Resume generation method, display method, equipment, storage medium and program product
By automatically identifying audio information and generating resume data, the problem of low efficiency and low accuracy of resume data generation in the prior art is solved, and efficient and accurate automatic generation of resume data is achieved.
Patent Information
- Application Number
- CN202510123462.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-24
- Publication Date
- 2025-05-30
AI Technical Summary
In the prior art, resume data needs to be manually edited and generated, which is low in efficiency and low in accuracy.
By in response to resume generation requests, target job categories are determined, interview questions are generated, and audio information is used for voice recognition, and job search information dimensions are automatically identified and resume data are generated.
It realizes automatic generation of resume data, improves generation efficiency and accuracy, and improves the interview experience of job seekers.
Smart Images
Figure CN120068809A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of Internet technologies, and in particular, to a resume generation method, a display method, a device, a storage medium, and a program product. Background Art
[0002] Resume data is a very important part in job hunting. It is a brief summary of a job seeker's abilities, experiences, and skills, and is a microcosm of the comprehensive qualities and abilities of the job seeker.
[0003] In the prior art, resume data usually needs to be manually edited and generated, with low efficiency and low accuracy. Summary of the Invention
[0004] The embodiments of the present application provide a resume generation method, a display method, a device, a storage medium, and a program product, which are used to automatically generate resume data and improve the generation efficiency and accuracy of resume data.
[0005] In a first aspect, the embodiments of the present application provide a resume generation method, including:
[0006] Responding to a resume generation request to determine a target job category;
[0007] Generating interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category;
[0008] Sending the interview questions to a client;
[0009] Obtaining audio information triggered by a job hunting user for the interview questions sent by the client, and performing speech recognition on the audio information to obtain text information;
[0010] Identifying text data corresponding to each of the at least one job hunting information dimension from the text information;
[0011] Determining resume fields respectively mapped by the at least one job hunting information dimension, and generating job hunting data based on the text data corresponding to each job hunting information dimension;
[0012] In the case where the job hunting user does not meet the resume generation condition, returning to the step of generating interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category and continuing to execute;
[0013] In the case where the job hunting user meets the resume generation condition, generating resume data of the job hunting user based on the resume fields respectively mapped by multiple job hunting information dimensions corresponding to the target job category and the corresponding job hunting data.
[0014] In a second aspect, the embodiments of the present application provide a display method, including:
[0015] Display resume generation prompt messages corresponding to multiple job categories in the user interface;
[0016] In response to a confirmation operation of a job-seeking user for any one of the resume generation prompt messages, generate a resume generation request and send it to the server, so that the server, in response to the resume generation request, determines a target job category, and generates interview questions based on at least one unrecognized job-seeking information dimension corresponding to the target job category;
[0017] Obtain the interview questions and display them in the user interface;
[0018] Send the audio information triggered by the job-seeking user for the interview questions to the server, so that the server performs speech recognition on the audio information to obtain text information, identifies the text data corresponding to each of the at least one job-seeking information dimension from the text information, determines the resume fields mapped by each of the at least one job-seeking information dimension, and generates job-seeking data based on the text data corresponding to each job-seeking information dimension;
[0019] Obtain resume data and display it in the user interface; wherein, the resume data is generated by the server based on the resume fields mapped by multiple job-seeking information dimensions corresponding to the target job category and the corresponding job-seeking data when the job-seeking user meets the resume generation conditions.
[0020] In a third aspect, an embodiment of the present application provides a computing device, including a storage component and a processing component; the storage component stores one or more computer program instructions, and the computer program instructions are called and executed by the processing component, and the processing component executes the one or more computer program instructions to implement the resume generation method described in the first aspect or the display method described in the second aspect.
[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and the computer program is executed by a computer to implement the resume generation method described in the first aspect or the display method described in the second aspect.
[0022] In a fifth aspect, an embodiment of the present application provides a computer program product storing a computer program, and the computer program, when executed by a computer, implements the resume generation method described in the first aspect or the display method described in the second aspect.
[0023] In the solution of the embodiment of the present application, by recognizing audio information to obtain text information, identifying the text data corresponding to at least one job hunting information dimension from the text information, then generating the job hunting data of the corresponding resume fields based on the text data, and generating resume data based on the job hunting data, the automatic generation of resume data is realized, and the generation efficiency is improved. Moreover, through the setting of the job information dimension, adopting a structured data recognition method, the text data corresponding to at least one job hunting information dimension is identified from the text information, realizing the targeted recognition of text data, improving the recognition accuracy, and further improving the accuracy of job hunting data and resume data. In addition, through real-time text data recognition and job hunting data generation, and generating the next interview question according to at least one unrecognized job hunting information dimension, on the basis of improving the data recognition and generation efficiency, the accuracy and coherence of interview question generation are improved, and the interview experience of job hunting users is enhanced.
[0024] 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
[0025] 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 also be obtained based on these drawings.
[0026] Figure 1 FIG. shows a flowchart of an embodiment of a resume generation method provided by the present application;
[0027] Figure 2 FIG. shows a flowchart of an embodiment of a display method provided by the present application;
[0028] Figure 3 FIG. shows a schematic structural diagram of an embodiment of a resume generation system provided by the present application;
[0029] Figure 4 FIG. shows a schematic structural diagram of an embodiment of a resume generation device provided by the present application;
[0030] Figure 5 FIG. shows a schematic structural diagram of an embodiment of a display device provided by the present application;
[0031] Figure 6 FIG. shows a schematic structural diagram of an embodiment of a computing device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0032] To enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.
