Position description optimization method and device and electronic equipment

Abstract

The invention discloses a position description optimization method and apparatus, and an electronic device. The method comprises the steps of obtaining recruitment demand information input by a recruiter to a to-be-recruitment position; generating position description to be optimized according to the recruitment demand information; wherein the position description to be optimized comprises a plurality of label attributes and attribute values; querying a target database according to the recruitment demand information to obtain a function portrait attribute and an attribute value corresponding to the to-be-recruitment post; according to each label attribute value and the corresponding function portrait attribute value, constructing an optimization prompt item to obtain a target function attribute information set; wherein the optimization prompt item is used for prompting a recruiter whether the label attribute value needs to be modified or not under the condition that the label attribute value is inconsistent with the corresponding function portrait attribute value, so as to obtain the modified label attribute value of the recruiter; and based on a preset position description prompt template, according to the recruitment demand information and the target function attribute information set, generating an optimized 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 optimizing job descriptions. Background Art

[0002] In the corporate recruitment process, whenever a job vacancy needs to be filled, the first task is to carefully write a detailed job description (Job Description, hereinafter referred to as JD), and then accurately publish it through major recruitment platforms. The quality of the written JD will significantly affect the recruitment effect, so various recruitment platforms have begun to pay attention to the quality of JD. At present, in order to improve the quality of JD, a JD quality diagnosis function is provided, but it only focuses on text issues such as whether key modules in JD are missing and whether the expression is smooth, and does not provide technical means to optimize JD; and for the existing JD and the JD intelligently generated by the users of the recruitment platform through the large model, there is no method to optimize JD.

[0003] Based on this, a method to optimize job descriptions is urgently needed. Summary of the invention

[0004] The purpose of this application is to provide a method, device and electronic device for optimizing job descriptions.

[0005] The present application embodiment provides a method for optimizing job descriptions, including:

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

[0007] Generate a job description to be optimized according to the recruitment demand information; wherein the job description to be optimized includes multiple tag attributes and attribute values;

[0008] Query the target database according to the recruitment demand information to obtain the functional profile attributes and attribute values ​​corresponding to the positions to be recruited;

[0009] According to each label attribute value and the corresponding functional profile attribute value, an optimization prompt item is constructed to obtain a target functional attribute information set; wherein the optimization prompt item is used to prompt the recruiter whether the label attribute value needs to be modified when the label attribute value and the corresponding functional profile attribute value are inconsistent, so as to obtain the label attribute value modified by the recruiter; the target functional attribute information set includes the modified label attribute value;

[0010] Based on the preset job description prompt template, an optimized job description for the position to be recruited is generated according to the recruitment demand information and the target function attribute information set.

[0011] Furthermore, the querying of the target database according to the recruitment demand information to obtain the functional profile attributes and attribute values ​​corresponding to the positions to be recruited includes:

[0012] Estimating functions based on recruitment demand information to obtain the first functions corresponding to the positions to be recruited;

[0013] Obtain multiple functional portrait attributes under the first function;

[0014] According to the multiple functional portrait attributes under the first function and the set target area, a job seeker portrait attribute information set is obtained; wherein the job seeker portrait attribute information set includes a job seeker portrait attribute value corresponding to each functional portrait attribute;

[0015] According to the multiple functional portrait attributes under the first function and the set target area, a job portrait attribute information set is obtained; wherein the job portrait attribute information set includes a job portrait attribute value corresponding to each functional portrait attribute;

[0016] Compare the job seeker profile attribute value corresponding to each functional profile attribute with the job profile attribute value to obtain the attribute value corresponding to each functional profile attribute;

[0017] The attribute value corresponding to each functional profile attribute is stored in the target database.

[0018] Furthermore, the method of obtaining a job seeker portrait attribute information set based on multiple functional portrait attributes under the first function and the set target area includes:

[0019] Obtain the first-category statistical attribute values ​​and the corresponding number of resumes of all job seekers under each functional profile attribute in the set target area;

[0020] According to the number of resumes corresponding to each first-category statistical attribute value and the total number of resumes of the first-category statistical attribute value, calculate the proportion of the number of resumes of each first-category statistical attribute value;

[0021] Sort the percentage of resumes for each first-category statistical attribute value, and take the statistical attribute value corresponding to the maximum percentage of resumes as the job seeker portrait attribute value.

[0022] Furthermore, the job portrait attribute information set is obtained based on the multiple function portrait attributes and the set target area under the first function, including:

[0023] Obtain the second-category statistical attribute values ​​of all historical job descriptions under each functional profile attribute in the set target area and the corresponding number of historical job descriptions;

[0024] Calculate the proportion of descriptions for each second-category statistical attribute value based on the number of historical job descriptions corresponding to each second-category statistical attribute value and the total number of historical job descriptions for the second-category statistical attribute value;

[0025] Sort the description share ratio of each second-category statistical attribute value, and take the statistical attribute value corresponding to the maximum description share ratio as the job profile attribute value.

