WO2022247231A1 - 简历筛选方法、简历筛选装置、终端设备及存储介质 - Google Patents

简历筛选方法、简历筛选装置、终端设备及存储介质 Download PDF

Info

Publication number
WO2022247231A1
WO2022247231A1 PCT/CN2021/137819 CN2021137819W WO2022247231A1 WO 2022247231 A1 WO2022247231 A1 WO 2022247231A1 CN 2021137819 W CN2021137819 W CN 2021137819W WO 2022247231 A1 WO2022247231 A1 WO 2022247231A1
Authority
WO
WIPO (PCT)
Prior art keywords
resume
screened
screening
key information
resumes
Prior art date
Application number
PCT/CN2021/137819
Other languages
English (en)
French (fr)
Inventor
荣华帅
申妍燕
王书强
Original Assignee
中国科学院深圳先进技术研究院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2022247231A1 publication Critical patent/WO2022247231A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/105—Human resources
    • G06Q10/1053—Employment or hiring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling

Definitions

  • the application belongs to the technical field of data processing, and in particular relates to a method for screening resumes, a device for screening resumes, terminal equipment and a storage medium.
  • Embodiments of the present application provide a method for screening resumes, a device for screening resumes, a terminal device, and a storage medium, so as to improve the efficiency of screening resumes.
  • the embodiment of the present application provides a method for screening resumes, and the method for screening resumes includes:
  • the second key information corresponds to the soft index of the target position
  • the second key information is input into the trained resume screening model to obtain the screening result of the resume to be screened.
  • the embodiment of the present application provides a resume screening device, and the resume screening device includes:
  • the resume acquisition module is used to obtain the resumes to be screened for the target positions
  • the first extraction module is used to extract the first key information of the resume to be screened, and the first key information corresponds to the hard index of the target position;
  • the second extraction module is used to extract the second key information of the resume to be screened if the first key information meets the hard index requirements, and the second key information corresponds to the soft index of the target position;
  • a resume screening module configured to input the second key information into the trained resume screening model to obtain a screening result of the resumes to be screened.
  • an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and operable on the processor.
  • the processor executes the computer program, Realize the steps of the method for screening resumes as described in the first aspect above.
  • an embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for screening resumes as described in the first aspect above is implemented A step of.
  • the embodiment of the present application provides a computer program product, which, when the computer program product is run on a terminal device, enables the terminal device to execute the steps of the method for screening resumes as described in the first aspect above.
  • the first key information corresponding to the hard index can be extracted from the resume to be screened, and when the first key information meets the requirements of the hard index, the resume to be screened can be extracted from the resume to be screened Extract the second key information corresponding to the soft index, and input the second key information into the trained resume screening model to obtain the screening results of resumes to be screened.
  • resume screening process manual participation is not required, which improves the efficiency of resume screening, and this application can screen out resumes that are more suitable for the target position through two-layer screening of hard indicators and soft indicators, which improves the accuracy of resume screening.
  • FIG. 1 is a schematic diagram of the implementation flow of the resume screening method provided in Embodiment 1 of the present application;
  • FIG. 2 is a schematic diagram of the implementation flow of the resume screening method provided in Embodiment 2 of the present application;
  • FIG. 3 is a schematic structural diagram of a resume screening device provided in Embodiment 3 of the present application.
  • FIG. 4 is a schematic structural diagram of a terminal device provided in Embodiment 4 of the present application.
  • references to "one embodiment” or “some embodiments” or the like in the specification of the present application means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application.
  • appearances of the phrases “in one embodiment,” “in some embodiments,” “in other embodiments,” “in other embodiments,” etc. in various places in this specification are not necessarily All refer to the same embodiment, but mean “one or more but not all embodiments” unless specifically stated otherwise.
  • the terms “including”, “comprising”, “having” and variations thereof mean “including but not limited to”, unless specifically stated otherwise.
  • FIG. 1 it is a schematic flow chart of implementing a resume screening method provided in Embodiment 1 of the present application, and the resume screening method is applied to a terminal device.
  • the resume screening method may include the following steps:
  • Step 101 obtaining resumes to be screened for target positions.
  • the target position may refer to any position for which the enterprise needs to recruit employees.
  • back-end R&D engineers financial assistants, sales executives, etc.
  • the number of resumes to be screened is one or at least two, which is not limited here.
  • the terminal device can realize the screening of resumes within the same position, eliminate the resumes that have not been delivered to the target position, reduce the number of resumes to be screened, and save the time and cost of resume screening.
  • Step 102 extracting the first key information of the resume to be screened.
  • the first key information corresponds to the hard indicator of the target position.
  • Hard indicators refer to indicators that cannot be changed flexibly. Hard indicators have specific data requirements or quotas and are highly operable. The hard indicators of the target position refer to the indicators that the target position must meet.
  • the terminal device can pre-set hard index keywords for the target position, and after obtaining the resumes to be screened for the target positions, the first key information can be extracted from the resumes to be screened based on the hard index keywords.
  • the number of the above-mentioned hard indicators may be one or at least two, which is not limited here.
  • the hard indicators of the target position include: age is 20 to 35 years old, gender is female, education is master degree, then the keywords of the hard indicators are age, gender, education, and the first key information extracted from a resume to be screened is: 30 years old, female, master degree.
  • Step 103 if the first key information satisfies the requirement of the hard index, extract the second key information of the resume to be screened.
  • the second key information corresponds to the soft indicator of the target post.
  • Soft indicators have a certain range or range, and their operability is weak. Compared with hard indicators, the soft indicators of target positions are relatively broad, such as project experience, work experience, honorary awards, etc.
  • artificial intelligence technology such as a resume screening model
  • the terminal device can extract the second key information of the resume to be screened to perform soft index screening according to the second key information; if the first key information of the resume to be screened does not meet the hard index Requirements, it means that the resumes to be screened do not meet the requirements of the target position, and the terminal equipment can directly eliminate the resumes to be screened, without the need for soft index screening.
  • the first key information of the resume to be screened is 30 years old, female, and master, and the hard indicators include: age is 20 to 35 years old, gender is female, and education is master's degree, then it can be determined that the first key information of the resume to be screened meets Hard target requirements.
  • the above-mentioned first key information meeting the requirements of the hard indicators means that the above-mentioned first key information meets the requirements of the above-mentioned at least two hard indicators. If the first key information does not meet the requirements of any one of the at least two hard indicators, it is determined that the first key information does not meet the requirements of the hard indicators.
  • the first key information of the resume to be screened is 30 years old, female, undergraduate, and the hard indicators include: age is 20 to 35 years old, gender is female, and education is master's degree, then it can be determined that the first key information of the resume to be screened is not Meet the hard target requirements.
  • the terminal device can pre-set soft indicators for the target position.
  • the second key information can be extracted from the resumes to be screened based on the keywords of the soft indicators.
  • the quantity of the aforementioned soft indicators may be one or at least two, which is not limited here.
  • soft indicators include project experience, work experience, honor awards, etc.
  • the double screening improves the resume screening efficiency, reduces the complexity of the resume screening model, and improves the accuracy of the resume screening model.
  • Step 104 inputting the second key information into the trained resume screening model to obtain the screening result of resumes to be screened.
  • the above-mentioned resume screening model is used to screen the resumes to be screened according to the second key information of the resumes to be screened, and output the screening results of the resumes to be screened.
  • the screening results of the resumes to be screened include whether the resumes to be screened have passed the screen or the resumes to be screened have not passed the screen.
  • the above resume screening model may be a classifier based on any classification algorithm, which is not limited here.
