A labor matching method, system and storage medium

By combining the input information of enterprise users and historical recruitment data, accurate part-time recruitment information is generated and part-time requirements are updated using genetic algorithms, the problems of low recruitment efficiency and insufficient matching in the existing technology are solved, and efficient employment matching and Communication channels have significantly improved the efficiency and success rate of corporate recruitment.

CN118505176BActive Publication Date: 2024-11-08深圳市灵智数字科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410980800.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-22
Publication Date
2024-11-08
Estimated Expiration
2044-07-22

AI Technical Summary

Technical Problem

The existing technology is difficult to achieve immediate response and rapid processing of large-scale recruitment needs, and the lack of precise matching of job seekers' interests and abilities, resulting in companies wasting time and resources in the recruitment process, limiting job seekers' ability to find suitable jobs.

Method used

A employment matching method is proposed, which can obtain part-time input information through input instructions from the enterprise user side, generate part-time recruitment information based on historical recruitment information, and display job seeker information from high to low based on matching degree, provide communication channels and store interactive data, and use genetics The algorithm updates the weight of the part-time job requirements, supports text, voice and image input, and processes unstructured data through Mel spectrum analysis and content area recognition.

Benefits of technology

Improve the quality and matching of recruitment information, reduce repetitive work, optimize the recruitment process, significantly improve recruitment efficiency and success rate, provide more accurate matching of job seekers and part-time positions, and support multi-modal input and personality Serving services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118505176B_ABST
    Figure CN118505176B_ABST
Patent Text Reader

Abstract

The present invention provides a method, system and storage medium for employment matching. The method can respond to input instructions from an enterprise user end, obtain part-time job input information based on the input instructions, determine the part-time job type corresponding to the part-time job input information, and summarize historical part-time job information to generate part-time job recruitment information, so as to obtain matching job seeker information through the part-time job recruitment information and allow the enterprise user end to selectively send it, so as to complete employment matching after receiving positive intention information fed back by the job seeker end. The scheme proposed by the present invention supports enterprise users to input instructions in multiple ways, can combine input information and historical information to generate more comprehensive and accurate part-time job recruitment information, display part-time workers who meet the needs for enterprise users according to the matching degree, provide communication channels and store interactive data to realize communication between enterprise users and part-time workers, which helps to improve the quality and matching degree of recruitment, thereby significantly improving the efficiency and success rate of enterprise recruitment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and specifically relates to a labor matching method, system and storable medium. Background Art

[0002] In the modern economy and work environment, companies are faced with the challenge of how to efficiently match part-time and job seekers. Traditional recruitment methods often rely on advertising, job search platform registration, and manual screening by human resources departments, but these methods have some limitations. For example, traditional methods may not be able to achieve instant response and rapid processing of large-scale recruitment needs, and may also lack precise matching of job seekers' interests and abilities.

[0003] Online recruitment platforms in the prior art provide certain conveniences, allowing companies and job seekers to publish and browse information on one platform. However, these platforms usually focus on full-time recruitment or general part-time recruitment information, and may not be able to provide sufficient personalized services, especially for part-time positions that require specific skills or work experience.

[0004] In addition, existing technologies often lack effective algorithms and systems to handle a large amount of part-time recruitment information and cannot ensure efficient matching between companies and job seekers. This deficiency causes companies to waste too much time and resources in the recruitment process, while also limiting job seekers' ability to find the most suitable job opportunities. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention proposes a labor matching method, which comprises:

[0006] In response to at least one type of input instruction from the enterprise user end, obtaining part-time job input information based on the input instruction, and determining the part-time job type corresponding to the part-time job input information; the type of the input instruction includes: one or any multiple of text type, voice type, and image type;

[0007] Extracting first historical part-time job information based on the historical recruitment information corresponding to the part-time job type at the enterprise user end, and summarizing the part-time job input information and the first historical part-time job information to generate part-time job recruitment information;

[0008] Acquire all job seeker information matching the part-time job input information, and display it to the enterprise user terminal in a descending order based on the degree of matching the part-time job recruitment information from the acquired job seeker information; or acquire all job seeker information matching the part-time job recruitment information, and display it to the enterprise user terminal in a descending order based on the degree of matching; the job seeker information includes the information input by the job seeker terminal and the second historical part-time job information corresponding to the job seeker terminal;

[0009] In response to a selection instruction of the enterprise user terminal, sending the part-time job recruitment information to all selected job seeker terminals based on the selection instruction;

[0010] If positive intention information is received from the job seeker, the positive intention information is sent to the enterprise user to complete the job matching, provide a communication channel between the enterprise user and the job seeker, and store all interaction data between the enterprise user and the job seeker.

[0011] Specifically, the part-time job recruitment information includes a plurality of part-time job requirement information; different part-time job requirement information corresponds to respective weight coefficients; the method further includes: regularly determining the employment preference of the enterprise user terminal according to the first historical part-time job information within a preset time period before the current one; updating the weight information of each part-time job requirement information through a genetic algorithm based on the employment preference;

[0012] The job seeker information displayed to the enterprise user terminal is screened and sorted based on the matching degree with the part-time job recruitment information. The formula for determining the matching degree is:

[0013]

[0014] in, represents the matching degree between the job seeker information and the part-time job recruitment information, Represents the part-time job recruitment information, Represents the said job seeker information, represents various job-seeking information in the job seeker information that meets the corresponding part-time job requirement information, represents the score of each job application information in the job seeker information, Represents the latest weight coefficient of each job search information.

[0015] Specifically, the “obtaining part-time job input information based on the input instruction” includes:

[0016] If the type of the input instruction is a voice type, the input instruction is subjected to noise reduction processing to obtain voice data after noise reduction; the voice data is subjected to Mel spectrum analysis to extract voice features, and the voice features are imported into a trained voice model to obtain text information; the text information is imported into a trained semantic model to obtain part-time input information;

[0017] If the type of the input instruction is an image type, content area recognition is performed on the image corresponding to the input instruction to extract the text content area containing text content in the image; the text content area is divided into multiple sub-text content areas, each of the sub-text content areas includes at least one character or string; the image of each sub-text content area is imported into a trained neural network model to obtain text information; the text information is combined based on the division order of each sub-text content area to obtain text information; the text information is imported into a trained semantic model to obtain part-time input information.

