Position description generation method and device based on intention completion and electronic equipment

Abstract

The invention discloses a position description generation method and device based on intention completion and electronic equipment. The method comprises the steps that recruitment demand information input by a recruiter to a to-be-recruitment position is acquired; according to the recruitment demand information, obtaining multiple function key attributes corresponding to the to-be-recruitment post; according to the multiple function key attributes and a pre-constructed intention model, obtaining a target function attribute information set of the to-be-recruitment post; wherein the intention model is used for helping the recruiter to supplement the intention of the recruitment demand according to the industry information and the expectation of the job seeker; the target function attribute information set comprises a target attribute value corresponding to each function key attribute; the target attribute value is an attribute value selected by the recruiter for a plurality of attribute value options in each function key attribute according to the supplemented recruitment demand intention; and based on a preset position description prompt template, according to the recruitment demand information and the target function attribute information set, generating position description of the to-be-recruitment position.

Description

Technical Field

[0001] The present application relates to the technical field of computers and the Internet, and in particular to a method, device and electronic device for generating a job description based on intent completion. Background Art

[0002] In the recruitment process of an enterprise, whenever a job vacancy needs to be filled, the first task is to carefully write a detailed job description (JD), and then publish it accurately through major recruitment platforms. At present, recruitment platforms provide two JD construction modes to meet different needs: first, provide preset refined templates to facilitate HR to quickly fill in and publish JD; second, through HR briefly describing the core recruitment needs, using the powerful algorithm function of the platform to automatically and intelligently generate personalized JD. In this case, there are usually the following two problems: On the one hand, the problem is that HR's recruitment intention is unclear: through the current online user usage data statistical analysis, most HR usually only input very short recruitment requirements, such as: "Recruiting sales representatives, 3 years of work experience, experience in the fast-moving consumer goods industry is preferred"; the main reasons are: 1) Most HR may not be familiar with the recruitment positions; 2) HR has no experience in the use of JD intelligent generation; this results in the current generated JD not really meeting the needs of HR, and HR needs to do a lot of optimization work after the algorithm is generated. Another problem is that the interactive experience of JD generation is poor: HR inputs their recruitment requirements through text, and then the big model generates JD. If HR is not satisfied with the JD, they need to restate their recruitment requirements or manually optimize the returned results.

[0003] It can be seen that the current job description construction system cannot help users express their needs and requires HR to repeat operations many times, so HR has a poor user experience. Summary of the invention

[0004] The purpose of this application is to provide a method, device and electronic device for generating a job description based on intent completion.

[0005] The present application embodiment provides a method for generating a job description based on intent completion, including:

[0006] Obtain the recruitment demand information input by the recruiter for the recruitment position;

[0007] According to the recruitment demand information, multiple key attributes of functions corresponding to the positions to be recruited are obtained; wherein each key attribute of functions includes multiple attribute value options;

[0008] According to multiple key functional attributes and a pre-built intention model, a target functional attribute information set of the position to be recruited is obtained; wherein the intention model is used to help recruiters supplement the intention of recruitment needs according to industry information and job seekers' expectations; the target functional attribute information set includes a target attribute value corresponding to each key functional attribute; the target attribute value is the attribute value selected by the recruiter for multiple attribute value options in each key functional attribute according to the supplemented recruitment needs intention;

[0009] Based on the preset job description prompt template, the job description of the position to be recruited is generated according to the recruitment demand information and the target function attribute information set.

[0010] Furthermore, according to the recruitment demand information, multiple key attributes of functions corresponding to the positions to be recruited are obtained, including:

[0011] Estimating functions based on recruitment demand information to obtain the first functions corresponding to the positions to be recruited;

[0012] According to the function screening strategy, multiple candidate attributes of the first function are screened to obtain multiple key attributes of the function;

[0013] Save multiple functional key attributes to the target database;

[0014] According to the first function code, a query is made in the target database to obtain a plurality of function key attributes corresponding to the position to be recruited.

[0015] Furthermore, the target function attribute information set of the positions to be recruited is obtained based on the multiple key function attributes and the pre-built intention model, including:

[0016] Traverse multiple functional key attributes;

[0017] Determine whether the recruitment demand information contains the first attribute; wherein the first attribute is any one of the key attributes of the function;

[0018] If the recruitment requirement information does not contain the first attribute, a corresponding first type of question is constructed according to a preset construction rule to obtain a target attribute value corresponding to the key attribute of the function.