  • the above resume screening model is based on the support vector machine (Support Vector Machine, SVM) algorithm classifier.
  • SVM is a kind of generalized linear classifier for binary classification of data according to the supervised learning method. Its decision boundary is the maximum margin hyperplane solved for the learning samples, which can achieve the optimal classification effect.
  • the training results can classify resumes into two categories: "pass” and "fail”.
  • Pass refers to passing the screening
  • Fail refers to not passing the screening
  • the terminal device Before using the resume screening model to screen the resumes to be screened, the terminal device may first use the training set to train the resume screening model, so that the resume screening model can output relatively accurate screening results.
  • the above training set includes the second key information and labels of multiple sample resumes. Labels for each sample resume include Passed Screening or Failed Screening.
  • This application adopts a robot-based process automation (Robotic process automation, RPA) and artificial intelligence technology (that is, steps 101 to 104 above, and steps 201 to 206 in Embodiment 2) to complete the initial screening of resumes, which can reduce the manpower and labor required for the initial screening of resumes. time, improving the efficiency of the enterprise in the recruitment process.
  • RPA Robot process automation
  • artificial intelligence technology that is, steps 101 to 104 above, and steps 201 to 206 in Embodiment 2
  • RPA aims to automate the execution of manual tasks by terminal equipment, which can replace manual repetitive work and automate it, fundamentally liberating the labor force and enabling manual participation in more complex activities.
  • RPA simulates the behavior of human beings interacting with information systems through software robots, and its goal is to quickly and reliably perform structured and repetitive tasks, significantly saving costs and improving reliability.
  • the third key information of the resume to be screened is extracted, and the third key information includes but not limited to the name and contact information of the applicant corresponding to the resume to be screened;
  • the above-mentioned contact information can be at least one of various methods such as telephone number, email address, and instant messaging account.
  • the terminal device can send the third key information and the resume to be screened to the target user through at least one of various methods such as mailbox and instant messaging account.
  • the terminal device sends the third key information and the resume to be screened to the mailbox of the target user, or to the instant messaging account of the target user.
  • the target user may be a human resource manager, a recruiter, etc., and is not limited here.
  • the target user can view the third key information and the resume to be screened through the electronic device, so as to facilitate subsequent interview arrangements for candidates corresponding to the resume to be screened, And combined with the interview situation, finally determine the review results of the target user's resume to be screened.
  • the review results of resumes to be screened include hiring or non-hiring. Hiring refers to hiring the applicant corresponding to the resume to be screened, and not hiring refers to not hiring the applicant corresponding to the resume to be screened.
  • the target user checks the third key information and the resume to be screened through the computer, contacts the applicant based on the third key information, arranges the interview time and place of the applicant, and finally determines whether to hire the applicant based on the interview situation after the interview.
  • sending the third key information and the resume to be screened to the target user includes:
  • the terminal device writes the third key information into the target document, and sends the target document to the target user when sending the resume to be screened, so that the user can view the third key information conveniently.
  • the aforementioned target document may refer to a document in a target format.
  • the target format is Excel
  • the target document is an Excel table.
  • the third key information of all resumes to be screened can be written into the target document, and the target document and all resumes to be screened can be sent to the target user, which can facilitate the target user to pass Destination Document View all applicants' names, contact information, and more.
  • the target information of the applicant corresponding to the resume to be screened is entered into the employee database.
  • the terminal device When the terminal device detects that the review result of the resume to be screened is employment, it indicates that the applicant corresponding to the resume to be screened meets the recruitment requirements of the target position.
  • the target information of the applicant By entering the target information of the applicant into the employee database of the enterprise, the recruitment of new employees can be automatically completed. Information input without manual input, which improves the efficiency of employee information input.
  • the above target information may be the applicant's name, contact information, gender, education background and other information.
  • the target user can set the type of target information by himself according to actual needs, which is not limited here.
  • Entering the target information of the applicant into the employee database may include: filling the target information of the applicant into the input page of the employee management system, and saving the target information filled in the input page to the employee management system when a confirmation operation is detected on the input page Employee database in the system.
  • the above-mentioned determination operation may refer to a click operation, a slide operation, and the like on the entry option.
  • An employee management system may refer to a system that manages various information of employees.
  • obtaining the review result of the target user's resume to be screened includes:
  • the evaluation system may refer to a system that manages various information of candidates. For example, target users can fill in and save the review results of candidates in the evaluation system.
  • the terminal device can also determine the screening result corresponding to the audit result according to the audit result; add the second key information and the screening result corresponding to the audit result to the training set, and the training set is used for training Resume screening model.
  • the corresponding relationship between the review result and the screening result includes: when the review result is employment, the corresponding screening result is passed screening; when the review result is not hired, the corresponding screening result is failed screening.
  • the terminal device can use the screening result corresponding to the audit result as the label of the resume to be screened, and add the second key information and label of the resume to be screened to the training set, which can increase the number of samples in the training set, so that the trained resume screening model can be used for job Improve the matching of resumes and improve the consistency between resumes and recruitment standards for corresponding positions.
  • the terminal device Before the terminal device adds the second key information and labels of the resumes to be screened to the training set, it can first encapsulate the second key information and labels of the resumes to be screened into the format of the training set, and then add them to the training set.
  • the above-mentioned resume screening model can be a linear model, so in the competition for the same post, the factors in the second key information x are all influencing factors of the resume screening model, so that more factors are considered when training the resume screening model, and the resume screening model is improved. Model screening efficiency.
  • the resume screening model can be continuously revised with the expansion of the training set, that is, the terminal device will continuously correct the resume screening model according to the review standards of the target users, so that the resume screening model can be realized.
  • the self-learning of the screening model continuously improves the accuracy of the resume screening model.
  • the terminal device when it extracts information from the resumes to be screened, it can first set the keyword table according to the target position, and use natural language processing (Natural Language Processing, NLP) technology can extract information corresponding to keywords in the keyword table.
  • NLP Natural Language Processing
  • NLP is a discipline that studies language issues in human-computer interaction, involving automatic word segmentation, part-of-speech analysis, syntactic analysis, and semantic analysis.
  • the specific algorithm for extracting information may be a commonly used algorithm in the field of NLP, which is not limited here.
  • the hard index keyword table includes at least one hard index keyword, and the first key information corresponding to the at least one hard index keyword can be extracted by using NLP technology.
  • the first key information corresponding to the hard indicators can be extracted from the resumes to be screened, and when the first key information meets the requirements of the hard indicators, the resumes to be screened can be extracted from the resumes to be screened.
  • the second key information corresponding to the indicator and input the second key information into the trained resume screening model to obtain the screening results of the resumes to be screened.
  • FIG. 2 it is a schematic diagram of the implementation flow of the method for screening resumes provided in Embodiment 2 of the present application, and the method for screening resumes is applied to a terminal device.
  • the resume screening method may include the following steps:
  • Step 201 when an applicant applies for a target position, obtain the resume information filled in by the applicant on the recruitment web page, and determine that the resume information is a resume to be screened.
