A position matching method and device for business administration majors

Abstract

The application relates to the technical field of position planning, and particularly provides a position matching method and device for business administration majors, which comprises the following steps: performing keyword extraction on a pre-filled student resume based on a recruitment keyword set; generating a position score based on the position of a resume keyword in corresponding recruitment information, and generating a frequency score based on the appearance frequency of the resume keyword in the corresponding recruitment information; generating a field score corresponding to each resume keyword based on the similarity between the resume keyword and a professional keyword; calculating a matching score corresponding to each resume keyword according to the position score, the frequency score and the field score of the resume keyword; and screening target recruitment information from all recruitment information based on the sum of all matching scores corresponding to the same recruitment information. The method can effectively solve the problem that high-quality matching between recruitment information and resumes cannot be realized due to the simple appearance of resume keywords for position matching.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of position planning, in particular to a position matching method and device for business administration majors. BACKGROUND

[0002] In the specific application scenario of job preparation of business administration major students in colleges and universities, students need to use a position matching system to recommend suitable positions from the recruitment information published on various recruitment websites according to their own resumes. The position matching system of the related technology depends on the number of appearance of resume keywords (keywords extracted from the resume) to recommend suitable positions, that is, the position matching system defines the positions corresponding to the recruitment information whose resume keyword appearance number reaches a preset number as suitable positions. Since the related technology only relies on the simple appearance of resume keywords for position matching, and different recruitment information pays different attention to the same resume keyword, the related technology has the problem of being unable to achieve high-quality matching of recruitment information and resumes due to only relying on the simple appearance of resume keywords for position matching, thereby resulting in low position matching precision.

[0003] At present, there is no effective technical solution to the above problems. It should be noted that the above information disclosed in this part is only used to understand the background of the present application concept, and therefore can contain information that does not constitute prior art. SUMMARY

[0004] The purpose of the present application is to provide a position matching method and device for business administration majors, which can effectively solve the problem of being unable to achieve high-quality matching of recruitment information and resumes due to only relying on the simple appearance of resume keywords for position matching.

[0005] In a first aspect, the present application provides a position matching method for business administration majors, comprising the following steps:

[0006] S1, respectively, on a plurality of recruitment information in turn keyword extraction, to obtain a plurality of recruitment keyword sets, and the recruitment keyword set is segmented, removed stop words and synonym expansion, each recruitment keyword set corresponds to a recruitment information, each recruitment keyword set includes a plurality of recruitment keywords;

[0007] S2, based on the recruitment keyword set pre-filled student resume keyword extraction, so that each recruitment information corresponds to a resume keyword set, and the resume keyword set includes a plurality of resume keywords;

[0008] S3, based on the position of the resume keyword in the corresponding recruitment information, the position score corresponding to each resume keyword is generated, and the frequency score corresponding to each resume keyword is generated based on the frequency of the resume keyword in the corresponding recruitment information;

[0009] S4, generating a field score corresponding to each resume keyword based on the similarity between the resume keyword and the professional keyword in the pre-constructed field knowledge base of the business administration major;

[0010] S5, calculating a matching score corresponding to each resume keyword according to the position score, the frequency score and the field score of the resume keyword;

[0011] S6, screening the target recruitment information from all recruitment information based on the sum of all matching scores corresponding to the same recruitment information, so as to complete the position matching.

[0012] The position matching method for the business administration major provided by the present application first generates the position score, the frequency score and the field score corresponding to the resume keyword, and then screens the target recruitment information from all recruitment information based on the position score, the frequency score and the field score, that is, the present application recommends the appropriate position from the three aspects of the position of the resume keyword in the recruitment information, the appearance frequency of the resume keyword in the recruitment information and the similarity between the resume keyword and the professional keyword, so the present application is equivalent to analyze whether the recruitment information matches the student resume from multiple angles, thereby effectively solving the problem that the high-quality matching between the recruitment information and the resume cannot be realized due to the simple appearance of the resume keyword for position matching, and further effectively improving the position matching precision.