[0018] Specifically, the job seeker information also includes a resume, and the method further includes:

[0019] Extracting information on specific parts of speech from the part-time job recruitment information and the job seeker's resume respectively;

[0020] Based on the part-time job recruitment information and the information of the specific part of speech in the job seeker's resume, the matching degree between the job seeker's resume and the part-time job recruitment information is calculated; the matching degree between the resume and the part-time job recruitment information is used as the matching degree between the part-time job input information and the part-time job recruitment information;

[0021] The matching degree between the job seeker information and the part-time job recruitment information is obtained by comprehensively considering the matching degree between the part-time job input information and the part-time job recruitment information, and the matching degree between the second historical part-time job information and the part-time job recruitment information.

[0022] Preferably, the “respectively extracting information of specific parts of speech from the part-time job recruitment information and the job seeker’s resume” includes:

[0023] Performing text preprocessing on the part-time job recruitment information and the job seeker's resume respectively;

[0024] Part-of-speech tagging is performed on the preprocessed text to extract information about specific parts of speech in the text.

[0025] Furthermore, the specific parts of speech include nouns, adjectives, verbs and numerals. The formula for calculating the matching degree between the job seeker's resume and the part-time job recruitment information is:

[0026]

[0027] in, Represents the part-time job recruitment information, Resume of the applicant, Represents the matching degree between the job seeker's resume and the part-time job recruitment information;

[0028] Represents the noun information in the part-time job recruitment information. Represents the noun information in the resume of the job seeker. Represents the matching degree between the job seeker's resume and the noun information in the part-time job recruitment information, The weight coefficient representing the matching degree of noun information;

[0029] Represents the adjective information in the part-time job recruitment information, Represents the adjective information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the adjective information in the part-time job recruitment information, The weight coefficient representing the matching degree of adjective information;

[0030] Represents the verb information in the part-time job recruitment information, Represents the verb information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the verb information in the part-time job recruitment information, The weight coefficient representing the matching degree of verb information;

[0031] Represents the numeral information in the part-time job recruitment information, Represents the numerical information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the numeral information in the part-time job recruitment information, The weight coefficient representing the matching degree of numeral information.

[0032] Preferably, the method further comprises:

[0033] Determine other enterprise user terminals of the same type as the enterprise user terminal;

[0034] Selecting historical part-time job information corresponding to the part-time job type of the other enterprise user terminals whose business scale is not less than that of the enterprise user terminal;

[0035] The selected historical part-time job information of the other enterprise user terminals is added to the first historical part-time job information, and the operation of "aggregating the part-time job input information and the first historical part-time job information to generate part-time job recruitment information" is performed.

[0036] Preferably, the method further comprises:

[0037] Determine a first recruitment requirement from the historical recruitment information of the enterprise user terminal;

[0038] Extracting second recruitment requirements from historical recruitment information of other enterprise user terminals of the same type as the enterprise user terminal;

[0039] Summarizing the first recruitment requirement and the second recruitment requirement to generate recruitment requirements, and labeling the recruitment requirements to obtain recruitment requirement labels;

[0040] Determine the parts of all the recruitment requirement tags that are different from the recruitment requirements corresponding to the input instruction, and display the different parts to the enterprise user end, so that when the enterprise user end triggers the displayed recruitment requirement tag, the input instruction is updated based on the triggered recruitment requirement tag, and the operation of "obtaining part-time job input information based on the input instruction" is performed.

[0041] Furthermore, the method further comprises:

[0042] If a salary analysis request from the enterprise user is obtained, determining the position information corresponding to the salary analysis request; the position information includes: position type, position location, position time and required personnel information for the position;

[0043] After the job information is digitized, it is combined with the current market information corresponding to the job information and then imported into a trained salary regression model to obtain estimated salary information; wherein the salary regression model includes a multiple regression model, a ridge regression model or a lasso regression model;

[0044] The estimated salary information is fed back to the enterprise user end.

[0045] The present invention also proposes a labor matching system, the system comprising:

[0046] An input module, for responding to at least one type of input instruction from an enterprise user terminal, acquiring part-time job input information based on the input instruction, and determining a part-time job type corresponding to the part-time job input information; the type of the input instruction includes: one or any combination of text type, voice type, and image type;

[0047] A generating module, configured to extract first historical part-time job information based on the historical recruitment information corresponding to the part-time job type at the enterprise user end, and to aggregate the part-time job input information and the first historical part-time job information to generate part-time job recruitment information;

[0048] A display module is used to obtain all the job seeker information matching the part-time job input information, and display it to the enterprise user terminal in a descending order based on the degree of matching the part-time job recruitment information from the obtained job seeker information; or obtain all the job seeker information matching the part-time job recruitment information, and display it to the enterprise user terminal in a descending order based on the degree of matching; the job seeker information includes the information input by the job seeker terminal and the second historical part-time job information corresponding to the job seeker terminal;

[0049] A sending module, configured to respond to a selection instruction of the enterprise user terminal and send the part-time job recruitment information to all selected job seeker terminals based on the selection instruction;

[0050] The communication module is used to send the positive intention information to the enterprise user end after receiving the positive intention information fed back by the job seeker end to complete the employment matching, provide a communication channel between the enterprise user end and the job seeker end, and store all the interaction data between the enterprise user end and the job seeker end.

[0051] The present invention also proposes a computer-readable storage medium, wherein the computer-readable storage medium stores executable instructions for implementing the method described above when executed by a processor.

[0052] The present invention has at least the following beneficial effects:

[0053] The solution proposed by the present invention supports enterprise users to provide recruitment demand information through multiple input methods such as text, voice or image, and can also analyze and summarize the recruitment information provided by enterprise users in combination with historical recruitment data to generate more comprehensive and accurate part-time recruitment information, which helps to improve information quality, reduce repetitive work and optimize the recruitment process. It improves the matching efficiency by displaying to the enterprise user end in order from high to low matching degree, and at the same time provides communication channels and storage of interactive data to help establish and maintain effective communication between enterprise users and job seekers;

[0054] Furthermore, the scheme proposed in the present invention can update the weight of part-time job requirement information by using a genetic algorithm, and can dynamically adjust the display order and matching degree of recruitment information according to the employment preferences of enterprise users, so as to more accurately meet the needs of enterprises. The scheme takes into account voice and image type input instructions, and can convert unstructured voice and image data into structured text information through Mel spectrum analysis of voice data and image content area recognition. Multimodal input support enables the system to handle richer and more complex user input. The method that comprehensively considers the matching degree between historical part-time job information and current part-time job recruitment information, as well as the matching degree between personal resumes and job recruitment information can more comprehensively evaluate the compatibility between job seekers and part-time positions, and improve the precision and accuracy of matching.

