figure 2 The artificial intelligence interview method described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated further. For the artificial intelligence interview device in the above embodiments, the specific manners in which each module and unit perform operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0252] An embodiment of the present application further provides a computing device, as Figure 6 shown, the device may include a storage component and a processing component;

[0253] The storage component stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component to implement the artificial intelligence interview method provided by the embodiment of the present application.

[0254] Of course, the computing device may necessarily further include other components, such as an input / output interface, a display component, a communication component, etc.

[0255] The input / output interface provides an interface between the processing component and a peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0256] Among them, the processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0257] The storage component is configured to store various types of data to support the operation of the terminal. The storage component 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.

[0258] The display component can be an electroluminescent (EL) element, a liquid crystal display or a micro display with a similar structure, or a retina-direct display or a similar laser scanning display.

[0259] It should be noted that the above computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. It can be implemented as a distributed cluster composed of multiple servers or terminal devices, or can be implemented as a single server or a single terminal device.

[0260] The embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 2 artificial intelligence interview method shown in the embodiment. The computer-readable medium can be included in the electronic device described in the above embodiment; or can exist separately without being assembled into the electronic device.

[0261] The embodiment of the present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium, and when the computer program is executed by a computer, it can implement the artificial intelligence interview method as shown in the above Figure 2 embodiment. In such an embodiment, the computer program can be downloaded and installed from the network and / or installed from a removable medium. When the computer program is executed by the processor, it executes various functions defined in the system of the present application.

[0262] It should be noted that the embodiments of the present application may involve the use of user data. In actual applications, user-specific personal data can be used in the solutions described herein within the scope permitted by applicable laws and regulations in the country where the user is located (for example, with the user's explicit consent, giving the user a practical notice, etc.).

[0263] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0264] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0265] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0266] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An artificial intelligence interview method, characterized in that: Applied to the server, the method includes: Obtaining an interview request sent by a client; the interview request is generated by the client in response to an interview operation triggered by a target position of a target user; Determine a question list corresponding to the target position; the question list includes a plurality of question data; Based on at least one round of historical conversation data of the target user, determining whether the target user meets the question generation condition; When the target user meets the question generation condition, generating target question data from the question list by using the target dialogue model in combination with at least one round of historical dialogue data; the target dialogue model is trained based on at least one round of sample dialogue data; Determine whether the target problem data satisfies the corresponding constraint conditions; When the target question data satisfies the corresponding constraint condition, sending the target question data to the client; The response data fed back by the client is obtained, and at least one round of historical conversation data combined with the target user is returned to continue the step of determining whether the target user meets the question generation condition.

2. The method according to claim 1, characterized in that: The determining whether the target problem data satisfies the corresponding constraint condition comprises: Determining whether the at least one round of historical dialogue data contains the pre-information of the target question data; If so, it is determined that the constraint condition is satisfied; if not, it is determined that the constraint condition is not satisfied.

3. The method according to claim 1, characterized in that The step of combining at least one round of historical conversation data to determine whether the target user meets the question generation condition includes: Determine the previous round of question data and the previous round of answer data in the previous round of dialogue data; Determine whether the previous round of answer data matches the previous round of question data; if so, determine that the target user meets the question generation condition, otherwise, the question generation condition is not met; The method further comprises: If the target user does not meet the question generation condition, the previous round of question data is used as the target question data.

4. The method according to claim 3, characterized in that If the target user does not meet the question generation condition, taking the previous round of question data as the target question data includes: If the target user does not meet the problem generation conditions, determine whether the number of retries of the previous round of problem data meets the restriction conditions; If not, the previous round of question data is used as the target question data, and the number of retries is accumulated; If so, the target dialogue model is used in combination with at least one round of historical dialogue data to generate target question data from the question list.

5. The method according to claim 3, characterized in that: If the target user does not meet the question generation condition, taking the previous round of question data as the target question data includes: If the target user does not meet the question generation conditions, determine whether the previous round of answer data is question data; If not, the previous round of question data is used as the target question data; If so, the conversation model is used to generate reply data corresponding to the question data, and the reply data is sent to the client.

6. The method according to claim 1, characterized in that The step of combining at least one round of historical conversation data to determine whether the target user meets the question generation condition includes: Determine the previous round of question data and the previous round of answer data in the previous round of dialogue data; Determine whether the previous round of answer data is question data; if so, determine that the target user meets the question generation condition; The method further comprises: If the target user does not meet the question generation conditions, the previous round of question data is used as the target question data; When the target user meets the question generation condition, generating target question data from the question list by using the target dialogue model in combination with at least one round of historical dialogue data includes: If the target user meets the question generation condition, generate reply data corresponding to the question data using the conversation model, and send the reply data to the client; The dialog model is used to generate target question data from the question list in combination with the historical dialog data.

7. The method according to claim 1, characterized in that Using the target dialogue model in combination with at least one round of historical dialogue data to generate target question data from the question list includes: The target dialogue model is combined with at least one round of historical dialogue data to generate candidate question data from the unmarked question data in the question list, and it is determined from the at least one round of historical dialogue data whether there is response data corresponding to the candidate question data. If so, the candidate question data is marked and the candidate question data is regenerated. If not, the candidate question data is used as the target question data and the target question data is marked.

8. The method according to claim 1, characterized in that The step of generating target question data from the question list by using the target dialogue model in combination with at least one round of historical dialogue data includes: Generate target question data from the question list by using the target dialogue model in combination with at least one round of historical dialogue data according to at least one question output requirement; The at least one question output requirement includes one or more of the following options: Match the answer data and question data in the previous round of historical dialogue data; The number of retries for the question data in the previous round of historical conversation data exceeds the limit; There is no answer data matching the target question data in at least one round of historical dialogue data; as well as, The target problem data satisfies its corresponding constraints.

9. The method according to claim 1, characterized in that: After obtaining the response data fed back by the client, the method further includes: Determine whether there is unselected question data in the question list; If yes, select the question data step from the question list to continue, if no, generate an interview end prompt message.

10. The method according to claim 1, characterized in that Also includes: Receiving a resume submission operation from the client for the target position; In response to the resume submission operation, sending an interview invitation notification to the client; The obtaining of the interview request sent by the client includes: The interview request sent by the client by triggering the interview invitation notification is obtained.

11. A computing device, characterized in that: including a processing component and a storage component; The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the artificial intelligence interview method as described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by the processing component, the artificial intelligence interview method as described in any one of claims 1 to 10 is implemented.

13. A computer program product, characterized in that It includes computer programs / instructions, which, when executed by a processing component, implement the artificial intelligence interview method as described in any one of claims 1 to 10.

Images