Method and device for evaluating resume, electronic equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a resume evaluation method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-evaluated resume file; analyzing the to-be-evaluated resume file to obtain a resume text; splitting the resume text according to preset resume elements to form decomposed texts corresponding to the resume elements; and evaluating each decomposed text, and summarizing evaluation information of each decomposed text as evaluation information of the to-be-evaluated resume file. Therefore, the to-be-evaluated resume file is decomposed into the plurality of decomposed texts according to the resume elements, and then the content of each decomposed text is evaluated, so that each resume element can be automatically evaluated, and the resume can be comprehensively evaluated.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a resume evaluation method and device, electronic device, and storage medium. Background Art

[0002] In the process of job hunting, users usually need to prepare resumes for the companies they are applying for. A good resume will increase the chances of the user being accepted by the company. In the related art, there is a method of evaluating resumes by human resources experts or career consultants, but this method is inefficient and costly. Based on this, a method of evaluating resumes based on machine learning algorithms is currently proposed. That is, a labeler writes an overall evaluation annotation for a sample resume file; and uses the resume file with the evaluation annotation for model training to obtain a resume evaluation model; finally, the resume file to be evaluated is input into the resume evaluation model to obtain evaluation information. However, by evaluating in this way, only the overall evaluation information of the resume file can be obtained, and the evaluation information is relatively broad and less helpful to users.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0005] The embodiments of the present application provide a method and device for evaluating a resume, an electronic device, and a storage medium to comprehensively evaluate a resume.

[0006] An embodiment of the present application provides a method for evaluating a resume, including: obtaining a resume file to be evaluated; parsing the resume file to be evaluated to obtain a resume text; splitting the resume text according to preset resume elements to form decomposed texts corresponding to each resume element; evaluating each decomposed text separately, and aggregating the evaluation information of each decomposed text as the evaluation information of the resume file to be evaluated.

[0007] It is understandable that a resume usually contains multiple resume elements, such as basic information, self-evaluation, educational background, work / internship experience, project experience, school experience, skill proficiency, awards, competition experience, hobbies, postgraduate entrance examination information, paper journals, etc. In the above implementation, by decomposing the resume file to be evaluated into multiple decomposed texts according to the resume elements, and then evaluating the content of each decomposed text respectively, each resume element can be automatically evaluated, so that the resume can be comprehensively evaluated.

[0008] Furthermore, parsing the resume file to be evaluated to obtain the resume text includes: converting the resume file to be evaluated into a picture; and extracting characters from the picture using optical character recognition technology to obtain the resume text.

[0009] It is understandable that in the related art, resume parsing technology is used to extract the resume text of the resume file to be evaluated. However, when extracting the resume text through resume parsing technology, parsing may fail, and the resume text may not be obtained. At present, optical character recognition technology (OCR technology) is relatively mature, and the text in the picture can be accurately recognized by optical character recognition technology. The present application converts the resume file to be evaluated into a picture, and then uses optical character recognition technology to extract the resume text, so that the resume text can be extracted from the resume file to be evaluated, avoiding the situation where the resume text cannot be obtained, thereby improving the stability of evaluating the resume file to be evaluated.

[0010] Furthermore, the resume text is split according to preset resume elements to form decomposed texts corresponding to each resume element, including: desensitizing the resume text to obtain desensitized text; inputting the desensitized text and a preset first prompt word into a preset first language model to obtain decomposed text; the first prompt word is used to indicate that the desensitized text is split according to the preset resume elements.

[0011] In the above implementation, the user's privacy can be protected by desensitizing the resume text and then splitting the desensitized resume text. By splitting the resume text through a large language model, complex text structures can be processed to avoid the situation where the resume text cannot be split, thereby improving the stability of evaluating the resume file to be evaluated.

[0012] Furthermore, each of the decomposed texts is evaluated separately, including: for each of the decomposed texts: using a preset field database to perform a table lookup operation on the resume elements corresponding to the decomposed text to obtain the field information corresponding to the decomposed text; determining the integrity of the decomposed text based on the inclusion of the field information in the decomposed text, and using the integrity as the evaluation information of the decomposed text.