[0026] Furthermore, the optimization prompt items are constructed according to each tag attribute value and the corresponding function profile attribute value to obtain a target function attribute information set, including:

[0027] Traverse each tag attribute and attribute value in the job description to be optimized;

[0028] Compare the current label attribute value with the corresponding functional portrait attribute value, and if there is a difference between the current label attribute value and the corresponding functional portrait attribute value, generate an optimization prompt item; wherein the current label attribute value belongs to a numerical type or a text option;

[0029] According to the generated optimization prompt items, the recruiter makes a choice as to whether to modify the label attribute value according to the recruitment intention, so as to obtain the target function attribute information set.

[0030] Furthermore, the current label attribute value is compared with the corresponding functional portrait attribute value, and if there is a difference between the current label attribute value and the corresponding functional portrait attribute value, an optimization prompt item is generated, including:

[0031] If the current tag attribute value is a numeric value, and the difference between the current tag attribute value and the corresponding functional profile attribute value is higher than the set threshold, an optimization prompt item is generated; wherein,

[0032] The threshold is set to 10%-20% of the corresponding functional profile attribute value;

[0033] If the job profile attribute value is derived from the job seeker profile attribute value, the generated optimization prompt item includes prompt content derived from the job seeker profile attribute and the attribute value;

[0034] If the function portrait attribute value is derived from the position portrait attribute value, the generated optimization prompt item includes the prompt content derived from the position portrait attribute and attribute value.

[0035] Furthermore, the current label attribute value is compared with the corresponding functional portrait attribute value, and if there is a difference between the current label attribute value and the corresponding functional portrait attribute value, an optimization prompt item is generated, which also includes:

[0036] If the current label attribute value belongs to a text option, and the current label attribute value is inconsistent with the corresponding functional portrait attribute value, an optimization prompt item is generated; wherein,

[0037] If the job profile attribute value is derived from the job seeker profile attribute value, the generated optimization prompt item includes prompt content derived from the job seeker profile attribute and the attribute value;

[0038] If the function portrait attribute value is derived from the position portrait attribute value, the generated optimization prompt item includes the prompt content derived from the position portrait attribute and attribute value.

[0039] The present application embodiment provides a device for optimizing job descriptions, including:

[0040] An acquisition module is used to acquire recruitment demand information input by recruiters for recruitment positions;

[0041] A first generating module, which is used to generate a job description to be optimized according to the recruitment demand information; wherein the job description to be optimized includes a plurality of tag attributes and attribute values;

[0042] A query module is used to query the target database according to the recruitment demand information to obtain the functional profile attributes and attribute values ​​corresponding to the positions to be recruited;

[0043] A construction module, which is used to construct an optimization prompt item according to each label attribute value and the corresponding functional profile attribute value to obtain a target functional attribute information set; wherein the optimization prompt item is used to prompt the recruiter whether the label attribute value needs to be modified according to the difference between the label attribute value and the corresponding functional profile attribute value; the target functional attribute information set includes the modified label attribute value;

[0044] The second generation module is used to generate an optimized 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] The above technical solution of the present application has the following beneficial technical effects:

[0049] In an embodiment of the present application, by traversing the label attributes in the job description to be optimized, each label attribute value is compared with the corresponding functional portrait attribute value. If the attribute values ​​of the two are inconsistent, an optimization prompt item can be constructed to prompt the recruiter whether it is necessary to modify the label attribute value, so that a target functional attribute information set corresponding to the job to be recruited can be obtained, and an optimized job description for the job to be recruited can be further generated; this can help enterprise HR quickly optimize JD and generate high-quality JD that is more in line with industry standards. The generated JD is of higher quality, which can improve recruitment efficiency and enhance the user experience of HR. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] 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.

[0051] Figure 1 It is a schematic diagram of the system architecture of an embodiment of the present application.

[0052] Figure 2 It is a flowchart of a method for optimizing job descriptions in an embodiment of the present application.

[0053] Figure 3 It is a schematic diagram of a processing process for obtaining functional portrait attributes and attribute values ​​in an embodiment of the present application.

[0054] Figure 4 It is a schematic diagram of the processing process of a method for optimizing job descriptions in an embodiment of the present application.

[0055] Figure 5 It is a structural block diagram of a device for optimizing job descriptions according to an embodiment of the present application.

[0056] Figure 6 It is a schematic diagram of an electronic device used to implement a method for optimizing job descriptions in an embodiment of the present application. DETAILED DESCRIPTION

[0057] 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.

