Resume screening method, device, terminal and computer-readable storage medium
By calculating the matching degree between resume and job portrait data and adjusting job requirements, the problems of low resume screening efficiency and difficulty in recruiting are solved, and an efficient and intelligent resume screening process is achieved.
Patent Information
- Application Number
- CN201910449915.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2019-05-24
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2039-05-24
AI Technical Summary
In the existing technology, resume screening efficiency is low. Enterprises need to spend a lot of manpower and material resources to screen suitable resumes from large numbers of resumes. If the job requirements are too high or too low, the problem of not being able to recruit suitable talents is likely to occur.
By calculating the matching degree between the resume submitted by the job seeker and the job portrait data, and adjusting the job portrait data according to the matching degree until qualified resumes within the number of people meeting the recruitment needs are selected, the efficiency and intelligence of resume screening are improved.
It has achieved efficient screening of the appropriate number of resumes, avoiding recruitment difficulties caused by excessive number of resumes or excessively high/low job requirements, and improving the efficiency and intelligence of the company's resume screening.
Smart Images

Figure CN110263818B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of computer technology, and in particular relates to a resume screening method, device, terminal and computer-readable storage medium. Background Art
[0002] At present, companies can publish recruitment information for various positions on online recruitment platforms for job seekers to browse and choose. After selecting a suitable position, job seekers can submit their resumes. Companies can screen the resumes submitted by job seekers to find suitable talents, making the company's talent recruitment more intelligent.
[0003] However, when job seekers submit their resumes, they generally adopt a job search strategy of casting a wide net to increase the chances of being successfully hired. This approach often increases the burden of resume screening for companies, and companies need to spend a lot of manpower and material resources to find suitable resumes from a large number of resumes. The efficiency of resume screening is low, which is not conducive to the smooth development of corporate talent recruitment. Summary of the invention
[0004] The embodiments of the present invention provide a resume screening method, device, terminal and computer-readable storage medium, which can solve the technical problem of low resume screening efficiency in the prior art.
[0005] A first aspect of an embodiment of the present invention provides a resume screening method, comprising:
[0006] Obtaining resumes submitted by job seekers for job recruitment, and obtaining the number of people required for the job recruitment and job profile data corresponding to the job recruitment;
[0007] Calculating the matching degree between the resume and the job profile data, and counting the resumes whose matching degree is greater than a first preset threshold to obtain the number of qualified resumes;
[0008] If the number of qualified resumes is less than the first multiple of the number of recruitment needs, or the number of qualified resumes is greater than the second multiple of the number of recruitment needs, the job profile data will be adjusted, the matching degree between the resume and the adjusted job profile data will be recalculated, and the number of qualified resumes will be recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data will be stopped, and the screened qualified resumes will be output; the second multiple is greater than the first multiple.
[0009] A second aspect of an embodiment of the present invention provides a resume screening device, comprising:
[0010] An acquisition unit is used to acquire resumes submitted by job seekers for job recruitment, and to acquire the number of people required for the job recruitment and job profile data corresponding to the job recruitment;
[0011] A calculation unit, used to calculate the matching degree between the resume and the job profile data, and to count the resumes whose matching degree is greater than a first preset threshold to obtain the number of qualified resumes;
[0012] A screening unit is used to adjust the job profile data, recalculate the matching degree between the resume and the adjusted job profile data, and recount the number of qualified resumes if the number of qualified resumes is less than the first multiple of the number of recruitment needs, or the number of qualified resumes is greater than the second multiple of the number of recruitment needs, and stop adjusting the job profile data and output the screened qualified resumes until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs; the second multiple is greater than the first multiple.
[0013] A third aspect of an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0014] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0015] In an embodiment of the present invention, the matching degree between the resumes submitted by job seekers and the job profile data is calculated, and the resumes with the matching degree greater than a first preset threshold are counted to obtain the number of qualified resumes. When the number of qualified resumes is less than a first multiple of the number of recruitment needs, or greater than a second multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the resumes and the adjusted job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, the adjustment of the job profile data is stopped, and the screened qualified resumes are output, so that the enterprise can screen out a suitable number of resumes, and will not increase the burden of resume screening for the enterprise due to the excessive number of resumes submitted by job seekers, thereby improving the efficiency of resume screening; at the same time, the problem of being unable to recruit suitable talents will not occur when the job requirements set by the enterprise are too high or too low, making resume screening more intelligent. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 It is a schematic diagram of an implementation flow of a resume screening method provided by an embodiment of the present invention;
[0018] Figure 2 It is a schematic diagram of a specific implementation flow of a resume screening method provided by an embodiment of the present invention;
[0019] Figure 3 This is a first specific implementation flow diagram of step 102 of a resume screening method provided by an embodiment of the present invention;
[0020] Figure 4 This is a second specific implementation flow diagram of step 102 of a resume screening method provided by an embodiment of the present invention;
[0021] Figure 5 It is a structural schematic diagram of a resume screening device provided by an embodiment of the present invention;
[0022] Figure 6 It is a schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.
