Method, device, electronic device and storage medium for searching candidate users

Abstract

The present application discloses a method, device, electronic device and storage medium for searching candidate users. The method includes: accessing a recruitment website and requesting a job-seeking user information set from the recruitment website; sending the job-seeking user information set to a preset language analysis model to generate an adaptation result through the preset language analysis model; according to the adaptation result, sending a first dialogue message to a first candidate user, the first dialogue content including job invitation information and job information; sending a text analysis instruction and a second dialogue message to the preset language analysis model so that the preset language analysis model generates an analysis result; obtaining the contact information of the recruitment user corresponding to the job information, and sending the contact information of the recruitment user to the target user, wherein the target user is a candidate user whose entry intention level meets the second level requirements. The embodiments of the present application can improve the success rate of recruitment users in completing recruitment work and reduce the time cost and manpower cost of recruitment users in mining talents.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and storage medium for searching candidate users. Background Art

[0002] With the popularization of the Internet and the increasing maturity of data processing technology, more and more convenience has been brought to users' lives and work. For example, in the recruitment industry, recruiters can post recruitment information on recruitment websites and find the required job seekers in recruitment software, while job seekers can post resumes on recruitment software and find suitable positions in recruitment software.

[0003] In some scenarios where there is a large demand for manpower or recruitment is urgent, recruiters need to combine their personal recruitment experience to find job seekers who are more interested in the position from a large number of resumes, and then send interview invitations to these job seekers one by one to advance the recruitment progress. It can be seen that during the entire recruitment process, recruiters need to process information from each recruitment link, which incurs huge manpower costs.

[0004] Although existing recruitment websites provide resume screening functions, in the case of a wide range of skills required for occupations, even after screening, recruiters still need to review a large number of resumes. In addition, since the resumes posted by different job seekers are also diverse, recruiters need to spend extra energy in the process of reviewing resumes. Moreover, since job hunting and recruitment are a two-way selection process, whether a suitable employee can be successfully found also needs to consider the job seeker's interest in the position. Therefore, recruiters need to communicate with job seekers separately, which brings a huge workload to recruiters for some companies with large employee needs. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method, device, electronic device and storage medium for searching candidate users, which are used to improve the success rate of recruiting users in completing recruitment work and reduce the time and labor costs of recruiting users in discovering talents.

[0006] The embodiment of the present application provides a method for searching candidate users, comprising: accessing a recruitment website and requesting a job seeker information set from the recruitment website, the job seeker information set including resume information corresponding to a plurality of job seekers respectively; in response to receiving the job seeker information set, sending the job seeker information set to a preset language analysis model, so as to generate an adaptation result through the preset language analysis model, the adaptation result including the adaptation level of each resume information and job information, the preset language analysis model being pre-configured with job information of a target job; in response to receiving the adaptation result, sending a first dialogue message to a first candidate user according to the adaptation result, the first dialogue content including job application invitation information and job information, wherein the candidate user is a job seeker whose adaptation level meets the requirements of the first preset level; in response to receiving a second dialogue message in which the candidate user replies to the first dialogue message, sending a text analysis instruction and a second dialogue message to the preset language analysis model, so that the preset language analysis model generates an analysis result, wherein the analysis result includes the level of employment intention; in response to receiving the analysis result, obtaining contact information of the recruitment user corresponding to the job information, and sending the contact information of the recruitment user to the target user, wherein the target user is a candidate user whose employment intention level meets the requirements of the second level.

[0007] Optionally, according to the method of an embodiment of the present application, the text analysis instruction includes: the text range to be analyzed, the text analysis angle, the output format of the analysis results and the reference text information of the output results; wherein the text analysis angle includes at least any one of the job seeker's employment intention, emotion type and emotion intensity.

[0008] Optionally, before visiting a recruitment website, the method according to an embodiment of the present application includes: obtaining a suitability analysis requirement corresponding to a target position, the suitability analysis requirement including at least one of a work experience suitability analysis, a skill requirement suitability analysis, a customer service awareness suitability analysis, a teamwork and adaptability suitability analysis, and an overall suitability analysis; sending the position information and the suitability analysis instruction of the target position to a preset language analysis model to configure the preset language analysis model, the suitability analysis instruction including the suitability analysis requirement, a first output format of the adaptation result, and a reason for generating the adaptation result.

[0009] Optionally, according to the method of the embodiment of the present application, in response to receiving the adaptation result, the method further includes: receiving and saving the adaptation result of the first output format generated by the preset language analysis model and the reason for the adaptation result of the first output format.

[0010] Optionally, according to the method of the embodiment of the present application, the method further includes: generating, for the target user, a reference text requesting to add a contact, and sending the reference text to the target user.

[0011] Optionally, according to the method of the embodiment of the present application, the method also includes: sending information extraction requirements to a preset language analysis model, the information extraction requirements including resume information extraction requirements, position information extraction requirements and a first output format; after sending the job seeker information set and the position information of the target position to the preset language analysis model, the method also includes: receiving and saving the extracted information in the first output format generated by the preset language analysis model; wherein the extracted information includes resume extraction information and position extraction information; the resume extraction information includes: basic information, education information, work experience, work content, skills and expertise, and self-evaluation; the position extraction information includes: position title, company name, work location, salary, release date, job responsibilities, job requirements, benefits, company profile, and application method.