[0013] It is understandable that each resume element will correspond to multiple fields that need to be filled in. For example, if the resume element is "work experience", it can be determined whether the resume contains the company name, position, responsibilities, start and end time of the company, etc. This application can accurately determine whether the resume element is complete by confirming whether the decomposed text corresponding to the resume element contains the corresponding fields, thereby accurately determining the integrity of the resume file to be evaluated.

[0014] Furthermore, each of the decomposed texts is evaluated separately, including: for each of the decomposed texts: inputting the decomposed text and a preset second prompt word into a preset second largest language model to obtain evaluation information corresponding to the decomposed text; the second prompt word is used to indicate that the second largest language model gives evaluation information for the content input into the second largest language model.

[0015] In the above implementation, since the second largest language model can pre-learn other sample decomposition texts and the evaluation information corresponding to the sample decomposition texts, the decomposition texts can be automatically and accurately evaluated by automatically evaluating the decomposition texts through the second largest language model. In the evaluation process, no human intervention is required, which can improve the efficiency of evaluating the decomposition texts.

[0016] Furthermore, after evaluating each of the decomposed texts respectively, the method also includes: inputting each of the resume elements, the decomposed texts corresponding to each of the resume elements and a preset third prompt word into a preset third language model to obtain interview question recommendations corresponding to the resume file to be evaluated; the third prompt word is used to instruct the third language model to recommend interview questions based on the content input into the third language model.

[0017] In the above implementation, based on the specific content of the resume file to be evaluated filled in by the user, the third language model is used to automatically recommend interview question samples that may be used in the interview to the user, which can help the user improve his or her job hunting competitiveness and thus improve the user's usage experience.

[0018] Furthermore, after evaluating each of the decomposed texts respectively, the method also includes: obtaining a job position; inputting each of the resume elements, the decomposed text corresponding to each of the resume elements, the job position and a preset fourth prompt word into a preset fourth language model to obtain a competitiveness analysis corresponding to the resume file to be evaluated; the fourth prompt word is used to instruct the fourth language model to perform a competitiveness analysis on the content input to the fourth language model with reference to a preset template resume.

[0019] In the above implementation, based on the specific content of the resume file to be evaluated filled in by the user, the fourth language model is used to automatically analyze the competitiveness of the resume file to be evaluated compared with other resume files for the user, which can help the user improve his job hunting competitiveness and improve the user's usage experience.

[0020] The embodiment of the present application provides a device for evaluating resumes, including: an acquisition module for acquiring a resume file to be evaluated; a parsing module for parsing the resume file to be evaluated to obtain a resume text; a decomposition module for splitting the resume text according to preset resume elements to form decomposed texts corresponding to each resume element; an evaluation module for evaluating each decomposed text separately, and summarizing the evaluation information of each decomposed text as the evaluation information of the resume file to be evaluated.

[0021] An embodiment of the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the above-mentioned resume evaluation method.

[0022] In some embodiments, the storage medium stores computer executable instructions, and when the computer executable instructions are called and executed by the processor, the computer executable instructions enable the processor to implement the above-mentioned resume evaluation method.

[0023] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] One or more embodiments are exemplarily described by corresponding drawings, and these exemplary descriptions and drawings do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are considered similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0025] Figure 1 It is a schematic diagram of a device and method for evaluating resumes provided in an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of another device and method for evaluating resumes provided in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of a resume evaluation device provided in an embodiment of the present application;

[0028] Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application.

[0029] Reference numerals:

[0030] 1: Acquisition module; 2: Parsing module; 3: Decomposition module; 4: Evaluation module; 5: Processor; 6: Bus; 7: Memory; 8: Communication interface. DETAILED DESCRIPTION

[0031] In order to be able to understand the features and technical contents of the embodiments of the present application in more detail, the implementation of the embodiments of the present application is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present application. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0032] The terms "first", "second", etc. in the specification and claims of the embodiments of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the embodiments of the present application described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0033] Unless otherwise stated, the term "plurality" means two or more.

[0034] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0035] Embodiment 1

[0036] This application embodiment provides a method for evaluating resumes. Figure 1 As shown, Figure 1 The flowchart of the method for evaluating resumes provided in the embodiment of the present application includes:

[0037] Step S101, obtaining the resume file to be evaluated.

[0038] In some embodiments, the user can upload the resume file to be evaluated to an electronic device equipped with the resume evaluation method of the present application. The resume file to be evaluated can be in the form of a PDF (portable document format) document or a WORD document (a file format).