[0024] At present, companies often encounter the problem of low resume screening efficiency during the resume screening process. For example, when job seekers submit their resumes, they adopt a wide-ranging job search strategy to increase the chances of successful application, which requires companies to select suitable resumes from a large number of resumes, resulting in low resume screening efficiency. In addition, when the job requirements set by the company are too high or too low, it is easy to screen too many or too few resumes, resulting in the company being unable to recruit suitable talents.
[0025] In an embodiment of the present invention, the matching degree between the resumes submitted by job seekers and the job profile data is calculated, and the resumes with the matching degree greater than a first preset threshold are counted to obtain the number of qualified resumes. When the number of qualified resumes is less than a first multiple of the number of recruitment needs, or greater than a second multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the resumes and the adjusted job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, the adjustment of the job profile data is stopped, and the screened qualified resumes are output, so that the enterprise can screen out a suitable number of resumes, and will not increase the burden of resume screening for the enterprise due to the excessive number of resumes submitted by job seekers, thereby improving the efficiency of resume screening; at the same time, the problem of being unable to recruit suitable talents will not occur when the job requirements set by the enterprise are too high or too low, making resume screening more intelligent.
[0026] like Figure 1 A flowchart of an implementation method of a resume screening method provided by an embodiment of the present invention is shown, which specifically includes steps 101 to 103.
[0027] Step 101, obtain the resumes submitted by job seekers for job recruitment, and obtain the number of job vacancies for the job recruitment and the job profile data corresponding to the job recruitment.
[0028] In an embodiment of the present invention, the method of obtaining a resume submitted by a job seeker for a job position may include obtaining a resume submitted by a job seeker for a job position from a recruitment platform, or may include obtaining a resume submitted by a job seeker for a job position from a pre-set mailbox, or receiving a resume of a job seeker input by a user. It should be noted that this is merely an example of a resume acquisition method, and the present invention does not limit this. In other embodiments of the present invention, the resume submitted by a job seeker for a job position may also be obtained by other methods.
[0029] The number of people needed for job recruitment refers to the number of people that an enterprise plans to recruit when recruiting talents for a certain position, and can be used to estimate the number of resumes that need to be screened.
[0030] The job profile data refers to the job requirements set by an enterprise for personnel engaged in a certain position when recruiting for that position, such as requirements for education, age, work experience, professional type, salary, etc., which are used to determine the basis for screening resumes.
[0031] Step 102, calculate the matching degree between the resume and the job profile data, and count the resumes whose matching degree is greater than a first preset threshold to obtain the number of qualified resumes.
[0032] After obtaining the resumes submitted by job seekers for job vacancies and the job profile data corresponding to the job vacancies, the matching degree between the resumes and the job profile data can be calculated, and the resumes with matching degrees greater than a first preset threshold can be counted to obtain the number of qualified resumes.
[0033] Among them, the resumes with a matching degree greater than the first preset threshold are resumes that successfully match the job profile data, and the resumes with a matching degree less than or equal to the first preset threshold are eliminated resumes.
[0034] The first preset threshold may be set according to actual application scenarios. For example, the first preset threshold may be 80% to 100%.
[0035] Step 103, if the number of qualified resumes is less than the first multiple of the number of recruitment needs, or the number of qualified resumes is greater than the second multiple of the number of recruitment needs, adjust the job profile data, recalculate the matching degree between the resume and the adjusted job profile data, and recount the number of qualified resumes until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, stop adjusting the job profile data, and output the screened qualified resumes; the second multiple is greater than the first multiple.
[0036] Among them, when the number of qualified resumes is less than the first multiple of the number of recruitment needs, it means that there are too few qualified resumes screened out and the job requirements set by the company are too high. It is necessary to adjust the job portrait data to lower the job requirements and increase the number of qualified resumes screened out to avoid the company's failure to recruit suitable talents.
[0037] When the number of qualified resumes is greater than the second multiple of the number of recruitment needs, it means that too many qualified resumes have been screened out and the job requirements set by the company are too low. It is necessary to adjust the job portrait data to increase the job requirements, reduce the number of qualified resumes screened out, and at the same time reduce the burden of resume screening on the company, making it easier for the company to recruit suitable talents.
[0038] It should be noted that the specific values of the first multiple and the second multiple can be determined according to the type of job recruitment. For example, if the job recruitment is for a senior management position, the values of the first multiple and the second multiple can be larger, for example, the first multiple can be 100 and the second multiple can be 200; if the job recruitment is for ordinary employees, the values of the first multiple and the second multiple can be smaller, for example, the first multiple can be 10 and the second multiple can be 20.
[0039] Optionally, adjusting the job portrait data in step 103 may include: dividing the job portrait data into multiple groups of data with different screening priorities, and adjusting the job portrait data according to the screening priorities.