  • the resume information in the above step 201 is filled in by the applicant on the recruitment webpage through the client.
  • the format of the resume information filled in the recruitment webpage is more standardized, and it is easier to extract key information.
  • Terminal devices can be based on Hyper Text Transfer Protocol (Hyper Text Transfer Protocol, HTTP) sends an information acquisition request to the server corresponding to the recruitment webpage, and after receiving the information acquisition request, the server corresponding to the recruitment webpage returns the resume information filled in by the applicant on the recruitment webpage to the terminal device.
  • HTTP Hyper Text Transfer Protocol
  • Step 202 when the applicant applies for the target position, obtain the electronic version of the resume sent by the applicant, and determine that the electronic version of the resume is the resume to be screened.
  • the electronic version of the resume can be a resume in Word, PDF and other formats.
  • the electronic version of the resume sent by the applicant may be the electronic version of the resume sent by the applicant to the target user, or the electronic version of the resume uploaded by the applicant to the recruitment webpage, which is not limited here.
  • the terminal device obtains the electronic version of the resume sent by the applicant, which can realize the automatic extraction of key information and facilitate the review of target users.
  • Step 203 when the applicant applies for the target position, scan the paper version of the resume provided by the applicant to obtain the electronic version of the resume, and determine that the electronic version of the resume is the resume to be screened.
  • Terminal equipment through optical character recognition Optical Character Recognition (OCR) scans the paper version of the resume to obtain the electronic version of the resume, so as to realize the automatic extraction of key information and facilitate the review of target users.
  • OCR Optical Character Recognition
  • OCR technology refers to the process in which the terminal device checks the characters printed on the paper version of the resume, determines its shape by detecting dark and light patterns, and then uses the character recognition method to translate the shape into computer text.
  • the terminal device may acquire resumes to be screened through at least one of three acquisition methods including step 201, step 202, and step 203.
  • Step 204 extracting the first key information of the resume to be screened.
  • step 102 is the same as step 102, for details, please refer to the relevant description of step 102, which will not be repeated here.
  • Step 205 if the first key information satisfies the requirement of the hard index, extract the second key information of the resume to be screened.
  • step 103 is the same as step 103, for details, please refer to the related description of step 103, which will not be repeated here.
  • Step 206 inputting the second key information into the trained resume screening model to obtain the screening result of resumes to be screened.
  • step 104 is the same as step 104, for details, please refer to the related description of step 104, which will not be repeated here.
  • the embodiment of this application can provide more resumes to be screened for the target position by obtaining the resume information filled in by the applicant on the recruitment webpage, the electronic resume sent by the applicant, and the paper resume provided by the scanned applicant, thereby increasing the number of recruits. The probability of an applicant matching the target job.
  • FIG. 3 it is a schematic structural diagram of a resume screening device provided in Embodiment 3 of the present application. For convenience of description, only parts related to the embodiment of the present application are shown.
  • the resume screening devices mentioned above include:
  • Resume acquiring module 31 used to acquire resumes to be screened for target positions
  • the first extraction module 32 is used to extract the first key information of the resume to be screened, and the first key information corresponds to the hard index of the target position;
  • the second extraction module 33 is used to extract the second key information of the resume to be screened if the first key information meets the requirements of the hard index, and the second key information corresponds to the soft index of the target post;
  • the resume screening module 34 is configured to input the second key information into the trained resume screening model to obtain a screening result of resumes to be screened.
  • the above-mentioned resume screening device also includes:
  • the third extraction module is used to extract the third key information of the resume to be screened if the screening result of the resume to be screened is passed, and the third key information includes the name and contact information of the applicant corresponding to the resume to be screened;
  • An information sending module configured to send the third key information and the resume to be screened to the target user; the third key information and the resume to be screened are used to instruct the target user to review the resume to be screened;
  • the result obtaining module is used to obtain the review result of the target user's resume to be screened.
  • the above-mentioned resume screening device also includes:
  • an information writing module configured to write the third key information into the target document
  • the above information sending module is specifically used for:
  • the above-mentioned resume screening device also includes:
  • the information input module is used to input the target information of the applicant corresponding to the resume to be screened into the employee database if the review result of the resume to be screened is employment.
  • the above-mentioned result acquisition module is specifically used for:
  • the above-mentioned resume screening device also includes:
  • the result determination module is used to determine the screening result corresponding to the audit result according to the audit result
  • the information adding module is used to add the screening results corresponding to the second key information and the review results to the training set, and the training set is used to train the resume screening model.
  • resume acquisition module 31 is specifically used for:
  • the device for screening resumes provided in the embodiment of the present application can be applied in the foregoing method embodiments 1 and 2.
  • FIG. 4 is a schematic structural diagram of a terminal device provided in Embodiment 4 of the present application.
  • the terminal device 4 of this embodiment includes: one or more processors 40 (only one is shown in the figure), a memory 41 and a program stored in the memory 41 and capable of running on at least one processor 40 Computer program 42.
  • processors 40 executes the computer program 42, the steps in the above embodiments of the resume screening method are realized.
  • the terminal device 4 may be computing devices such as desktop computers, notebooks, palmtop computers, and cloud servers.
  • the terminal device may include, but not limited to, a processor 40 and a memory 41 .
  • FIG. 4 is only an example of the terminal device 4, and does not constitute a limitation on the terminal device 4. It may include more or less components than those shown in the figure, or combine some components, or different components.
  • a terminal device may also include an input and output device, a network access device, a bus, and the like.
  • the so-called processor 40 can be a central processing unit (Central Processing Unit, CPU), and the processor can also be other general processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the storage 41 may be an internal storage unit of the terminal device 4 , such as a hard disk or memory of the terminal device 4 .
  • the memory 41 can also be an external storage device of the terminal device 4, such as a plug-in hard disk equipped on the terminal device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card) and so on. Further, the memory 41 may also include both an internal storage unit of the terminal device 4 and an external storage device.
  • the memory 41 is used to store computer programs and other programs and data required by the terminal device.
  • the memory 41 can also be used to temporarily store data that has been output or will be output.
  • the disclosed apparatus/terminal device and method may be implemented in other ways.
  • the device/terminal device embodiments described above are only illustrative, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components May be combined or may be integrated into another system, or some features may be omitted, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • a unit described as a separate component may or may not be physically separated, and a component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.
  • an integrated module/unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the present application realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through computer programs, and the computer programs can be stored in a computer-readable storage medium.
  • the computer program includes computer program code
  • the computer program code may be in the form of source code, object code, executable file or some intermediate form.
  • Computer-readable media may include: any entity or device capable of carrying computer program code, recording media, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained on computer readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media does not include Electrical carrier signals and telecommunication signals.
  • This application realizes all or part of the processes in the methods of the above-mentioned embodiments, and can also be completed by a computer program product.
  • the computer program product runs on the terminal device, the terminal device can realize the implementation of the above-mentioned various method embodiments when executed. A step of.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