[0013] Optionally, the step S3 comprises:

[0014] S31, selecting a resume keyword;

[0015] S32, obtaining the position type information according to the recruitment information corresponding to the selected resume keyword;

[0016] S33, generating a position score according to the position of the selected resume keyword in the corresponding recruitment information and the position type information corresponding thereto;

[0017] S34, generating a frequency score according to the appearance frequency of the selected resume keyword in the corresponding recruitment information and the position type information corresponding thereto;

[0018] S35, analyzing whether there is a resume keyword without generating the position score and the frequency score, if yes, selecting any resume keyword without generating the position score and the frequency score, and returning to the step S32, if not, executing the step S4.

[0019] Since different types of positions pay different attention to the appearance position and appearance frequency of the same resume keyword in the recruitment information, and the technical solution first acquires the position type information, then generates the position score according to the position of the selected resume keyword in the corresponding recruitment information and the position type information corresponding thereto, and generates the frequency score according to the appearance frequency of the selected resume keyword in the corresponding recruitment information and the position type information corresponding thereto, therefore, the technical solution is equivalent to considering the influence of the attention of the position type to the appearance position and appearance frequency in the recruitment information when generating the position score and the frequency score, thereby effectively improving the accuracy of the position score and the frequency score, and further effectively improving the position matching precision.

[0020] Optionally, the step S33 comprises:

[0021] S331, acquiring a position correction coefficient according to the position of the selected resume keyword in the corresponding recruitment information, the corresponding position type information and the first preset conversion relationship;

[0022] S332, calculating the position score according to the position correction coefficient and the preset preliminary position score.

[0023] Optionally, the step S4 comprises:

[0024] S41, selecting a resume keyword;

[0025] S42, acquiring a field score according to the maximum value of the similarity between the selected resume keyword and the professional keyword in the pre-constructed business administration professional field knowledge base and the second preset conversion relationship;

[0026] S43, analyzing whether there is a resume keyword without generating a field score, if yes, selecting any resume keyword without generating a field score, and returning to the step S42, if no, executing the step S5.

[0027] Since the technical solution acquires the field score according to the maximum value of the similarity between the selected resume keyword and the professional keyword in the pre-constructed business administration professional field knowledge base and the second preset conversion relationship, that is, the field score of each resume keyword can reflect the association degree with the professional knowledge with the highest relevance in the business administration professional field knowledge base, therefore, the technical solution can effectively improve the accuracy of the field score, thereby further improving the position matching precision.

[0028] Optionally, the step S42 comprises:

[0029] S421, acquiring position type information according to the corresponding recruitment information of the selected resume keyword;

[0030] S422, acquiring a first correction coefficient corresponding to different professional keywords according to the position type information and the third preset conversion relationship;

[0031] S423. Calculate the similarity between the selected resume keywords and all professional keywords in the pre-built business administration professional knowledge base to obtain the preliminary similarity corresponding to each professional keyword.

[0032] S424. Calculate the similarity between each professional keyword and the selected resume keywords based on the preliminary similarity and the first correction coefficient corresponding to the professional keywords, and obtain the domain score based on the maximum similarity and the second preset conversion relationship.

[0033] Since different types of positions pay varying degrees of attention to the same professional keywords, this technical solution first obtains the first correction coefficient corresponding to different professional keywords based on the job type information, and then obtains the preliminary similarity corresponding to each professional keyword. Next, it calculates the similarity between each professional keyword and the selected resume keywords based on the preliminary similarity and the first correction coefficient. Finally, it obtains the domain score based on the maximum similarity. In other words, this technical solution considers the influence of job type on the degree of attention to professional keywords when calculating the domain score. Therefore, this technical solution can further improve the accuracy of the domain score, thereby further improving the job matching accuracy.

[0034] Optionally, the third preset transformation relationship is a pre-constructed mapping relationship regarding job type, professional keywords, and correction coefficients. The pre-construction process of the third preset transformation relationship includes the following steps:

[0035] Based on the clustering algorithm, the historical recruitment data is divided into multiple job type clusters according to the job descriptions and skill requirements in the historical recruitment data. Each job type cluster corresponds to a job type.