[0040] Specifically, as shown in Table 1, the salary requirements and age requirements in the job portrait data can be regarded as the lowest priority job portrait data, the work experience requirements in the job portrait data can be regarded as the second lowest priority job portrait data, and the educational requirements and professional requirements can be regarded as the highest priority job portrait data. Then, the job portrait data can be adjusted according to the divided screening priorities until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs. Then, the adjustment of the job portrait data can be stopped and the screening of resumes can be completed.
[0041] Table 1:
[0042] Job profile data Priority Salary and age requirements Lowest priority Work experience requirements Next lowest priority Educational requirements, major requirements Highest priority
[0043] Optionally, adjusting the job portrait data according to the screening priority may include: starting from the job portrait data with the lowest screening priority or starting from the job portrait data with the highest screening priority, adjusting one job portrait data with a screening priority at a time, and after completing the adjustment of the job portrait data with a screening priority, recalculating the matching degree between the resume and the adjusted job portrait data, and recounting the number of qualified resumes, until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, stopping the adjustment of the job portrait data and outputting the screened qualified resumes.
[0044] Among them, if the number of qualified resumes is less than the first multiple of the number of recruitment needs, then each adjustment of the job portrait data of a screening priority level includes: lowering the job requirements corresponding to the job portrait data of the screening priority level and / or reducing the job portrait data of the screening priority level; if the number of qualified resumes is greater than the second multiple of the number of recruitment needs, then each adjustment of the job portrait data of a screening priority level includes: increasing the job requirements corresponding to the job portrait data of the screening priority level and / or increasing the job portrait data of the screening priority level.
[0045] For example, the job requirements corresponding to the job profile data that improves the screening priority include improving educational requirements, improving professional requirements, improving work experience requirements, improving salary requirements, and improving age requirements, etc.
[0046] Similarly, the job requirements corresponding to the job profile data that lowers the screening priority include lowering educational requirements, lowering professional requirements, lowering work experience requirements, lowering salary requirements, and lowering age requirements, etc.
[0047] The embodiments of the present invention can avoid the situation where the job portrait data after adjustment differ too much from the job portrait data before adjustment, resulting in a huge gap between the job requirements initially formulated by the enterprise and the job requirements corresponding to the job portrait data are sometimes too low and sometimes too high, by gradually adjusting the job portrait data starting from the data with the lowest screening priority or starting from the data with the highest screening priority, step by step. At the same time, it can avoid the situation where the job requirements corresponding to the job portrait data are sometimes too low and sometimes too high, thereby reducing the amount of calculation for calculating the matching degree between the resume and the job portrait data.
[0048] Optionally, in the above step 103, if the number of qualified resumes is less than the first multiple of the number of recruitment needs, the adjusting of the job portrait data, recalculating the matching degree between the resume and the adjusted job portrait data, and recounting the number of qualified resumes may include: if the number of qualified resumes is less than the first multiple of the number of recruitment needs, adjusting the job portrait data, recalculating the matching degree between the eliminated resumes and the job portrait data, and recounting the number of qualified resumes, until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, stopping the adjustment of the job portrait data and outputting the screened qualified resumes.
[0049] When the number of qualified resumes screened out is less than the first multiple of the number of recruitment needs, it means that too few qualified resumes are screened out and the job requirements set by the company are too high. However, since the resumes screened out at this time are resumes screened out when the job requirements set by the company are too high, they should be resumes that meet the job requirements. Therefore, when adjusting the job portrait data and recalculating the matching degree between the resume and the adjusted job portrait data, there is no need to recalculate the matching degree of these resumes that have been screened out, but only the matching degree between the eliminated resumes and the job portrait data is required, thereby reducing the amount of calculation of the matching degree.
[0050] Optionally, the above step 102 counts the resumes whose matching degree is greater than the first preset threshold to obtain the number of qualified resumes, then recalculates the matching degree between the resume and the adjusted job profile data, and recounts the number of qualified resumes, and may also include: steps 201 to 203.
[0051] Step 201, if the number of qualified resumes is greater than the second multiple of the number of recruitment needs, determine whether the number of qualified resumes is greater than the third multiple of the number of recruitment needs; the third multiple is greater than the second multiple.
[0052] Step 202: If the number of qualified resumes is greater than or equal to the third multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the resume and the adjusted job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data is stopped, and the screened qualified resumes are output.
[0053] Step 203: If the number of qualified resumes is less than the third multiple of the number of recruitment needs, the resumes are sorted according to the matching degree between the resumes and the job profile data, and the resumes with the highest matching degree, which is the second multiple of the number of recruitment needs, are output.
[0054] In this embodiment, when the number of qualified resumes is greater than the second multiple of the number of recruitment needs, it means that too many qualified resumes have been screened out, and the job requirements set by the enterprise are too low. It is necessary to adjust the job profile data to increase the job requirements and reduce the number of qualified resumes screened out. However, since when the number of qualified resumes is greater than the second multiple of the number of recruitment needs, it is possible that the number of qualified resumes screened out is not much more than the second multiple, and therefore, it is not necessary to adjust the job profile data, recalculate the matching degree between the resume and the adjusted job profile data, and re-count the number of qualified resumes. Instead, the resumes can be directly sorted according to the matching degree between the resume and the job profile data, and the resumes with the highest matching degree, which is the second multiple of the number of recruitment needs, can be output.