[0058] 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 requests protection for a method, apparatus, electronic device, computer-readable storage medium, and computer program product for optimizing job descriptions. 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.

[0059] 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).

[0060] The following is a brief description of the concepts and technical terms that may be involved in the embodiments of the present application.

[0061] HR: The abbreviation of Human Resource, which means human resources, for example, it refers to the recruitment specialist in a company.

[0062] 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.

[0063] LLM: Large Language Model (“Large Language Model”) is a natural language processing model based on deep learning technology, especially trained using neural network technology.

[0064] Function: In the recruitment field, function is the classification of positions, such as "sales representative", "sales director", etc.

[0065] Redis: Redis (Remote Dictionary Server) is an open source, ANSI C-language, network-supported, memory-based, and persistent log-based Key-Value database.

[0066] Prompt: refers to an input method or instruction used to guide large-scale language models to perform specific outputs or tasks.

[0067] Figure 2 A flow chart of a method for optimizing job descriptions according to an embodiment of the present application is shown, and the method includes the following specific steps:

[0068] S110: Obtaining recruitment demand information input by the recruiter regarding the recruitment position.

[0069] 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, information such as job title, job requirements, job responsibilities, and recruitment city.

[0070] S120: Generate a job description to be optimized according to the recruitment demand information; wherein the job description to be optimized includes a plurality of tag attributes and attribute values.

[0071] Specifically, according to the recruitment demand information, the job description to be optimized can be generated based on the large-scale language model LLM; the job description to be optimized may, for example, include two or more of the following label attributes: age, education level, years of work experience, expected salary and benefits, etc.; among which, for example, the attribute value of age is a numeric type, and the attribute value of education level is a text option, such as "junior college, undergraduate, graduate or doctoral degree, etc."

[0072] S130: Query the target database according to the recruitment demand information to obtain the functional portrait attributes and attribute values ​​corresponding to the positions to be recruited.

[0073] Specifically, the server 104 can perform keyword extraction on the received recruitment demand information to classify the positions, thereby obtaining the functions corresponding to the positions to be recruited. In the embodiment of the present application, a function estimation based on FastText can be adopted, and the function ID and function name corresponding to the position to be recruited can be output. It can be understood by those skilled in the art that the functions and function IDs corresponding to the positions to be recruited can also be directly input by the recruiter. By querying the redis KV database based on the function ID, a set of function portrait attributes (or function attributes) and attribute values ​​corresponding to the current position to be recruited can be obtained.

[0074] S140: Construct optimization prompt items according to each label attribute value and the corresponding functional portrait attribute value to obtain a target functional attribute information set; wherein, the optimization prompt items are used to prompt the recruiter whether the label attribute value needs to be modified when the label attribute value is inconsistent with the corresponding functional portrait attribute value, so as to obtain the label attribute value modified by the recruiter; the target functional attribute information set includes the modified label attribute value.

[0075] Specifically, when the label attribute and the functional portrait attribute are the same, the label attribute value and the functional portrait attribute value are compared. If they are inconsistent, an optimization prompt item is constructed. For example, when the attribute characteristics are both age, the age settings of the two are compared. When the attribute value of age in the job description to be optimized is 30 years old, and the attribute value of age in the functional portrait attribute obtained by querying the redis KV database is 35 years old, an optimization prompt item can be constructed. The optimization prompt item can be a pop-up dialog window in the form of a question and answer. HR can choose and confirm whether to modify the attribute value of each label attribute based on the intention or idea of ​​the recruitment needs, and collect the modified label attribute values. Finally, the target functional attribute information set corresponding to the position to be recruited can be output.

[0076] S150: Based on a preset job description prompt template, an optimized job description of the job to be recruited is generated according to the recruitment demand information and the target function attribute information set.

[0077] 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 expectation, 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 functional attribute information set are input to generate a job description extraction instruction; the large-scale language model LLM can generate an optimized job description for the job to be recruited based on the job description extraction instruction. In the embodiment of the present application, by traversing the label attributes in the job description to be optimized, each label attribute value is compared with the corresponding functional portrait attribute value. If the attribute values ​​of the two are inconsistent, an optimization prompt item can be constructed to prompt the recruiter whether it is necessary to modify the label attribute value, so that the target functional attribute information set corresponding to the job to be recruited can be obtained, and the optimized job description of the job to be recruited can be further generated; this can help enterprise HR quickly optimize JD and generate high-quality JD that is more in line with industry standards. The generated JD is of higher quality, which can improve recruitment efficiency and enhance the user experience of HR.