[0036] The set of correction coefficients for each job type cluster is calculated based on the frequency of occurrence of different professional keywords in all historical recruitment data corresponding to the same job type cluster. Each set of correction coefficients includes multiple sets of professional keywords and their corresponding correction coefficients, so that each job type corresponds to a set of correction coefficients.

[0037] A third preset transformation relationship is constructed based on the job type and the corresponding set of correction coefficients.

[0038] Optionally, the student's resume includes internship experience, and step S6 includes:

[0039] S61. Calculate the sum of all matching scores corresponding to each recruitment information to obtain a preliminary total score. Each preliminary total score corresponds to one recruitment information.

[0040] S62, obtaining a second correction coefficient corresponding to each of the recruitment information according to the text similarity and a fourth preset conversion relationship, the text similarity being a similarity between the description text of the internship experience and a description text of the recruitment information;

[0041] S63, calculating a matching total score corresponding to each of the recruitment information according to the preliminary total score corresponding to the recruitment information and the second correction coefficient;

[0042] S64, screening a recruitment information with a highest matching total score from all the recruitment information as the target recruitment information to complete the position matching.

[0043] The technical solution is equivalent to performing the position matching from two dimensions of a matching degree between the resume keywords and the recruitment information and a similarity between the internship experience and the recruitment information, and thus the technical solution can effectively improve a matching quality between the recruitment information and the student resume, thereby further improving the position matching precision.

[0044] Optionally, the step S6 further includes a step performed before the step S63:

[0045] S65, obtaining a user click volume and a publishing duration of the recruitment information, and calculating a position heat corresponding to each of the recruitment information according to the user click volume and the publishing duration based on a time decay function;

[0046] S66, obtaining a third correction coefficient corresponding to each of the recruitment information according to the position heat and a fifth preset conversion relationship;

[0047] The step S63 includes:

[0048] S631, calculating a matching total score corresponding to each of the recruitment information according to the preliminary total score corresponding to the recruitment information, the second correction coefficient and the third correction coefficient.

[0049] Since the position heat is positively correlated with a position competition intensity and a recruitment standard, a change in the position competition intensity and the recruitment standard will cause a change in a success rate of the student job hunting, and the technical solution is equivalent to considering an influence of the position heat when performing the position matching, and thus the technical solution can make the target recruitment information more suitable for an actual situation of the student and market demand, thereby effectively improving the position matching precision and quality.

[0050] Optionally, the step S6 further includes a step performed before the step S63:

[0051] S67, counting a position demand quantity of different position types according to all the recruitment information, and calculating a fourth correction coefficient according to a position demand quantity corresponding to a position type to which the recruitment information belongs and all the position demand quantities;

[0052] The step S631 includes:

[0053] S6311、According to the preliminary total score corresponding to the recruitment information, the second correction coefficient, the third correction coefficient and the fourth correction coefficient, the matching total score corresponding to each recruitment information is calculated.

[0054] Since the fourth correction coefficient is introduced when calculating the matching total score, and the fourth correction coefficient can reflect the demand proportion of the market for different position types, that is, the calculation of the matching total score of the technical solution takes into account the demand amount of the market for different position types, therefore, the technical solution can make the position matching result more comprehensive, balanced and in line with the market supply and demand relationship, thereby effectively improving the rationality of position matching.

[0055] In a second aspect, the present application also provides a position matching device for business administration majors, comprising:

[0056] A recruitment keyword acquisition module is configured to sequentially perform keyword extraction on a plurality of recruitment information to obtain a plurality of recruitment keyword sets, and perform word segmentation, stop word removal and synonym expansion on the recruitment keyword sets. Each recruitment keyword set corresponds to one recruitment information, and each recruitment keyword set includes a plurality of recruitment keywords.