[0012] The embodiment of the present application provides a device for searching candidate users, including: a sending module for accessing a recruitment website and requesting a job-seeking user information set from the recruitment website, the job-seeking user information set including resume information corresponding to a plurality of job-seeking users respectively; the sending module is also used for sending the job-seeking user information set to a preset language analysis model in response to receiving the job-seeking user information set, so as to generate an adaptation result through the preset language analysis model, the adaptation result including the adaptation level of each resume information and the job information, the preset language analysis model being pre-configured with the job information of the target job; the sending module is also used for sending a first dialogue message to a first candidate user in response to receiving the adaptation result according to the adaptation result, the dialogue content including the job application invitation information and the job information, wherein the candidate user is a candidate user with an adaptation level. a job seeker who meets the first preset level requirement; a sending module, which is also used to send a text analysis instruction and a second dialogue message to the preset language analysis model in response to receiving a second dialogue message in which the candidate user replies to the first dialogue message, so that the preset language analysis model generates an analysis result, wherein the analysis result includes the entry intention level; an acquisition module, which is used to, in response to receiving the analysis result, obtain the contact information of the recruiting user corresponding to the job information when the entry intention level meets the second level requirement; the acquisition module is also used to, in response to receiving the analysis result, obtain the contact information of the recruiting user corresponding to the job information; the sending module is also used to send the contact information of the recruiting user to the target user, wherein the target user is a candidate user whose entry intention level meets the second level requirement.

[0013] 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.

[0014] 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.

[0015] 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.

[0016] By using the embodiment of the present application, a large number of resume information of job seekers can be automatically obtained by visiting a recruitment website. The resume information of the job seekers and the job information of the target position are sent to a preset language analysis model, and the language analysis model determines the level of suitability between each resume and the position through semantic analysis. Therefore, there is no need to write complex resume screening codes for different positions, and flexible response to different job requirements can be achieved, and resumes with higher suitability for the position can be conveniently found among a large number of resumes. Afterwards, by sending a conversation content including application invitation information and job information to candidate users who meet the first preset level requirements, candidate users can easily understand the job information and can choose whether to respond to the conversation content according to their needs. After receiving the second dialogue message in which the candidate user replies to the first dialogue message, the second dialogue message is analyzed through the preset language analysis model according to the instructions of the branch instruction, and the candidate user's employment intention level has been obtained. In particular, for the target user whose employment intention level meets the second preset level, the recruiting user's contact information can be actively sent to the target user, so that the target user has more sufficient options to choose whether to further communicate with the recruiting user. Once the target user actively communicates with the recruiting user, this means that the job seeker contacted by the recruiting user has a higher intention to join the job, which improves the success rate of the recruiting user in completing the recruitment work and reduces the time and manpower costs of the recruiting user in discovering talents. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 It is a schematic diagram of the system architecture of an embodiment of the present application.

[0019] Figure 2 It is a flowchart of the method for searching candidate users according to an embodiment of the present application.

[0020] Figure 3 It is a structural block diagram of a device for searching candidate users according to an embodiment of the present application.

[0021] Figure 4 It is a schematic diagram of an electronic device used to implement the method for searching candidate users in an embodiment of the present application. DETAILED DESCRIPTION

[0022] 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.

[0023] It should be noted that the acquisition, storage, use, and processing of data in the embodiments of the present application are in compliance with the relevant provisions of national laws and regulations.

[0024] 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).

[0025] Embodiments of the present application relate to terminal devices and / or servers. Those skilled in the art will appreciate that the embodiments of the present application may be implemented as a system, apparatus, device, method, computer-readable storage medium, or computer program product. Therefore, the present disclosure may be specifically implemented as at least one of the following forms: complete hardware, complete software, or a combination of hardware and software. According to the embodiments of the present application, the present application claims protection for a method, apparatus, electronic device, computer-readable storage medium, and computer program product for searching for candidate users.

[0026] Figure 1 A schematic diagram of a system architecture of an embodiment of the present application is shown. Figure 1As 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.

[0027] With the popularization of the Internet and the increasing maturity of data processing technology, more and more convenience has been brought to users' lives and work. For example, in the recruitment industry, recruiters can post recruitment information on recruitment websites and find the required job seekers in recruitment software, while job seekers can post resumes on recruitment software and find suitable positions in recruitment software.

[0028] In the related art, existing recruitment websites provide the function of resume screening. However, in the case of a wide range of skills required for occupations, even after screening, recruiters still need to review a large number of resumes. Moreover, after reviewing the resumes one by one, recruiters need to send invitations and then answer questions related to the job introduction. Relevant technical personnel have found that in some scenarios where there is a large demand for manpower or the urgency of recruitment is high, the entire recruitment process not only takes a lot of time and generates huge labor costs, but also the recruitment effect is difficult to estimate, which leads to recruitment difficulties.

[0029] Based on the above considerations, an embodiment of the present application provides a method for searching candidate users. By visiting a recruitment website, a large amount of resume information of job seekers can be automatically obtained. Afterwards, a language analysis model analyzes each resume to find a resume with a higher degree of adaptability. Then, based on the content of the resume, the method automatically communicates with the job seeker corresponding to the resume to find out users with a higher intention to join the job. Afterwards, the candidate user actively sends the contact information of the recruiting user, so that the candidate user has more sufficient choice to choose whether to further communicate with the recruiting user. Once the candidate user actively communicates with the recruiting user, this means that the job seeker contacted by the recruiting user has a higher tendency to join the job, thereby improving the success rate of the recruiting user in completing the recruitment work and reducing the time and labor costs of the recruiting user in discovering talents.