[0055] In addition, this solution takes into account part-of-speech tagging and the extraction of specific part-of-speech information in the processing of personal resumes and recruitment information, which can analyze the text content more accurately, further improve the efficiency and accuracy of the matching algorithm, and can obtain historical part-time job information from other corporate user terminals to supplement the historical part-time job information of the current system, as well as extract recruitment requirements from multiple corporate user terminals, so that the system can provide more targeted services and support.

[0056] Therefore, the present invention provides a method, system and storable medium for employment matching. The scheme proposed in the present invention supports enterprise users to input instructions in a variety of ways, can combine input information and historical information to generate more comprehensive and accurate part-time recruitment information, and display part-time workers who meet the needs to enterprise users according to the matching degree. It provides communication channels and can store interactive data to realize communication between enterprise users and part-time workers, which helps to improve the quality and matching degree of recruitment, thereby significantly improving the efficiency and success rate of enterprise recruitment. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 A schematic diagram of the overall method flow of the employment matching method provided in Example 1;

[0059] Figure 2 A flowchart of a method for obtaining a matching degree;

[0060] Figure 3 A flow chart of a method for generating part-time job recruitment information by supplementing information for an enterprise user end;

[0061] Figure 4 A flowchart of a method for an enterprise user to obtain part-time job input information through supplementary information;

[0062] Figure 5 A flowchart of the method for estimating salary;

[0063] Figure 6 A schematic diagram of the module structure of the employment matching method provided in Example 2.

[0064] Reference numerals

[0065] 10-input module; 20-generation module; 30-display module; 31-extraction unit; 32-calculation unit; 33-integration unit; 40-sending module; 50-communication module; 61-query module; 62-selection module; 63-supplement module; 71-determination module; 72-acquisition module; 73-label module; 74-update module; 81-analysis module; 82-estimation module; 83-feedback module. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Hereinafter, various embodiments of the present invention will be described more fully. The present invention may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present invention to the specific embodiments disclosed herein, but the present invention should be understood to cover all adjustments, equivalents and / or alternatives falling within the spirit and scope of the various embodiments of the present invention.

[0068] Hereinafter, the term "include" or "may include" used in various embodiments of the present invention indicates the presence of disclosed functions, operations or elements, and does not limit the addition of one or more functions, operations or elements. In addition, as used in various embodiments of the present invention, the terms "include", "have" and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0069] In various embodiments of the present invention, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0070] The expressions (such as "first", "second", etc.) used in various embodiments of the present invention may modify the various constituent elements in various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing an element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of various embodiments of the present invention, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0071] It should be noted that in the present invention, unless otherwise clearly specified and defined, the terms such as "installation", "connection", "fixation" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0072] In the present invention, those skilled in the art need to understand that the terms indicating orientation or positional relationship herein are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0073] The terms used in various embodiments of the present invention are only used for the purpose of describing specific embodiments and are not intended to limit various embodiments of the present invention. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meaning generally understood by those of ordinary skill in the art to which the various embodiments of the present invention belong. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in various embodiments of the present invention.

[0074] Example 1

[0075] This embodiment proposes a method for matching employment. Figure 1 , the method comprising:

[0076] S100: In response to at least one type of input instruction from the enterprise user end, obtain part-time job input information based on the input instruction, and determine the part-time job type corresponding to the part-time job input information.

[0077] Specifically, the type of input instruction includes: one or more of text type, voice type, and image type, and the input instruction may include but is not limited to enterprise information, work content information, work time information, work location information, and salary information;

[0078] Exemplarily, when the input instruction type is a voice type, the input instruction may be subjected to noise reduction processing to obtain voice data after noise reduction; the voice data may be subjected to Mel spectrum analysis to extract voice features, and the voice features may be imported into a trained voice model to obtain text information; the text information may be imported into a trained semantic model to obtain part-time input information;

[0079] When the type of input instruction is an image type, content area recognition can be performed on the image corresponding to the input instruction to extract the text content area containing text content in the image; the text content area is divided into multiple sub-text content areas, each sub-text content area includes at least one character or string; the image of each sub-text content area is imported into a trained neural network model to obtain text information; the text information is combined based on the division order of each sub-text content area to obtain text information; and the text information is imported into a trained semantic model to obtain part-time input information.

[0080] Therefore, the method proposed in this embodiment can process various types of input instructions such as text, voice and image, so that users can choose a suitable input method according to their preferences or environmental conditions, thereby improving user experience and flexibility and convenience of use;

[0081] Among them, noise reduction processing and Mel spectrum analysis technologies are used for voice-type input instructions, which help to improve the accuracy and stability of voice input and ensure that the process of converting voice to text can be carried out efficiently and accurately; content area recognition technology is used for image-type input instructions, which can accurately extract content areas containing text and effectively process the complex information structure in the image, thereby extracting and combining relevant text information.

[0082] Using trained speech models and neural network models for information processing and analysis can improve the ability to acquire and understand part-time job information, thereby further improving the accuracy and completeness of part-time job information and effectively responding to the diverse needs of corporate users.

[0083] S200: extracting first historical part-time job information from historical recruitment information corresponding to the part-time job type at the enterprise user end, and aggregating the part-time job input information and the first historical part-time job information to generate part-time job recruitment information.

[0084] Specifically, the extracted historical recruitment information can be analyzed from the records of historical completed employment matching, such as the preferred gender, preferred age, preferred residential range, preferred education level and preferred work experience of historical employment, and updated and iterated; preferably, the historical recruitment information will also be continuously updated according to the specific employment of each enterprise user, so that the method can generate more personalized and accurate part-time recruitment information based on the part-time information input by the user in combination with historical data, predict the degree of matching between part-time demand and supply, thereby optimizing the recruitment process and accelerating the matching speed, and improving the recruitment efficiency and success rate, and through continuous data iteration and updating, it can reflect the current changes in user needs and maintain the timeliness and accuracy of part-time recruitment information.