适用于数据处理技术领域，提供了一种简历筛选方法、简历筛选装置、终端设备及存储介质，所述简历筛选方法包括：获取针对目标岗位的待筛选简历（101）；提取所述待筛选简历的第一关键信息（102），所述第一关键信息对应所述目标岗位的硬指标；若所述第一关键信息满足硬指标要求，则提取所述待筛选简历的第二关键信息（103），所述第二关键信息对应所述目标岗位的软指标；将所述第二关键信息输入至已训练的简历筛选模型，得到所述待筛选简历的筛选结果（104）。方法可提高简历筛选效率。

Description

简历筛选方法、简历筛选装置、终端设备及存储介质 技术领域
本申请属于数据处理技术领域，尤其涉及一种简历筛选方法、简历筛选装置、终端设备及存储介质。
 背景技术
在企业招聘员工的过程中，企业发布职业需求信息，应聘者针对想要应聘的岗位进行简历投递。企业在招聘过程中，会收到针对不同岗位的大量简历。面对大量的简历，现有技术通常是采用人工进行简历筛选，其工作量较大，导致筛选效率较低。
 技术问题
本申请实施例提供了一种简历筛选方法、简历筛选装置、终端设备及存储介质，以提高简历筛选效率。
 技术解决方案
第一方面，本申请实施例提供了一种简历筛选方法，所述简历筛选方法包括：
获取针对目标岗位的待筛选简历；
提取所述待筛选简历的第一关键信息，所述第一关键信息对应所述目标岗位的硬指标；
若所述第一关键信息满足硬指标要求，则提取所述待筛选简历的第二关键信息，所述第二关键信息对应所述目标岗位的软指标；
将所述第二关键信息输入至已训练的简历筛选模型，得到所述待筛选简历的筛选结果。
第二方面，本申请实施例提供了一种简历筛选装置，所述简历筛选装置包括：
简历获取模块，用于获取针对目标岗位的待筛选简历；
第一提取模块，用于提取所述待筛选简历的第一关键信息，所述第一关键信息对应所述目标岗位的硬指标；
第二提取模块，用于若所述第一关键信息满足硬指标要求，则提取所述待筛选简历的第二关键信息，所述第二关键信息对应所述目标岗位的软指标；
简历筛选模块，用于将所述第二关键信息输入至已训练的简历筛选模型，得到所述待筛选简历的筛选结果。
第三方面，本申请实施例提供了一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述第一方面所述简历筛选方法的步骤。
第四方面，本申请实施例提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现如上述第一方面所述简历筛选方法的步骤。
第五方面，本申请实施例提供了一种计算机程序产品，当所述计算机程序产品在终端设备上运行时，使得所述终端设备执行如上述第一方面所述简历筛选方法的步骤。
 有益效果
由上可见，本申请在获取到针对目标岗位的待筛选简历之后，可以先从待筛选简历中提取与硬指标对应的第一关键信息，在第一关键信息满足硬指标要求时，再从待筛选简历中提取与软指标对应的第二关键信息，并将第二关键信息输入至已训练的简历筛选模型，得到待筛选简历的筛选结果。在上述简历筛选过程中，无需人工参与，提高了简历筛选效率，且本申请通过硬指标和软指标两层筛选，能够筛选出与目标岗位较为匹配的简历，提高了简历筛选的准确性。
 附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例一提供的简历筛选方法的实现流程示意图；
图2是本申请实施例二提供的简历筛选方法的实现流程示意图；
图3是本申请实施例三提供的简历筛选装置的结构示意图；
图4是本申请实施例四提供的终端设备的结构示意图。
 本发明的实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定系统结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的系统、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。
应当理解，当在本说明书和所附权利要求书中使用时，术语“包括”指示所描述特征、整体、步骤、操作、元素和/或组件的存在，但并不排除一个或多个其它特征、整体、步骤、操作、元素、组件和/或其集合的存在或添加。
还应当理解，在此本申请说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本申请。如在本申请说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
另外，在本申请说明书和所附权利要求书的描述中，术语“第一”、“第二”、“第三”等仅用于区分描述，而不能理解为指示或暗示相对重要性。
在本申请说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此，在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例，而是意味着“一个或多个但不是所有的实施例”，除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”，除非是以其他方式另外特别强调。
在本申请实施例中，为了解决现有技术采用人工进行简历筛选时工作量较大，导致筛选效率较低的这一问题，提出了获取针对目标岗位的待筛选简历，并先从待筛选简历中提取与硬指标对应的第一关键信息，在第一关键信息满足硬指标要求时，再从待筛选简历中提取与软指标对应的第二关键信息，并将第二关键信息输入至已训练的简历筛选模型，得到待筛选简历的筛选结果，此简历筛选过程无需人工参与，提高了简历筛选效率，且本申请通过硬指标和软指标两层筛选，能够筛选出与目标岗位较为匹配的简历，提高了简历筛选的准确性。
应理解，本实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
为了说明本申请所述的技术方案，下面通过具体实施例来进行说明。
参见图1，是本申请实施例一提供的简历筛选方法的实现流程示意图，该简历筛选方法应用于终端设备。如图1所示，该简历筛选方法可以包括以下步骤：
步骤101，获取针对目标岗位的待筛选简历。
其中，目标岗位可以是指企业需要招聘员工的任一岗位。例如，后端研发工程师、财务助理、销售主管等。待筛选简历的数量为一份或者至少两份，在此不做限定。
终端设备通过获取针对目标岗位的待筛选简历，能够实现在同一岗位内部进行简历筛选，排除了未投递目标岗位的简历，减少了待筛选简历的数量，节省了简历筛选的时间成本。
步骤102，提取待筛选简历的第一关键信息。
其中，第一关键信息对应目标岗位的硬指标。
硬指标是指不能通融改变的指标。硬指标有具体的数据要求或定额，可操作性强。目标岗位的硬指标是指目标岗位必须要满足的指标。
终端设备可以预先为目标岗位设定硬指标关键词，在获取到针对目标岗位的待筛选简历之后，可以基于硬指标关键词，从待筛选简历中提取第一关键信息。上述硬指标的数量可以为一项或者至少两项，在此不做限定。例如，目标岗位的硬指标包括：年龄为20至35岁、性别为女、学历为硕士，那么硬指标关键词为年龄、性别、学历，从一份待筛选简历中提取出的第一关键信息为：30岁、女、硕士。
步骤103，若第一关键信息满足硬指标要求，则提取待筛选简历的第二关键信息。
其中，第二关键信息对应目标岗位的软指标。