[0030] The following is an introduction to the method for searching candidate users provided in the embodiment of the present application in conjunction with the accompanying drawings. Figure 2 A schematic flow chart of a method for searching candidate users according to an embodiment of the present application is shown. The method includes the following steps 201 to 205 .

[0031] Step 201 : accessing a recruitment website and requesting a job-seeking user information set from the recruitment website. The job-seeking user information set includes resume information corresponding to a plurality of job-seeking users.

[0032] Step 202, in response to receiving the job seeker information set, sends the job seeker information set to a preset language analysis model to generate an adaptation result through the preset language analysis model, the adaptation result including the adaptation level of each resume information and the job information, and the preset language analysis model is pre-configured with the job information of the target job.

[0033] Step 203, in response to receiving the adaptation result, a first dialogue message is sent to a first candidate user according to the adaptation result, the first dialogue content includes job invitation information and position information, wherein the candidate user is a job seeker whose adaptation level meets the first preset level requirement.

[0034] Step 204, in response to receiving a second dialogue message in which the candidate user replies to the first dialogue message, sending a text analysis instruction and the second dialogue message to a preset language analysis model, so that the preset language analysis model generates an analysis result, wherein the analysis result includes a level of intention to join the job.

[0035] Step 205, in response to receiving the analysis result, obtaining the contact information of the recruiting user corresponding to the position information, and sending the contact information of the recruiting user to the target user, wherein the target user is a candidate user whose employment intention level meets the second level requirement.

[0036] The above steps are described in detail below in conjunction with specific embodiments, as shown below.

[0037] In an embodiment of the present application, the executor of the method for searching candidate users may be an electronic device with data processing capabilities, such as a service terminal. The service terminal may be a physical server, a virtual server, or a cloud server. No specific restrictions are imposed on the form of expression of the service terminal.

[0038] Involving the above step 201, the recruitment website can be used for job seekers to find jobs and help recruiters recruit employees. Resumes posted by job seekers and job information posted by recruiters can be collected on the recruitment website. Therefore, by visiting the recruitment website, a large number of job seekers who are looking for jobs can be easily found.

[0039] Optionally, in an embodiment of the present application, the number of the above-mentioned recruitment websites may be one or more, that is, the resume information included in the job-seeking user information set may come from different recruitment websites.

[0040] After obtaining the resume information of the job seeker, step 202 is involved, sending the job seeker information set to a preset language analysis model to generate an adaptation result through the preset language analysis model.

[0041] The preset language analysis model is a model that has been trained and optimized with a large amount of recruitment data and job seekers' resume data.

[0042] Before recruiting for a target position, you can configure the preset language analysis model so that it can fully learn the job information of the target position, understand the requirements and responsibilities of the job information, etc. After receiving the resume information, the preset language analysis model can automatically analyze the resume and determine the level of compatibility between the resume and the target position, thereby obtaining the matching result.

[0043] After the preset language analysis model determines the adaptation result, the adaptation result service terminal can be provided, involving step 203. The service terminal can determine the job seeker who meets the first preset level requirement from the adaptation result according to the adaptation result.

[0044] Exemplarily, the adaptation level can be a simplified level classification, for example, low adaptation, medium adaptation, and high adaptation. The adaptation level can also be quantified with specific numerical values, for example, the adaptation level is a score of 0 to 1, where 0 is the lowest adaptation and 1 is the highest adaptation.

[0045] The first preset level requirement can be configured in combination with the specific settings of the adaptation level. For example, if the adaptation level is a simplified level division, the first preset level requirement may be to obtain resume information with a high adaptability level; if the adaptation level is numerically quantified, the first preset level requirement may be to obtain resume information with a score greater than a preset value, such as 80%.

[0046] In the embodiment of the present application, job seekers who meet the first preset level requirements are determined as candidate users. After determining the job seekers who meet the first preset level requirements, the service terminal can automatically determine the contact information of the candidate users, and then send the first dialogue content including the job invitation information and the job information to the candidate users. On the one hand, after seeing the dialogue content, the candidate users can easily understand the job information and fully consider whether to apply for the target job according to their own needs. On the other hand, the candidate users have more choices to choose whether to further respond to the first dialogue content.

[0047] Optionally, the first conversation content may be sent to the candidate user via a recruitment website, or via a text message, or other ways of contacting the candidate user, which are not listed here.

[0048] In the case where the candidate user replies to the first conversation content, that is, the service terminal can receive the second conversation information input by the candidate user, which involves step 204. The service terminal can send the second conversation message to the preset language analysis model, and at the same time, send the text analysis instruction to the preset language analysis model, so that the preset language analysis model can analyze the second conversation message in combination with the content of the instruction and generate an analysis result. The analysis result at least includes the candidate user's employment intention level.

[0049] Exemplarily, the employment intention level can be a simplified level classification, for example, low employment intention, medium employment intention, and high employment intention. The employment intention level can also be quantified with specific numerical values, for example, the employment intention value is a score of 0 to 1, where 0 is the lowest employment intention and 1 is the highest employment intention.

[0050] Optionally, the preset language analysis model may also generate reply information for the second dialogue message, and send the reply message to the candidate user through the service terminal.