[0078] In some embodiments, step S130, querying the target database according to the recruitment demand information to obtain the function profile attributes and attribute values ​​corresponding to the position to be recruited, may include the following specific steps:

[0079] S131: perform function estimation based on recruitment demand information to obtain the first function corresponding to the position to be recruited;

[0080] S132: Obtain multiple functional portrait attributes under the first function;

[0081] S133: obtaining a job seeker portrait attribute information set according to the multiple functional portrait attributes under the first function and the set target area; wherein the job seeker portrait attribute information set includes a job seeker portrait attribute value corresponding to each functional portrait attribute;

[0082] S134: obtaining a job portrait attribute information set according to the multiple function portrait attributes under the first function and the set target area; wherein the job portrait attribute information set includes a job portrait attribute value corresponding to each function portrait attribute;

[0083] S135: comparing the job seeker portrait attribute value corresponding to each functional portrait attribute with the job profile attribute value to obtain the attribute value corresponding to each functional portrait attribute;

[0084] S136: Store the attribute value corresponding to each functional portrait attribute in the target database.

[0085] Specifically, according to the recruitment demand information, the 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, redis is queried KV database can obtain the functional portrait attributes corresponding to the current position; the set target area can be divided according to the city levels of large cities, megacities, municipalities, etc. in my country, and can also be subdivided by adding second- and third-tier cities to obtain more subdivided areas and accurate employment information. Specific examples can be Shanghai, Beijing, Chengdu, Zhengzhou and other cities. The portrait attribute values ​​of job seekers in a certain urban area are constructed, which can fully reflect the needs of job seekers from multiple dimensions; the job portrait attribute values ​​are constructed based on the information of historical job descriptions published in a certain urban area, which can reflect the recruitment needs of corporate HR for the position; when the functional portrait attribute characteristics are the same, the corresponding job seeker portrait attribute values ​​are compared with the job portrait attribute values, and the attribute values ​​of the two with relatively lower recruitment requirements can be used as the attribute values ​​corresponding to the functional portrait attributes, so that more job seekers can meet the recruitment requirements, and recruiters can receive resumes from more job seekers, and then recruiters can screen out talents that meet the development of the enterprise to improve recruitment efficiency; it can be seen that by comparing the job portrait attribute values ​​and the job seeker portrait attribute values ​​based on big data statistics, JD optimization can be promoted based on the supply and demand relationship.

[0086] In some embodiments, step S133, obtaining a job seeker portrait attribute information set according to multiple functional portrait attributes under the first function and the set target area, may include the following specific steps:

[0087] S1331: Obtain the first category statistical attribute values ​​and the corresponding number of resumes of all job seekers under each functional profile attribute in the set target area;

[0088] S1332: Calculate the percentage of the number of resumes for each first-category statistical attribute value based on the number of resumes corresponding to each first-category statistical attribute value and the total number of resumes for the first-category statistical attribute value;

[0089] S1333: Sort the percentage of the number of resumes for each first-category statistical attribute value, and take the statistical attribute value corresponding to the maximum percentage of the number of resumes as the job seeker portrait attribute value.

[0090] Specifically, a cluster analysis is conducted on job seekers under the functional classification corresponding to the recruitment positions in a certain urban area. Job seekers can submit multiple resumes to positions in different companies during the job search process. After the company HR distributes the recruitment information, it can receive multiple resumes submitted by different job seekers. By counting the number of resumes that have been submitted to the position on the recruitment platform, the demand status of job seekers can be reflected. For example, when the attribute feature of the functional portrait is "age", by counting the resume data submitted by different job seekers, it can be obtained that job seekers of different ages are competing for the same position. Therefore, by statistically analyzing the distribution of job seekers in each age group, the proportion of resumes of job seekers in each age group is calculated, and the age group corresponding to the maximum proportion of resumes is taken as the job seeker portrait attribute value.

[0091] In some embodiments, step S134, obtaining a set of job profile attribute information according to multiple job profile attributes and a set target area under the first job, may include the following specific steps:

[0092] S1341: Obtain the second type statistical attribute values ​​of all historical job descriptions under each functional profile attribute in the set target area and the corresponding number of historical job descriptions;

[0093] S1342: Calculate the proportion of the number of descriptions of each second-category statistical attribute value according to the number of historical job descriptions corresponding to each second-category statistical attribute value and the total number of historical job descriptions of the second-category statistical attribute value;

[0094] S1343: Sort the description share ratios of each second-category statistical attribute value, and take the statistical attribute value corresponding to the maximum description share ratio as the job profile attribute value.

[0095] Specifically, cluster analysis of all historical job descriptions that have been posted by corporate HRs in a certain city can reflect the recruitment needs of corporate HRs for the position. For example, when the attribute feature of the functional profile is "age", by counting the historical job description information posted by HRs of different companies, the requirements of most corporate HRs for "age" can be obtained. Therefore, by counting the distribution of job requirements for each age group, the proportion of historical job descriptions for each age group is calculated and sorted, and the age group corresponding to the maximum proportion of descriptions is taken as the job profile attribute value.