软指标有一定的范围或幅度，可操作性弱。相比于硬指标，目标岗位的软指标比较宽泛，比如项目经历、工作经历、荣誉奖励等。对于这些软指标，可以采用人工智能技术（例如简历筛选模型）完成对待筛选简历的筛选。
若待筛选简历的第一关键信息满足硬指标要求，则终端设备可以提取待筛选简历的第二关键信息，以根据第二关键信息进行软指标筛选；若待筛选简历的第一关键信息不满足硬指标要求，则说明待筛选简历不满足目标岗位的要求，终端设备可以直接淘汰待筛选简历，无需再进行软指标筛选。
示例性的，待筛选简历的第一关键信息为30岁、女、硕士，硬指标包括：年龄为20至35岁、性别为女、学历为硕士，那么可以确定待筛选简历的第一关键信息满足硬指标要求。
需要说明的是，在硬指标的数量为至少两项时，上述第一关键信息满足硬指标要求是指上述第一关键信息满足上述至少两项硬指标的要求。若上述第一关键信息不满足上述至少两项硬指标中任一硬指标的要求，则确定上述第一关键信息不满足硬指标要求。
示例性的，待筛选简历的第一关键信息为30岁、女、本科，硬指标包括：年龄为20至35岁、性别为女、学历为硕士，那么可以确定待筛选简历的第一关键信息不满足硬指标要求。
终端设备可以预先为目标岗位设定软指标，在待筛选简历的第一关键信息满足硬指标要求时，可以基于软指标关键词，从待筛选简历中提取第二关键信息。上述软指标的数量可以为一项或者至少两项，在此不做限定。例如，软指标包括项目经历、工作经历、荣誉奖励等。
在一实施例中，通过设置上述软指标关键词与上述硬指标关键词不存在相同的关键词（即要求第一关键信息与第二关键信息不存在相同的信息），能够避免对同一关键信息进行两次筛选，提高了简历筛选效率，也减少了简历筛选模型的复杂性，提高了简历筛选模型的精度。
步骤104，将第二关键信息输入至已训练的简历筛选模型，得到待筛选简历的筛选结果。
其中，上述简历筛选模型用于根据待筛选简历的第二关键信息对待筛选简历进行筛选，并输出待筛选简历的筛选结果。待筛选简历的筛选结果包括待筛选简历通过筛选或者待筛选简历未通过筛选。
上述简历筛选模型可以是基于任一分类算法的分类器，在此不做限定。例如，上述简历筛选模型为基于支持向量机（Support Vector Machine, SVM）算法的分类器。SVM是一类按照监督学习方式对数据进行二元分类的广义线性分类器，其决策边界是对学习样本求解的最大边距超平面，能够达到最优分类效果。基于SVM算法的分类器的设计和训练，训练结果可以将简历分为“通过”和“不通过”两类。上述“通过”是指通过筛选，上述“不通过”是指未通过筛选
终端设备在使用简历筛选模型对待筛选简历进行筛选之前，可以先使用训练集对简历筛选模型进行训练，使得简历筛选模型能够输出较为准确的筛选结果。其中，上述训练集包括多份样本简历各自的第二关键信息和标签。每份样本简历的标签包括通过筛选或者未通过筛选。
本申请通过一种基于机器人流程自动化（Robotic process automation, RPA）和人工智能技术相结合的方案（即上述步骤101至104，以及实施例二中的步骤201至步骤206）完成对简历的初步筛选，可以减少简历初步筛选阶段需要消耗的人力和时间，提升了企业在招聘流程中的工作效率。
RPA旨在使终端设备自动化地执行人工任务，可以代替人工从事重复性的工作并使其自动化，从根本上解放劳动力，并使人工可以参与到更为复杂的活动中去。RPA通过软件机器人模拟人类与信息系统交互的行为，其目标是快速和可靠地执行结构化和重复性任务，显著节约成本，提高可靠性。
在一实施例中，在得到待筛选简历的筛选结果之后，还包括：
若待筛选简历的筛选结果为通过筛选，则提取待筛选简历的第三关键信息，第三关键信息包括但不限于待筛选简历对应的应聘者的姓名和联系方式；
将第三关键信息和待筛选简历发送给目标用户；第三关键信息和待筛选简历用于指示目标用户对待筛选简历进行审核；
获取目标用户对待筛选简历的审核结果。
上述联系方式可以为电话号码、邮箱、即时通信账号等多种方式中的至少一种。
终端设备可以通过邮箱、即时通信账号等多种方式中的至少一种方式，将第三关键信息和待筛选简历发送给目标用户。例如，终端设备将第三关键信息和待筛选简历发送给目标用户的邮箱，或者发送给目标用户的即时通信账号。其中，目标用户可以为人力资源管理人员、招聘专员等，在此不做限定。
终端设备在将第三关键信息和待筛选简历发送给目标用户之后，目标用户可以通过电子设备查看第三关键信息和待筛选简历，以便于对待筛选简历对应的应聘者进行后续的面试等安排，并结合面试情况最终确定目标用户对待筛选简历的审核结果。对待筛选简历的审核结果包括录用或者不录用，录用是指录用待筛选简历对应的应聘者，不录用是指不录用待筛选简历对应的应聘者。例如，目标用户通过电脑查看第三关键信息和待筛选简历，基于第三关键信息联系应聘者，安排应聘者的面试时间和地点，面试结束后，结合面试情况最终确定是否录用应聘者。
在一实施例中，在提取待筛选简历的第三关键信息之后，还包括：
将第三关键信息写入目标文档；
相应地，将第三关键信息和待筛选简历发送给目标用户包括：
将目标文档和待筛选简历发送给目标用户。
终端设备将第三关键信息写入目标文档，并在发送待筛选简历时将目标文档发送给目标用户，可以便于用户查看第三关键信息。上述目标文档可以是指格式为目标格式的文档。例如目标格式为Excel，目标文档为Excel表格。
在待筛选简历的数量为至少两份时，可以将所有的待筛选简历的第三关键信息均写入目标文档，并将目标文档和所有的待筛选简历发送给目标用户，能够方便目标用户通过目标文档查看所有应聘者的姓名、联系方式等信息。
在一实施例中，在获取目标用户对待筛选简历的审核结果之后，还包括：
若待筛选简历的审核结果为录用，则将待筛选简历对应的应聘者的目标信息录入至员工数据库。
终端设备在检测到待筛选简历的审核结果为录用时，表示待筛选简历对应的应聘者符合目标岗位的招聘要求，通过将应聘者的目标信息录入至企业的员工数据库，可以自动完成新员工的信息输入，而无需人工录入，提高了员工信息的录入效率。其中，上述目标信息可以为应聘者的姓名、联系方式、性别、学历等信息。可选地，目标用户可以根据实际需求自行设定目标信息的类型，在此不做限定。
将应聘者的目标信息录入至员工数据库可以包括：将应聘者的目标信息填写至员工管理系统的录入页面，在检测到录入页面的确定操作时，将填写至录入页面的目标信息保存至员工管理系统中的员工数据库。上述确定操作可以是指对录入选项的点击操作、滑动操作等。员工管理系统可以是指管理员工的各种信息的系统。
在一实施例中，获取对目标用户对待筛选简历的审核结果包括：
获取目标用户在填写审核结果时形成的log日志；
根据log日志，确定审核结果。
在待筛选简历对应的应聘者面试完之后，目标用户通常会通过电子设备登录评估系统，在评估系统填写对应聘者的审核结果，此时电子设备可以获取目标用户在评估系统的填写动作形成的log日志，并将该log日志发送至终端设备，终端设备接收到该log日志后，可以根据该log日志得到审核结果。评估系统可以是指管理应聘者的各种信息的系统，例如目标用户可以在评估系统填写并保存对应聘者的审核结果。
在一实施例中，终端设备在获取到审核结果之后，还可以根据审核结果，确定审核结果对应的筛选结果；将第二关键信息和审核结果对应的筛选结果加入训练集，训练集用于训练简历筛选模型。