[0039] Step S102, parsing the resume file to be evaluated to obtain the resume text.

[0040] In some embodiments, step S102 may be: using a privately deployed resume parsing service to parse the resume file to be evaluated, parsing the resume file to be evaluated into a json string text, and using the json string text as the resume text.

[0041] In other embodiments, step S102 may be: importing the resume file to be evaluated into a preset resume parsing software, extracting the text content of the resume file to be evaluated, and obtaining the resume text.

[0042] In other embodiments, step S102 may be: converting the resume file to be evaluated into a picture; extracting characters from the picture using optical character recognition technology to obtain the resume text.

[0043] After extracting characters from the image using optical character recognition technology, Java language can be used to match sensitive information using a preset regular expression to obtain a processed string text, and the string text is used as the resume text. The sensitive information can be a field included in a preset resume element.

[0044] For example, the resume file to be evaluated can be analyzed using a preset resume analysis software or resume analysis service. If the analysis fails, the resume file to be evaluated is converted into an image; and characters are extracted from the image using optical character recognition technology to obtain the resume text.

[0045] It is understandable that in order to make computer language more convenient for processing, the resume text in non-computer language can be converted into a format that can be processed by computer language. For example, convert the resume text in Chinese into a string in JSON language, and then use the string in JSON language as the new resume text for subsequent processing.

[0046] Step S103, splitting the resume text according to the preset resume elements to form decomposed texts corresponding to each resume element.

[0047] Among them, resume elements can be titles in the resume, such as basic information, self-evaluation, educational background, work / internship experience, project experience, school experience, skill proficiency, awards, competition experience, hobbies, postgraduate entrance examination information, paper journals, etc.

[0048] It is understood that the resume elements can be set by engineers according to needs.

[0049] In some embodiments, step S103 may be to perform desensitization processing on the resume text to obtain desensitized text; and input the desensitized text and a preset first prompt word into a preset first language model to obtain a decomposed text. The first prompt word is used to indicate that the desensitized text is to be split according to preset resume elements.

[0050] In the above embodiment, the resume elements that need to be desensitized can be pre-set by the engineer. Only the decomposed text corresponding to the resume elements that need to be desensitized is desensitized. The decomposed text that has been desensitized and the decomposed text corresponding to the resume elements that have not been desensitized are called desensitized text.

[0051] Exemplarily, the decomposed text corresponding to the resume element representing the basic information of the user in the resume text may be desensitized. The decomposed text that has been desensitized and the decomposed text that has not been desensitized and corresponds to the resume element are referred to as desensitized text.

[0052] In the above embodiments, engineers can select a desensitization method according to usage requirements, such as data replacement, data shielding, data obfuscation, etc., which is not limited here.

[0053] In the above embodiment, the first language model, for example: ChatGPT (a chat robot program). Sample resume texts and sample decomposed texts after decomposing the sample resume texts can be collected. The first language model is trained using the sample resume texts and the sample decomposed texts corresponding to the sample resume texts. The trained first language model can split the resume text with reference to the previous decomposition logic. At this time, the sample resume text used for training the first language model can be a text that has been desensitized. Among them, the sample resume text can be a json string text and / or a text text.

[0054] In the above embodiment, the desensitized text and the preset first prompt word are input into the preset first large language model to obtain the decomposed text, which may be: the desensitized text and the preset first prompt word are combined to obtain the first combined text. The first combined text is input into the preset first large language model to obtain the decomposed text.

[0055] Among them, the first specific symbol can be set in the preset first prompt word, so as to fill the desensitized text in the first specific symbol to realize the combination of the desensitized text and the preset first prompt word.

[0056] It can be understood that the first specific symbol can be a single symbol or a combination of multiple symbols, such as double quotation marks, single quotation marks, slashes, colons, etc.

[0057] In the above embodiment, the first prompt word may also include a split format, wherein the split format may be a set data structure, for example, the split format is a json format.

[0058] It can be understood that the json format is usually composed of keys and values, and a structure with only keys can be pre-built for each resume element. Among them, the key is the specific directory that the resume element needs to be split, for example: for the resume element "education experience", the corresponding specific directory, such as: school name, college name, major name, etc. For the resume element "work experience", the corresponding specific directory, such as: work unit, position, etc. When the desensitized text and the preset first prompt word are input into the preset first language model, the first language model will use the content belonging to the key in the desensitized text as the value corresponding to the key, and then output the split resume text in the form of key-value pairs.