[0051] For example, when the preset language analysis model detects that the first dialogue message lacks key information, the reply message may include questions regarding the key information; for another example, when it is detected that the first dialogue message of the candidate user contains job-related questions, the reply message may include answers to the questions.

[0052] After the service terminal obtains the analysis results of the candidate users, it involves step 205, and can determine the candidate users whose employment intention levels meet the second level requirements, that is, the target users, according to the analysis results. Optionally, the second preset level requirement can be configured in combination with the specific setting of the employment intention level. For example, if the employment intention level is a simplified level division, the second preset level requirement can be to obtain candidate users with a high employment intention level; if the employment intention level is a numerical quantification, the second preset level requirement can be to obtain candidate users with a score greater than a preset value, such as 80%.

[0053] After determining the target user, the contact information of the recruiter can be proactively sent to the target user. This gives the target user more options to choose whether to further communicate with the recruiter. Once the candidate user proactively communicates with the recruiter, it means that the job seeker contacted by the recruiter has a higher tendency to join the job, thereby increasing the success rate of the recruiter in completing the recruitment work and reducing the time and labor costs of the recruiter in discovering talents.

[0054] In some embodiments of the present application, the method for searching for candidate users further includes: generating, for the target user, a reference text for requesting to add a contact, and sending the reference text to the target user.

[0055] Specifically, the preset language analysis model can also determine the target user based on the analysis results generated by it, and can generate a reference text based on the language style of the target user, and send the reference text to the target user through the service terminal.

[0056] Based on this, if the target user wants to add the recruiting user corresponding to the job information as a contact, he can choose to use the reference text as the request information for adding a contact, which saves the trouble of the target user editing the text and brings convenience to the target user. In this way, after seeing the request information, the recruiting user can also quickly understand the target user, saving the communication cost between the recruiting user and the target user.

[0057] In some embodiments of the present application, a Robotic Process Automation (RPA) tool can be used to replace the recruiting user to visit the recruitment website and request the job seeker information set from the recruitment website. Specifically, a Selenium+Python language browser automation tool can be used to simulate the daily recruitment behavior of the recruiting user, and extract repetitive and regular work steps based on the daily recruitment behavior, such as automatically collecting and processing job seekers' resumes, automatically screening and matching positions, etc., and design corresponding automated processes for these work steps.

[0058] Based on this, RPA tools can replace recruiters in logging into recruitment websites, viewing job seekers' information, obtaining job seekers' resumes, saving job seekers' resumes, etc., thereby reducing the workload of recruiters.

[0059] Based on this, RPA tools can automatically collect resume information of job seekers from major recruitment websites, social media platforms and other channels. Optionally, RPA tools can also pre-configure data preprocessing capabilities. For example, before the resume information of job seekers is input into the preset language analysis model, the resume information can be pre-processed by RPA tools. The preprocessing includes but is not limited to format conversion and data cleaning to ensure the accuracy and consistency of the resume information.

[0060] Optionally, you can build the graphical user interface (GUI) of the RPA tool through Java (server-side language) + Vue (front-end interface), and configure the RPA tool to execute the designed automation process. This includes setting the operation steps, logical conditions, error handling, etc. of the RPA tool. In addition, after deploying the configured RPA tool to the working environment, the RPA tool can be monitored and managed in real time. Ensure that the RPA tool can run normally and handle abnormal situations in a timely manner.

[0061] The resume information obtained and preprocessed by the RPA tool can be input into the preset language analysis model. For example, the preset language analysis model can be a model that can perform language analysis, such as ChatGPT. The RPA tool and the preset meta-analysis model work together to provide decision support for recruiting users. For example, based on the target position and the resume information of the job seeker, recruitment reports and suggestions are automatically generated to help recruiters make more informed decisions. In this way, there is no need for developers to write logical operation formulas and complex execution codes for matching positions with resumes, which reduces the workload of developers and facilitates flexible and rapid response to different matching needs.

[0062] In some embodiments of the present application, before visiting a recruitment website, the following steps may be specifically included: obtaining the suitability analysis requirements corresponding to the target position, the suitability analysis requirements including at least one of work experience suitability analysis, skill requirement suitability analysis, customer service awareness suitability analysis, teamwork and adaptability suitability analysis, and overall suitability analysis; sending the position information and suitability analysis instructions of the target position to a preset language analysis model to configure the preset language analysis model, the suitability analysis instructions including the suitability analysis requirements, the first output format of the adaptation result, and the reason for generating the adaptation result.

[0063] Based on this, it is easy to provide intelligent decision support for recruiters through the data analysis capabilities of the preset language analysis model. For example, according to the job requirements and the resume information of the job seeker, the adaptation results are automatically generated to help recruiters make more informed decisions.

[0064] In some embodiments of the present application, when the preset language analysis model is completed based on the above configuration, after the service terminal responds to the step of receiving the adaptation result, the method for searching candidate users may also include the following steps: receiving and saving the adaptation result of the first output format generated by the preset language analysis model and the reason for the adaptation result of the first output format.

[0065] The first output format may be JSON format or other required format.