[0055] For example, the second multiple is 100, the third multiple is 120, and the number of recruits required is 3. When the number of qualified resumes screened out is 330, since 330 is greater than the second multiple of the number of recruits required, 300, but less than the third multiple of the number of recruits required, 360, it can be determined that the number of qualified resumes screened out at this time is not too much more, and the resumes can be sorted according to the matching degree between the resumes and the job profile data, and the resumes with the highest matching degree, which is the second multiple of the number of recruits required, are output, so as to reduce the number of adjustments to the job profile data and reduce the difficulty of adjusting the job profile data, so as to avoid the situation where the job profile data cannot be adjusted so that the number of qualified resumes output is greater than or equal to the first multiple of the number of recruits required, and less than or equal to the second multiple of the number of recruits required.
[0056] In an embodiment of the present invention, the specific value of the third multiple can be determined according to the job recruitment type. For example, if the job recruitment is for a senior management position, the value of the third multiple can be smaller in order to improve the accuracy of resume screening; if the job recruitment is for ordinary employees, the value of the third multiple can be larger in order to reduce the number of adjustments to the job portrait data and reduce the difficulty of adjusting the job portrait data.
[0057] It should be noted that, in some embodiments of the present invention, when the number of qualified resumes is less than the first multiple of the number of recruitment needs, it is also possible to judge whether the number of qualified resumes is less than the fourth multiple of the number of recruitment needs. If the number of qualified resumes is less than the fourth multiple of the number of recruitment needs, the job portrait data is adjusted, the matching degree between the resume and the adjusted job portrait data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job portrait data is stopped, and the screened qualified resumes are output; when the number of qualified resumes is greater than or equal to the fourth multiple of the number of recruitment needs, the resumes are sorted according to the matching degree between the resumes and the job portrait data, and the resumes with the highest matching degree for the first multiple of the number of recruitment needs are output; so as to reduce the number of adjustments to the job portrait data, reduce the difficulty of adjusting the job portrait data, and avoid the situation where the number of qualified resumes output cannot be greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs by adjusting the job portrait data.
[0058] Optional, such as Figure 3 As shown, in each method embodiment described above, the step 102, the step of calculating the matching degree between the resume and the job profile data may include: steps 301 to 306.
[0059] Step 301, segment the text content contained in the resume to obtain at least one first keyword, and segment the text content contained in the job profile data to obtain at least one second keyword.
[0060] Among them, specific word segmentation methods may include a word segmentation method based on string matching, a word segmentation method based on understanding, and a word segmentation method based on statistics.
[0061] Among them, the word segmentation method based on string matching refers to matching the Chinese character string with the words in the dictionary. If a certain string is found in the dictionary, a word is identified. Commonly used word segmentation methods of this type are: forward maximum matching method, reverse maximum matching method and minimum segmentation method. Among them, the principle of the forward maximum matching method is: assuming that the number of Chinese characters contained in the largest entry in the dictionary is n, take the first n characters of the string to be processed as the matching field; if the dictionary contains the word, the match is successful, the word is separated, and then the field composed of n characters is taken from n+1 of the compared string and re-matched in the dictionary; if the match is not successful, the last bit of the field composed of n characters is removed, and the field composed of the remaining n-1 characters is matched in the dictionary, and so on until the segmentation is successful; it has the characteristics of fast word segmentation speed and simple implementation. In the embodiment of the present invention, the first keyword and the second keyword can respectively include data composed of academic qualifications keywords, age keywords, work experience keywords, professional type keywords, and salary keywords.
[0062] Step 302: perform synonym and / or near-synonym expansion on the second keyword to obtain an expanded keyword of the second keyword, and match each of the first keywords with all the second keywords and all the expanded keywords respectively to obtain a first matching value of each of the first keywords.
[0063] For example, when semantically expanding the second keyword "bachelor's degree and above", it can be expanded into extended keywords such as "bachelor's degree", "master's degree" and "doctorate".
[0064] It should be noted that since job profile data is relatively fixed compared to a resume, and job profile data is a recruitment requirement, its content is generally less than that of a resume. Therefore, it is only necessary to expand the second keyword of the job profile data, without expanding the first keyword of the resume.
[0065] After the second keyword is expanded with synonyms and / or near-synonyms, each of the first keywords in the resume can be matched with all the second keywords and all the extended keywords in the job profile data to obtain the first matching value of each of the first keywords.
[0066] For example, the first keyword is matched with all the second keywords and all the extended keywords in the job profile data to determine whether a completely identical keyword can be matched. If so, the first matching value of the first keyword is determined to be 1, otherwise it is 0.