[0059] For example, assuming that the sample resume text is a JSON string text, take the content related to education experience in the resume text as an example. The first prompt word, for example: Please help me organize the content in "" according to the following JSON format:

[0060] "resumeEducationDTOList":[

[0061] {

[0062] "schoolName":"School Name",

[0063] "collegeName":"College Name",

[0064] "majorName":"Major Name",

[0065] "startTime":"Start time Date type",

[0066] "endTime":"End time Date type",

[0067] "experience":"Description"

[0068] }

[0069] ].

[0070] Among them, the "" is filled with desensitized text. By sorting in the above JSON format, the decomposed text corresponding to the resume element "education experience" can be obtained.

[0071] As another example, assume that the sample resume text is a text in a non-json format. The first prompt word, for example: Please help me divide the content in [] according to resume elements such as basic information, self-evaluation, educational background, work / internship experience, project experience, school experience, skill proficiency, awards, competition experience, hobbies, postgraduate entrance examination information, paper journals, etc. For resume elements that do not exist in the text, the decomposed content corresponding to the resume element is empty. Among them, the desensitized text is filled in []. Assuming that the desensitized text contains the content "Company name is A, position is B, responsibility is C, school is D, and education is E", by combining the first prompt word and the desensitized text and inputting it into the first language model, the first language model will split the desensitized text into the decomposed text corresponding to the work / internship experience as company name A, position B and responsibility C. The decomposed text corresponding to the school experience is school D and education E.

[0072] In other embodiments, step S103 may be to input the resume text and the preset fifth prompt word into the preset first language model to obtain the decomposed text; in this case, the fifth prompt word is used to indicate to split the resume text according to the preset resume elements.

[0073] It can be understood that in the above embodiment, when the first language model is trained, the sample resume text can be the collected sample resume text that has not been desensitized. The specific steps of inputting the resume text and the preset fifth prompt word into the preset first language model can refer to the specific steps of inputting the desensitized text and the preset first prompt word into the preset first language model, which will not be repeated here.

[0074] Step S104, evaluating each decomposed text respectively, and summarizing the evaluation information of each decomposed text as the evaluation information of the resume file to be evaluated.

[0075] In some embodiments, step S104 may include: for each decomposed text: using a preset field database to perform a table lookup operation on the resume element corresponding to the decomposed text to obtain the field information corresponding to the decomposed text; determining the integrity of the decomposed text according to the inclusion of the field information in the decomposed text, and using the integrity as the evaluation information of the decomposed text. The preset field database stores the correspondence between the best efforts element and the field information.

[0076] It can be understood that the field information can be one or more fields, such as school, position, responsibility, etc.

[0077] In an optional manner of the above embodiment, the completeness of the decomposed text is determined based on the inclusion of field information in the decomposed text: if the decomposed text contains all field information, the decomposed text is determined to be complete; otherwise, the decomposed text is determined to be incomplete.

[0078] In another optional method of the above embodiment, the field information includes multiple fields; determining the integrity of the decomposed text based on the inclusion of the field information in the decomposed text can be: determining the fields contained in the decomposed text as existing fields; when the ratio of the number of existing fields to the total number of fields in the field information is greater than a preset ratio, determining that the decomposed text is complete; otherwise, determining that the decomposed text is incomplete.

[0079] It can be understood that in order to facilitate the user to intuitively understand the integrity of the decomposed text, the integrity score of the decomposed text can be determined according to the ratio of the number of existing fields to the total number of fields in the field information, and the integrity score can be determined as the evaluation information of the decomposed text. Exemplarily, the integrity score corresponding to the ratio can be searched in a preset first score database. The first score database stores the corresponding relationship between the ratio of the number of existing fields to the total number of fields in the field information and the integrity score.

[0080] For example, if the resume element is "education background", it will be determined whether the decomposed text of the resume element "education background" contains fields such as school and academic qualifications. If the resume element is "work experience", it will be determined whether the decomposed text of the resume element "work experience" contains fields such as company name, position, responsibilities, and start and end time of employment.