[0033] In some processes described in the specification, claims and the above-mentioned accompanying drawings of this 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 each different operation, 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", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.
[0034] As described in the foregoing background art section, current resume data is usually generated by manual editing, with low efficiency and low accuracy.
[0035] To improve the efficiency of resume generation, the inventor thought that with the development of Internet technology and video technology, and the increasing demand for personalized and efficient communication in modern society, online video interviews, especially artificial intelligence interviews, have gradually become popular. For example, in the domestic service industry, through artificial intelligence interviews, job-seeking information such as the work experience and work expectations of domestic service personnel can be extracted from the interview videos to generate resume data for domestic service personnel.
[0036] However, in the above method, usually after the video interview ends, the job-seeking information of the job-seeking user is extracted offline from the interview video to generate resume data, with low efficiency and poor interview effects.
[0037] Based on this, the inventor proposed the technical solution of this application, including: in response to a resume generation request, determining a target job category; generating interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category; sending the interview questions to the client; obtaining audio information triggered by the job hunting user for the interview questions sent by the client, and performing speech recognition on the audio information to obtain text information; identifying text data corresponding to each of the at least one job hunting information dimension from the text information; determining resume fields respectively mapped by the at least one job hunting information dimension, and generating job hunting data based on the text data corresponding to each job hunting information dimension; in the case that the job hunting user does not meet the resume generation condition, returning to the step of generating interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category and continuing to execute; in the case that the job hunting user meets the resume generation condition, generating resume data of the job hunting user based on resume fields respectively mapped by multiple job hunting information dimensions corresponding to the target job category and corresponding job hunting data respectively.
[0038] By recognizing text information based on audio information, identifying text data corresponding to each of at least one job hunting information dimension from the text information, then generating job hunting data of corresponding resume fields based on the text data, and generating resume data based on the job hunting data, the automatic generation of resume data is realized, and the generation efficiency is improved. Moreover, through the setting of job information dimensions and adopting a structured data recognition method, text data corresponding to each of at least one job hunting information dimension is identified from the text information, realizing the targeted recognition of text data, improving the recognition accuracy, and further improving the accuracy of job hunting data and resume data. In addition, through real-time text data recognition and job hunting data generation, and generating the next interview question according to at least one unrecognized job hunting information dimension, on the basis of improving the data recognition and generation efficiency, the accuracy and coherence of interview question generation are improved, and the interview experience of the job hunting user is enhanced.
[0039] 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 in the present application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of the present application.
[0040] The technical solution of the embodiment of the present application can be applied to a system architecture including a client and a server, and a connection is established between the client and the server through a network. The network provides a medium for the communication link between the client and the server. The network can include various connection types, such as wired, wireless communication links or fiber optic cables, etc.
[0041] The client can interact with the server via the network to send resume generation requests, audio information, or receive interview questions, resume data, etc.
[0042] Among them, the client 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 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, etc. For ease of understanding, 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.
[0043] The server can include servers that provide various services, such as a server that responds to the resume generation request sent by the client, a server that generates interview questions, etc.
[0044] It should be noted that the server 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, or an intelligent cloud computing server or an intelligent cloud host with artificial intelligence technology.
[0045] It should be noted that in the embodiments of the present application, the resume generation method provided generally is executed by the server, and the display method generally is executed by the client. Correspondingly, the resume generation device is generally deployed in the server, and the display device is generally deployed in the client. However, in other embodiments of the present application, the client can also have similar functions to the server, so as to execute the resume generation method provided in the embodiments of the present application. In other embodiments, the resume generation method provided in the embodiments of the present application can also be jointly executed by the client and the server.
[0046] 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, provided that the requirements of the applicable laws and regulations of the country where the user is located are met (for example, the user clearly consents, and the user is effectively notified, etc.).
[0047] 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 this 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 the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject.
[0048] It should be noted that the technical solution of the embodiment of this 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.
[0049] As Figure 1 shown, it is a flowchart of an embodiment of a resume generation method provided by this application, which can be executed by the server. The method may include the following steps:
[0050] 101: In response to a resume generation request, determine the target job category.
[0051] Among them, the resume generation request can be generated and sent to the server by the client in response to the confirmation operation of the job-seeking user for the resume generation prompt information of the target job category. The resume generation request may include the identification information of the target job category, and the server can determine the target job category therefrom.
[0052] It should be noted that in the embodiment of this application, the job category may refer to different categories of positions such as waiters, salespersons, and domestic helpers, rather than specific job positions.
[0053] 102: Generate interview questions based on at least one unrecognized job-seeking information dimension corresponding to the target job category.
[0054] 103: Send the interview questions to the client.
[0055] Among them, the job-seeking information dimension refers to the dimension of job-seeking information. For example, it may include different dimensions such as name, gender, age, education level, work experience, and work expectations. One job category may correspond to multiple job-seeking information dimensions, and the job-seeking information dimensions corresponding to different job categories may be the same or different, which can be set according to actual needs.