[0066] In some embodiments of the present application, information extraction requirements can also be sent to a preset language analysis model, and the information extraction requirements include resume information extraction requirements, position information extraction requirements and a first output format; based on this, after sending a job seeker information set and position information of a target position to the preset language analysis model, the method also includes: receiving and saving the extraction information in the first output format generated by the preset language analysis model; wherein the extraction information includes resume extraction information and position extraction information; the resume extraction information includes: basic information, education information, work experience, work content, skills and expertise, and self-evaluation; the position extraction information includes: position title, company name, work location, salary, release date, job responsibilities, job requirements, benefits, company profile, and application method.

[0067] For a resume information, the results output by the preset language analysis model may include the resume information converted into json format, the position information in json format and the reason in json format. The specific examples are shown below.

[0068] Resume information in json format: {"Basic Information":{"Name":"XXX","Gender":"Male","Age":"xx","Contact Information":{"Tel":"1xxxxxxxxx8","Email":"xxxxx@example.com"},"Address":"No. X Street, Chaoyang District, Beijing"},"Education Background":{"Graduate School":"XX Vocational and Technical College","Education":"College","Major":"Food Science and Engineering","Graduation Date":"June 2015"},"Work Experience":[{"Company Name":"XX Cafe","Position":"Barista","Work Time":"March 2016 to Present","Job Description":["Responsible for the production and sales of coffee, including the production of classic coffees such as hand-brewed, espresso, and latte","Prepare specialty coffee according to customer needs to improve customer satisfaction","Participate in the research and development and testing of new coffee products and put forward suggestions for improvement","Maintain the hygiene and order of the cafe and ensure good customer experience"]},{"Company Name":"YY Cafe","Position":"Coffee Assistant","Working Time":"July 2015 to February 2016","Job Description":["Assisting the barista in the preparation and production of coffee","Learning coffee culture and knowledge, and improving coffee making skills","Participating in the daily operation and management of the cafe"]}],"Skills and Expertise":["Proficient in various coffee making techniques, including hand brewing, espresso, etc.","Having a deep understanding of coffee beans, and being able to brew coffee beans according to their characteristics","Having good customer service awareness and communication skills, and being able to solve customer problems","Familiar with the operation and management process of the cafe, and having certain management capabilities"],"Self-evaluation":"I am a barista who loves the coffee business and has rich experience in coffee making. I pay attention to details, pursue quality, and am committed to providing customers with the best coffee experience. At the same time, I also have a strong learning ability and team spirit, and am willing to constantly challenge and improve myself."}.

[0069] Job information in json format: {"Job title":"Barista","Company name":"NN Coffee House","Work location":"Xuhui District, Shanghai","Salary":"xxxx-xxxx yuan / month","Release date":"YYYY-YY-YY","Job responsibilities":["Responsible for the production and sales of coffee in the store, including the preparation of classic coffee and specialty coffee","Understand customer needs, provide personalized coffee recommendations, and improve customer satisfaction","Participate in the research and development and testing of new coffee products, and put forward innovative suggestions","Maintain store hygiene and order to ensure a good customer experience","Assist the store manager in daily operations and management of the store, including inventory management, equipment maintenance, etc."],"Job requirements":["Have at least 1 year of experience as a barista and be familiar with the coffee making process and techniques","Have a deep understanding of coffee beans and be able to prepare them according to the characteristics of coffee beans","Have good customer service"] Customer service awareness and communication skills, able to solve customer problems", "Love coffee business, pay attention to details, pursue quality", "Have teamwork spirit, able to adapt to a fast-paced work environment", "Prioritize candidates with barista-related certificates or food industry experience"],"Benefits":["Five insurances and one fund","Paid annual leave","Holiday benefits","Employee training","Promotion opportunities"],"Company Profile":"Dream Cafe is a cafe that focuses on providing high-quality coffee and a comfortable environment. We are committed to providing customers with the best coffee experience. We have a passionate and creative team, and welcome you who are interested in the coffee business to join our big family.","How to apply":"Please send your resume to xxxxx@xxxxx.com, and please indicate 'Apply for Barista-Name' in the email subject. We will contact suitable candidates within one week after receiving the resume to arrange an interview."}

[0070] The big model analyzes the match between the position and the resume, and outputs the reason in json format: {"Position Name":"Barista","Resume Name":"Zhang San","Fitness Analysis":{"Work Experience":{"Fitness":"High","Reason":"Zhang San has more than 1 year of experience as a barista, and has accumulated rich experience in coffee making and sales while working as a barista in XX coffee shop, which meets the requirements of the position."},"Skill Requirements":{"Fitness":"High","Reason":"Zhang San is proficient in various coffee making techniques, including hand brewing, espresso, etc., and has a deep understanding of coffee beans. He can mix according to the characteristics of different coffee beans, which meets the skill requirements of the position."},"Customer Service Awareness":{"Fitness":"High","Reason":"Zhang San has good customer service awareness and communication skills, and can Solving customer problems meets the position's customer service requirements."},"Teamwork and adaptability":{"Fitness":"Medium","Reason":"The resume mentions that Zhang San has strong learning ability and teamwork spirit, but does not explicitly mention the ability to adapt to a fast-paced work environment. However, based on his work experience, it can be inferred that he should have a certain degree of adaptability."},"Other requirements":{"Fitness":"High","Reason":"Zhang San loves the coffee business, pays attention to details, pursues quality, and has experience in the food industry (with a background in food science and engineering from XX Vocational and Technical College), which meets the other requirements of the position. "}},"Overall suitability":"High","Recommendation":"Based on the above analysis, Zhang San is highly suitable for the barista position. It is recommended to conduct an interview to further evaluate his professional skills and teamwork ability."}.