[0057] A resume keyword acquisition module is configured to perform keyword extraction on a pre-filled student resume based on the recruitment keyword set, so that each recruitment information corresponds to one resume keyword set, and the resume keyword set includes a plurality of resume keywords.

[0058] A position score and frequency score acquisition module is configured to generate a position score corresponding to each resume keyword based on the position of the resume keyword in the corresponding recruitment information, and generate a frequency score corresponding to each resume keyword based on the frequency of the resume keyword in the corresponding recruitment information.

[0059] A field score acquisition module is configured to generate a field score corresponding to each resume keyword based on the similarity between the resume keyword and a professional keyword in a pre-constructed business administration major field knowledge base.

[0060] A matching score acquisition module is configured to calculate a matching score corresponding to each resume keyword according to the position score, the frequency score and the field score of the resume keyword.

[0061] A position matching module is configured to filter out target recruitment information from all recruitment information based on the sum of all matching scores corresponding to the same recruitment information, so as to complete position matching.

[0062] The position matching device for business administration specialty provided by the application generates position score, frequency score and field score corresponding to resume keywords first, and then filters target recruitment information from all recruitment information based on the position score, the frequency score and the field score, that is, the application recommends suitable positions from the three aspects of the position of the resume keywords in the recruitment information, the appearance frequency of the resume keywords in the recruitment information and the similarity between the resume keywords and the professional keywords, so the application is equivalent to analyze whether the recruitment information matches the student resume from multiple angles, thereby effectively solving the problem that high-quality matching between the recruitment information and the resume cannot be achieved due to the simple appearance of the resume keywords for position matching, and further effectively improving the position matching precision.

[0063] As can be seen from the above, the position matching method and device for business administration specialty provided by the application generate position score, frequency score and field score corresponding to resume keywords first, and then filter target recruitment information from all recruitment information based on the position score, the frequency score and the field score, that is, the application recommends suitable positions from the three aspects of the position of the resume keywords in the recruitment information, the appearance frequency of the resume keywords in the recruitment information and the similarity between the resume keywords and the professional keywords, so the application is equivalent to analyze whether the recruitment information matches the student resume from multiple angles, thereby effectively solving the problem that high-quality matching between the recruitment information and the resume cannot be achieved due to the simple appearance of the resume keywords for position matching, and further effectively improving the position matching precision. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 The flowchart of the position matching method for business administration specialty provided by the embodiment of the application.

[0065] Figure 2 The structural schematic diagram of the position matching device for business administration specialty provided by the embodiment of the application.

[0066] The drawings show that: 1, recruitment keyword acquisition module; 2, resume keyword acquisition module; 3, position score and frequency score acquisition module; 4, field score acquisition module; 5, matching score acquisition module; 6, position matching module. DETAILED DESCRIPTION

[0067] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0068] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0069] In a first aspect, as shown in the drawings, the present application provides a position matching method for business management majors, which comprises the following steps: Figure 1

[0070] S1, respectively extracting keywords from a plurality of recruitment information in sequence to obtain a plurality of recruitment keyword sets, and performing word segmentation, removing stop words and synonym expansion on the recruitment keyword sets, each recruitment keyword set corresponding to one recruitment information, and each recruitment keyword set comprising a plurality of recruitment keywords;

[0071] S2, extracting keywords from a pre-filled student resume based on the recruitment keyword sets, so that each recruitment information corresponds to one resume keyword set, and the resume keyword set comprises a plurality of resume keywords;

[0072] S3, generating a position score corresponding to each resume keyword based on the position of the resume keyword in the corresponding recruitment information, and generating a frequency score corresponding to each resume keyword based on the frequency of the resume keyword in the corresponding recruitment information;

[0073] S4, generating a domain score corresponding to each resume keyword based on the similarity between the resume keyword and the professional keywords in the pre-constructed business management major domain knowledge base;

[0074] S5, calculating a matching score corresponding to each resume keyword according to the position score, the frequency score and the domain score of the resume keyword;

[0075] S6, screening target recruitment information from all recruitment information based on the sum of all matching scores corresponding to the same recruitment information, to complete the position matching.​