[0056] Specifically, the server can first determine multiple job application information dimensions corresponding to the target job category. Based on one or more unrecognized job application dimensions among the multiple job application information dimensions, a generative model is used to generate interview questions. Among them, the generative model can be implemented as a large model, that is, a machine learning model with a large number of parameters and a complex structure. For example, the large model can be a large language model (LLM for short), and the large language model is trained based on a large amount of text data and can generate natural language text or understand the meaning of language text. The large language model can adopt a generative pre-trained model (Generative Pre-Trained Transformer, GPT for short), etc., and this application does not limit this. For example, based on three job application information dimensions of name, age, and education background, the interview questions generated by the large language model can be: Please introduce your name, age, and education background to me.
[0057] The server can send the generated interview questions to the client to trigger the job application user to reply to the interview questions, so as to obtain the job application information of the job application user subsequently. As an optional implementation, a virtual interview user, which can be understood as a digital human, can be used to voice broadcast the interview questions to the job application user, so as to trigger the job application user to reply to the interview questions in the way of an artificial intelligence (AI) interview. As another optional implementation, the interview questions can be sent to the client for display in the user interface. As yet another optional implementation, while using a virtual interview user to voice broadcast the interview questions to the job application user, the interview questions can be displayed in the user interface. The specific implementation will be described in the subsequent embodiments.
[0058] 104: Obtain the audio information triggered by the job application user for the interview questions sent by the client, and perform speech recognition on the audio information to obtain text information.
[0059] Among them, the audio information can be collected by the client during the process of the job application user's reply to the interview questions and sent to the server. As an optional implementation, the client can send the collected multiple pieces of audio information to the server respectively based on the pause information during the job application user's reply to the interview questions. As another optional implementation, the client can also send the audio information to the server after the job application user finishes replying to the interview questions, and this application does not limit this.
[0060] For the convenience of subsequent data processing, after receiving the audio information sent by the client, the server can use a preset speech recognition algorithm to convert the audio information into text information.
[0061] 105: Identify the text data corresponding to at least one job hunting information dimension from the text information.
[0062] Specifically, the server can use a text processing model to identify the text data corresponding to at least one job hunting information dimension from the text information. Among them, the text processing model can also be implemented as a large model, such as a large language model. For example, the text information is: I am 32 years old and have graduated from university for 10 years. Then, using the large model, two job hunting information dimensions can be identified: age and education level, and the text data corresponding to the age dimension is: 32 years old, and the text data corresponding to the education level dimension is: graduated from university.
[0063] It should be noted that this large language model can be the same as or different from the aforementioned large language model, and this application does not limit this.
[0064] 106: Determine the resume fields respectively mapped by at least one job hunting information dimension, and generate job hunting data based on the text data corresponding to each job hunting information dimension.
[0065] Among them, according to the pre-generated mapping relationship between the job hunting information dimension and the resume field, the resume fields respectively mapped by the identified at least one job hunting information dimension can be determined, and according to the data format corresponding to each resume field, the job hunting data corresponding to each resume field can be generated based on the text information corresponding to each job hunting information dimension. For example, the resume field mapped by the age dimension is age, and the corresponding data format is: xx years old, where xx represents a number; the resume field mapped by the education level dimension is the highest education level, and the corresponding data format is: high school, undergraduate, master, etc.; the resume field mapped by the job expectation dimension is the expected salary, and the corresponding data format is below 3000 yuan, 3000 - 10000 yuan, above 10000 yuan. Then, based on the text data corresponding to the age dimension: 32 years old, the job hunting data corresponding to the corresponding resume field can be generated: 32 years old; based on the text data corresponding to the education level dimension: undergraduate degree, the job hunting data corresponding to the corresponding resume field can be generated: undergraduate; based on the text data corresponding to the job expectation dimension: 5000 yuan, the job hunting data corresponding to the corresponding resume field can be generated: 3000 - 10000 yuan.
[0066] 107: Determine whether the job hunting user meets the resume generation conditions. If not, return to step 102 and continue to execute; if so, execute the operation in step 108.
[0067] 108: Generate the resume data of the job hunting user based on the resume fields respectively mapped by multiple job hunting information dimensions corresponding to the target job category and the corresponding job hunting data.
[0068] Among them, the resume generation conditions can be implemented in various ways. As an alternative implementation, the resume generation conditions can be that all multiple job hunting information dimensions corresponding to the target job category are recognized. As another alternative implementation, the resume generation conditions can be that the number of recognized job hunting information dimensions reaches a threshold. As yet another alternative implementation, the resume generation conditions can be that at least one preset job hunting information dimension is recognized, etc., which can be set according to actual needs.
[0069] When it is determined that the resume generation conditions are not met, the operation in step 102 can be returned to continue execution, that is, based on one or more unrecognized job hunting information dimensions, generate the next interview question and send it to the client to trigger the job hunting user to reply to it. When it is determined that the resume generation conditions are met, the resume data of the job hunting user can be generated according to the resume fields respectively mapped by the multiple job hunting information dimensions and the corresponding job hunting data.
[0070] Optionally, based on the resume fields respectively mapped by the multiple job hunting information dimensions and the corresponding job hunting data, the resume data of the job hunting user can be generated according to the resume format. For example, the resume format can include the arrangement of each resume field, and according to this resume format, text-form resume data can be generated.
[0071] In this embodiment, by obtaining text information based on audio information recognition, identifying the text data corresponding to at least one job hunting information dimension from the text information, then generating the job hunting data of the corresponding resume field based on the text data, and generating resume data based on the job hunting data, the automatic generation of resume data is realized, and the generation efficiency is improved. Moreover, through the setting of the job information dimension, adopting a structured data recognition method, the text data corresponding to at least one job hunting information dimension is identified from the text information, realizing the targeted recognition of text data, improving the recognition accuracy, and further improving the accuracy of job hunting data and resume data. In addition, through real-time text data recognition and job hunting data generation, and generating the next interview question according to at least one unrecognized job hunting information dimension, on the basis of improving the data recognition and generation efficiency, the accuracy and coherence of interview question generation are improved, and the interview experience of the job hunting user is enhanced.