[0096] In some embodiments, step S130, constructing optimization prompt items according to each tag attribute value and the corresponding function profile attribute value to obtain a target function attribute information set, may include the following specific steps:

[0097] S131: traverse each tag attribute and attribute value in the job description to be optimized;

[0098] S132: comparing the current label attribute value with the corresponding functional portrait attribute value, and generating an optimization prompt item if there is a difference between the current label attribute value and the corresponding functional portrait attribute value; wherein the current label attribute value is a numerical value or a text option;

[0099] S133: Based on the generated optimization prompt items, the recruiter makes a choice as to whether to modify the label attribute value according to the recruitment intention, so as to obtain a target function attribute information set.

[0100] Specifically, when corporate HR releases recruitment information for pending positions, in addition to considering the company's own development, they often do not do much research on the market employment situation and job seekers' needs. The situation where the submitted resumes received after the recruitment information is released are not ideal is usually because each label attribute value in the published job description is not properly set, and the requirements may be set too high without the recruiter's knowledge, resulting in too few resumes received, making it difficult to screen suitable talents; therefore, by comparing each label attribute value in the optimized job description with the corresponding functional portrait attribute value, when there is a difference between the two, an optimization prompt item is generated; based on the generated optimization prompt item, the recruiter makes a choice whether to modify the label attribute value according to the recruitment intention to obtain the target functional attribute information set, so that the recruiter can modify the label attribute value in a targeted manner, thereby generating an optimized JD and improving recruitment efficiency; and it can help recruiters quickly optimize the JD and generate high-quality JDs that are more in line with industry standards.

[0101] In some embodiments, step S132, comparing the current tag attribute value with the corresponding functional portrait attribute value, and if there is a difference between the current tag attribute value and the corresponding functional portrait attribute value, generating an optimization prompt item, may include the following specific steps:

[0102] S1321: if the current tag attribute value is of numerical type, and it is determined that the difference between the current tag attribute value and the corresponding functional profile attribute value is higher than a set threshold, then an optimization prompt item is generated; wherein the set threshold is 10%-20% of the corresponding functional profile attribute value;

[0103] If the job profile attribute value is derived from the job seeker profile attribute value, the generated optimization prompt item includes prompt content derived from the job seeker profile attribute and the attribute value;

[0104] If the function portrait attribute value is derived from the position portrait attribute value, the generated optimization prompt item includes the prompt content derived from the position portrait attribute and attribute value.

[0105] Specifically, if the current label attribute value is of numerical type, by comparing the current label attribute value with the corresponding functional portrait attribute value, when there is a difference between the two, and comparing the difference with the set threshold, if the difference is higher than the set threshold, an optimization prompt item is generated; by setting a threshold as a quantitative indicator to compare the difference, it is easier for recruiters to judge and confirm whether the current label attribute value needs to be modified; for example, when the attribute characteristics are all age, the threshold is set to 10% of the corresponding functional portrait attribute value. If the current label attribute value is 30 years old, the attribute value of age in the functional portrait attribute obtained by querying the redis KV database is 35 years old. The difference between the two is 5 years old and is higher than the set threshold, then an optimization prompt item can be constructed; accordingly, displaying the source of the functional portrait attribute value in the prompt is conducive to recruiters to judge and confirm whether the current label attribute value needs to be modified.

[0106] In some embodiments, step S132, comparing the current tag attribute value with the corresponding functional portrait attribute value, and generating an optimization prompt item if there is a difference between the current tag attribute value and the corresponding functional portrait attribute value, also includes the following specific steps:

[0107] S1322: If the current label attribute value belongs to a text option, and the current label attribute value is inconsistent with the corresponding functional profile attribute value, then an optimization prompt item is generated; wherein,

[0108] If the job profile attribute value is derived from the job seeker profile attribute value, the generated optimization prompt item includes prompt content derived from the job seeker profile attribute and the attribute value;

[0109] If the function portrait attribute value is derived from the position portrait attribute value, the generated optimization prompt item includes the prompt content derived from the position portrait attribute and attribute value.

[0110] Specifically, if the current label attribute value belongs to a text option, for example, when the attribute characteristics are all "educational qualifications", if the current label attribute value is "graduate student" and the functional portrait attribute value is "undergraduate degree", an optimization prompt item is generated; accordingly, the source of the functional portrait attribute value is displayed in the prompt, which is helpful for recruiters to judge and confirm whether the current label attribute value needs to be modified.

[0111] The above describes the implementation methods and advantages of the embodiments of the present application through multiple embodiments. The following describes the specific processing process of the embodiments of the present application in detail with reference to specific examples.