[0019] Furthermore, the first type of question is constructed according to the preset construction rules to obtain the target attribute value corresponding to the key attribute of the function, including:

[0020] Different question forms are constructed according to the types of key attributes of the functions; among them,

[0021] The question form includes clicking to select multiple attribute value options or filling in the target attribute value with text. The target attribute value includes at least one of the multiple options, or is customized content of the recruiter.

[0022] Furthermore, the multiple candidate attributes of the first function are screened according to the function screening strategy to obtain multiple key attributes of the function, including:

[0023] Obtain historical job description information corresponding to the first function;

[0024] Counting multiple candidate item attributes in the historical job description information corresponding to the first function to obtain a first probability of the current candidate item attribute; wherein the first probability is the number of historical job descriptions corresponding to the first function that contain the current candidate item attribute divided by the total number of historical job descriptions under the first function;

[0025] Acquire job seeker chat session data corresponding to the first function;

[0026] According to the job seeker chat session data corresponding to the first function, a second probability of the current candidate attribute is obtained; wherein the second probability is the number of chat sessions corresponding to the first function that contain the current candidate attribute divided by the total number of chat sessions under the first function;

[0027] Performing a weighted sum of the first probability and the second probability of the current candidate item attribute to obtain a score of the current candidate item attribute;

[0028] The scores of the current candidate attributes are sorted to obtain multiple key attributes of the functions.

[0029] Furthermore, the determining whether the recruitment requirement information contains the first attribute includes:

[0030] Based on the preset judgment attribute prompt template, the recruitment demand information is used as the original content of the input, the keywords in the recruitment information are extracted, and the second question is generated; wherein the second question includes the first attribute or the target attribute value corresponding to the first attribute;

[0031] Get the recruiter to respond with a "yes" or "no" to the second question.

[0032] Furthermore, the key attributes of the function include two or more of the following: industry, work system, work method, customer type, professional ability or language requirement.

[0033] The embodiment of the present application provides a device for generating a job description based on intention completion, including:

[0034] An acquisition module is used to acquire recruitment demand information input by recruiters for recruitment positions;

[0035] A key attribute module is used to obtain multiple key attributes of functions corresponding to the positions to be recruited according to the recruitment demand information; each key attribute of a function includes multiple attribute value options;

[0036] A determination module is used to obtain a target function attribute information set of a position to be recruited based on multiple function key attributes and a pre-built intention model; wherein the intention model is used to help recruiters supplement the intention of recruitment needs based on industry information and job seekers' expectations; the target function attribute information set includes a target attribute value corresponding to each function key attribute; the target attribute value is the attribute value selected by the recruiter for multiple attribute value options in each function key attribute based on the supplemented recruitment needs intention;

[0037] The generation module is used to generate the job description of the position to be recruited based on the preset job description prompt template, according to the recruitment demand information and the target function attribute information set.

[0038] An embodiment of the present application provides an electronic device, which includes a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the method described above are implemented.

[0039] An embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the steps of the method described above are implemented.

[0040] An embodiment of the present application provides a computer program product, wherein the computer program product includes computer program instructions, and when the computer program instructions are executed by a processor, the steps of the method described above are implemented.

[0041] The above technical solution of the present application has at least the following beneficial technical effects:

[0042] 1. In the embodiment of the present application, by traversing each key attribute of the function under the current function type in the intent model, it is possible to help HR complete the intention of the recruitment demand, and then output the target function attribute information set corresponding to the position to be recruited. In this way, the recruitment intention of the enterprise HR is clearer and the content is more detailed, so that the generated JD is of higher quality and more personalized, which can improve the recruitment efficiency, and can help HR complete the intention of the recruitment demand through multiple rounds of dialogue, without the need for HR to restate its recruitment needs or manually optimize the returned results, which can improve the user experience of HR.

[0043] 2. In the embodiment of the present application, based on the LLM intent model and the core label profile of the function, the intent model is used to allow recruiters to complete the recruitment needs, thereby achieving more accurate talent matching.

[0044] 3. Use multiple rounds of dialogue and a variety of selection forms to provide more friendly interactions and help recruiters generate JDs that meet the requirements to improve recruiter satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following briefly introduces the drawings in the embodiments of the present application.

[0046] Figure 1 It is a schematic diagram of the system architecture of an embodiment of the present application.

[0047] Figure 2 It is a flowchart of a method for generating a job description based on intent completion in an embodiment of the present application.