审核结果与筛选结果之间的对应关系包括：在审核结果为录用时，对应的筛选结果为通过筛选；在审核结果为不录用时，对应的筛选结果为未通过筛选。
终端设备可以将审核结果对应的筛选结果作为待筛选简历的标签，将待筛选简历的第二关键信息和标签加入训练集，可以增加训练集中的样本数量，使得已训练的简历筛选模型可以为岗位提高匹配度较高的简历，提高简历与相应岗位招聘标准的吻合性。
终端设备在将待筛选简历的第二关键信息和标签加入训练集之前，可以先将待筛选简历的第二关键信息和标签封装为训练集格式，然后再加入训练集，训练集中第二关键信息的格式可以为x=[年龄,学历,院校类型,平均学分绩点,英语能力,反映计算机能力的关键词,反映项目经历的关键词,反映荣誉的关键词]，训练集中标签类型可以表示为y={通过,未通过}。上述简历筛选模型可以为线性模型，那么在同一岗位的竞争中，第二关键信息x中的因素均为简历筛选模型的影响因子，使得在训练简历筛选模型时考虑较多的因素，提高简历筛选模型的筛选效率。
终端设备在使用简历筛选模型对简历进行不断筛选的过程中，随着训练集的扩大可以不断修正简历筛选模型，即终端设备会不断地根据目标用户的审核标准修正简历筛选模型，从而可实现简历筛选模型的自学习，不断提高简历筛选模型的精度。
需要说明的是，终端设备在从待筛选简历中提取信息时，可以先依据目标岗位设置关键词表，采用自然语言处理（Natural Language Processing，NLP）技术可以提取与关键词表中的关键词对应的信息。NLP是研究人与计算机交互的语言问题的一门学科，涉及自动分词、词性分析、句法分析和语义分析等内容。其中，信息的具体提取算法可选用NLP领域的常用算法，在此不做限定。
例如，在关键词表为硬指标关键词表时，该硬指标关键词表包括至少一个硬指标关键词，采用NLP技术可以提取与上述至少一个硬指标关键词对应的第一关键信息。
本申请实施例在获取到针对目标岗位的待筛选简历之后，可以先从待筛选简历提取与硬指标对应的第一关键信息，在第一关键信息满足硬指标要求时，再从待筛选简历提取与软指标对应的第二关键信息，并将第二关键信息输入至已训练的简历筛选模型，得到待筛选简历的筛选结果。在上述筛选过程中，无需人工参与，提高了筛选效率，且本申请通过硬指标和软指标两层筛选，能够筛选出与目标岗位较为匹配的简历，提高了简历筛选的准确性。
参见图2，是本申请实施例二提供的简历筛选方法的实现流程示意图，该简历筛选方法应用于终端设备。如图2所示，该简历筛选方法可以包括以下步骤：
步骤201，在应聘者应聘目标岗位时，获取应聘者在招聘网页填写的简历信息，并确定该简历信息为待筛选简历。
其中，上述步骤201中的简历信息是应聘者通过客户端在招聘网页填写的。在招聘网页填写的简历信息的格式较为规范，比较容易对关键信息进行提取。
终端设备可以基于超文本传输协议（Hyper Text Transfer Protocol，HTTP）向招聘网页对应的服务器发送信息获取请求，招聘网页对应的服务器在接收到该信息获取请求之后，向终端设备返回应聘者在招聘网页填写的简历信息。
步骤202，在应聘者应聘目标岗位时，获取应聘者发送的电子版简历，并确定电子版简历为待筛选简历。
其中，电子版简历可以为Word、PDF等格式的简历。
应聘者发送的电子版简历可以是应聘者发送给目标用户的电子版简历，也可以是应聘者上传至招聘网页的电子版简历，在此不做限定。
终端设备获取应聘者发送的电子版简历，能够实现对关键信息的自动提取以及方便目标用户的审核。
步骤203，在应聘者应聘目标岗位时，扫描应聘者提供的纸质版简历，得到电子版简历，并确定电子版简历为待筛选简历。
终端设备通过光学字符识别（Optical Character Recognition，OCR）扫描纸质版简历，可以得到电子版简历，从而实现对关键信息的自动提取以及方便目标用户的审核。
OCR技术是指终端设备检查纸质版简历上打印的字符，通过检测暗、亮的模式确定其形状，然后用字符识别方法将形状翻译成计算机文字的过程。
需要说明的是，终端设备可以通过步骤201、步骤202、步骤203等三种获取方式中的至少一种获取待筛选简历。
步骤204，提取待筛选简历的第一关键信息。
该步骤与步骤102相同，具体可参见步骤102的相关描述，在此不再赘述。
步骤205，若第一关键信息满足硬指标要求，则提取待筛选简历的第二关键信息。
该步骤与步骤103相同，具体可参见步骤103的相关描述，在此不再赘述。
步骤206，将第二关键信息输入至已训练的简历筛选模型，得到待筛选简历的筛选结果。
该步骤与步骤104相同，具体可参见步骤104的相关描述，在此不再赘述。
本申请实施例通过获取应聘者在招聘网页填写的简历信息、应聘者发送的电子版简历以及扫描应聘者提供的纸质版简历，能够为目标岗位提供较多的待筛选简历，从而增加招聘到与目标岗位匹配的应聘者的概率。
参见图3，是本申请实施例三提供的简历筛选装置的结构示意图，为了便于说明，仅示出了与本申请实施例相关的部分。
上述简历筛选装置包括：
简历获取模块31，用于获取针对目标岗位的待筛选简历；
第一提取模块32，用于提取待筛选简历的第一关键信息，第一关键信息对应目标岗位的硬指标；
第二提取模块33，用于若第一关键信息满足硬指标要求，则提取待筛选简历的第二关键信息，第二关键信息对应目标岗位的软指标；
简历筛选模块34，用于将第二关键信息输入至已训练的简历筛选模型，得到待筛选简历的筛选结果。
可选地，上述简历筛选装置还包括：
第三提取模块，用于若待筛选简历的筛选结果为通过筛选，则提取待筛选简历的第三关键信息，第三关键信息包括待筛选简历对应的应聘者的姓名和联系方式；
信息发送模块，用于将第三关键信息和待筛选简历发送给目标用户；第三关键信息和待筛选简历用于指示目标用户对待筛选简历进行审核；
结果获取模块，用于获取目标用户对待筛选简历的审核结果。
可选地，上述简历筛选装置还包括：
信息写入模块，用于将第三关键信息写入目标文档；
上述信息发送模块具体用于：
将目标文档和待筛选简历发送给目标用户。
可选地，上述简历筛选装置还包括：
信息录入模块，用于若待筛选简历的审核结果为录用，则将待筛选简历对应的应聘者的目标信息录入至员工数据库。
可选地，上述结果获取模块具体用于：
获取目标用户在填写审核结果时形成的log日志；
根据log日志，确定审核结果。
可选地，上述简历筛选装置还包括：
结果确定模块，用于根据审核结果，确定审核结果对应的筛选结果；
信息加入模块，用于将第二关键信息和审核结果对应的筛选结果加入训练集，训练集用于训练简历筛选模型。
可选地，上述简历获取模块31具体用于：
在应聘者应聘目标岗位时，获取应聘者在招聘网页填写的简历信息，并确定该简历信息为待筛选简历；
在应聘者应聘目标岗位时，获取应聘者发送的电子版简历，并确定电子版简历为待筛选简历；
在应聘者应聘目标岗位时，扫描应聘者提供的纸质版简历，得到电子版简历，并确定电子版简历为待筛选简历。
本申请实施例提供的简历筛选装置可以应用在前述方法实施例一和实施例二中，详情参见上述方法实施例一和实施例二的描述，在此不再赘述。
图4是本申请实施例四提供的终端设备的结构示意图。如图4所示，该实施例的终端设备4包括：一个或多个处理器40（图中仅示出一个）、存储器41以及存储在存储器41中并可在至少一个处理器40上运行的计算机程序42。处理器40执行计算机程序42时实现上述各个简历筛选方法实施例中的步骤。