[0112] refer to Figure 3 and Figure 4 A method for optimizing job descriptions in an embodiment of the present application may include the following specific steps:

[0113] S210, Functional Profile Attribute Construction

[0114] Functional profile attributes can be constructed offline, based on the city where the job is located and the functional classification of the job. Applicant profile attributes and job profile attributes can be constructed from the perspectives of job seekers and job requirements. The construction process of applicant profile attributes and job profile attributes can be set to be consistent. The following takes the construction of applicant profile attributes as an example to illustrate:

[0115] S211. Obtain the statistical attribute values ​​of all job seekers under the function portrait attribute corresponding to the job to be recruited and the city to which it belongs. Job seekers can submit multiple resumes to positions in different companies during the job search process. By counting the number of resumes that have been submitted to the position on the recruitment platform, the demand status of job seekers can be reflected. Now, an example is given with age as the function portrait attribute:

[0116] Age: {16:510,17:518,…,35:5000,…,40:616}, where each item is [age: number of resumes]. Calculate the percentage of resumes corresponding to the age, and arrange the percentages of each resume from small to large according to age. For example, it can be expressed as a percentage or a fraction. If [5.5%, 5.5%,…, 53.9%,…, 6.6%] is used to express the percentage of resumes, it can be seen that the age corresponding to the maximum percentage of resumes is 35 years old. In this way, the statistical attribute value corresponding to the maximum percentage of resumes is taken as the attribute value of the job seeker portrait to ensure that most job seekers meet the job requirements.

[0117] S212. All attributes under the functional portrait attribute are traversed in sequence to complete the construction of the job applicant portrait attribute value.

[0118] S213. Similarly, the construction of the job portrait attribute value can also be completed; wherein, during the construction of the job portrait attribute value, the statistical attribute values ​​of the function corresponding to the job to be recruited and all recruiters in the city to which it belongs under the function portrait attribute can be obtained. Each recruiter for the job to be recruited can publish a job description during the recruitment process. By counting the number of job descriptions that have been published on the recruitment platform for this job, the demand status of the job can be reflected.

[0119] S214. Integrate the job seeker profile attribute values ​​and the job profile attribute values:

[0120] Traverse each functional portrait attribute. For the same attributes in the job seeker portrait attribute and the position portrait attribute, you can take the attribute value that is relatively lower than the recruitment requirements. For example, age. If the job seeker portrait attribute value is 35 years old, and the position portrait attribute value is 30 years old, then when the functional portrait attribute feature is "age", the attribute value is under 35 years old, that is, job seekers under 35 years old can meet the recruitment requirements. Therefore, according to the type of functional portrait attribute, the final reasonable statistical attribute value can be selected. For example, the older the age, the lower the recruitment requirements. Relatively speaking, more job seekers can meet the recruitment requirements, so the larger attribute value of "age" is taken to achieve that more job seekers can meet the recruitment requirements.

[0121] S215. Generate functional profile attributes and attribute values ​​based on the city where the job to be recruited belongs, and store them in the redis database.

[0122] S220, generating optimized job descriptions for the positions to be recruited. The steps are as follows:

[0123] S221. Input the recruitment demand information of the positions to be recruited, which mainly includes the following fields: position name, position description, function ID, recruitment city, position tag, etc.

[0124] S222. Obtaining functional portrait attributes: Based on the recruitment city and functional ID input by the recruiter, obtain the corresponding functional portrait attributes and attribute values ​​by querying the redis database.

[0125] S223. Based on the recruitment demand information input by the recruiter, the large model LLM is used to generate the job description to be optimized.

[0126] S224. Construct optimization prompt items according to the tag attributes in the job description to be optimized:

[0127] Traverse each tag attribute in the job description to be optimized. If the current tag attribute value is slightly different from the industry, that is, the current tag attribute value is slightly different from or consistent with the functional profile attribute value, continue to compare the next tag attribute value, otherwise prompt the recruiter; among them, the tag attribute value can be divided into: numerical type and text options.

[0128] Numerical tag attribute value: If the current tag attribute value requirement is 10% higher than the set standard, the recruiter will be prompted; the set standard can be, for example, an industry standard, or a corresponding function portrait attribute value obtained by querying the redis KV database based on the function ID. The prompt can be generated according to the source of the function portrait attribute value. Take age as an example: if the attribute value of age comes from the job portrait attribute value, the user will be prompted: "Most JDs with the same function require job seekers to be under 35 years old. Do you want to relax the age limit?" If the attribute value of age comes from the job seeker portrait attribute value, the prompt is: "Most job seekers are under 35 years old. Do you want to relax the age limit?"