[0048] Figure 3 It is a schematic diagram of the processing process of a method for generating a job description based on intent completion in an embodiment of the present application.

[0049] Figure 4 It is a schematic diagram of the processing process of another method for generating job descriptions based on intent completion in an embodiment of the present application.

[0050] Figure 5 It is a structural block diagram of a job description generation device based on intent completion in an embodiment of the present application.

[0051] Figure 6 It is a schematic diagram of an electronic device used to implement a method for generating a job description based on intent completion in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that the purpose of providing these embodiments is to make the principles and spirit of the present application clearer and more thorough, so that those skilled in the art can better understand and implement the principles and spirit of the present application. The exemplary embodiments provided herein are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments herein, all other embodiments obtained by ordinary technicians of the art without creative work are within the scope of protection of this application.

[0053] Embodiments of the present application relate to terminal devices and / or servers. Those skilled in the art will appreciate that the embodiments of the present application may be implemented as a system, apparatus, device, method, computer-readable storage medium, or computer program product. Therefore, the present disclosure may be specifically implemented as at least one of the following forms: complete hardware, complete software, or a combination of hardware and software. According to the embodiments of the present application, the present application claims protection for a method, apparatus, electronic device, computer-readable storage medium, and computer program product for generating a job description based on intent completion. Figure 1 A schematic diagram of a system architecture of an embodiment of the present application is shown. Figure 1 As shown, the system includes a terminal device 102 and a server 104. Among them, the terminal device 102 may include at least one of the following: a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart TV, various wearable devices, an augmented reality AR device, a virtual reality VR device, etc. A client can be installed on the terminal device 102. For example, the client can be a client that specifically performs a specific function (such as an application app), or a client with multiple application applets (different functions) embedded in it, or a client logged in through a browser. The user can operate on the terminal device 102. For example, the user can open the client installed on the terminal device 102 and input instructions through the client operation, or the user can open the browser installed on the terminal device 102 and input instructions through the browser operation. After the terminal device 102 receives the instruction input by the user, the request information containing the instruction is sent to the server 104. After receiving the request information, the server 104 performs corresponding processing and then returns the processing result information to the terminal device 102. The user instruction is completed through a series of data processing and information interaction.

[0054] In this document, terms such as first, second, third, etc. are only used to distinguish one entity (or operation) from another entity (or operation), but not to require or imply any order or relationship between these entities (or operations).

[0055] The following is a brief description of the concepts and technical terms that may be involved in the embodiments of the present application.

[0056] HR: The abbreviation of Human Resource, which means human resources, for example, it refers to the recruitment specialist in a company.

[0057] JD: A "Job Description" or "Job Description Document" details the specific requirements, scope of responsibilities, required skills, education, work experience, salary range, and other relevant information for a particular position.

[0058] LLM: Large Language Model (“Large Language Model”) is a natural language processing model based on deep learning technology, especially trained using neural network technology.

[0059] Function: In the recruitment field, function is the classification of positions, such as "sales representative", "sales director", etc.

[0060] ES: ES (Elasticsearch) is a distributed, scalable, real-time search and analysis engine.

[0061] Redis: Redis (Remote Dictionary Server) is an open source, ANSI C-language, network-supported, memory-based, and persistent log-based Key-Value database.

[0062] FastText: FastText is a word vector calculation and text classification tool open sourced by Facebook AI Research in 2016.

[0063] Prompt: refers to an input method or instruction used to guide large-scale language models to perform specific outputs or tasks.

[0064] Session: In the present invention, Session represents a chat session, and there may be multiple information exchanges in one chat session.

[0065] Figure 2 A flowchart of a method for generating a job description based on intention completion according to an embodiment of the present application is shown, and the method includes the following specific steps:

[0066] S110: Obtaining recruitment demand information input by the recruiter regarding the recruitment position.

[0067] Specifically, in the embodiment of the present application, the recruiter is, for example, a recruitment specialist HR in a company. The HR can input recruitment demand information in the terminal device 102, which may include, for example, core information such as job requirements for the position and job responsibilities.

[0068] S120: According to the recruitment demand information, a plurality of key functional attributes corresponding to the positions to be recruited are obtained; wherein each key functional attribute includes a plurality of attribute value options.

[0069] Specifically, the server 104 can extract keywords from the received recruitment demand information to classify positions, thereby obtaining the functions of HR recruitment. In the embodiment of the present application, the FastText-based function estimation can be used to output the function ID and function name corresponding to the position to be recruited. Based on the function ID, the redis KV database can be queried to obtain the key attributes of the function corresponding to the current position to be recruited.