终端设备4可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。终端设备可包括，但不仅限于，处理器40、存储器41。本领域技术人员可以理解，图4仅仅是终端设备4的示例，并不构成对终端设备4的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如终端设备还可以包括输入输出设备、网络接入设备、总线等。
所称处理器40可以是中央处理单元(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器 (Digital Signal Processor，DSP)、专用集成电路 (Application Specific Integrated Circuit，ASIC)、现成可编程门阵列 (Field-Programmable Gate Array，FPGA) 或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
存储器41可以是终端设备4的内部存储单元，例如终端设备4的硬盘或内存。存储器41也可以是终端设备4的外部存储设备，例如终端设备4上配备的插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。进一步地，存储器41还可以既包括终端设备4的内部存储单元也包括外部存储设备。存储器41用于存储计算机程序以及终端设备所需的其他程序和数据。存储器41还可以用于暂时地存储已经输出或者将要输出的数据。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的装置/终端设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/终端设备实施例仅仅是示意性的，例如，模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，计算机程序包括计算机程序代码，计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。计算机可读介质可以包括：能够携带计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、电载波信号、电信信号以及软件分发介质等。需要说明的是，计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。
本申请实现上述实施例方法中的全部或部分流程，也可以通过一种计算机程序产品来完成，当计算机程序产品在终端设备上运行时，使得终端设备执行时实现可实现上述各个方法实施例中的步骤。
以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种简历筛选方法，其特征在于，所述简历筛选方法包括：
    获取针对目标岗位的待筛选简历；
    提取所述待筛选简历的第一关键信息，所述第一关键信息对应所述目标岗位的硬指标；
    若所述第一关键信息满足硬指标要求，则提取所述待筛选简历的第二关键信息，所述第二关键信息对应所述目标岗位的软指标；
    将所述第二关键信息输入至已训练的简历筛选模型，得到所述待筛选简历的筛选结果。
  2. 如权利要求1所述的简历筛选方法，其特征在于，在得到所述待筛选简历的筛选结果之后，还包括：
    若所述待筛选简历的筛选结果为通过筛选，则提取所述待筛选简历的第三关键信息，所述第三关键信息包括所述待筛选简历对应的应聘者的姓名和联系方式；
    将所述第三关键信息和所述待筛选简历发送给目标用户；所述第三关键信息和所述待筛选简历用于指示所述目标用户对所述待筛选简历进行审核；
    获取所述目标用户对所述待筛选简历的审核结果。
  3. 如权利要求2所述的简历筛选方法，其特征在于，在提取所述待筛选简历的第三关键信息之后，还包括：
    将所述第三关键信息写入目标文档；
    相应地，所述将所述第三关键信息和所述待筛选简历发送给目标用户包括：
    将所述目标文档和所述待筛选简历发送给所述目标用户。
  4. 如权利要求2所述的简历筛选方法，其特征在于，在获取所述目标用户对所述待筛选简历的审核结果之后，还包括：
    若所述待筛选简历的审核结果为录用，则将所述应聘者的目标信息录入至员工数据库。
  5. 如权利要求2所述的简历筛选方法，其特征在于，所述获取所述目标用户对所述待筛选简历的审核结果包括：
    获取所述目标用户在填写所述审核结果时形成的log日志；
    根据所述log日志，确定所述审核结果。
  6. 如权利要求2所述的简历筛选方法，其特征在于，所述简历筛选方法还包括：
    根据所述审核结果，确定所述审核结果对应的筛选结果；
    将所述第二关键信息和所述审核结果对应的筛选结果加入训练集，所述训练集用于训练所述简历筛选模型。
  7. 如权利要求1至6任一项所述的简历筛选方法，其特征在于，所述待筛选简历的获取方式包括如下三种方式中的至少一种；
    在应聘者应聘所述目标岗位时，获取所述应聘者在招聘网页填写的简历信息，并确定该简历信息为所述待筛选简历；
    在所述应聘者应聘所述目标岗位时，获取所述应聘者发送的电子版简历，并确定所述电子版简历为所述待筛选简历；
    在所述应聘者应聘所述目标岗位时，扫描所述应聘者提供的纸质版简历，得到所述电子版简历，并确定所述电子版简历为所述待筛选简历。
  8. 一种简历筛选装置，其特征在于，所述简历筛选装置包括：
    简历获取模块，用于获取针对目标岗位的待筛选简历；
    第一提取模块，用于提取所述待筛选简历的第一关键信息，所述第一关键信息对应所述目标岗位的硬指标；
    第二提取模块，用于若所述第一关键信息满足硬指标要求，则提取所述待筛选简历的第二关键信息，所述第二关键信息对应所述目标岗位的软指标；
    简历筛选模块，用于将所述第二关键信息输入至已训练的简历筛选模型，得到所述待筛选简历的筛选结果。
  9. 一种终端设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至7任一项所述简历筛选方法的步骤。
  10. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述简历筛选方法的步骤。
PCT/CN2021/137819 2021-05-27 2021-12-14 简历筛选方法、简历筛选装置、终端设备及存储介质 WO2022247231A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110583302.6 2021-05-27
CN202110583302.6A CN113298495A (zh) 2021-05-27 2021-05-27 简历筛选方法、简历筛选装置、终端设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022247231A1 true WO2022247231A1 (zh) 2022-12-01