[0067] Optionally, in some embodiments of the present invention, when performing synonym expansion, near-synonym expansion and / or semantic expansion on the second keyword, matching value marking can also be performed based on the degree of similarity of the second keyword corresponding to the expanded keyword and the level between each expanded keyword, and then the first keyword is matched with all the second keywords and all expanded keywords in the job portrait data respectively.
[0068] For example, after the second keyword "bachelor's degree and above" is semantically expanded to "bachelor's degree", "master's degree" and "doctorate", the matching values of the expanded keywords "bachelor's degree", "master's degree" and "doctorate" can be marked as 0.8, 0.9 and 1 respectively according to the levels between each extended keyword; and when a first keyword in the resume is obtained, for example, when the first keyword is "bachelor's degree", the first keyword can be matched with all extended keywords of the second keyword, and a matching result of the first keyword "bachelor's degree" and the extended keyword "bachelor's degree" being successfully matched is obtained, and the first matching value of the first keyword and the extended keyword "bachelor's degree" is determined to be 0.8.
[0069] Step 303: Calculate the average value of the first matching values as the first matching degree of the resume.
[0070] After obtaining the first matching values corresponding to the first keywords contained in the resume, the average value between the first matching values can be calculated as the first matching degree of the resume.
[0071] Step 304, extracting at least one capability label contained in the job portrait data; the capability label includes one or more of an innovation capability label, a communication capability label, a hands-on capability label, a collaboration capability label, and a loyalty label.
[0072] For example, by matching the second keyword with each capability label in a predetermined capability label library, all capability labels included in the job profile data can be obtained.
[0073] Step 305: semantically parse the resume to obtain a second matching value between the resume and each of the capability labels; and calculate an average value of the second matching values as a second matching degree of the resume.
[0074] For example, the ability labels contained in the job portrait data include an innovation ability label and a communication ability label. When parsing the resume, it is necessary to determine the second matching value of the innovation ability label corresponding to the resume and the second matching value of the corresponding communication ability label, and average these two matching values to obtain the second matching degree of the resume.
[0075] Among them, when performing semantic analysis on the resume and determining the second matching values of each capability label corresponding to the resume, a conventional semantic recognition algorithm can be used to perform semantic analysis on the resume. For example, a trained fully connected convolutional neural network or recurrent neural network RNNs is used to perform semantic analysis and determine the second matching values of each capability label corresponding to the resume.
[0076] For example, the job profile data requires job applicants to have good hands-on and innovative abilities. If a job applicant has a text description about his / her experience doing experiments at school in his / her resume, then by using the trained fully connected convolutional neural network to perform semantic analysis on this text, we can know whether the job applicant has hands-on and innovative abilities. If the applicant has hands-on abilities but not innovative abilities, the second matching value between the resume and the hands-on ability label is 1, and the second matching value between the resume and the innovative ability label is 0.
[0077] Step 306, calculating the average value between the first matching degree and the second matching degree as the matching degree between the resume and the job profile data.
[0078] After obtaining the first matching degree and the second matching degree through the above steps 301 to 305, the average value between the first matching degree and the second matching degree can be obtained, that is, the matching degree between the resume and the job profile data.
[0079] In this embodiment, the first matching degree and the second matching degree are respectively obtained, and then the average value between the first matching degree and the second matching degree is calculated as the matching degree between the resume and the job portrait data, rather than just using the first matching degree as the matching degree between the resume and the job portrait data, or using the second matching degree as the matching degree between the resume and the job portrait data, thereby improving the accuracy of the matching degree calculation and making the screened resumes more in line with the company's recruitment needs.
[0080] Optionally, in some embodiments of the present invention, the step 102, the step of calculating the matching degree between the resume and the job profile data can also be performed by inputting the resume into a trained neural network model and calculating the matching degree using the trained neural network model.
[0081] Among them, before inputting the resume into the trained neural network model, the method includes: training the neural network model to be trained to obtain the trained neural network model.
[0082] Specifically, Figure 4 As shown, the training of the neural network model to be trained may include: steps 401 to 403.
[0083] Step 401, obtain resume sample data, job profile sample data, and the calibration matching degree corresponding to each resume sample data.
[0084] For example, resumes and job portrait data with high, good, or poor adaptability to the recruitment positions obtained in the company's historical recruitment process can be extracted, and their matching degrees can be manually marked to obtain the resume sample data, job portrait sample data, and the calibrated matching degrees corresponding to each resume sample data; or resumes and job portrait data with high, good, or poor adaptability to the recruitment positions can be obtained from various recruitment platforms, and their matching degrees can be manually marked to obtain the resume sample data, job portrait sample data, and the calibrated matching degrees corresponding to each resume sample data.
[0085] Step 402, input the resume sample data and the job profile sample data into the neural network model to be trained, and the neural network model to be trained calculates the matching degree of the input resume sample data and the job profile sample data, and outputs the matching degree between the resume sample data and the job profile sample data.
[0086] The neural network models to be trained may include: a feedforward neural network model, a feedback neural network model, a self-organizing neural network model and a random neural network model.