[0081] In some embodiments, step S104 may include: for each decomposed text: inputting the decomposed text and a preset second prompt word into a preset second largest language model to obtain evaluation information corresponding to the decomposed text; the second prompt word is used to indicate that the second largest language model gives evaluation information for the content input into the second largest language model.

[0082] In the above embodiment, the decomposed text and the preset second prompt word are input into the preset second largest language model, and the evaluation information corresponding to the decomposed text is obtained by: combining the decomposed text and the preset second prompt word to obtain a second combined text. The second combined text is input into the preset second largest language model to obtain the decomposed text.

[0083] Among them, the second specific symbol can be set in the preset second prompt word, so that the decomposed text is filled in the second specific symbol to realize the combination of the decomposed text and the preset second prompt word.

[0084] It can be understood that the second specific symbol can be a single symbol or a combination of multiple symbols.

[0085] Exemplarily, the second prompt word is, for example: Please evaluate the content in "". The "" is filled with decomposed text.

[0086] It can be understood that the second largest language model, for example: ChatGPT. Sample decomposition texts corresponding to the same resume elements and sample evaluation information corresponding to each sample decomposition text can be collected. The second largest language model is trained using the sample decomposition texts of the same resume elements and the sample evaluation information corresponding to the sample decomposition texts. The trained second largest language model can refer to the previous evaluation logic to evaluate the decomposition texts corresponding to the resume elements used in training. It is worth noting that since there are multiple resume elements, a second largest language model can be trained for each resume element here. When in use, the decomposition text and the preset second prompt word are input into the second largest language model of the resume element corresponding to the decomposition text to obtain the evaluation information corresponding to the decomposition text.

[0087] It can be understood that the second largest language model can also be trained using resume elements, sample decomposed texts of resume elements, and sample evaluation information corresponding to the sample decomposed texts. The trained second largest language model can evaluate the decomposed texts corresponding to the resume elements with reference to the previous evaluation logic. In this case, only one second largest language model can be trained. When in use, the decomposed text, the resume elements corresponding to the decomposed text, and the preset second prompt words are input into the second largest language model to obtain the evaluation information corresponding to the decomposed text.

[0088] In this way, due to the stage of parsing the resume file to be evaluated, the parsed resume may not be completely correct and may contain characters that are not related to the resume. Or, the resume file itself contains some non-resume content, which causes the parsed resume text to contain characters that are not related to the resume. If the resume text is not split, the trained large language model is directly used for evaluation. Due to the presence of characters that are not related to the resume, the evaluation of the large language model may not be accurate enough. By splitting the resume text, some characters that are not related to the resume can be filtered out, so that the impact of characters that are not related to the resume is smaller, thereby making the evaluation of the large language model more accurate. At the same time, by adding a split format to the first prompt word, the decomposed text split according to the resume elements can be further made more accurate, thereby making the evaluation of the large language model more accurate.

[0089] In the above embodiment, the second prompt word may also be provided with a writing format, so that the second largest language model rewrites the decomposed text according to the writing format in the second prompt word, and outputs the rewritten decomposed text.

[0090] In some embodiments, after evaluating each decomposed text respectively, the method for evaluating a resume also includes: inputting each resume element, the decomposed text corresponding to each resume element and a preset third prompt word into a preset third language model to obtain interview question recommendations corresponding to the resume file to be evaluated; the third prompt word is used to instruct the third language model to recommend interview questions based on the content input into the third language model.

[0091] In the above embodiment, each resume element, the decomposed text corresponding to each resume element, and the preset second prompt word are input into the preset third language model, which can be: the resume module and the preset third prompt word are combined to obtain a third combined text. The third combined text is input into the preset third language model. The resume elements and the decomposed text corresponding to the resume elements constitute a resume module.

[0092] Among them, a third specific symbol can be set in the preset third prompt word, so as to fill in each resume module in the third specific symbol to obtain a third combined text.

[0093] It can be understood that the third specific symbol can be a single symbol or a combination of multiple symbols.

[0094] Exemplarily, the third prompt word, for example: Please recommend interview questions for the content in "". Among them, "" is filled with a resume module.

[0095] It can be understood that the third language model, such as ChatGPT, can collect sample resume modules and interview questions corresponding to the sample resume modules. The sample resume modules and interview questions corresponding to the sample resume modules are used to train the third language model. The trained third language model can refer to the previous interview question recommendation logic for interview question recommendation.