[0085] S300: Obtain all job seeker information that matches the part-time job input information, and display it to the enterprise user end based on the degree of matching the part-time job recruitment information from the obtained job seeker information in a descending order, or obtain all job seeker information that matches the part-time job recruitment information, and display it to the enterprise user end based on the degree of matching in a descending order.

[0086] Through step S300, the method proposed in this embodiment can ensure that enterprise users see the most relevant candidates, greatly reduce the time and resource consumption of the enterprise in the screening and interview process, provide data support for enterprise users to assist in making quick decisions, and can significantly improve recruitment efficiency, shorten the recruitment cycle, and reduce the labor cost in the recruitment process.

[0087] S400: In response to a selection instruction from the enterprise user terminal, part-time job recruitment information is sent to all selected job seekers based on the selection instruction.

[0088] S500: If positive intention information is received from the job seeker, the positive intention information is sent to the enterprise user to complete the job matching, provide a communication channel between the enterprise user and the job seeker, and store all the interaction data between the enterprise user and the job seeker.

[0089] It should be noted that the corporate user can publicly publish the part-time job recruitment information generated in step S200 on the platform, and at the same time choose to send it to some specific job seekers in step S400. The job seekers who provide feedback on their intention information in step S500 may include job seekers who have read the publicly released part-time job recruitment information on the platform, as well as specific job seekers who have received the information sent by the corporate user in step S400.

[0090] Preferably, the part-time job recruitment information includes multiple part-time job requirement information, and different part-time job requirement information corresponds to respective weight coefficients. The method proposed in this embodiment can also determine the employment preference of the enterprise user terminal according to the first historical part-time job information within a preset time period before the current one, and update the weight information of each part-time job requirement information through a genetic algorithm based on the employment preference;

[0091] Specifically, the job seeker information displayed to the enterprise user terminal is screened and sorted based on the matching degree with the part-time job recruitment information. In this embodiment, the matching degree is calculated by the formula Certainly, among them, Represents the matching degree between job seeker information and part-time job recruitment information. Representative part-time recruitment information, Represents job seeker information, Represents various information in the job seeker information. Represents the score of each information in the job applicant information. Represents the weight coefficient of each information.

[0092] In this embodiment, the job seeker information includes information input by the job seeker end and the second historical part-time job information of the corresponding job seeker end. For example, the job seeker information may include but is not limited to the gender, age, marital status, graduation school, major, work experience, work skills and other information of the job seeker input by the job seeker end, and may also include the working hours, past wages, enterprise user evaluation and other information of the corresponding job seeker end, and the weight coefficient of each information is determined based on the genetic algorithm. The method for determining the weight coefficient is specifically as follows:

[0093] The job seeker information is converted into a form that can be processed in the genetic algorithm, for example, the information is encoded into a series of initial individuals represented by numbers or symbols so that the algorithm can understand and process it, a certain number of initial individuals are generated as an initial population, and the size of the population is determined, that is, how many individuals are included in the population, and a fitness function is selected to evaluate the performance or adaptability of each individual in the solution space. The genetic operator is used to continuously perform crossover and mutation operations so that the solutions in the population will gradually evolve, and eventually the individual corresponding to the optimal solution or the one closest to the optimal solution is generated;

[0094] In a specific embodiment, the weight coefficients of various information are shown in Table 1.

[0095] Table 1 Weight coefficient table of each information

[0096]

[0097] Furthermore, the scores of various job seeker information can be classified and summarized and represented by specific numbers. For example, if the job seeker has the same work experience as the part-time job recruitment information, the work experience score is increased by 1; if the job seeker has part-time work experience in the enterprise user's enterprise, the work experience score is increased by 1.

[0098] In this embodiment, the job seeker information also includes a resume. In addition to using the formula mentioned above, In addition to determining the matching degree, the job seeker information displayed to the enterprise user end can also take into account the matching degree between the job seeker's personal resume and the part-time job recruitment information, see Figure 2 , the method further comprises:

[0099] S310: Extracting information about specific parts of speech from part-time job recruitment information and job seekers' resumes respectively.

[0100] S320: Based on the part-time job recruitment information and the information of specific parts of speech in the job seeker's resume, the matching degree between the job seeker's resume and the part-time job recruitment information is calculated, and the matching degree between the resume and the part-time job recruitment information is used as the matching degree between the part-time job input information and the part-time job recruitment information.

[0101] S330: The matching degree between the job seeker information and the part-time job recruitment information is obtained by comprehensively considering the matching degree between the part-time job input information and the part-time job recruitment information, and the matching degree between the second historical part-time job information and the part-time job recruitment information.

[0102] Among them, step S320 can also determine the part-time working time information and the job seeker's intended working time information based on the part-time recruitment information and the information of specific parts of speech in the job seeker's personal resume, so as to determine that the job seeker's personal resume is incompatible with the part-time recruitment information when the part-time working time information does not match the intended working time information; in this embodiment, the part-time working time information includes part-time work start time information, part-time work end time information and part-time work scheduling time information.

[0103] Specifically, step S310 includes:

[0104] The part-time job recruitment information and job seekers' resumes are preprocessed respectively; the preprocessed texts are tagged with parts of speech to extract information about specific parts of speech in the texts.

[0105] In this embodiment, the text preprocessing includes but is not limited to steps such as word segmentation, stop word removal, lemma restoration and stem extraction, so as to better process the text;

[0106] It should be noted that word segmentation is the process of dividing text into words or other basic units, which is used to split continuous text sequences into meaningful words or tags. Stop words refer to words that often appear in texts but usually have no practical meaning or do not need to be analyzed. Lemma restoration is the process of transforming words into their basic forms in the dictionary. Stemming is the process of transforming words into their stems or basic forms, which can be achieved by deleting affixes.