[0071] Compared with the traditional method of writing regular expressions to parse out the keywords in the resume and hard-coding the matching relationship in the system, if the job information of the target position and the filling target of the resume information change, the matching rules need to be rewritten. According to the embodiment of the present application, by introducing a preset language analysis model, not only can various versions of official position information or resume information be flexibly responded to, but also corresponding adaptation results can be output.

[0072] For example, during the resume screening process, the preset language analysis model can automatically parse resumes of different formats and accurately extract key information of job seekers, such as work experience, educational background, etc., even if the format or data structure in the resume information changes, it can maintain high accuracy. For another example, during the resume screening process, if the RPA tool encounters unrecognizable characters or incorrectly formatted resume information, the preset language analysis model can automatically analyze the error type and try to fix or mark these errors without manual intervention. This can significantly improve the accuracy and efficiency of the recruitment process.

[0073] According to the embodiment of the present application, the preset language analysis model can also convert resume information of different templates and formats into a unified format for output, which is also convenient for simplifying the complexity of extracting data from resume information in the subsequent resume analysis scenario.

[0074] In addition, in some embodiments of the present application, the preset language analysis model is a model that has been trained and optimized with a large amount of recruitment data and resume data of job seekers.

[0075] Exemplarily, a language analysis model can be trained using examples including text analysis instructions, wherein the text analysis instructions may include: the text range to be analyzed, the text analysis angle, the output format of the analysis results, and reference text information of the output results; wherein the text analysis angle includes at least any one of the job seeker's employment intention, emotion type, and emotion intensity.

[0076] Based on this, during the application process, the preset language analysis model is combined with the text analysis instructions to analyze the first conversation information of the job seeker, thereby generating an analysis result.

[0077] Exemplarily, the reference text information used to train the preset language analysis model is as follows.

[0078] Reference text information (1) Analysis of job seekers’ employment intentions through conversation content

[0079] "Applicant: I am very interested in this position and hope to have the opportunity to join your company. I think my skills and experience are in line with the requirements of this position."

[0080] Prompt: Please analyze the above conversation to determine whether the applicant is interested and whether he / she meets the conditions for actively providing contact information, and output the analysis results in JSON format. Expected output:

[0081] {

[0082] "Is the intention strong":true,

[0083] "Whether to actively provide contact information": true,

[0084] "Analysis reason": "The applicant expressed great interest in the position and believed that his / her skills and experience meet the requirements of the position, so he / she has a strong intention and may be willing to actively provide contact information."

[0085] }

[0086] Reference text information (2): Emotional type analysis

[0087] "Applicant: I think this position is suitable for me, but your company's salary is a bit low. I am still considering it."

[0088] Prompt: Please analyze the emotions in the above conversation content and output the analysis results in JSON format, including the emotion type (such as positive, negative, neutral) and emotion intensity.

[0089] {

[0090] "Emotional type": "Neutral to negative",

[0091] "Emotional intensity": "Medium",

[0092] "Analysis reason": "The applicant thinks the position is suitable, but is dissatisfied with the salary and benefits, so the emotion is neutral to negative."

[0093] }

[0094] Reference text information (3) Output format of analysis results and reference text information of output results

[0095] Prompt: You are the recruiter of the job information, and the applicant replies: I think the position is suitable for me. You need to reply with your contact information and ask the other party to add it. Return the content in json format.

[0096] {"response":"I'm glad to hear that you think this position is a good fit for you. In order to better communicate the subsequent interview and onboarding process, please add my contact information. My WeChat / email address is [your WeChat ID or email address]. I look forward to further communication with you. If you have any questions or need more information about the position, please feel free to contact me. I wish you all the best!"}

[0097] It is understandable that the above reference text information is only an example to facilitate understanding of the technical solution of the present application, and is not intended as a specific limitation on the embodiments of the present application.

[0098] According to an embodiment of the present application, the second conversation information is analyzed by a preset language analysis model according to the instructions of the branch instruction, and the candidate user's employment intention level has been obtained. Especially when the employment intention level meets the second preset level, the candidate user can be actively sent the contact information of the recruiting user, so that the candidate user has more sufficient options to choose whether to further communicate with the recruiting user. Once the candidate user actively communicates with the recruiting user, it means that the job seeker contacted by the recruiting user has a higher intention to join the job, which improves the success rate of the recruiting user in completing the recruitment work and reduces the time and manpower costs of the recruiting user in discovering talents.

[0099] In some optional embodiments, the RPA tool can be configured to automatically arrange the interview time and location, confirm with the job seeker, and track the recruitment progress in real time, including resume delivery, interview arrangement, result feedback and other links. It can also automatically collect job seekers' feedback on the recruitment process, and organize and analyze it to continuously improve and optimize the recruitment process. Ultimately, the recruitment process can be efficiently automated and intelligent, the recruitment efficiency and quality can be improved, the labor cost and time cost can be reduced, and greater value can be brought to the enterprise.

[0100] According to the method for finding candidate users provided in the embodiment of the present application, the RPA tool and the preset language analysis model are used to automatically guide job seekers, significantly improving the efficiency of recruitment. Compared with the traditional time-consuming, labor-intensive and error-prone recruitment process. The method for finding candidate users provided in the embodiment of the present application realizes automatic screening, preliminary evaluation and classification of resumes, and combines the preset language analysis model to deeply understand and analyze the background of job seekers, which can more accurately match job requirements with job seekers' abilities, thereby speeding up the recruitment process and improving the quality of recruitment.