[0129] Label attribute value of text options: If the current label attribute value filled in by the recruiter is inconsistent with the selection options of most users (for example, HR from other companies), if the functional portrait attribute value is derived from the position portrait attribute value, that is, from the recruitment needs of HR from other companies, the recruiter will be prompted: for example, "Most of the functions under this position require a bachelor's degree or above. Do you also want to adjust it to a bachelor's degree or above?"

[0130] S225, prompting the recruiter whether to modify the prompt item, that is, prompting the recruiter whether to accept the suggestion item, and asking the recruiter to confirm in the form of a form bar. If the recruiter confirms to modify the current tag attribute value, the recruiter selects to check the option.

[0131] S226, generate prompt: based on the input recruitment demand information and the confirmed new function attribute information, the corresponding function prompt template and example are obtained based on the function corresponding to the position to be recruited, so as to construct a preset position description prompt. The template and example can be constructed by experts to ensure the quality of the final generated JD.

[0132] S227, JD generation: call the large-scale language model, input the preset job description prompt, and generate the optimized JD. The preset job description prompt is as follows:

[0133] You are a recruitment expert in the field of human resources. Please complete the following task: Help HR optimize JD. The requirements are as follows:

[0134] 1. Optimize the structure to make it clear and include the following parts: "Job responsibilities, job requirements, and benefits";

[0135] 2. Based on the provided company information, optimize the JD according to the company's nature, industry, etc., so that the JD is more suitable for the company's attributes;

[0136] 3. Based on the functional labels provided by the industry, please generate around these labels;

[0137] 4. Do not produce content that does not have positive values, and do not generate content that is irrelevant to JD.

[0138] {

[0139] Recruitment requirements are as follows:

[0140] ###

[0141]

Job Responsibilities

[0142] 1.XXX

[0143] 2.XXX

[0144]

Job Requirements

[0145] 1.XXX

[0146] 2.XXX

[0147]

Benefits

[0148] XXX

[0149] ###

[0150] JD optimization example:

[0151] [input]

[0152] #Example JD#

[0153] Modification: #Example {k, v}#

[0154] [output]

[0155] #Optimized results#

[0156] Please optimize JD according to the following information:

[0157] [input]

[0158] #JD#

[0159] Modification item:#{k,v}#

[0160] [output]

[0161] }

[0162] Among them, k is the label attribute, and v is the corresponding label attribute value.

[0163] Corresponding to the method embodiment of the present application, the present application also provides a device for optimizing job descriptions, such as Figure 5 As shown, specifically, it may include:

[0164] An acquisition module 510 is used to acquire recruitment demand information input by the recruiter for the recruitment position;

[0165] A first generating module 520 is used to generate a job description to be optimized according to the recruitment demand information; wherein the job description to be optimized includes a plurality of tag attributes and attribute values;

[0166] A query module 530 is used to query the target database according to the recruitment demand information to obtain the function profile attributes and attribute values ​​corresponding to the positions to be recruited;

[0167] A construction module 540 is used to construct an optimization prompt item according to each tag attribute value and the corresponding function profile attribute value to obtain a target function attribute information set; wherein the optimization prompt item is used to prompt the recruiter whether the tag attribute value needs to be modified according to the difference between the tag attribute value and the corresponding function profile attribute value; the target function attribute information set includes the modified tag attribute value;

[0168] The second generating module 550 is used to generate an optimized job description of the position to be recruited based on a preset job description prompt template, according to recruitment demand information and a target function attribute information set.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

Claims

1. A method for optimizing job description, characterized in that: include: Obtain the recruitment demand information input by the recruiter for the recruitment position; Generate a job description to be optimized according to the recruitment demand information; wherein the job description to be optimized includes multiple tag attributes and attribute values; Query the target database according to the recruitment demand information to obtain the functional profile attributes and attribute values ​​corresponding to the positions to be recruited; According to each label attribute value and the corresponding functional profile attribute value, an optimization prompt item is constructed to obtain a target functional attribute information set; wherein the optimization prompt item is used to prompt the recruiter whether the label attribute value needs to be modified when the label attribute value and the corresponding functional profile attribute value are inconsistent, so as to obtain the label attribute value modified by the recruiter; the target functional attribute information set includes the modified label attribute value; Based on the preset job description prompt template, an optimized job description for the position to be recruited is generated according to the recruitment demand information and the target function attribute information set.