Family

ID=77325386

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/137819 WO2022247231A1 (zh) 2021-05-27 2021-12-14 简历筛选方法、简历筛选装置、终端设备及存储介质

Country Status (2)

Country Link
CN (1) CN113298495A (zh)
WO (1) WO2022247231A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113298495A (zh) * 2021-05-27 2021-08-24 中国科学院深圳先进技术研究院 简历筛选方法、简历筛选装置、终端设备及存储介质
CN117132172B (zh) * 2023-10-26 2024-01-26 四川省瑞人网络科技有限公司 一种员工岗位匹配和绩效评估管理方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130198599A1 (en) * 2012-01-30 2013-08-01 Formcept Technologies and Solutions Pvt Ltd System and method for analyzing a resume and displaying a summary of the resume
CN111078971A (zh) * 2019-11-19 2020-04-28 平安金融管理学院(中国·深圳) 简历文件的筛选方法、装置、终端及存储介质
CN111105209A (zh) * 2019-12-17 2020-05-05 上海沃锐企业发展有限公司 适用于人岗匹配推荐系统的职位简历匹配方法及装置
CN111192024A (zh) * 2019-12-31 2020-05-22 广东轩辕网络科技股份有限公司 一种基于强化学习的人岗匹配方法及装置
CN113298495A (zh) * 2021-05-27 2021-08-24 中国科学院深圳先进技术研究院 简历筛选方法、简历筛选装置、终端设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002203200A (ja) * 2000-12-28 2002-07-19 Dainippon Printing Co Ltd 電子経歴書システム、サーバ及び記録媒体
CN108710657A (zh) * 2018-05-11 2018-10-26 广州松榛企业管理有限公司 一种企业员工招聘用简历自动管理系统
CN110991988A (zh) * 2019-11-18 2020-04-10 平安金融管理学院(中国·深圳) 基于岗位信息文档的目标简历文件筛选方法和装置
CN111105203A (zh) * 2019-11-19 2020-05-05 平安金融管理学院(中国·深圳) 简历筛选控制方法、装置、计算机设备及存储介质
CN112256877A (zh) * 2019-12-30 2021-01-22 北京来也网络科技有限公司 结合rpa和ai的简历筛选方法、装置、设备及存储介质
CN111461637A (zh) * 2020-02-28 2020-07-28 平安国际智慧城市科技股份有限公司 简历筛选方法、装置、计算机设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130198599A1 (en) * 2012-01-30 2013-08-01 Formcept Technologies and Solutions Pvt Ltd System and method for analyzing a resume and displaying a summary of the resume
CN111078971A (zh) * 2019-11-19 2020-04-28 平安金融管理学院(中国·深圳) 简历文件的筛选方法、装置、终端及存储介质
CN111105209A (zh) * 2019-12-17 2020-05-05 上海沃锐企业发展有限公司 适用于人岗匹配推荐系统的职位简历匹配方法及装置
CN111192024A (zh) * 2019-12-31 2020-05-22 广东轩辕网络科技股份有限公司 一种基于强化学习的人岗匹配方法及装置
CN113298495A (zh) * 2021-05-27 2021-08-24 中国科学院深圳先进技术研究院 简历筛选方法、简历筛选装置、终端设备及存储介质

Also Published As

Publication number Publication date
CN113298495A (zh) 2021-08-24

Similar Documents

Publication Publication Date Title
US11687827B2 (en) Artificial intelligence (AI)-based regulatory data processing system
US20230004604A1 (en) Ai-augmented auditing platform including techniques for automated document processing
CN108153729B (zh) 一种面向金融领域的知识抽取方法
US9020944B2 (en) Systems and methods for organizing documented processes
WO2022247231A1 (zh) 简历筛选方法、简历筛选装置、终端设备及存储介质
Chou et al. Integrating XBRL data with textual information in Chinese: A semantic web approach
US20240338961A1 (en) Processing forms using artificial intelligence models
CN114185935A (zh) 结合rpa和ai的社保数据处理方法、装置及存储介质
CN115687647A (zh) 公证文书生成方法、装置、电子设备及存储介质
CN116150613A (zh) 信息抽取模型训练方法、信息抽取方法及装置
CN113902009A (zh) 一种简历分析方法、装置、电子设备、介质及产品
US20220067361A1 (en) Form processing and analysis system
CN117132226A (zh) 一种用户行为审核管理系统
Minggao et al. Research on the Application of LLM in Power Finance Middle Platform
CN116868212A (zh) 术语定义的定制转换和质量评估
WO2024055862A1 (zh) 结合rpa和ai实现ia的文档审核方法、装置及电子设备
CN117332761B (zh) 一种pdf文档智能识别标注系统
CN111797237B (zh) 文本实体关系识别方法、系统及介质
US11900272B2 (en) Method and system for mapping labels in standardized tables using machine learning
CN114820211B (zh) 理赔资料质检核验方法、装置、计算机设备及存储介质
CN116308237B (zh) 一种erp邮件处理方法及其相关设备
WO2023119497A1 (ja) 要望抽出装置
CN115587582A (zh) 公证文书模板生成方法、装置、电子设备及存储介质
US20220198323A1 (en) System for preparing machine learning training data for use in evaluation of term definition quality
Blostein et al. Asymptotic cost in document conversion

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21942794

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21942794

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21942794

Country of ref document: EP

Kind code of ref document: A1