[0101] In addition, RPA tools can automatically handle a large number of repetitive recruitment tasks, such as resume collection and preliminary screening, which greatly reduces the workload of recruiters and reduces labor costs. RPA tools can also intelligently screen and classify collected resumes based on preset rules and algorithms. This intelligent processing not only improves screening efficiency, but also reduces misjudgments caused by human factors, making screening results more accurate and reliable. In addition, RPA can flexibly adjust screening criteria according to changes in recruitment needs to adapt to the recruitment needs of different positions.

[0102] By using the preset language analysis model to deeply understand and analyze the background of job seekers, we can provide personalized recommendations and guidance for job seekers. For example, we can determine the positions and recruitment processes for job seekers based on their professional skills, work experience and job search intentions, thereby improving job seekers' satisfaction and participation. At the same time, the big model can also provide job seekers with real-time consultation and answers through the intelligent dialogue system, enhancing the interactivity and humanity of the recruitment process.

[0103] The combination of RPA tools and preset language analysis models enables the recruitment team to focus on higher-value tasks, such as candidate communication, interview assessment, etc., optimizes the allocation of human resources, and improves the efficiency and professionalism of the overall recruitment team.

[0104] Corresponding to the method embodiment of the present application, the present application also provides a device for searching candidate users, such as Figure 3 As shown, the device 300 for searching for candidate users includes: a processing module 301 , and sending modules 302 and 303 .

[0105] The processing module 301 is used to access a recruitment website and request a job-seeking user information set from the recruitment website. The job-seeking user information set includes resume information corresponding to a plurality of job-seeking users.

[0106] The sending module 302 is also used to send the job seeker information set to the preset language analysis model in response to receiving the job seeker information set, so as to generate an adaptation result through the preset language analysis model, and the adaptation result includes the adaptation level of each resume information and the position information. The preset language analysis model is pre-configured with the position information of the target position.

[0107] The sending module 302 is also used to respond to receiving the adaptation result and send a first dialogue message to the first candidate user according to the adaptation result. The dialogue content includes application invitation information and position information, wherein the candidate user is a job seeker whose adaptation level meets the first preset level requirement.

[0108] The sending module 302 is also used to send a text analysis instruction and the second dialogue information to the preset language analysis model in response to receiving a second dialogue information in which the candidate user replies to the first dialogue information, so that the preset language analysis model generates an analysis result, wherein the analysis result includes the level of intention to join the job.

[0109] The acquisition module 303 is used to, in response to receiving the analysis result, acquire the contact information of the recruiting user corresponding to the job information when the employment intention level meets the second level requirement.

[0110] The acquisition module 303 is further used to obtain the contact information of the recruiting user corresponding to the position information in response to receiving the analysis result.

[0111] The sending module 302 is further used to send the contact information of the recruiting user to the target user, wherein the target user is a candidate user whose employment intention level meets the second level requirements.

[0112] In some embodiments, the text analysis instruction includes: a text range to be analyzed, a text analysis angle, an output format of the analysis result, and reference text information of the output result.

[0113] The text analysis angle includes at least one of the job seeker's employment intention, emotion type, and emotion intensity.

[0114] In some embodiments, the acquisition module 303 is also used to obtain the suitability analysis requirements corresponding to the target position, and the suitability analysis requirements include at least one of work experience suitability analysis, skill requirement suitability analysis, customer service awareness suitability analysis, teamwork and adaptability suitability analysis, and overall suitability analysis.

[0115] The sending module 302 is also used to send the job information and adaptation analysis instructions of the target job to the preset language analysis model to configure the preset language analysis model. The adaptation analysis instructions include the fitness analysis requirements, the first output format of the adaptation result and the reason for generating the adaptation result.

[0116] In some embodiments, the device for searching for candidate users further includes a receiving module.

[0117] The receiving module is used to receive and save the adaptation result of the first output format generated by the preset language analysis model and the reason for the adaptation result of the first output format.

[0118] In some embodiments, the processing module is further used to generate a reference text for requesting to add a contact for the target user, and send the reference text to the target user.

[0119] In some embodiments, the sending module 302 is further used to send information extraction requirements to the preset language analysis model, where the information extraction requirements include resume information extraction requirements, job information extraction requirements and a first output format.

[0120] The receiving module is further used to receive and save the extracted information in the first output format generated by the preset language analysis model. The extracted information includes resume extracted information and position extracted information. The resume extracted information includes: basic information, education information, work experience, work content, skills and expertise, and self-evaluation. The position extracted information includes: position title, company name, work location, salary, release date, job responsibilities, job requirements, benefits, company profile, and application method.

[0121] It can be understood that the candidate user searching device of the embodiment of the present application can correspond to the execution entity of the candidate user searching method provided in the embodiment of the present application. The specific details of the operation and / or function of each module / unit of the candidate user searching device can be found in the description of the corresponding parts of the candidate user searching method provided in the above-mentioned embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0122] 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 4 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 401 and a memory 402 storing computer program instructions. When the processor 401 executes the computer program instructions, the process or function of any of the above-mentioned embodiments of the method is implemented.