[0096] For example, the resume module includes the resume element "skill proficiency" and the decomposed text "proficient in using CAD" corresponding to "skill proficiency". The interview question recommended by the third language model based on the resume module may be "Please share the most challenging project you have completed using CAD software and explain how you overcame the difficulties."

[0097] In some embodiments, after evaluating each decomposed text respectively, the resume evaluation method further includes: obtaining a job position. Inputting each resume element, the decomposed text corresponding to each resume element, the job position and the preset fourth prompt word into the preset fourth language model to obtain the competitiveness analysis corresponding to the resume file to be evaluated. The fourth prompt word is used to instruct the fourth language model to perform a competitiveness analysis on the content input to the fourth language model with reference to the preset template resume.

[0098] It is understandable that some resume elements have little impact on job-seeking competitiveness, such as the user's basic information. Therefore, each resume element, the decomposed text corresponding to each resume element, the job position and the preset fourth prompt word are input into the preset fourth language model, and only the resume elements that are the same as the preset resume elements and their corresponding decomposed text, job position and the preset fourth prompt word can be input into the preset fourth language model.

[0099] Among them, the preset resume elements can be pre-set by engineers based on experience.

[0100] In the above embodiment, inputting each resume element, the decomposed text corresponding to each resume element, the job position and the preset fourth prompt word into the preset fourth language model can be: combining the resume module, the job position and the preset fourth prompt word to obtain a fourth combined text. Inputting the fourth combined text into the preset fourth language model.

[0101] The fourth prompt word includes multiple resumes and the competitiveness level corresponding to each resume. The resume team can mark the competitiveness level of the resumes in advance for different job positions.

[0102] Among them, the fourth specific symbol and the fifth specific symbol can be set in the preset fourth prompt word, so as to fill in the resume module in the fourth specific symbol and fill in the job position in the fifth specific symbol to obtain the fourth combined text. It can be understood that the fourth specific symbol and the fifth specific symbol can be a single symbol or a combination of multiple symbols.

[0103] For example, the fourth prompt word is: Please refer to the competitiveness level g corresponding to resume G and resume G, the competitiveness level f corresponding to resume F and resume F, and the competitiveness level e corresponding to resume E and the positions in [], and give the competitiveness level for the content in "". Among them, [] is filled with job positions, and "" is filled with resume modules.

[0104] It can be understood that the fourth language model can refer to the template resume of the same job position, compare the content of the resume module with the template resume, and give the competitiveness level of each resume module according to the competitiveness level corresponding to the template resume. And the competitiveness level of each resume module is summarized to obtain the competitiveness level corresponding to the resume file to be evaluated.

[0105] Among them, comparing the content of the resume module with the template resume can be used to see the similarity between the content of the resume module and the template resume.

[0106] The competitiveness level may be in the form of a score, such as 10 points, 0 points, etc. It may also be in the form of a text level, such as excellent, good, medium, poor, etc.

[0107] Wherein, when the competitiveness level is a score, the competitiveness level of each resume module can be summarized by taking the average score of each resume module as the competitiveness level corresponding to the resume file to be evaluated. When the competitiveness level is a text level, the competitiveness level of each resume module can be summarized by setting a corresponding numerical value for each text level, calculating the numerical average of the numerical values ​​corresponding to each text level, and determining the text level closest to the numerical average as the competitiveness level corresponding to the resume file to be evaluated.

[0108] In some embodiments, the present application provides another method for evaluating resumes, which can be found in Figure 2 As shown, Figure 2 The flowchart of the method for evaluating resumes provided in the embodiment of the present application includes:

[0109] Step S201, obtain the resume file to be evaluated, and then execute step S202.

[0110] Step S202, using the preset resume parsing software or resume parsing service to parse the resume file to be evaluated, and then executing step S203.

[0111] Step S203, determine whether the resume file to be evaluated is parsed successfully. If the parsing fails, execute step S204. If the parsing succeeds, execute step S205.

[0112] Step S204, convert the resume file to be evaluated into an image, extract characters from the image using optical character recognition technology, and obtain the resume text. Then, execute step S205.

[0113] Step S205, split the resume text according to the preset resume elements to form decomposed text corresponding to each resume element, and then execute step S206.