[0107] In this embodiment, the part-of-speech tagging is implemented by a part-of-speech tagger, which will tag the part of speech for each word, such as noun, verb, and adjective;

[0108] For example, after word segmentation and part-of-speech tagging of the text "Currently recruiting 2 part-time cashiers" in the part-time recruitment information, it will be divided into a text including "currently, recruiting, 2, name, part-time, cashier", among which "currently" is an adverb, "recruiting" is a verb, "2" is a numeral, "name" is a quantifier, "part-time" is a noun, and "cashier" is a noun.

[0109] In this embodiment, specific parts of speech include nouns, adjectives, verbs and numerals. The formula for calculating the matching degree between the job seeker's resume and the part-time job recruitment information is:

[0110]

[0111] in, Representative part-time recruitment information, Resume representing the job seeker, Represents the matching degree between the job seeker's resume and part-time job recruitment information;

[0112] Represents the noun information in part-time job recruitment information. Represents the noun information in the job seeker's resume. Represents the matching degree between the noun information in the job seeker's resume and the part-time job recruitment information. The weight coefficient representing the matching degree of noun information;

[0113] Represents adjective information in part-time job recruitment information. Represents the adjective information in the job seeker's resume. Represents the matching degree between the adjective information in the job seeker's resume and the part-time job recruitment information. The weight coefficient representing the matching degree of adjective information;

[0114] Represents the verb information in part-time job recruitment information. Represents the verb information in the job seeker's resume. Represents the matching degree between the job seeker's resume and the verb information in the part-time job recruitment information. The weight coefficient representing the matching degree of verb information;

[0115] Represents the numeral information in part-time job recruitment information. Represents the numerical information in the job seeker's resume. Represents the matching degree between the job seeker's resume and the number information in the part-time job recruitment information. The weight coefficient representing the matching degree of numeral information.

[0116] In this embodiment, , , , The value of can also be determined based on a genetic algorithm.

[0117] Further, see Figure 3 , Figure 4 , the method further comprises:

[0118] S610: Determine other enterprise user terminals of the same type as the enterprise user terminal.

[0119] S620: Select historical part-time job information of corresponding part-time job types of other enterprise user terminals whose business scale is not less than that of the enterprise user terminal.

[0120] S630: Supplement the selected historical part-time job information of other enterprise users to the first historical part-time job information, and execute the operation of "aggregating the part-time job input information and the first historical part-time job information to generate part-time job recruitment information" in step S200.

[0121] S710: Determine the first recruitment requirement from the historical recruitment information of the enterprise user end.

[0122] S720: Extracting the second recruitment requirement from historical recruitment information of other enterprise user terminals of the same type as the enterprise user terminal.

[0123] S730: Summarize the first recruitment requirement and the second recruitment requirement to generate recruitment requirements, and label the recruitment requirements to obtain recruitment requirement labels.

[0124] S740: Determine the parts of all recruitment requirement tags that are different from the recruitment requirements corresponding to the input instructions, and display the different parts to the enterprise user end, so that when the enterprise user end triggers the displayed recruitment requirement tag, the input instruction is updated based on the triggered recruitment requirement tag, and the operation of "obtaining part-time job input information based on input instructions" in step S100 is executed.

[0125] Through steps S610 to S630, the method proposed in this embodiment can integrate the historical part-time job information of multiple enterprise users of the same type, expand the system's data field of view of candidates, and improve the matching degree between the part-time job input information and the historical part-time job information, so as to more accurately recommend suitable candidates to enterprise users;

[0126] Steps S710 to S740 enable enterprise users to more clearly understand the differences in recruitment requirements of different enterprise users by labeling and displaying different parts of the recruitment requirements, making it easier to find candidates that meet specific needs, thereby improving the efficiency and success rate of recruitment and effectively enhancing the user experience of enterprise users.

[0127] Therefore, the method proposed in this embodiment integrates data, improves personalized display and optimizes the system feedback mechanism. For some corporate users with insufficient data, similar corporate data can be used to supplement them, thereby further optimizing the matching method to ensure that the matched job seekers can meet the needs of the corporate users as much as possible. At the same time, it can also continuously optimize the user experience of corporate users and ensure that the method can continue to adapt and improve in long-term use.

[0128] Further, see Figure 5 , the method further comprises:

[0129] S810: If a salary analysis request from the enterprise user is obtained, determine the position information corresponding to the salary analysis request.

[0130] S820: After the job information is digitized, it is combined with the current market information corresponding to the job information and then imported into the trained salary regression model to obtain estimated salary information.

[0131] S830: Feedback the estimated salary information to the enterprise user end.

[0132] Therefore, the method proposed in this embodiment can also determine the reference salary corresponding to each job seeker information based on the part-time recruitment information and the job seeker information matching the part-time recruitment information. Further, the method proposed in this embodiment can automatically execute step S810 synchronously when executing step S300, so that when the job seeker information is displayed to the enterprise user end in step S300, the estimated salary information corresponding to each job seeker information is also displayed;

[0133] In this embodiment, the reference salary is determined based on the job information data from part-time recruitment information and job seeker information. The job information may include but is not limited to job type, job location, job time, professional level, and required information of the personnel required for the job, such as education, work experience, and work skills. Therefore, the method proposed in this embodiment can determine a relatively accurate range of reference wages based on factors such as the industry average level, regional average level, etc., combined with the enterprise user end and the personal situation of the job seeker.

[0134] Exemplarily, the method proposed in this embodiment can determine the reference salary through regression analysis. In a specific embodiment, after the collected variable data are processed by adding or subtracting missing values, converting data, and standardizing, the reference salary range of each job applicant is predicted through a pre-trained salary regression model; optionally, the salary regression model may include but is not limited to a multiple regression model, a ridge regression model, or a lasso regression model.