[0070] S130: Obtain a target function attribute information set of the job to be recruited based on multiple function key attributes and a pre-built intention model; wherein the intention model is used to help recruiters supplement the intention of recruitment needs based on industry information and job seekers' expectations; the target function attribute information set includes a target attribute value corresponding to each function key attribute; the target attribute value is the attribute value selected by the recruiter for multiple attribute value options in each function key attribute based on the supplemented recruitment need intention.

[0071] Specifically, the intent model is built based on the Large Scale Language Model (LLM). By training a large amount of text data, it learns the grammar, semantics and contextual information of the language, so that it can model and generate natural language text. Each key attribute of the function can be input into the pre-built intent model in turn. After being processed by the intent model, one or more responses can be generated for each key attribute of the function. The response can be a pop-up dialog window in the form of a question and answer, for example. HR can make a selection from multiple attribute value options under each key attribute of the function according to the intention or idea of ​​the recruitment needs, and combine the multiple determined attribute values ​​​​made, and finally output the target function attribute information set corresponding to the position to be recruited. In this way, the intent model mainly helps HR complete the intention completion of recruitment needs based on key attributes of the function.

[0072] S140: Based on a preset job description prompt template, a job description of the job to be recruited is generated according to the recruitment demand information and the target function attribute information set.

[0073] Among them, prompt refers to an instruction project that interacts with a large-scale language model LLM. The prompt instruction can guide the large-scale language model to generate an output result that meets the expectations, that is, the large-scale language model can generate the corresponding output according to the prompt instruction. Therefore, based on the preset job description prompt template, the recruitment demand information and the target function attribute information set are input to generate a job description extraction instruction; the large-scale language model LLM can generate a job description for the position to be recruited based on the job description extraction instruction. In the embodiment of the present application, by traversing each key attribute of the function under the current function type in the intention model, it is possible to help HR complete the intention of the recruitment demand, and then output the target function attribute information set corresponding to the position to be recruited, so that the recruitment intention of the enterprise HR is clearer and the content is more detailed, so that the generated JD is of higher quality and more personalized, which can improve the recruitment efficiency, and can help HR complete the intention of the recruitment demand through multiple rounds of dialogue, without the need for HR to restate its recruitment needs or manually optimize the returned results, which can improve the user experience of HR.

[0074] In some embodiments, step S120, obtaining multiple key attributes of functions corresponding to the positions to be recruited according to the recruitment demand information, includes the following specific steps:

[0075] S121: perform function estimation based on recruitment demand information to obtain the first function corresponding to the position to be recruited;

[0076] S122: screening multiple candidate attributes of the first function according to the function screening strategy to obtain multiple key attributes of the function;

[0077] S123: Save multiple functional key attributes to the target database;

[0078] S124: Query the target database according to the first function code to obtain multiple function key attributes corresponding to the position to be recruited.

[0079] Specifically, according to the recruitment demand information, FastText-based function estimation can be used to obtain the first function corresponding to the position to be recruited, and the function ID and function name can be output; based on the function ID, the redis KV database can be queried to obtain the key attributes of the function corresponding to the current position.

[0080] In some embodiments, step S122, screening multiple candidate attributes of the first function according to the function screening strategy to obtain multiple key attributes of the function, includes the following specific steps:

[0081] S1221: Obtain historical job description information corresponding to the first function;

[0082] S1222: Counting multiple candidate item attributes in the historical job description information corresponding to the first function to obtain a first probability of the current candidate item attribute; wherein the first probability is the number of historical job descriptions corresponding to the first function that contain the current candidate item attribute divided by the total number of historical job descriptions under the first function;

[0083] S1223: Acquire job seeker chat session data corresponding to the first function;

[0084] S1224: Obtain a second probability of the current candidate attribute based on the job seeker chat session data corresponding to the first function; wherein the second probability is the number of chat sessions corresponding to the first function that include the current candidate attribute divided by the total number of chat sessions under the first function;

[0085] S1225: Perform a weighted sum of the first probability and the second probability of the current candidate item attribute to obtain a score of the current candidate item attribute;

[0086] S1226: Sort by scores of attributes of current candidate items to obtain multiple key attributes of functions.