[0114] Step S206, use the preset field database to perform a table lookup operation on the resume elements corresponding to the decomposed text to obtain the field information corresponding to the decomposed text; determine the integrity of the decomposed text based on the inclusion of the field information in the decomposed text, use the integrity as the evaluation information of the decomposed text, and then execute step S207.

[0115] Step S207, for each decomposed text: input the decomposed text and the preset second prompt word into the preset second largest language model to obtain the evaluation information corresponding to the decomposed text, and then execute step S208.

[0116] Step S208, input each resume element, the decomposed text corresponding to each resume element and the preset third prompt word into the preset third language model, obtain the interview question recommendation corresponding to the resume file to be evaluated, and then execute step S209.

[0117] Step S209, obtaining job positions; inputting each resume element, the decomposed text corresponding to each resume element, the job position and the preset fourth prompt word into the preset fourth language model to obtain the competitiveness analysis corresponding to the resume file to be evaluated.

[0118] Embodiment 2

[0119] Based on the same inventive concept, the present application embodiment provides a device for evaluating resumes, such as Figure 3 As shown, the resume evaluation device includes: an acquisition module 1, a parsing module 2, a decomposition module 3 and an evaluation module 4. Among them, the acquisition module 1 is used to obtain the resume file to be evaluated; the parsing module 2 is used to parse the resume file to be evaluated and obtain the resume text; the decomposition module 3 is used to split the resume text according to the preset resume elements to form the decomposed text corresponding to each resume element; the evaluation module 4 is used to evaluate each decomposed text respectively, and summarize the evaluation information of each decomposed text as the evaluation information of the resume file to be evaluated.

[0120] In some embodiments, the parsing module 2 is used to parse the resume file to be evaluated and obtain the resume text in the following manner: converting the resume file to be evaluated into a picture; and extracting characters from the picture using optical character recognition technology to obtain the resume text.

[0121] In some embodiments, the decomposition module 3 is used to split the resume text according to preset resume elements in the following manner to form decomposed text corresponding to each resume element: desensitizing the resume text to obtain desensitized text; inputting the desensitized text and a preset first prompt word into a preset first language model to obtain decomposed text; the first prompt word is used to indicate that the desensitized text is to be split according to the preset resume elements.

[0122] In some embodiments, the evaluation module 4 is used to evaluate each decomposed text separately in the following manner: for each decomposed text: use a preset field database to perform a table lookup operation on the resume elements corresponding to the decomposed text to obtain the field information corresponding to the decomposed text; determine the integrity of the decomposed text based on the inclusion of the field information in the decomposed text, and use the integrity as the evaluation information of the decomposed text.

[0123] In some embodiments, the evaluation module 4 is used to evaluate each decomposed text separately in the following manner: for each decomposed text: the decomposed text and a preset second prompt word are input into a preset second largest language model to obtain evaluation information corresponding to the decomposed text; the second prompt word is used to indicate that the second largest language model gives evaluation information for the content input into the second largest language model.

[0124] In some embodiments, the device for evaluating resumes also includes: an interview question recommendation module, which is used to evaluate each decomposed text separately, input each resume element, the decomposed text corresponding to each resume element and a preset third prompt word into a preset third language model, and obtain interview question recommendations corresponding to the resume file to be evaluated; the third prompt word is used to instruct the third language model to recommend interview questions based on the content input to the third language model.

[0125] In some embodiments, the device for evaluating resumes also includes: a competitiveness analysis module, which is used to obtain job positions after evaluating each decomposed text respectively; input each resume element, the decomposed text corresponding to each resume element, the job position and a preset fourth prompt word into a preset fourth language model to obtain a competitiveness analysis corresponding to the resume file to be evaluated; the fourth prompt word is used to instruct the fourth language model to perform a competitiveness analysis on the content input to the fourth language model with reference to a preset template resume.

[0126] It can be understood that the various embodiments described in the first embodiment are also applicable to the second embodiment if there is no conflict. Based on the consideration of brevity of description, they will not be repeated here.

[0127] Embodiment 3

[0128] Combination Figure 4 As shown, an embodiment of the present application provides an electronic device, including a processor 5 and a memory 7. Optionally, the device may also include a communication interface 8 and a bus 6. The processor 5, the communication interface 8, and the memory 7 may communicate with each other through the bus 6. The communication interface 8 may be used for information transmission. The processor 5 may call the logic instructions in the memory 7 to execute the resume evaluation method of the above embodiment.