2. The optimization method according to claim 1, characterized in that: The querying of the target database according to the recruitment demand information to obtain the functional profile attributes and attribute values ​​corresponding to the positions to be recruited includes: Estimating functions based on recruitment demand information to obtain the first functions corresponding to the positions to be recruited; Obtain multiple functional portrait attributes under the first function; According to the multiple functional portrait attributes under the first function and the set target area, a job seeker portrait attribute information set is obtained; wherein the job seeker portrait attribute information set includes a job seeker portrait attribute value corresponding to each functional portrait attribute; According to the multiple functional portrait attributes under the first function and the set target area, a job portrait attribute information set is obtained; wherein the job portrait attribute information set includes a job portrait attribute value corresponding to each functional portrait attribute; Compare the job seeker profile attribute value corresponding to each functional profile attribute with the job profile attribute value to obtain the attribute value corresponding to each functional profile attribute; The attribute value corresponding to each functional profile attribute is stored in the target database.

3. The optimization method according to claim 2, characterized in that: The method of obtaining a job seeker portrait attribute information set based on multiple functional portrait attributes under the first function and the set target area includes: Obtain the first-category statistical attribute values ​​and the corresponding number of resumes of all job seekers under each functional profile attribute in the set target area; According to the number of resumes corresponding to each first-category statistical attribute value and the total number of resumes of the first-category statistical attribute value, calculate the proportion of the number of resumes of each first-category statistical attribute value; Sort the percentage of resumes for each first-category statistical attribute value, and take the statistical attribute value corresponding to the maximum percentage of resumes as the job seeker portrait attribute value.

4. The optimization method according to claim 2, characterized in that: The method of obtaining a set of job profile attribute information based on multiple job profile attributes and a set target area under the first job includes: Obtain the second-category statistical attribute values ​​of all historical job descriptions under each functional profile attribute in the set target area and the corresponding number of historical job descriptions; Calculate the proportion of descriptions for each second-category statistical attribute value based on the number of historical job descriptions corresponding to each second-category statistical attribute value and the total number of historical job descriptions for the second-category statistical attribute value; Sort the description share ratio of each second-category statistical attribute value, and take the statistical attribute value corresponding to the maximum description share ratio as the job profile attribute value.

5. The optimization method according to claim 1, characterized in that: The optimization prompt items are constructed according to each tag attribute value and the corresponding function profile attribute value to obtain a target function attribute information set, including: Traverse each tag attribute and attribute value in the job description to be optimized; Compare the current label attribute value with the corresponding functional portrait attribute value, and if there is a difference between the current label attribute value and the corresponding functional portrait attribute value, generate an optimization prompt item; wherein the current label attribute value belongs to a numerical type or a text option; According to the generated optimization prompt items, the recruiter makes a choice as to whether to modify the label attribute value according to the recruitment intention, so as to obtain the target function attribute information set.

6. The optimization method according to claim 5, characterized in that: The current tag attribute value is compared with the corresponding functional portrait attribute value, and if there is a difference between the current tag attribute value and the corresponding functional portrait attribute value, an optimization prompt item is generated, including: If the current tag attribute value is a numeric value, and the difference between the current tag attribute value and the corresponding functional profile attribute value is higher than the set threshold, an optimization prompt item is generated; wherein, The threshold is set to 10%-20% of the corresponding functional profile attribute value; If the job profile attribute value is derived from the job seeker profile attribute value, the generated optimization prompt item includes prompt content derived from the job seeker profile attribute and the attribute value; If the function portrait attribute value is derived from the position portrait attribute value, the generated optimization prompt item includes the prompt content derived from the position portrait attribute and attribute value.

7. The optimization method according to claim 5, characterized in that: The step of comparing the current tag attribute value with the corresponding functional portrait attribute value and generating an optimization prompt item if there is a difference between the current tag attribute value and the corresponding functional portrait attribute value also includes: If the current label attribute value belongs to a text option, and the current label attribute value is inconsistent with the corresponding functional portrait attribute value, an optimization prompt item is generated; among which, If the job profile attribute value is derived from the job seeker profile attribute value, the generated optimization prompt item includes prompt content derived from the job seeker profile attribute and the attribute value; If the function portrait attribute value is derived from the position portrait attribute value, the generated optimization prompt item includes the prompt content derived from the position portrait attribute and attribute value.

8. A device for optimizing job descriptions, characterized in that: include: An acquisition module is used to acquire recruitment demand information input by recruiters for recruitment positions; A first generating module, which is used to generate a job description to be optimized according to the recruitment demand information; wherein the job description to be optimized includes a plurality of tag attributes and attribute values; A query module is used to query the target database according to the recruitment demand information to obtain the functional profile attributes and attribute values ​​corresponding to the positions to be recruited; A construction module, which is used to construct an optimization prompt item according to each label attribute value and the corresponding functional profile attribute value to obtain a target functional attribute information set; wherein the optimization prompt item is used to prompt the recruiter whether the label attribute value needs to be modified according to the difference between the label attribute value and the corresponding functional profile attribute value; the target functional attribute information set includes the modified label attribute value; The second generation module is used to generate an optimized 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.

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