[0072] The following describes the artificial intelligence interview process.
[0073] In some embodiments, before performing the artificial intelligence interview, the above method may further include:
[0074] Determine the virtual interview users corresponding to the target job category, create an interview environment, and add the virtual interview users to the interview environment; and generate an interview page and send it to the client for the job-seeking user to enter the interview environment based on the interview page; use the virtual interview users to voice the interview questions to the job-seeking user.
[0075] Among them, different job categories can correspond to different virtual interview users, that is, digital human images, such as the gender, clothing, voice, etc. of the digital human. The interview environment can refer to an online space. The server can add virtual interview users and trigger the job-seeking user to enter this interview environment through the interview page. In this interview environment, use the virtual interview users to voice the interview questions to the job-seeking user to perform an artificial intelligence interview operation.
[0076] By determining the virtual interview users corresponding to the target job category and using these virtual interview users to voice the interview questions to the job-seeking user, the sense of intimacy towards the virtual interview users in the artificial intelligence interview process is enhanced, and further the interview experience of the job-seeking user.
[0077] At the beginning of the artificial intelligence interview, a large model can also be used to generate the initial interview questions corresponding to the target job category. For example, if the target job category is a waiter, the initial interview question can be: Please briefly introduce your personal information and work experience related to being a waiter. Perform speech recognition on the audio information triggered by the job-seeking user for this initial interview question to obtain text information, and according to multiple job-seeking information dimensions corresponding to the target job category, identify at least one piece of text data corresponding to each job-seeking information dimension and generate the job-seeking data for the corresponding resume field. After that, according to at least one unrecognized job-seeking information dimension among the multiple job-seeking information dimensions, generate the next interview question.
[0078] Optionally, if the number of interview questions generated based on any unrecognized job-seeking information dimension reaches the threshold, no more interview questions will be generated based on this job-seeking information dimension. That is to say, if the job-seeking user is interviewed multiple times for a certain job-seeking information dimension and no corresponding text data is identified, it can be considered that the job-seeking user has not given a corresponding answer, and then no more questions will be asked to avoid affecting the interview experience.
[0079] Optionally, if for any job-seeking information dimension, job-seeking data corresponding to the corresponding resume field cannot be generated based on the identified text data, the job-seeking data corresponding to this resume field can be set to the default value. For example, for the expected salary dimension, if the identified text data is no specific value, the job-seeking data corresponding to the corresponding resume field can be set to the default value or negotiable, which can be set according to actual needs.
[0080] Optionally, when all multiple job hunting information dimensions corresponding to the target job category are recognized, the artificial intelligence interview operation can be terminated.
[0081] In some embodiments, in order to further improve the accuracy and coherence of interview questions, the method for generating interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category may include:
[0082] Based on at least one unrecognized job hunting information dimension corresponding to the target job category and the job hunting data corresponding to historical interview questions, use a generation model to generate interview questions.
[0083] Among them, historical interview questions may include one or more interview questions before the current interview question. That is to say, according to the reply situation of the job hunting user to the previous interview questions and at least one unrecognized job hunting information dimension, use a generation model to generate interview questions. For example, the job hunting user has previously replied about their work situation, and the recognized job hunting data is, for example, the salary of the previous job is 3000 yuan, and the unrecognized job hunting information dimension includes the expected salary. Then, using the generation model, the next interview question can be generated as: You just mentioned that the salary of your previous job was 3000 yuan. May I ask what is your expected salary for the next job? This greatly improves the coherence between adjacent two interview questions and further improves the interview experience of the job hunting user.
[0084] In some embodiments, the method for identifying the text data corresponding to at least one job hunting information dimension from text information may include:
[0085] Based on the preset text representation methods corresponding to multiple job hunting information dimensions, use a text processing model to identify the text data corresponding to at least one job hunting information dimension from text information.
[0086] Among them, for each job hunting information dimension, a corresponding text representation method can be preset, which may include specified words, phrases, sentence patterns, etc. For example, for the age dimension, the corresponding preset text representation methods may include: xx years old this year, born in xx, etc., where xx represents a number. For example, if the text information is: I was born in 2000, it can be recognized that the corresponding is the age dimension, and the corresponding text data is the age is 25 years old.
[0087] By using the text processing model to identify text data based on the preset text representation methods corresponding to job hunting information dimensions, the accuracy of text data recognition is further improved.
[0088] In practical applications, there may be a situation where the job hunting user replies multiple times for the same job hunting information dimension and the reply information is inconsistent. Therefore, in some embodiments, the above method may further include:
[0089] When the current text data corresponding to any identified job application information dimension is different from the historical text data, update the resume fields according to the job application data corresponding to the current text data.
[0090] Among them, the historical text data can refer to the text data identified from the text information corresponding to the audio information triggered by the job applicant for historical interview questions. For example, for the dimension of working years, the identified historical text data is that the working years are more than 5 years, and the current text data is that the working years are 4 years. At this time, the job application data corresponding to the current text data can be used to update the resume fields.