[0076] The step S1 can extract keywords from the recruitment information by using an existing TF-IDF algorithm, the step S1 can perform word segmentation on the recruitment keyword set by using an existing jieba word segmentation tool, the step S1 can remove stop words from the recruitment keyword set by using a pre-collected general stop word table, and the step S1 can expand synonyms of the recruitment keyword set by using an existing synonym dictionary such as wordnet. The step S1 can reduce noise interference by performing word segmentation and removing stop words on the recruitment information, so as to improve the quality of the recruitment keywords. Since the step S2 needs to extract keywords from the student resume based on the recruitment keyword set, the step S1 can avoid the situation that some keywords matching the recruitment keywords are missed due to word difference by expanding synonyms of the recruitment keyword set.

[0077] The step S2 can extract keywords from the pre-filled student resume based on the recruitment keyword set by using an existing TF-IDF algorithm, so as to obtain a plurality of resume keyword sets. Each recruitment information corresponds to a resume keyword set, and each resume keyword set includes a plurality of resume keywords. Since the resume keywords are extracted from the student resume based on the recruitment keywords, each resume keyword corresponds to a recruitment keyword.

[0078] The embodiment can configure different weight coefficients for different positions of the recruitment information. The process of the step S3 of generating a position score corresponding to the resume keyword based on the position of the resume keyword in the corresponding recruitment information can be: determining the weight coefficient corresponding to the resume keyword based on the position of the resume keyword in the corresponding recruitment information; multiplying the preset position score and the weight coefficient corresponding to the resume keyword to obtain the position score corresponding to the resume keyword. The embodiment can set a plurality of frequency ranges and set a corresponding score for each frequency range. The frequency of the resume keyword in the corresponding recruitment information can reflect the number of times of appearance of the resume keyword in the corresponding recruitment information. The process of the step S3 of generating a frequency score corresponding to the resume keyword based on the frequency of the resume keyword in the corresponding recruitment information can be: taking the score corresponding to the frequency range in which the frequency of the resume keyword in the corresponding recruitment information as the frequency score.

[0079] The database of the business administration professional field in step S4 stores a plurality of professional keywords, which can be professional terms, skills or knowledge points in the business administration patent field. Step S4 can calculate the similarity between the resume keywords and the professional keywords in the pre-constructed business administration professional field knowledge base by using existing word vector models such as word2vec or fasttext. The embodiment can set a plurality of similarity ranges, and set a corresponding score for each similarity range. The process of step S4 of generating the field score corresponding to each resume keyword based on the similarity between the resume keyword and the professional keyword in the pre-constructed business administration professional field knowledge base can be: taking the score corresponding to the similarity range of the similarity between the resume keyword and the professional keyword in the pre-constructed business administration professional field knowledge base as the frequency score. Step S5 can calculate the matching score corresponding to the resume keyword by summing the position score, the frequency score and the field score corresponding to the resume keyword. Step S6 can first calculate the sum of all matching scores corresponding to each recruitment information, and then filter out the recruitment information with the largest sum of matching scores from all recruitment information as the target recruitment information. Since the recruitment information is associated with the position, step S6 can complete the position matching by filtering out the target recruitment information from all recruitment information based on the sum of all matching scores corresponding to the same recruitment information.