[0087] Step 403, calculate the difference between the matching degree between the resume sample data and the job profile sample data and the calibrated matching degree of the resume sample data. If the difference is greater than the second preset threshold, adjust the parameters of the neural network model to be trained, and re-input the resume sample data and the job profile sample data into the neural network model to be trained until the difference is less than or equal to the second preset threshold, or the number of training times is greater than the third preset threshold, and then use the next resume sample data and its corresponding job profile sample data to train the neural network model to be trained until the confidence of the neural network model to be trained is greater than the fourth preset threshold, so as to obtain a trained neural network model.
[0088] The parameter adjustment of the neural network model to be trained may include parameter adjustment of the weight, bias, and coefficient of the regression function of each convolutional layer, and may also include adjustment of the learning rate, number of iterations, and number of neurons in each layer of the neural network model to be trained.
[0089] The second preset threshold, the third preset threshold and the fourth preset threshold can be set according to the actual application scenario. For example, the second preset threshold can be 5%, the third preset threshold can be 200 times, and the fourth preset threshold can be 99.9%. The confidence of the neural network model refers to the probability of the neural network model to be trained outputting the correct matching degree when performing the first matching calculation on the input resume sample data and the job profile sample data. When the probability is greater than the fourth preset threshold, it means that the neural network model to be trained can already perform accurate matching calculation on the input resume and the job profile data, that is, the neural network model to be trained has been trained.
[0090] It should be noted that this is only an example of a method for calculating the matching degree between resumes and job profile data, and it does not limit the scope of protection of this application. Other methods that can achieve matching degree calculation are also applicable to the present invention and are not listed one by one here.
[0091] like Figure 5 As shown, an embodiment of the present invention provides a resume screening device 500, comprising:
[0092] The acquisition unit 501 is used to acquire resumes submitted by job seekers for job recruitment, and acquire the number of people required for the job recruitment and job profile data corresponding to the job recruitment;
[0093] A calculation unit 502 is used to calculate the matching degree between the resume and the job profile data, and to count the resumes whose matching degree is greater than a first preset threshold to obtain the number of qualified resumes;
[0094] Screening unit 503 is used to adjust the job profile data, recalculate the matching degree between the resume and the adjusted job profile data, and recount the number of qualified resumes if the number of qualified resumes is less than the first multiple of the number of recruitment needs, or the number of qualified resumes is greater than the second multiple of the number of recruitment needs, and stop adjusting the job profile data and output the screened qualified resumes until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs; the second multiple is greater than the first multiple.
[0095] Optionally, the screening unit 503 is also used to adjust the job profile data, recalculate the matching degree between the eliminated resumes and the job profile data, and recount the number of qualified resumes if the number of qualified resumes is less than the first multiple of the number of recruitment needs. When the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, the adjustment of the job profile data is stopped and the screened qualified resumes are output.
[0096] Optionally, the screening unit 503 is further used for:
[0097] If the number of qualified resumes is greater than the second multiple of the number of recruiting needs, then determine whether the number of qualified resumes is greater than the third multiple of the number of recruiting needs; the third multiple is greater than the second multiple;
[0098] If the number of qualified resumes is greater than or equal to the third multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the resume and the adjusted job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data is stopped, and the screened qualified resumes are output;
[0099] If the number of qualified resumes is less than the third multiple of the number of recruitment needs, the resumes are sorted according to the matching degree between the resumes and the job profile data, and the resumes with the highest matching degree, which is the second multiple of the number of recruitment needs, are output.
[0100] Optionally, the screening unit 503 is also used to divide the job profile data into multiple groups of data with different priorities, and adjust them one by one starting from the data with the lowest priority until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, and then stop adjusting the job profile data.
[0101] Optionally, the computing unit 502 is further configured to:
[0102] Segmenting the text content contained in the resume to obtain at least one first keyword, and segmenting the text content contained in the job profile data to obtain at least one second keyword;
[0103] Performing synonym expansion, near-synonym expansion and / or semantic expansion on the second keyword to obtain an expanded keyword of the second keyword;
[0104] Match each of the first keywords with all the second keywords and all the extended keywords respectively to obtain a first matching value of each of the first keywords;
[0105] Calculate the average of the first matching values as the first matching degree of the resume;
[0106] Extracting at least one capability label contained in the job profile data; the capability label includes one or more of an innovation capability label, a communication capability label, a hands-on capability label, a collaboration capability label, and a loyalty label;
[0107] Performing semantic parsing on the resume to obtain a second matching value between the resume and each of the capability tags;
[0108] Calculating an average value of the second matching values as a second matching degree of the resume;
[0109] The average value between the first matching degree and the second matching degree is calculated as the matching degree between the resume and the job profile data.
[0110] Optionally, the computing unit 502 is further configured to:
[0111] The resume is input into a trained neural network model, and the trained neural network model calculates the matching degree between the resume and the job profile data.