[0135] Example 2

[0136] This embodiment proposes a job matching system for implementing the job matching method proposed in Embodiment 1. Figure 6 , the system comprising:

[0137] An input module 10, for responding to at least one type of input instruction from the enterprise user end, acquiring part-time job input information based on the input instruction, and determining a part-time job type corresponding to the part-time job input information;

[0138] A generating module 20, configured to extract first historical part-time job information based on historical recruitment information corresponding to the part-time job type at the enterprise user end, and to aggregate the part-time job input information and the first historical part-time job information to generate part-time job recruitment information;

[0139] The display module 30 is used to obtain all the job seeker information matching the part-time job input information, and display it to the enterprise user end in a descending order based on the degree of matching the part-time job recruitment information from the obtained job seeker information; or obtain all the job seeker information matching the part-time job recruitment information, and display it to the enterprise user end in a descending order based on the degree of matching;

[0140] The sending module 40 is used to respond to the selection instruction of the enterprise user terminal and send part-time job recruitment information to all selected job seekers based on the selection instruction;

[0141] The communication module 50 is used to send the positive intention information to the enterprise user end after receiving the positive intention information fed back by the job seeker end to complete the employment matching, provide a communication channel between the enterprise user end and the job seeker end, and store all the interaction data between the enterprise user end and the job seeker end.

[0142] The types of input instructions in the input module 10 include: one or more of text type, voice type, and image type, and the job seeker information in the display module 30 includes information input through the job seeker end and the second historical part-time job information corresponding to the job seeker end.

[0143] Furthermore, the display module 30 can also determine the reference salary corresponding to each job seeker information based on the part-time recruitment information and the job seeker information matching the part-time recruitment information, so as to display the reference salary corresponding to each job seeker information when displaying the job seeker information to the enterprise user end.

[0144] Preferably, the part-time job recruitment information includes multiple part-time job requirement information, and different part-time job requirement information corresponds to respective weight coefficients. The method proposed in this embodiment can also determine the employment preference of the enterprise user terminal according to the first historical part-time job information within a preset time period before the current one, and update the weight information of each part-time job requirement information through a genetic algorithm based on the employment preference;

[0145] Specifically, the job seeker information displayed to the enterprise user terminal is screened and sorted based on the matching degree with the part-time job recruitment information. In this embodiment, the matching degree is calculated by the formula Certainly, among them, Represents the matching degree between job seeker information and part-time job recruitment information. Representative part-time recruitment information, Represents job seeker information, Represents various information in the job seeker information. Represents the score of each information in the job applicant information. Represents the weight coefficient of each information.

[0146] In this embodiment, the job seeker information also includes a resume, and the display module 30 includes:

[0147] The extraction unit 31 is used to extract information of specific parts of speech from the part-time job recruitment information and the job seeker's resume.

[0148] The calculation unit 32 is used to calculate the matching degree between the job seeker's resume and the part-time recruitment information based on the part-time recruitment information and the information of specific parts of speech in the job seeker's resume, and use the matching degree between the resume and the part-time recruitment information as the matching degree between the part-time input information and the part-time recruitment information.

[0149] The integration unit 33 is used to integrate the matching degree between the part-time job input information and the part-time job recruitment information, and the matching degree between the second historical part-time job information and the part-time job recruitment information to obtain the matching degree between the job seeker information and the part-time job recruitment information.

[0150] Specifically, the extraction unit 31 will perform text preprocessing on the part-time recruitment information and the job seeker's resume respectively, and perform part-of-speech tagging on the preprocessed text to extract information about specific parts of speech in the text; text preprocessing includes but is not limited to steps such as word segmentation, removal of stop words, morphological restoration and stem extraction, so as to better process the text.

[0151] Specifically, the extraction unit 31 implements the tagging of the part of speech through a part of speech tagger, and the part of speech tagger will tag the part of speech for each word, such as noun, verb, and adjective; in this embodiment, the specific part of speech includes noun, adjective, verb, and numeral. The formula for calculating the matching degree between the job seeker's resume and the part-time job recruitment information is:

[0152]

[0153] in, Representative part-time recruitment information, Resume representing the job seeker, Represents the matching degree between the job seeker's resume and part-time job recruitment information;

[0154] Represents the noun information in part-time job recruitment information. Represents the noun information in the job seeker's resume. Represents the matching degree between the noun information in the job seeker's resume and the part-time job recruitment information. The weight coefficient representing the matching degree of noun information;

[0155] Represents adjective information in part-time job recruitment information. Represents the adjective information in the job seeker's resume. Represents the matching degree between the adjective information in the job seeker's resume and the part-time job recruitment information. The weight coefficient representing the matching degree of adjective information;

[0156] Represents the verb information in part-time job recruitment information. Represents the verb information in the job seeker's resume. Represents the matching degree between the job seeker's resume and the verb information in the part-time job recruitment information. The weight coefficient representing the matching degree of verb information;

[0157] Represents the numeral information in part-time job recruitment information. Represents the numerical information in the job seeker's resume. Represents the matching degree between the job seeker's resume and the number information in the part-time job recruitment information. The weight coefficient representing the matching degree of numeral information.

[0158] Furthermore, the system further comprises:

[0159] The query module 61 is used to determine other enterprise user terminals of the same type as the enterprise user terminal.

[0160] The selection module 62 is used to select historical part-time job information of corresponding part-time job types of other enterprise user terminals whose business scale is not less than that of the enterprise user terminal.

[0161] The supplement module 63 is used to supplement the selected historical part-time job information of other enterprise users to the first historical part-time job information, and enable the generation module 20 to perform the operation of "aggregating the part-time job input information and the first historical part-time job information to generate part-time job recruitment information".

[0162] A determination module 71, configured to determine a first recruitment requirement from historical recruitment information of an enterprise user terminal;

[0163] The acquisition module 72 is used to extract the second recruitment requirement from the historical recruitment information of other enterprise user terminals of the same type as the enterprise user terminal.

[0164] The label module 73 is used to aggregate the first recruitment requirement and the second recruitment requirement to generate recruitment requirements, and label the recruitment requirements to obtain recruitment requirement labels.

[0165] The update module 74 is used to determine the parts of all recruitment requirement tags that are different from the recruitment requirements corresponding to the input instructions, and display the different parts to the enterprise user end, so that when the enterprise user end triggers the displayed recruitment requirement tag, the input instruction is updated based on the triggered recruitment requirement tag, and the input module 10 performs the operation of "obtaining part-time input information based on the input instruction".

[0166] The analysis module 81 is used to determine the position information corresponding to the salary analysis request when obtaining the salary analysis request from the enterprise user end;

[0167] The estimation module 82 is used to digitize the job information and then combine it with the current market information corresponding to the job information and then import it into the trained salary regression model to obtain the estimated salary information.