[0091] Optionally, in order to improve accuracy, when the current text data corresponding to any identified job application information dimension is different from the historical text data, the above method may further include:
[0092] Generate a confirmation prompt message based on the current text data and the historical text data, and send the confirmation prompt message to the client for the job applicant to confirm.
[0093] At this time, updating the resume fields according to the job application data corresponding to the current text data may include:
[0094] When the job applicant confirms that the current text data is correct, update the resume fields according to the job application data corresponding to the current text data.
[0095] Among them, based on the current text data and the historical text data, a generation model can be used to generate a confirmation prompt message. For example, the historical text data is that the working years are more than 5 years, and the current text data is that the working years are 4 years. The generated confirmation prompt message can be: You previously mentioned that the working years are more than 5 years, and then you mentioned that the working years are 4 years. Which one is accurate?
[0096] Optionally, the server can send the confirmation prompt message to the client as the next interview question, and identify the correct text data according to the job applicant's reply. When the job applicant confirms that the current text data is correct, update the resume fields according to the job application data corresponding to the current text data. When the job applicant confirms that the historical text data is correct, there is no need to update the resume fields. Of course, when the job applicant gives another new reply message, update the resume fields with the newly identified text data.
[0097] When the current text data identified for the same job application information dimension is different from the historical text data, a confirmation prompt message is generated and sent to the client, and the job application data corresponding to the resume field is updated in real time according to the response of the job applicant to the confirmation prompt message, further improving the accuracy of the job application data and the accuracy of the resume data.
[0098] After the resume data is generated, in some embodiments, the above method may further include:
[0099] Sending the resume data to the client for display in the user interface of the client;
[0100] Responding to a modification request to modify at least one job application data.
[0101] Optionally, the server may also send modification prompt messages corresponding to at least one job application data to the client for display in the user interface, and respond to the modification request triggered by the at least one modification prompt message to modify at least one job application. This further improves the accuracy of the resume data.
[0102] Optionally, in response to a confirmation request, the resume data may be saved to the database and / or sent to the client for the job applicant to save locally.
[0103] Optionally, after the artificial intelligence interview ends, the server may also obtain the interview video data of the job applicant collected and sent by the client during the interview, perform a series of video editing operations such as clipping, synthesizing, and auditing on it, generate the target interview video of the job applicant, save the target interview video to the database and / or send it to the client for the job applicant to save locally.
[0104] The technical solution of the present application will be described from the perspective of the client below. As Figure 2 shown, it is a flowchart of an embodiment of a display method provided by the present application, which may include the following steps;
[0105] 201: Display resume generation prompt messages corresponding to multiple job categories in the user interface.
[0106] Among them, the resume generation prompt message may include various forms such as text, icons, controls, etc. For example, the resume generation prompt message corresponding to the waiter job category may be: Please click the confirmation control to participate in the artificial intelligence interview for the waiter job category to generate your resume data.
[0107] 202: In response to the confirmation operation of the job-seeking user for generating a prompt message for any resume, generate a resume generation request and send it to the server, so that the server, in response to the resume generation request, determines the target job category and generates interview questions based on at least one unrecognized job-seeking information dimension corresponding to the target job category. The specific process has been described in the corresponding embodiments shown in Figure 1 and will not be elaborated here.
[0108] 203: Obtain the interview questions and display them in the user interface.
[0109] 204: Send the audio information triggered by the job-seeking user for the interview questions to the server, so that the server performs speech recognition on the audio information to obtain text information, identifies the text data corresponding to at least one job-seeking information dimension from the text information, determines the resume fields respectively mapped by at least one job-seeking information dimension, and generates job-seeking data based on the text data corresponding to each job-seeking information dimension.
[0110] Among them, an information collection device such as a microphone, a camera, etc. can be set in the client, which can collect the user's audio information, video information, etc. and send the audio information to the server.
[0111] 205: Obtain the resume data and display it in the user interface. Among them, the resume data is generated by the server based on the resume fields respectively mapped by multiple job-seeking information dimensions corresponding to the target job category and the corresponding job-seeking data when the job-seeking user meets the resume generation conditions.
[0112] By sending the audio information triggered by the job-seeking user for the interview questions to the server, the server obtains text information through recognition based on the audio information, identifies the text data corresponding to at least one job-seeking information dimension from the text information, then generates job-seeking data for the corresponding resume fields based on the text data, and generates resume data based on the job-seeking data, realizing the automatic generation of resume data and improving the generation efficiency. Moreover, through the setting of the job information dimension and adopting a structured data recognition method, the text data corresponding to at least one job-seeking information dimension is identified from the text information, realizing the targeted recognition of the text data and improving the recognition accuracy, thereby improving the accuracy of the job-seeking data and the resume data. In addition, through real-time text data recognition and job-seeking data generation, and generating the next interview question according to at least one unrecognized job-seeking information dimension, on the basis of improving the data recognition and generation efficiency, the accuracy and coherence of the interview question generation are improved, and the interview experience of the job-seeking user is improved.
[0113] In some embodiments, the above method may further include:
[0114] In response to a save operation, save the resume data locally.
[0115] In some embodiments, the above method may further include:
[0116] In response to a modification operation, obtain the modification data corresponding to at least one job application data for the job-seeking user, and generate a modification request to be sent to the server for the server to modify at least one job application data.
[0117] In some embodiments, the above method may further include:
[0118] Obtain interview prompt information and display it in the user interface.