[0080] The working principle of this embodiment is that the position of the keyword in the recruitment information can reflect the degree of attention of the enterprise to the keyword, for example, the degree of attention of the enterprise to the keyword appearing in the title or the position requirement of the recruitment information is higher than that of the keyword appearing in the company profile of the recruitment information, therefore the high or low of the position score generated based on the position of the resume keyword in the corresponding recruitment information can reflect the matching degree of the resume keyword and the recruitment information, and since the frequency of the keyword appearing in the recruitment information can also reflect the degree of attention of the enterprise to the keyword, for example, the repeated appearance of “financial analysis” in the recruitment information indicates that the degree of attention of the enterprise to the keyword “financial analysis” is high, therefore the high or low of the frequency score generated based on the frequency of the resume keyword appearing in the corresponding recruitment information can also reflect the matching degree of the resume keyword and the recruitment information, and since the professional keyword is a professional term, skill or knowledge point in the field of business administration, the similarity between the resume keyword and the professional keyword in the pre-constructed knowledge base in the field of business administration can reflect the possibility of the student having the professional knowledge corresponding to the professional keyword, and the higher the similarity, the greater the possibility of the student having the corresponding professional knowledge, that is, the similarity can reflect the professional ability level of the student, and the professional ability of the student is also the focus of the enterprise, that is, the professional ability level of the student is positively correlated with the matching degree thereof and the recruitment information, therefore the high or low of the field score generated based on the similarity between the resume keyword and the professional keyword in the pre-constructed knowledge base in the field of business administration can also reflect the matching degree of the resume keyword and the recruitment information.

[0081] The position matching method for the major of business administration provided by the present application first generates the position score, the frequency score and the field score corresponding to the resume keyword, and then filters the target recruitment information from all the recruitment information based on the position score, the frequency score and the field score, that is, the present application recommends suitable positions from the three aspects of the position of the resume keyword in the recruitment information, the frequency of the resume keyword appearing in the recruitment information and the similarity between the resume keyword and the professional keyword, therefore the present application is equivalent to analyzing whether the recruitment information matches the student resume from multiple aspects, thereby effectively solving the problem that high-quality matching between the recruitment information and the resume cannot be achieved due to the simple appearance of the resume keyword for position matching, and further effectively improving the position matching precision.

[0082] In some preferred embodiments, step S3 comprises:

[0083] S31, selecting a resume keyword;

[0084] S32, obtaining the position type information according to the recruitment information corresponding to the selected resume keyword;

[0085] S33, generating a position score according to the position of the selected resume keyword in the corresponding recruitment information and the corresponding position type information thereof;

[0086] S34, generating a frequency score according to the occurrence frequency of the selected resume keyword in the corresponding recruitment information and the corresponding position type information thereof;

[0087] S35, analyzing whether there is a resume keyword without generating a position score and a frequency score, if yes, selecting any resume keyword without generating a position score and a frequency score, and returning to step S32, if not, executing step S4.

[0088] The embodiment can select the resume keywords in a traversal manner, i.e., selecting the resume keywords in sequence according to the order of the resume keywords in the resume keyword set. The position type information in step S32 is analyzed and extracted from the selected resume keywords corresponding to the recruitment information, for example, by analyzing the keywords in the title or position description of the recruitment information to determine the position type information, which can be marketing, financial management, or human resources, etc. The specific process of generating the position score in step S33 can be: first generating a preliminary position score based on the position of the selected resume keywords in the corresponding recruitment information, and then adjusting the preliminary position score based on the position type information (for example, the financial management position pays more attention to the appearance of the resume keywords in the skill requirement or project experience, and the marketing position may pay more attention to the appearance of the resume keywords in the position description or job requirement, so for the financial management position, the embodiment will increase the preliminary position score of the resume keywords appearing in the skill requirement or project experience in the recruitment information, and for the marketing position, the embodiment will increase the preliminary position score of the resume keywords appearing in the position description or job requirement in the recruitment information), to obtain the position score. The specific process of generating the position score in step S34 can be: first generating a preliminary frequency score based on the frequency of the selected resume keywords appearing in the corresponding recruitment information, and then adjusting the preliminary frequency score based on the position type information (for example, for the financial management position, since the financial management position pays more attention to the resume keywords related to financial management than to the resume keywords related to communication ability, so in the case of the same appearance frequency, the embodiment will adjust the preliminary frequency score of the resume keywords related to financial management to be greater than the preliminary frequency score of the resume keywords related to communication ability), to obtain the frequency score. Since different types of positions pay different attention to the appearance position and appearance frequency of the same resume keyword in the recruitment information, and the embodiment first obtains the position type information, and then generates the position score according to the position of the selected resume keywords in the corresponding recruitment information and the corresponding position type information, and generates the frequency score according to the appearance frequency of the selected resume keywords in the corresponding recruitment information and the corresponding position type information, so the embodiment is equivalent to considering the influence of the attention of the position type to the appearance position and the appearance frequency in the recruitment information when generating the position score and the frequency score, thereby effectively improving the accuracy of the position score and the frequency score, and further effectively improving the position matching precision.