[0168] The feedback module 83 is used to feed back the estimated salary information to the enterprise user end.

[0169] In this embodiment, the job information determined by the analysis module 81 includes but is not limited to job type, job location, job time, professional level, and required information of the personnel required for the job such as education, work experience, work skills, etc.

[0170] Furthermore, the display module 30 is connected to the analysis module 81 and the feedback module 83 respectively, so that when the display module 30 executes the preset steps, the analysis module 81 can automatically execute the preset steps, so that when the display module 30 displays the job seeker information to the enterprise user end, the estimated salary information corresponding to each job seeker information fed back by the feedback module 83 is also displayed;

[0171] Exemplarily, the estimation module 82 can determine the reference salary through regression analysis. In a specific embodiment, the system proposed in this embodiment can perform processing such as adding and subtracting missing values, data conversion, and standardization on the collected variable data, and then predict the reference salary range of each job applicant through a pre-trained salary regression model; optionally, the salary regression model can include but is not limited to a multiple regression model, a ridge regression model, or a lasso regression model.

[0172] Example 3

[0173] This embodiment proposes a computer-readable storage medium, which stores executable instructions for implementing the employment matching method proposed in Embodiment 1 when executed by a processor.

[0174] In summary, the present invention provides a method, system and storable medium for employment matching. The solution proposed in the present invention supports enterprise users to input instructions in a variety of ways, can combine input information and historical information to generate more comprehensive and accurate part-time recruitment information, and display part-time workers who meet the needs to enterprise users according to the degree of matching. It provides communication channels and can store interactive data to realize communication between enterprise users and part-time workers, which helps to improve the quality and matching degree of recruitment, thereby significantly improving the efficiency and success rate of enterprise recruitment.

[0175] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A labor matching method, characterized in that: The method comprises: In response to at least one type of input instruction from the enterprise user end, obtaining part-time job input information based on the input instruction, and determining the part-time job type corresponding to the part-time job input information; the type of the input instruction includes: one or any multiple of text type, voice type, and image type; Extracting first historical part-time job information based on the historical recruitment information corresponding to the part-time job type at the enterprise user end, and summarizing the part-time job input information and the first historical part-time job information to generate part-time job recruitment information; Acquire all job seeker information matching the part-time job input information, and display it to the enterprise user terminal in a descending order based on the degree of matching the part-time job recruitment information from the acquired job seeker information; or acquire all job seeker information matching the part-time job recruitment information, and display it to the enterprise user terminal in a descending order based on the degree of matching; the job seeker information includes information input by the job seeker terminal and second historical part-time job information corresponding to the job seeker terminal; In response to a selection instruction of the enterprise user terminal, sending the part-time job recruitment information to all selected job seeker terminals based on the selection instruction; If positive intention information is received from the job seeker, the positive intention information is sent to the enterprise user to complete the job matching, and a communication channel is provided between the enterprise user and the job seeker, and all interaction data between the enterprise user and the job seeker are stored; The part-time job recruitment information includes a plurality of part-time job requirement information; different part-time job requirement information corresponds to respective weight coefficients; the method further includes: regularly determining the employment preference of the enterprise user end according to the first historical part-time job information within a preset time period before the current one; updating the weight information of each part-time job requirement information through a genetic algorithm based on the employment preference; The job seeker information displayed to the enterprise user terminal is screened and sorted based on the matching degree with the part-time job recruitment information. The formula for determining the matching degree includes: in, represents the matching degree between the job seeker information and the part-time job recruitment information, Represents the part-time job recruitment information, Represents the said job seeker information, represents various job-seeking information in the job seeker information that meets the corresponding part-time job requirement information, represents the score of each job application information in the job seeker information, Represents the latest weight coefficient of each job search information; The job seeker information also includes a resume, and the method further includes: Extracting information about specific parts of speech from the part-time job recruitment information and the job seeker's resume respectively; Based on the part-time job recruitment information and the information of the specific part of speech in the job seeker's resume, the matching degree between the job seeker's resume and the part-time job recruitment information is calculated; the matching degree between the resume and the part-time job recruitment information is used as the matching degree between the part-time job input information and the part-time job recruitment information; The matching degree between the job seeker information and the part-time job recruitment information is obtained by comprehensively analyzing the matching degree between the part-time job input information and the part-time job recruitment information, and the matching degree between the second historical part-time job information and the part-time job recruitment information; The "respectively extracting the information of specific parts of speech in the part-time job recruitment information and the job seeker's resume" includes: Performing text preprocessing on the part-time job recruitment information and the job seeker's resume respectively; Performing part-of-speech tagging on the preprocessed text to extract information about specific parts of speech in the text; The specific parts of speech include nouns, adjectives, verbs and numerals. The formula for calculating the matching degree between the job seeker's resume and the part-time job recruitment information is: in, Represents the part-time job recruitment information, Resume of the applicant, Represents the matching degree between the job seeker's resume and the part-time job recruitment information; Represents the noun information in the part-time job recruitment information, Represents the noun information in the resume of the job seeker. Represents the matching degree between the job seeker's resume and the noun information in the part-time job recruitment information, The weight coefficient representing the matching degree of noun information; Represents the adjective information in the part-time job recruitment information, Represents the adjective information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the adjective information in the part-time job recruitment information, The weight coefficient representing the matching degree of adjective information; Represents the verb information in the part-time job recruitment information, Represents the verb information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the verb information in the part-time job recruitment information, The weight coefficient representing the matching degree of verb information; Represents the numeral information in the part-time job recruitment information, Represents the numerical information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the numeral information in the part-time job recruitment information, The weight coefficient representing the matching degree of numeral information.

2. The employment matching method according to claim 1, characterized in that: The "obtaining part-time job input information based on the input instruction" includes: If the type of the input instruction is a voice type, the input instruction is subjected to noise reduction processing to obtain voice data after noise reduction; the voice data is subjected to Mel spectrum analysis to extract voice features, and the voice features are imported into a trained voice model to obtain text information; the text information is imported into a trained semantic model to obtain part-time input information; If the type of the input instruction is an image type, content area recognition is performed on the image corresponding to the input instruction to extract the text content area containing text content in the image; the text content area is divided into multiple sub-text content areas, each of the sub-text content areas includes at least one character or string; the image of each sub-text content area is imported into a trained neural network model to obtain text information; the text information is combined based on the division order of each sub-text content area to obtain text information; the text information is imported into a trained semantic model to obtain part-time input information.