[0119] Among them, the interview prompt information may include prompt information such as paying attention to dressing neatly, looking at the camera, and using the specified language, aiming to prompt the job-seeking user to conduct the interview in a better state. The interview prompt information can be generated and sent by the server.
[0120] In some embodiments, the above method may further include:
[0121] In response to the exit operation of the job-seeking user, obtain the exit prompt information and display it in the user interface.
[0122] Among them, the exit prompt information may include the reason for exiting the interview, an exit confirmation control, an exit cancellation control, etc. The exit prompt information can be generated and sent by the server.
[0123] In response to the trigger operation for the exit confirmation control, the artificial intelligence interview can be ended. And in response to the trigger operation for the exit cancellation control, the artificial intelligence interview can continue.
[0124] For ease of understanding, the technical solution of the present application will be described below in conjunction with Figure 3 the system architecture diagram shown. As Figure 3 shown, the system architecture may include a client 31 and a server 32. It can be understood that Figure 3 the forms of the client and the server shown are only exemplary descriptions, and the present application does not limit this.
[0125] The client 31 provides a user interface 311, and resume generation prompt information corresponding to multiple job categories is displayed in the user interface 311. In response to the confirmation operation of the job-seeking user for any resume generation prompt information, a resume generation request is generated and sent to the server 32.
[0126] In response to a resume generation request, the server 32 determines the target job category, the virtual interview users corresponding to the target job category, and multiple job hunting information dimensions. It creates an interview environment, adds virtual interview users, and sends an interview page to the client 31 to trigger the job seeker to enter the interview environment. It uses the virtual interview users to voice broadcast interview questions to the job seeker to conduct an artificial intelligence interview.
[0127] Specifically, the server 32 can generate interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category, send the interview questions to the client, obtain the audio information triggered by the job seeker for the interview questions collected and sent by the client 31 using information collection devices such as microphones, perform speech recognition on the audio information to obtain text information. Use a speech recognition algorithm to identify the text data corresponding to at least one job hunting information dimension from the text information, determine the resume fields mapped by at least one job hunting information dimension respectively, and generate job hunting data based on the text data corresponding to each job hunting information dimension. Determine whether the job seeker meets the resume generation condition. If not, return to the step of generating interview questions based on at least one unrecognized job hunting information dimension corresponding to the target job category and continue to execute; until the job seeker meets the resume generation condition, generate the resume data of the job seeker based on the resume fields mapped by multiple job hunting information dimensions corresponding to the target job category and the corresponding job hunting data respectively.
[0128] By identifying text information based on audio information, identifying the text data corresponding to at least one job hunting information dimension from the text information, then generating the job hunting data of the corresponding resume fields based on the text data, and generating resume data based on the job hunting data, the automatic generation of resume data is realized, improving the generation efficiency. Moreover, through the setting of job information dimensions, adopting a structured data recognition method to identify the text data corresponding to at least one job hunting information dimension from the text information, the targeted recognition of text data is realized, improving the recognition accuracy, and thus improving the accuracy of job hunting data and resume data. In addition, through real-time text data recognition and job hunting data generation, and generating the next interview question according to at least one unrecognized job hunting information dimension, on the basis of improving the data recognition and generation efficiency, the accuracy and coherence of interview question generation are improved, and the interview experience of job seekers is improved.
[0129] Optionally, in order to further improve the accuracy and coherence of interview questions, the server can generate interview questions using a generation model based on at least one unrecognized job hunting information dimension corresponding to the target job category and the job hunting data corresponding to historical interview questions to improve the interview experience.
[0130] Optionally, the server can use a text processing model to identify text data based on the preset text representation methods corresponding to the job hunting information dimensions respectively, further improving the accuracy of text data identification.
[0131] Optionally, when the current text data identified for the same job hunting information dimension is different from the historical text data, the server can generate a confirmation prompt message and send it to the client, and update the job hunting data corresponding to the resume field in real time according to the reply of the job hunting user to the confirmation prompt message, further improving the accuracy of the job hunting data and the accuracy of the resume data.
[0132] Optionally, after the resume data is generated, the server can send the resume data to the client for display in the user interface of the client, and modify at least one job hunting data in response to a modification request, further improving the accuracy of the resume data.
[0133] As Figure 4 shown, it is a schematic structural diagram of an embodiment of a resume generation device provided by the present application. The device may include the following modules:
[0134] A determination module 401, configured to determine a target position category in response to a resume generation request;
[0135] A first generation module 402, configured to generate interview questions based on at least one unrecognized job hunting information dimension corresponding to the target position category;
[0136] A first sending module 403, configured to send interview questions to the client;
[0137] A first acquisition module 404, configured to acquire audio information triggered by the job hunting user for the interview questions sent by the client, and perform speech recognition on the audio information to obtain text information;
[0138] An identification module 405, configured to identify text data corresponding to at least one job hunting information dimension respectively from the text information;
[0139] A second generation module 406, configured to determine resume fields respectively mapped by at least one job hunting information dimension, and generate job hunting data based on the text data corresponding to each job hunting information dimension;
[0140] A judgment module 407, configured to judge whether the job hunting user meets the resume generation conditions.
[0141] A third generation module 408, when the answer of the judgment module 407 is yes, is configured to generate resume data of the job hunting user based on the resume fields respectively mapped by multiple job hunting information dimensions corresponding to the target position category and the corresponding job hunting data.