[0087] Specifically, historical data of the recruitment platform may be obtained, for example, historical job description information and job-seekers' concerned functional attributes; multiple candidate attributes in the historical job description information corresponding to the first function are counted, and the number of historical job descriptions under the first function that contain the current candidate attribute is divided by the total number of historical job descriptions under the first function to obtain a first probability of the current candidate attribute; the functional attributes mentioned in the job seeker's chat are counted, and the number of chat sessions under the first function that contain the current candidate attribute is divided by the total number of chat sessions under the first function to obtain a second probability of the current candidate attribute; the score of the current candidate attribute is calculated by the following formula:

[0088] Score=α*JD_RATE+β*CHAT_RATE

[0089] Where: α+β=1, α and β are weights; JD_RATE represents the first probability, that is, the probability of the current candidate attribute appearing in the historical job description information; CHAT_RATE is the second probability, that is, the probability of the job seeker mentioning the current candidate attribute in the chat session;

[0090] Sort the scores of each candidate attribute from high to low, and take the top 6-8 candidate attributes as key functional attributes. Through a comprehensive analysis of the historical job description information of different companies in different industries, the higher the frequency of candidate attributes appearing in the historical job description information, the more it meets the recruitment needs of the recruiter; the higher the frequency of candidate attributes mentioned in the job seeker's chat session, the more the candidate attribute is concerned about or expected by the job seeker; therefore, the various key functional attributes screened in the embodiment of the present application comprehensively consider the industry analysis and the expectations of the job seeker. In an exemplary embodiment, key functional attributes may include, for example: industry, work system, work method, customer type, professional ability or language requirements, etc.

[0091] In some embodiments, step S130, obtaining a target function attribute information set of the position to be recruited based on multiple function key attributes and a pre-built intention model, includes the following specific steps:

[0092] S131: Traverse multiple functional key attributes;

[0093] S132: Determine whether the recruitment demand information contains the first attribute; wherein the first attribute is any one of the key attributes of the function;

[0094] S133: If the recruitment requirement information does not include the first attribute, construct a corresponding first type of question according to a preset construction rule to obtain a target attribute value corresponding to the key attribute of the function.

[0095] Specifically, there are multiple key attributes of each function stored in the redis KV database. A question-based dialog box can be constructed for each key attribute of the function. Even if the recruitment information entered by the recruiter is brief, the corresponding questions constructed can serve as prompts for the recruiter, and then prompt the recruiter to complete the recruitment intention, so as to output the target attribute value corresponding to the key attribute of the function. When the recruiter is not satisfied with the JD generated according to the large model, there is no need for the recruiter to restate his recruitment needs, which can avoid repeated operations of the recruiter.

[0096] In some embodiments, step S133, constructing the corresponding first type of question according to the preset construction rule to obtain the target attribute value corresponding to the key attribute of the function, includes the following specific steps:

[0097] Different question forms are constructed according to the types of key attributes of the job; wherein the question form includes clicking to select multiple attribute value options or filling in the target attribute value with text, and the target attribute value includes at least one of the multiple options, or is the recruiter's customized content.

[0098] Specifically, by clicking to select an option or filling in an option with text, the recruiter can be prompted and the recruitment intention can be quickly completed.

[0099] In some embodiments, step S132, determining whether the recruitment requirement information contains the first attribute, includes the following specific steps:

[0100] S1321: Based on a preset attribute judgment prompt template, the recruitment demand information is used as the original input content, keywords in the recruitment information are extracted, and a second question is generated; wherein the second question includes the first attribute or a target attribute value corresponding to the first attribute;

[0101] S1322: Obtain the recruiter's answer of "yes" or "no" in response to the second question.

[0102] The above describes the implementation methods and advantages of the embodiments of the present application through multiple embodiments. Figure 3-Figure 4 , describes in detail the specific processing process of the embodiment of the present application.

[0103] A method for generating a job description based on intention completion in an embodiment of the present application may include the following specific steps:

[0104] S210, HR input recruitment information:

[0105] The recruitment information input by HR mainly includes core information such as job requirements and job responsibilities, which may include job positions, years of experience requirements, educational requirements, etc.

[0106] For example, the recruitment information entered by HR is as follows: Recruiting a salesperson who will be mainly responsible for product sales in East China. Applicants are expected to have experience in pharmaceutical sales, more than 3 years of work experience, and be able to adapt to short-term business trips.

[0107] S220, Functional Estimates:

[0108] Classify the recruitment information input by HR and obtain the functions of HR recruitment. Function classification is one of the core functions of the recruitment platform. The recruitment platform can use FastText-based function estimation to output <function ID, function>.