3. The employment matching method according to claim 1, characterized in that: The method further comprises: Determine other enterprise user terminals of the same type as the enterprise user terminal; Selecting historical part-time job information corresponding to the part-time job type of the other enterprise user terminals whose business scale is not less than that of the enterprise user terminal; The selected historical part-time job information of the other enterprise user terminals is added to the historical part-time job information, and the operation of "aggregating the part-time job input information and the first historical part-time job information to generate part-time job recruitment information" is performed.

4. The employment matching method according to claim 1, characterized in that: The method further comprises: Determine a first recruitment requirement from the historical recruitment information of the enterprise user terminal; Extracting second recruitment requirements from historical recruitment information of other enterprise user terminals of the same type as the enterprise user terminal; Summarizing the first recruitment requirement and the second recruitment requirement to generate recruitment requirements, and labeling the recruitment requirements to obtain recruitment requirement labels; Determine the parts of all the recruitment requirement tags that are different from the recruitment requirements corresponding to the input instruction, and display the different parts to the enterprise user end, so that when the enterprise user end triggers the displayed recruitment requirement tag, the input instruction is updated based on the triggered recruitment requirement tag, and the operation of "obtaining part-time job input information based on the input instruction" is performed.

5. The employment matching method according to claim 1, characterized in that: The method further comprises: If a salary analysis request from the enterprise user is obtained, determining the position information corresponding to the salary analysis request; the position information includes: position type, position location, position time and required personnel information for the position; After the job information is digitized, it is combined with the current market information corresponding to the job information and then imported into a trained salary regression model to obtain estimated salary information; wherein the salary regression model includes a multiple regression model, a ridge regression model or a lasso regression model; The estimated salary information is fed back to the enterprise user end.

6. A job matching system, characterized in that: The system comprises: An input module, for responding to at least one type of input instruction from an enterprise user terminal, acquiring part-time job input information based on the input instruction, and determining a part-time job type corresponding to the part-time job input information; the type of the input instruction includes: one or any combination of text type, voice type, and image type; A generating module, configured to extract first historical part-time job information based on the historical recruitment information corresponding to the part-time job type at the enterprise user end, and to aggregate the part-time job input information and the first historical part-time job information to generate part-time job recruitment information; A display module is used to obtain all the job seeker information matching the part-time job input information, and display it to the enterprise user terminal in a descending order based on the degree of matching the part-time job recruitment information from the obtained job seeker information; or obtain all the job seeker information matching the part-time job recruitment information, and display it to the enterprise user terminal in a descending order based on the degree of matching; the job seeker information includes the information input by the job seeker terminal and the second historical part-time job information corresponding to the job seeker terminal; A sending module, configured to respond to a selection instruction of the enterprise user terminal and send the part-time job recruitment information to all selected job seeker terminals based on the selection instruction; A communication module, for sending the positive intention information fed back by the job seeker to the enterprise user end to complete the employment matching, providing a communication channel between the enterprise user end and the job seeker end, and storing all the interaction data between the enterprise user end and the job seeker end; The part-time job recruitment information includes multiple part-time job requirement information; different part-time job requirement information corresponds to respective weight coefficients; the generation module is also used to determine the employment preference of the enterprise user terminal according to the first historical part-time job information within a preset time period before the current time period; based on the employment preference, the weight information of each part-time job requirement information is updated through a genetic algorithm; the job seeker information displayed by the display module to the enterprise user terminal is screened and sorted based on the matching degree with the part-time job recruitment information, and the formula for determining the matching degree includes: in, represents the matching degree between the job seeker information and the part-time job recruitment information, Represents the part-time job recruitment information, Represents the said job seeker information, represents various job-seeking information in the job seeker information that meets the corresponding part-time job requirement information, represents the score of each job application information in the job seeker information, Represents the latest weight coefficient of each job search information; The job seeker information also includes a resume, and the display module includes: An extraction unit, used to extract information of specific parts of speech from the part-time job recruitment information and the resume of the job seeker respectively; A calculation unit is used to calculate the matching degree between the job seeker's resume and the part-time job recruitment information based on the part-time job recruitment information and the information of the specific part of speech in the job seeker's resume; and use the matching degree between the resume and the part-time job recruitment information as the matching degree between the part-time job input information and the part-time job recruitment information; A synthesis unit, configured to synthesize the matching degree between the part-time job input information and the part-time job recruitment information, and the matching degree between the second historical part-time job information and the part-time job recruitment information to obtain the matching degree between the job seeker information and the part-time job recruitment information; The extraction unit performs text preprocessing on the part-time job recruitment information and the job seeker's resume, and performs part-of-speech tagging on the preprocessed text to extract information on specific parts of speech in the text; The specific parts of speech include nouns, adjectives, verbs and numerals. The formula for calculating the matching degree between the job seeker's resume and the part-time job recruitment information is: in, Represents the part-time job recruitment information, Resume of the applicant, Represents the matching degree between the job seeker's resume and the part-time job recruitment information; Represents the noun information in the part-time job recruitment information. Represents the noun information in the resume of the job seeker. represents the matching degree between the job seeker's resume and the noun information in the part-time job recruitment information, The weight coefficient representing the matching degree of noun information; Represents the adjective information in the part-time job recruitment information, Represents the adjective information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the adjective information in the part-time job recruitment information, The weight coefficient representing the matching degree of adjective information; Represents the verb information in the part-time job recruitment information, Represents the verb information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the verb information in the part-time job recruitment information, The weight coefficient representing the matching degree of verb information; Represents the numeral information in the part-time job recruitment information, Represents the numerical information in the resume of the job seeker, represents the matching degree between the job seeker's resume and the numeral information in the part-time job recruitment information, The weight coefficient representing the matching degree of numeral information.

7. A computer-readable storage medium, characterized in that: Executable instructions are stored, and when executed by a processor, the instructions are used to implement the method according to any one of claims 1 to 5.