[0123] Specifically, the processor 401 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 402 may include a large-capacity memory for data or instructions. For example, the memory 402 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 402 may include a removable or non-removable (or fixed) medium. For another example, the memory 402 may be inside or outside the integrated gateway disaster recovery device. The memory 402 may be a non-volatile solid-state memory. In other words, the memory 402 generally 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 operations described in the method of the embodiments of the present application may be performed. The processor 401 implements the process or function of any method in the above embodiments by reading and executing the computer program instructions stored in the memory 402 .

[0124] In one example, Figure 4 The electronic device shown may also include a communication interface 403 and a bus 410. Among them, the processor 401, the memory 402, and the communication interface 403 are connected through the bus 410 and complete the communication between each other. The communication interface 403 is mainly used to realize the communication between each module, device, unit and / or device in the embodiment of the present application. The bus 410 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 410 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 searching candidate users, characterized in that: Methods include: Accessing a recruitment website and requesting a job-seeking user information set from the recruitment website, wherein the job-seeking user information set includes resume information corresponding to a plurality of job-seeking users; In response to receiving the job-seeking user information set, sending the job-seeking user information set to a preset language analysis model to generate an adaptation result through the preset language analysis model, the adaptation result including an adaptation level between each resume information and the job information, the preset language analysis model being pre-configured with the job information of the target job; In response to receiving the adaptation result, according to the adaptation result, a first dialogue message is sent to a first candidate user, wherein the first dialogue content includes the job invitation information and the position information, wherein the candidate user is a job seeker whose adaptation level meets the first preset level requirement; In response to receiving a second dialogue message in which the candidate user replies to the first dialogue message, sending a text analysis instruction and the second dialogue message to a preset language analysis model, so that the preset language analysis model generates an analysis result, wherein the analysis result includes an employment intention level; In response to receiving the analysis result, the contact information of the recruiting user corresponding to the position information is obtained, and the contact information of the recruiting user is sent to the target user, wherein the target user is a candidate user whose employment intention level meets the second level requirement.

2. The method according to claim 1, characterized in that The text analysis instruction includes: the text range to be analyzed, the text analysis angle, the output format of the analysis result and the reference text information of the output result; The text analysis angle includes at least one of the job seeker's employment intention, emotion type and emotion intensity.

3. The method according to claim 1, characterized in that Prior to visiting the recruitment website, the method includes: Obtaining the suitability analysis requirements corresponding to the target position, wherein the suitability analysis requirements include at least one of work experience suitability analysis, skill requirement suitability analysis, customer service awareness suitability analysis, teamwork and adaptability suitability analysis, and overall suitability analysis; Sending the position information of the target position and an adaptation analysis instruction to the preset language analysis model to configure the preset language analysis model, wherein the adaptation analysis instruction includes the fitness analysis requirement, the first output format of the adaptation result, and the reason for generating the adaptation result.

4. The method according to claim 3, characterized in that After receiving the adaptation result, the method further includes: The adaptation result of the first output format generated by the preset language analysis model and the reason for the adaptation result of the first output format are received and saved.

5. The method according to claim 1, characterized in that The method further comprises: For the target user, a reference text for requesting to add a contact is generated, and the reference text is sent to the target user.

6. The method according to claim 1, characterized in that The method further comprises: Sending an information extraction requirement to the preset language analysis model, wherein the information extraction requirement includes a resume information extraction requirement, a position information extraction requirement, and a first output format; After sending the job seeker information set and the target job position information to the preset language analysis model, the method further includes: Receiving and saving the extraction information in the first output format generated by the preset language analysis model; Among them, the extracted information includes resume extraction information and position extraction information; the resume extraction information includes: basic information, education information, work experience, work content, skills and expertise, and self-evaluation; the position extraction information includes: position title, company name, work location, salary, release date, job responsibilities, job requirements, benefits, company profile, and application method.

7. A device for searching candidate users, characterized in that: The device comprises: A sending module, used for accessing a recruitment website and requesting a job-seeking user information set from the recruitment website, wherein the job-seeking user information set includes resume information corresponding to a plurality of job-seeking users; The sending module is further configured to, in response to receiving the job seeker information set, send the job seeker information set to a preset language analysis model, so as to generate an adaptation result through the preset language analysis model, the adaptation result including an adaptation level between each resume information and the job information, and the preset language analysis model is pre-configured with the job information of the target job; The sending module is further configured to, in response to receiving the adaptation result, send a first dialogue message to a first candidate user according to the adaptation result, wherein the dialogue content includes the job application invitation information and the position information, wherein the candidate user is a job seeker whose adaptation level meets the first preset level requirement; The sending module is further configured to, in response to receiving a second dialogue message in which the candidate user replies to the first dialogue message, send a text analysis instruction and the second dialogue message to a preset language analysis model, so that the preset language analysis model generates an analysis result, wherein the analysis result includes an employment intention level; An acquisition module, configured to, in response to receiving the analysis result, acquire contact information of a recruiting user corresponding to the job information if the employment intention level meets the second level requirement; The acquisition module is further configured to, in response to receiving the analysis result, acquire contact information of a recruiting user corresponding to the position information; The sending module is further used to send the contact information of the recruiting user to the target user, wherein the target user is a candidate user whose employment intention level meets the second level requirements.

8. 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 6 is implemented.

9. 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 6 is implemented.

10. A computer program product, characterized in that It comprises computer program instructions, which implement the method according to any one of claims 1 to 6 when executed by a processor.

Images