[0109] For example, according to the recruitment information input by HR in step S210, after FastText job estimation, <Job ID: 0310, Job: Sales Representative> may be output.

[0110] S230. Determine the key attributes of the function:

[0111] Based on the function ID, the redis KV database is queried to obtain the function key attributes corresponding to the current position function. The function key attributes can also be the function core attributes, which can be selected from a large number of function attributes. For example, the multiple function key attributes of the function "sales representative" are as follows:

[0112] 1) Industry priority: automobile, insurance, medical, etc.;

[0113] 2) Working system: one day off per week, two days off per week, one day off per week and two days off per week;

[0114] 3) Working style: frequent business trips, office work, and overseas assignments;

[0115] 4) Language requirements: English, Japanese;

[0116] 5) Customer type: T0C, TOB, TOG;

[0117] 6) Professional abilities: customer development, business negotiation, marketing, office software, data analysis.

[0118] Among them, the embodiment of the present application takes into account the job attributes involved in the JD of the recruitment platform history and the job attributes that job seekers are concerned about. The job attributes can be scored from these two aspects, and linear weighting is used to obtain the corresponding total score. The total score is sorted from high to low, and the top N job attributes are selected. For example, the first 6-8 job attributes can be selected as the key job attributes. If too many key job attributes are selected, it may affect the user experience.

[0119] S240. Completing the intention of recruitment needs through pre-built intention models:

[0120] The intent model mainly helps HR complete the intention of recruitment needs based on the core attributes of the function. In the intent model, each key attribute of the current function is traversed to complete the intention of recruitment needs, as follows:

[0121] S241, determine whether the attribute value of the key attribute of the job function is already included in the recruitment information input by HR. Specifically, the large-scale language model LLM may be called to determine whether the key attribute information of the job function is included. The preset attribute judgment prompt template is, for example, as shown below:

[0122] You are a recruitment expert in the field of human resources. Please complete the following task to determine whether the HR recruitment description contains content related to the corresponding attributes and attribute values. The following is an example:

[0123] {

[0124] ###

[0125] [input]

[0126] "Recruiting a salesperson, mainly responsible for product sales in East China, hoping to have experience in pharmaceutical sales, more than 3 years of work experience, and be able to adapt to short-term business trips"

[0127] Please determine whether the job description contains the following attributes or attribute values: "Industry, Medicine"

[0128] [output]

[0129] Include

[0130] ###

[0131] Require:

[0132] Please answer directly, "includes", "does not include", "unknown", do not include other content

[0133] Please judge the following tasks

[0134]

input

[0135] <input_jd> ”

[0136] Please determine whether the job description contains the following attributes or attribute values: <attr>

[0137] [output]

[0138] }

[0139] in"<input_jd> "and" <attr>" is a variable, "<input_jd> " is the recruitment information (original content) entered by the recruiter (HR)," <attr>" is the attribute that needs to be judged.

[0140] When the input recruitment information contains the corresponding attribute or attribute value, the next attribute under the function is judged, and each key attribute of the function under the current function is traversed in turn.

[0141] S242. Prompt HR to complete recruitment intention: If the input recruitment information does not contain the corresponding attribute or attribute value, the HR is prompted to complete the recruitment intention. Different question forms are formed according to the attribute type. Currently, multiple forms are supported: multiple choice, single choice, and custom. The following is an example of a prompt:

[0142] What is the work system of this position? [Multiple choice]

[0143] "Single day off" "Double day off" "Single day off and double day off"

[0144] S243. The final result is obtained and saved in the intent profile. The format of the intent profile is as follows:

[0145] Customer type: T0G;

[0146] Working system: two days off per week;

[0147] Working style: Back office;

[0148] …….

[0149] S250, generating a job description prompt based on the recruitment information input by HR and the completed functional attribute information.

[0150] S260: Call the large-scale language model LLM to generate JD.