[0142] In some embodiments, the first generation module 402 may be specifically configured to generate interview questions by using a generation model based on at least one unrecognized job hunting information dimension corresponding to the target job category and job hunting data corresponding to historical interview questions.
[0143] In some embodiments, the recognition module 405 may be specifically configured to recognize text data corresponding to at least one job hunting information dimension from text information by using a text processing model based on preset text representation methods corresponding to multiple job hunting information dimensions respectively.
[0144] In some embodiments, the above device may further include:
[0145] An update module, configured to update resume fields according to job hunting data corresponding to the current text data when the current text data corresponding to any recognized job hunting information dimension is different from the historical text data.
[0146] In some embodiments, the above device may further include:
[0147] A fourth generation module, configured to generate a confirmation prompt message based on the current text data and the historical text data, and send the confirmation prompt message to the client for a job hunting user to confirm;
[0148] The update module may be specifically configured to update resume fields according to job hunting data corresponding to the current text data when the job hunting user confirms that the current text data is correct.
[0149] In some embodiments, the above device may further include:
[0150] A determination module, configured to determine that the job hunting user meets the resume generation condition when all job hunting information dimensions corresponding to the target job category are recognized.
[0151] In some embodiments, the third generation module 408 may be specifically configured to generate resume data of a job hunting user according to a resume format based on resume fields respectively mapped by multiple job hunting information dimensions corresponding to the target job category and job hunting data respectively corresponding thereto.
[0152] In some embodiments, the above device may further include:
[0153] A second sending module, configured to send the resume data to the client for display in a user interface of the client;
[0154] A modification module, configured to modify at least one piece of job hunting data in response to a modification request.
[0155] In some embodiments, the above device may further include:
[0156] A creation module, configured to determine virtual interview users corresponding to target job categories, create an interview environment, and add the virtual interview users to the interview environment;
[0157] A third sending module, configured to generate an interview page and send it to the client for a job-seeking user to enter the interview environment based on the interview page;
[0158] A broadcast module, configured to use the virtual interview users to broadcast interview questions to the job-seeking user by voice.
[0159] Figure 4 The resume generation device shown can be used to implement Figure 1 The resume generation method shown, and its implementation principle and technical effects will not be elaborated. Among them, Figure 4 One or more modules of the resume generation device shown can constitute the server in the above system architecture. For the resume generation device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0160] As Figure 5 shown, it is a schematic structural diagram of an embodiment of a display device provided by the present application. The device may include the following modules:
[0161] A first display module 501, configured to display resume generation prompt information corresponding to multiple job categories in a user interface;
[0162] A fourth sending module 502, configured to generate a resume generation request and send it to the server in response to a confirmation operation of a job-seeking user for any resume generation prompt information, so that the server determines a target job category in response to the resume generation request, and generates interview questions based on at least one unrecognized job-seeking information dimension corresponding to the target job category;
[0163] A second acquisition module 503, configured to acquire the interview questions and display them in the user interface;
[0164] A fifth sending module 504, configured to send audio information triggered by the job-seeking user for the interview questions to the server, so that the server performs speech recognition on the audio information to obtain text information, identifies text data corresponding to at least one job-seeking information dimension from the text information, determines resume fields respectively mapped by at least one job-seeking information dimension, and generates job-seeking data based on the text data corresponding to each job-seeking information dimension;
[0165] A third acquisition module 505 is configured to acquire resume data and display it in a user interface. The resume data is generated by a server based on resume fields respectively mapped from multiple job hunting information dimensions corresponding to a target job category and corresponding job hunting data when a job hunting user meets the resume generation conditions.
[0166] Figure 5 The display device shown can be used to implement Figure 2 the display method shown. The implementation principle and technical effects will not be elaborated further. Among them, Figure 5 one or more modules of the resume generation device shown can constitute the client in the above system architecture. For the display device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.
[0167] As Figure 6 shown, a schematic structural diagram of an embodiment of a computing device provided by this application is shown. The device may include a storage component 601 and a processing component 602.
[0168] The storage component 601 can be used to store one or more computer program instructions. One or more computer program instructions are called and executed by the processing component 602 to implement Figure 1 the resume generation method shown or Figure 2 the display method shown.
[0169] Of course, the above computing device may also necessarily include other components, such as an input / output interface, a communication component, etc.
[0170] The input / output interface provides an interface between the processing component and a peripheral interface module. The above peripheral interface module may be an output device, an input device, etc. The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.
[0171] It should be noted that when the above computing device is used to implement Figure 1 the resume generation method shown, it 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.
[0172] When the above computing device is used to implement Figure 2 the display method shown, it can be implemented as an electronic device. The electronic device may refer to a device used by a user and having functions such as Internet access, computing, communication, etc. required by the user. For example, it may be a mobile phone, a tablet computer, a personal computer, a wearable device, etc. It can be understood that the above electronic device may also necessarily include other components such as a display component, an input / output interface, a communication component, etc., which will not be elaborated further.
[0173] In one or more of the above embodiments, the processing component may include one or more processors to execute computer instructions to complete all or part of the steps in the above methods. Of course, the processing component may 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 performing the above methods.
[0174] The storage component is configured to store various types of data to support the operation of the terminal. The storage component may 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 disks or optical disks.
[0175] The display component may be an electroluminescent (EL) element, a liquid crystal display or a microdisplay having a similar structure, or a retina-direct display or a similar laser scanning display.
[0176] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, which when executed by a computer can implement Figure 1 the resume generation method shown or Figure 2 the display method shown. The computer-readable medium may be included in the computing device described in the above embodiments; or may exist separately without being assembled into the computing device.