[0129] In addition, the logic instructions in the above-mentioned memory 7 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0130] The memory 7 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present application. The processor 5 executes the function application and data processing by running the program instructions / modules stored in the memory 7, that is, the method for evaluating resumes in the above embodiment is implemented.

[0131] The memory 7 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 7 may include a high-speed random access memory and may also include a non-volatile memory.

[0132] The electronic device may be a computer or a server, etc.

[0133] An embodiment of the present application provides a storage medium storing computer executable instructions, wherein the computer executable instructions are configured to execute the above-mentioned resume evaluation method.

[0134] An embodiment of the present application provides a computer program product, which includes a computer program stored on a storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the above-mentioned resume evaluation method.

[0135] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0136] The technical solution of the embodiment of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium can be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., which can store program codes, or a transient storage medium.

[0137] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments indicated above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0138] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application. At the same time, the above embodiments can be combined with each other to form new embodiments without conflict.

Claims

1. A method for evaluating a resume, characterized in that: include: Get the resume file to be evaluated; Parsing the resume file to be evaluated to obtain the resume text; Splitting the resume text according to preset resume elements to form decomposed texts corresponding to each resume element; Each of the decomposed texts is evaluated respectively, and the evaluation information of each of the decomposed texts is summarized as the evaluation information of the resume file to be evaluated.

2. The method according to claim 1, characterized in that Parse the resume file to be evaluated to obtain the resume text, including: Convert the resume file to be evaluated into a picture; Optical character recognition technology is used to extract characters from the image to obtain the resume text.

3. The method according to claim 1, characterized in that The resume text is split according to the preset resume elements to form decomposed texts corresponding to the resume elements, including: Desensitizing the resume text to obtain a desensitized text; The desensitized text and a preset first prompt word are input into a preset first language model to obtain a decomposed text; the first prompt word is used to indicate that the desensitized text is to be split according to preset resume elements.

4. The method according to claim 1, characterized in that: Each of the decomposed texts is evaluated separately, including: For each of the decomposed texts: Using a preset field database to perform a table lookup operation on the resume elements corresponding to the decomposed text, to obtain the field information corresponding to the decomposed text; The integrity of the decomposed text is determined according to the inclusion of the field information in the decomposed text, and the integrity is used as evaluation information of the decomposed text.

5. The method according to claim 1, characterized in that Each of the decomposed texts is evaluated separately, including: For each of the decomposed texts: The decomposed text and the preset second prompt word are input into the preset second largest language model to obtain evaluation information corresponding to the decomposed text; the second prompt word is used to indicate that the second largest language model gives evaluation information for the content input into the second largest language model.

6. The method according to any one of claims 1 to 5, characterized in that: After evaluating each of the decomposed texts respectively, the method further includes: Input each of the resume elements, the decomposed text corresponding to each of the resume elements and a preset third prompt word into a preset third language model to obtain interview question recommendations corresponding to the resume file to be evaluated; the third prompt word is used to instruct the third language model to recommend interview questions based on the content input into the third language model.

7. The method according to any one of claims 1 to 5, characterized in that: After evaluating each of the decomposed texts respectively, the method further includes: Get job openings; Input each of the resume elements, the decomposed text corresponding to each of the resume elements, the job position and a preset fourth prompt word into a preset fourth language model to obtain a competitiveness analysis corresponding to the resume file to be evaluated; the fourth prompt word is used to instruct the fourth language model to perform a competitiveness analysis on the content input to the fourth language model with reference to a preset template resume.

8. A device for evaluating resumes, characterized in that: include: The acquisition module is used to obtain the resume file to be evaluated; A parsing module, used for parsing the resume file to be evaluated to obtain the resume text; A decomposition module, used to split the resume text according to preset resume elements to form decomposed texts corresponding to each resume element; The evaluation module is used to evaluate each of the decomposed texts respectively, and summarize the evaluation information of each of the decomposed texts as the evaluation information of the resume file to be evaluated.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the resume evaluation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores computer executable instructions, and when the computer executable instructions are called and executed by the processor, the computer executable instructions enable the processor to implement the resume evaluation method described in any one of claims 1 to 7.

Images