[0151] Corresponding to the method embodiment of the present application, the present application also provides a job description generation device based on intention completion, such as Figure 5 As shown, specifically, it may include:

[0152] An acquisition module 510 is used to acquire recruitment demand information input by the recruiter for the recruitment position;

[0153] The key attribute module 520 is used to obtain multiple key attributes of functions corresponding to the positions to be recruited according to the recruitment demand information; wherein each key attribute of a function includes multiple attribute value options;

[0154] The determination module 530 is used to obtain a target function attribute information set of the to-be-recruited position according to a plurality of function key attributes and a pre-built intention model; wherein the intention model is used to help the recruiter supplement the intention of the recruitment demand according to the industry information and the job seeker's expectations; the target function attribute information set includes a target attribute value corresponding to each function key attribute; the target attribute value is the attribute value selected by the recruiter for the multiple attribute value options in each function key attribute according to the supplemented recruitment demand intention;

[0155] The generation module 540 is used to generate a job description for the position to be recruited based on a preset job description prompt template, recruitment demand information and a target function attribute information set.

[0156] The electronic device in the embodiment of the present application may be a user terminal device, a server, other computing devices, or a cloud server. Figure 6 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application is shown. The electronic device may include a processor 601 and a memory 602 storing computer program instructions. When the processor 601 executes the computer program instructions, the process or function of any of the above-mentioned embodiments of the method is implemented.

[0157] Specifically, the processor 601 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application. The memory 602 may include a large-capacity memory for data or instructions. For example, the memory 602 may be at least one of the following: a hard disk drive (HDD), a read-only memory (ROM), a random access memory (RAM), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, a universal serial bus (USB) drive or other physical / tangible memory storage device. For another example, the memory 602 may include a removable or non-removable (or fixed) medium. For another example, the memory 602 may be inside or outside the integrated gateway disaster recovery device. The memory 602 may be a non-volatile solid-state memory. In other words, the memory 602 usually includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with computer-executable instructions, and when the software is executed (such as executed by one or more processors), the operation described in the method of the embodiment of the present application can be performed. The processor 601 implements the process or function of any method in the above embodiments by reading and executing the computer program instructions stored in the memory 602.

[0158] In one example, Figure 6 The electronic device shown may also include a communication interface 603 and a bus 610. Among them, the processor 601, the memory 602, and the communication interface 603 are connected through the bus 610 and complete the communication between each other. The communication interface 603 is mainly used to realize the communication between each module, device, unit and / or device in the embodiment of the present application. The bus 610 includes hardware, software or both, and can couple the components of the online data traffic billing device to each other. For example, the bus may include at least one of the following: an accelerated graphics port (AGP) or other graphics bus, an enhanced industrial standard architecture (EISA) bus, a front-end bus (FSB), a hypertransport (HT) interconnect, an industrial standard architecture (ISA) bus, an infinite bandwidth interconnect, a low pin count (LPC) bus, a memory bus, a micro channel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus or other suitable buses. The bus 610 may include one or more buses. Although the embodiments of the present application describe or illustrate a specific bus, the embodiments of the present application may consider any suitable bus or interconnection method.

[0159] In combination with the method in the above embodiments, an embodiment of the present application also provides a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the process or function of any method in the above embodiments is implemented.

[0160] In addition, an embodiment of the present application further provides a computer program product, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the process or function of any one of the methods in the above embodiments is implemented.

[0161] The above exemplarily describes the flowcharts and / or block diagrams of the methods, devices, systems and computer program products of the embodiments of the present application, and describes the relevant various aspects. It should be understood that each box or combination thereof in the flowchart and / or block diagram can be implemented by computer program instructions, or by dedicated hardware that performs a specified function or action, or by a combination of dedicated hardware and computer instructions. For example, these computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to form a machine that enables these instructions executed by such a processor to enable the implementation of the functions / actions specified in each box or combination thereof in the flowchart and / or block diagram. Such a processor can be a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.

[0162] The functional blocks shown in the structured block diagram of the embodiment of the present application can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc.; when implemented in software, it is a program or code segment used to perform the required task. The program or code segment can be stored in a memory, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0163] It should be noted that the present application is not limited to the specific configurations and processes described above or shown in the figures. The above is only a specific implementation mode of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the described system, device, module or unit can refer to the corresponding process in the method embodiment without further description. It should be understood that the scope of protection of the present application is not limited to this. Any technician familiar with the technical field can think of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and these modifications or substitutions should be included in the scope of protection of the present application.< / attr> < / attr> < / attr>

Claims

1. A method for generating job descriptions based on intention completion, characterized in that: include: Obtain the recruitment demand information input by the recruiter for the recruitment position; According to the recruitment demand information, multiple key attributes of functions corresponding to the positions to be recruited are obtained; wherein each key attribute of functions includes multiple attribute value options; According to multiple key functional attributes and a pre-built intention model, a target functional attribute information set of the position to be recruited is obtained; wherein the intention model is used to help recruiters supplement the intention of recruitment needs according to industry information and job seekers' expectations; the target functional attribute information set includes a target attribute value corresponding to each key functional attribute; the target attribute value is the attribute value selected by the recruiter for multiple attribute value options in each key functional attribute according to the supplemented recruitment needs intention; Based on the preset job description prompt template, the job description of the position to be recruited is generated according to the recruitment demand information and the target function attribute information set.