[0112] Wherein, before inputting the resume into the trained neural network model, it includes:
[0113] Training the neural network model to be trained to obtain the trained neural network model;
[0114] The training of the neural network model to be trained includes:
[0115] Obtain resume sample data, job profile sample data, and the calibration matching degree corresponding to each resume sample data;
[0116] Inputting the resume sample data and the job profile sample data into the neural network model to be trained, and having the neural network model to be trained calculate the matching degree of the input resume sample data and the job profile sample data, and outputting the matching degree between the resume sample data and the job profile sample data;
[0117] Calculate the difference between the matching degree between the resume sample data and the job profile sample data and the calibrated matching degree of the resume sample data. If the difference is greater than a second preset threshold, adjust the parameters of the neural network model to be trained, and re-input the resume sample data and the job profile sample data into the neural network model to be trained until the difference is less than or equal to the second preset threshold, or the number of training times is greater than a third preset threshold, and then use the next resume sample data and its corresponding job profile sample data to train the neural network model to be trained until the confidence of the neural network model to be trained is greater than a fourth preset threshold, thereby obtaining a trained neural network model.
[0118] It should be noted that, for the convenience and simplicity of description, the specific working process of the resume screening device 500 described above can be referred to Figure 1 and Figure 4 The corresponding process of the method will not be repeated here.
[0119] Figure 6 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 6 As shown, the terminal 6 includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60, such as a resume screening program. When the processor 60 executes the computer program 62, the steps in the above-mentioned resume screening method embodiments are implemented, such as Figure 1 Alternatively, when the processor 60 executes the computer program 62, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 5 Functions of modules 501 to 503 are shown.
[0120] The computer program may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal. For example, the computer program can be divided into an acquisition unit, a calculation unit and a screening unit, and the specific functions of each unit are as follows: the acquisition unit is used to acquire resumes submitted by job seekers for job recruitment, and acquire the number of recruitment requirements for the job recruitment and the job portrait data corresponding to the job recruitment; the calculation unit is used to calculate the matching degree between the resume and the job portrait data, and count the resumes with the matching degree greater than a first preset threshold to obtain the number of qualified resumes; the screening unit is used to adjust the job portrait data if the number of qualified resumes is less than a first multiple of the number of recruitment requirements, or the number of qualified resumes is greater than a second multiple of the number of recruitment requirements, recalculate the matching degree between the resume and the adjusted job portrait data, and recount the number of qualified resumes, until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment requirements, and less than or equal to the second multiple of the number of recruitment requirements, stop adjusting the job portrait data, and output the screened qualified resumes; the second multiple is greater than the first multiple.
[0121] The terminal may be a mobile terminal such as a smart phone, or a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will appreciate that Figure 6 It is only an example of a terminal and does not constitute a limitation on the terminal. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.
[0122] The processor 60 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (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 any conventional processor, etc.
[0123] The memory 61 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. The memory 61 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal. Further, the memory 61 may also include both an internal storage unit of the terminal and an external storage device. The memory 61 is used to store the computer program and other programs and data required by the terminal. The memory 61 may also be used to temporarily store data that has been output or is to be output.
[0124] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0125] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0126] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0127] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0130] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can 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 do not include electric carrier signals and telecommunication signals.
[0131] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A resume screening method, characterized in that: include: Obtaining resumes submitted by job seekers for job recruitment, and obtaining the number of people required for the job recruitment and job profile data corresponding to the job recruitment; Calculating the matching degree between the resume and the job profile data, and counting the resumes whose matching degree is greater than a first preset threshold to obtain the number of qualified resumes; If the number of qualified resumes is less than the first multiple of the number of recruitment needs, or the number of qualified resumes is greater than the second multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the resume and the adjusted job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs, and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data is stopped, and the screened qualified resumes are output; The second multiple is greater than the first multiple; wherein, when the number of qualified resumes is less than the number of recruitment needs of the first multiple, it means that too few qualified resumes are screened out, the set job requirements are too high, and the job profile data needs to be adjusted to lower the job requirements and increase the number of qualified resumes screened out; and when the number of qualified resumes is greater than the second multiple of the number of recruitment needs, it means that too many qualified resumes are screened out, the set job requirements are too low, and the job profile data needs to be adjusted to increase the job requirements and reduce the number of qualified resumes screened out; If the number of qualified resumes is less than the first multiple of the number of recruitment needs, adjusting the job profile data, recalculating the matching degree between the resume and the adjusted job profile data, and recounting the number of qualified resumes, includes: If the number of qualified resumes is less than the first multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the eliminated resumes and the job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data is stopped, and the screened qualified resumes are output; The adjusting of the job portrait data includes: dividing the job portrait data into multiple groups of data with different screening priorities, and adjusting the job portrait data according to the screening priorities; wherein the adjustment method includes: gradually adjusting the job portrait data starting from the data with the lowest screening priority or gradually adjusting starting from the data with the highest screening priority.