[0177] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above.
[0178] An embodiment of the present application also provides a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program when executed by a computer can implement Figure 1 the resume generation method shown or Figure 2 the display method shown.
[0179] In such an embodiment, the computer program may be downloaded and installed from a network and / or installed from a removable medium. When the computer program is executed by a processor, it performs various functions defined in the system of the present application.
[0180] 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 described herein again.
[0181] 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 effort.
[0182] 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 essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0183] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than 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 perform equivalent replacements for 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 each embodiment of the present application.
Claims
1. A resume generation method, characterized in that: include: In response to resume generation requests, determine target job categories; generating interview questions based on at least one unidentified job search information dimension corresponding to the target position category; Sending the interview questions to the client; Acquire audio information sent by the client and triggered by the job seeker in response to the interview question, and perform voice recognition on the audio information to obtain text information; Identifying text data corresponding to the at least one job-seeking information dimension from the text information; Determine the resume fields to which the at least one job search information dimension is respectively mapped, and generate job search data based on the text data corresponding to each job search information dimension; If the job seeker does not meet the resume generation condition, returning the at least one unidentified job search information dimension corresponding to the target position category, and continuing to execute the step of generating interview questions; When the job seeker meets the resume generation conditions, the resume data of the job seeker is generated based on the resume fields respectively mapped to the multiple job search information dimensions corresponding to the target position category and the respectively corresponding job search data.
2. The method according to claim 1, characterized in that The generating of interview questions based on at least one unidentified job search information dimension corresponding to the target position category includes: Interview questions are generated using a generation model based on at least one unidentified job search information dimension corresponding to the target position category and job search data corresponding to historical interview questions.
3. The method according to claim 1, characterized in that The step of identifying text data corresponding to at least one job search information dimension from the text information includes: Based on the preset text representation modes corresponding to the multiple job-seeking information dimensions, the text data corresponding to the at least one job-seeking information dimension is identified from the text information using a text processing model.
4. The method according to claim 1, characterized in that: Also includes: When the current text data corresponding to any identified job-seeking information dimension is different from the historical text data, the resume field is updated according to the job-seeking data corresponding to the current text data.
5. The method according to claim 4, characterized in that In the case where the current text data corresponding to any identified job search information dimension is different from the historical text data, it also includes: Generate confirmation prompt information based on the current text data and the historical text data, and send the confirmation prompt information to the client for the job seeker to confirm; The updating of the resume fields according to the job search data corresponding to the current text data includes: When the job seeker confirms that the current text data is correct, the resume fields are updated according to the job-seeking data corresponding to the current text data.
6. The method according to claim 1, characterized in that Also includes: When all the multiple job-seeking information dimensions corresponding to the target position category are identified, it is determined that the job-seeking user meets the resume generation condition.
7. The method according to claim 1, characterized in that The generating the resume data of the job seeker based on the resume fields respectively mapped to the multiple job search information dimensions corresponding to the target job category and the respectively corresponding job search data comprises: Based on the resume fields respectively mapped to the multiple job-seeking information dimensions corresponding to the target position category and the respectively corresponding job-seeking data, the resume data of the job-seeking user is generated in accordance with the resume format.
8. The method according to claim 1, characterized in that Also includes: Sending the resume data to the client to be displayed in the user interface of the client; In response to the modification request, at least one job search data is modified.
9. The method according to claim 1, characterized in that: Also includes: Determine a virtual interview user corresponding to the target job category, create an interview environment, and add the virtual interview user to the interview environment; Generate an interview page and send it to the client, so that the job seeker can enter the interview environment based on the interview page; The virtual interviewer is utilized to voice-cast the interview questions to the job seeker.
10. A display method, characterized in that: include: Displaying resume generation prompt information corresponding to multiple job categories in the user interface; In response to a confirmation operation of a job seeker for any resume generation prompt information, a resume generation request is generated and sent to a server, so that the server determines a target position category in response to the resume generation request, and generates interview questions based on at least one unidentified job search information dimension corresponding to the target position category; Obtaining the interview question and displaying it in the user interface; sending the audio information triggered by the job seeker in response to the interview question to the server, so that the server can perform speech recognition on the audio information to obtain text information, identify the text data corresponding to the at least one job seeker information dimension from the text information, determine the resume fields mapped to the at least one job seeker information dimension, and generate job seek data based on the text data corresponding to each job seeker information dimension; Obtaining resume data and displaying it in the user interface; wherein, the resume data is generated by the server based on the resume fields mapped to the multiple job search information dimensions corresponding to the target position category and the corresponding job search data when the job seeker meets the resume generation conditions.
11. The method according to claim 10, characterized in that Also includes: In response to the save operation, the resume data is saved locally.
12. A computing device, characterized in that: It comprises a storage component and a processing component; the storage component stores one or more computer program instructions, the computer program instructions are called and executed by the processing component, and the processing component executes the one or more computer program instructions to implement the resume generation method as described in any one of claims 1 to 9, or the display method as described in any one of claims 10 to 11.
13. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program is executed by a computer to implement the resume generation method according to any one of claims 1 to 9, or the display method according to any one of claims 10 to 11.
14. A computer program product, characterized in that A computer program is stored, and when the computer program is executed by a computer, the resume generation method according to any one of claims 1 to 9 or the display method according to any one of claims 10 to 11 is implemented.