2. The method for generating a job description according to claim 1, characterized in that: According to the recruitment demand information, multiple key attributes of functions corresponding to the positions to be recruited are obtained, including: Estimating functions based on recruitment demand information to obtain the first functions corresponding to the positions to be recruited; According to the function screening strategy, multiple candidate attributes of the first function are screened to obtain multiple key attributes of the function; Save multiple functional key attributes to the target database; According to the first function code, a query is made in the target database to obtain a plurality of function key attributes corresponding to the position to be recruited.

3. The method for generating a job description according to claim 1, characterized in that: According to the multiple key attributes of the functions and the pre-built intention model, a target function attribute information set of the positions to be recruited is obtained, including: Traverse multiple functional key attributes; Determine whether the recruitment demand information contains the first attribute; wherein the first attribute is any one of the key attributes of the function; If the recruitment requirement information does not contain the first attribute, a corresponding first type of question is constructed according to a preset construction rule to obtain a target attribute value corresponding to the key attribute of the function.

4. The method for generating a job description according to claim 3, characterized in that: The first type of question is constructed according to the preset construction rules to obtain the target attribute value corresponding to the key attribute of the function, including: Different question forms are constructed according to the types of key attributes of the functions; among them, The question form includes clicking to select multiple attribute value options or filling in the target attribute value with text. The target attribute value includes at least one of the multiple options, or is customized content of the recruiter.

5. The method for generating a job description according to claim 2, characterized in that: The multiple candidate attributes of the first function are screened according to the function screening strategy to obtain multiple key attributes of the function, including: Obtain historical job description information corresponding to the first function; Counting multiple candidate item attributes in the historical job description information corresponding to the first function to obtain a first probability of the current candidate item attribute; wherein the first probability is the number of historical job descriptions corresponding to the first function that contain the current candidate item attribute divided by the total number of historical job descriptions under the first function; Acquire job seeker chat session data corresponding to the first function; According to the job seeker chat session data corresponding to the first function, a second probability of the current candidate attribute is obtained; wherein the second probability is the number of chat sessions corresponding to the first function that contain the current candidate attribute divided by the total number of chat sessions under the first function; Performing a weighted sum of the first probability and the second probability of the current candidate item attribute to obtain a score of the current candidate item attribute; The scores of the current candidate attributes are sorted to obtain multiple key attributes of the functions.

6. The method for generating a job description according to claim 3, characterized in that: The step of judging whether the recruitment demand information contains the first attribute includes: Based on the preset judgment attribute prompt template, the recruitment demand information is used as the original input content, keywords in the recruitment demand information are extracted, and the second type of question is generated; wherein the second type of question includes the first attribute or the target attribute value corresponding to the first attribute; Get the recruiter's "yes" or "no" response to the second question.

7. The method for generating a job description according to any one of claims 1 to 6, characterized in that: The key attributes of the function include two or more of the following: Industry, work system, working methods, client types, professional capabilities or language requirements.

8. A device for generating job description based on intention completion, characterized in that: include: An acquisition module is used to acquire recruitment demand information input by recruiters for recruitment positions; A key attribute module is used to obtain multiple key attributes of functions corresponding to the positions to be recruited according to the recruitment demand information; each key attribute of a function includes multiple attribute value options; A determination module is used to obtain a target function attribute information set of a position to be recruited based on multiple function key attributes and a pre-built intention model; wherein the intention model is used to help recruiters supplement the intention of recruitment needs based on industry information and job seekers' expectations; the target function attribute information set includes a target attribute value corresponding to each function key attribute; the target attribute value is the attribute value selected by the recruiter for multiple attribute value options in each function key attribute based on the supplemented recruitment needs intention; The generation module is used to generate the job description of the position to be recruited based on the preset job description prompt template, according to the recruitment demand information and the target function attribute information set.

9. An electronic device, characterized in that: The electronic device comprises: a processor and a memory storing computer program instructions; when the electronic device executes the computer program instructions, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images