2. The method according to claim 1, characterized in that After counting the resumes whose matching degree is greater than the first preset threshold to obtain the number of qualified resumes, recalculating the matching degree between the resumes and the adjusted job profile data, and recounting the number of qualified resumes, including: If the number of qualified resumes is greater than the second multiple of the number of recruiting needs, then determine whether the number of qualified resumes is greater than the third multiple of the number of recruiting needs; the third multiple is greater than the second multiple; If the number of qualified resumes is greater than or equal to the third multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the resume and the adjusted job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data is stopped, and the screened qualified resumes are output; If the number of qualified resumes is less than the third multiple of the number of recruitment needs, the resumes are sorted according to the degree of match between the resumes and the job profile data, and the resumes with the highest degree of match, which is the second multiple of the number of recruitment needs, are output.
3. The method according to claim 1 or 2, characterized in that The calculating the matching degree between the resume and the job profile data includes: Segmenting the text content contained in the resume to obtain at least one first keyword, and segmenting the text content contained in the job profile data to obtain at least one second keyword; Performing synonym expansion, near-synonym expansion and / or semantic expansion on the second keyword to obtain an expanded keyword of the second keyword; Match each of the first keywords with all the second keywords and all the extended keywords respectively to obtain a first matching value of each of the first keywords; Calculate the average of the first matching values as the first matching degree of the resume; Extracting at least one capability label contained in the job profile data; the capability label includes one or more of an innovation capability label, a communication capability label, a hands-on capability label, a collaboration capability label, and a loyalty label; Performing semantic parsing on the resume to obtain a second matching value between the resume and each of the capability tags; Calculating an average value of the second matching values as a second matching degree of the resume; The average value between the first matching degree and the second matching degree is calculated as the matching degree between the resume and the job profile data.
4. The method according to claim 1 or 2, characterized in that: The calculating the matching degree between the resume and the job profile data includes: The resume is input into a trained neural network model, and the trained neural network model calculates the matching degree between the resume and the job profile data.
5. The method according to claim 4, characterized in that Before inputting the resume into the trained neural network model, the method includes: Training the neural network model to be trained to obtain the trained neural network model; The training of the neural network model to be trained includes: Obtain resume sample data, job profile sample data, and the calibration matching degree corresponding to each resume sample data; Inputting the resume sample data and the job profile sample data into the neural network model to be trained, and having the neural network model to be trained calculate the matching degree of the input resume sample data and the job profile sample data, and outputting the matching degree between the resume sample data and the job profile sample data; Calculate the difference between the matching degree between the resume sample data and the job profile sample data and the calibrated matching degree of the resume sample data. If the difference is greater than a second preset threshold, adjust the parameters of the neural network model to be trained, and re-input the resume sample data and the job profile sample data into the neural network model to be trained until the difference is less than or equal to the second preset threshold, or the number of training times is greater than a third preset threshold, and then use the next resume sample data and its corresponding job profile sample data to train the neural network model to be trained until the confidence of the neural network model to be trained is greater than a fourth preset threshold, thereby obtaining a trained neural network model.
6. A resume screening device, characterized in that: include: An acquisition unit is used to acquire resumes submitted by job seekers for job recruitment, and to acquire the number of people required for the job recruitment and job profile data corresponding to the job recruitment; A calculation unit, used to calculate the matching degree between the resume and the job profile data, and to count the resumes whose matching degree is greater than a first preset threshold to obtain the number of qualified resumes; A screening unit, for adjusting the job profile data, recalculating the matching degree between the resume and the adjusted job profile data, and recounting the number of qualified resumes if the number of qualified resumes is less than the first multiple of the number of recruitment needs, or the number of qualified resumes is greater than the second multiple of the number of recruitment needs, and stopping the adjustment of the job profile data and outputting the screened qualified resumes when the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs; The second multiple is greater than the first multiple; wherein, when the number of qualified resumes is less than the number of recruitment needs of the first multiple, it means that too few qualified resumes are screened out, the set job requirements are too high, and the job profile data needs to be adjusted to lower the job requirements and increase the number of qualified resumes screened out; and when the number of qualified resumes is greater than the second multiple of the number of recruitment needs, it means that too many qualified resumes are screened out, the set job requirements are too low, and the job profile data needs to be adjusted to increase the job requirements and reduce the number of qualified resumes screened out; The screening unit is further used for: If the number of qualified resumes is less than the first multiple of the number of recruitment needs, the job profile data is adjusted, the matching degree between the eliminated resumes and the job profile data is recalculated, and the number of qualified resumes is recounted until the number of qualified resumes is greater than or equal to the first multiple of the number of recruitment needs and less than or equal to the second multiple of the number of recruitment needs, then the adjustment of the job profile data is stopped, and the screened qualified resumes are output; Wherein, the adjusting of the job portrait data includes: dividing the job portrait data into multiple groups of data with different screening priorities, and adjusting the job portrait data according to the screening priorities; wherein, the adjustment method includes: gradually adjusting the job portrait data starting from the data with the lowest screening priority or gradually adjusting starting from the data with the highest screening priority.
7. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