[0089] In some preferred embodiments, step S33 comprises:

[0090] S331, obtaining a position correction coefficient according to the position of the selected resume keywords in the corresponding recruitment information, the corresponding position type information, and the first preset conversion relationship;

[0091] S332, calculate the position score according to the position correction coefficient and the preset preliminary position score.

[0092] The first preset conversion relationship of this embodiment is a mapping relationship about the position type, the position of the selected resume keyword in the corresponding recruitment information and the correction coefficient, which is constructed in advance. This embodiment can obtain the corresponding position correction coefficient from the first preset conversion relationship according to the position of the selected resume keyword in the corresponding recruitment information and the position type information. Step S332 can calculate the position score by multiplying the position correction coefficient and the preset preliminary position score. It should be understood that the specific process of step S34 for calculating the frequency score is similar to the specific process of this embodiment for calculating the position score, and therefore the present application will not be discussed in detail.

[0093] In some preferred embodiments, step S4 comprises:

[0094] S41, select a resume keyword;

[0095] S42, obtain the field score according to the maximum value of the similarity between the selected resume keyword and the professional keyword in the pre-constructed management professional field knowledge base and the second preset conversion relationship;

[0096] S43, analyze whether there is a resume keyword without a generated field score, if yes, select any resume keyword without a generated field score and return to step S42, and if no, execute step S5.

[0097] This embodiment can use the cosine similarity algorithm or other text similarity calculation methods to calculate the similarity between the selected resume keyword and the professional keyword. After obtaining a series of similarity values, this embodiment selects the maximum value from them. The maximum value represents the association degree between the resume keyword and the most relevant professional keyword in the management professional field knowledge base. The second preset conversion relationship of this embodiment can be a pre-constructed function relationship or a mapping relationship about the similarity and the field score. This embodiment can obtain the field score by inputting the maximum value of the similarity into the second preset conversion relationship. Since this embodiment obtains the field score according to the maximum value of the similarity between the selected resume keyword and the professional keyword in the pre-constructed management professional field knowledge base and the second preset conversion relationship, the field score of each resume keyword can reflect its association degree with the most relevant professional knowledge in the management professional field knowledge base. Therefore, this embodiment can effectively improve the accuracy of the field score, thereby further improving the position matching precision.

[0098] In some preferred embodiments, step S42 comprises:

[0099] S421, obtaining position type information according to the recruitment information corresponding to the selected resume keyword;

[0100] S422, obtaining a first correction coefficient corresponding to a different professional keyword according to the position type information and the third preset conversion relationship;

[0101] S423, calculating the similarity between the selected resume keyword and all professional keywords in the pre-constructed business management professional domain knowledge base respectively to obtain a preliminary similarity corresponding to each professional keyword;

[0102] S424, calculating the similarity between each professional keyword and the selected resume keyword based on the preliminary similarity corresponding to the professional keyword and the first correction coefficient, and obtaining a domain score according to the maximum value of the similarity and the second preset conversion relationship.

[0103] The third preset conversion relationship of this embodiment can be a pre-constructed mapping relationship about position type, professional keyword and correction coefficient. Step S424 can calculate the similarity between the professional keyword and the selected resume keyword by multiplying the preliminary similarity corresponding to the professional keyword and the first correction coefficient. Since the attention degree of different types of positions to the same professional keyword is different, this embodiment first obtains the first correction coefficient corresponding to the different professional keyword according to the position type information, obtains the preliminary similarity corresponding to each professional keyword, then calculates the similarity between each professional keyword and the selected resume keyword according to the preliminary similarity and the first correction coefficient, and finally obtains the domain score based on the maximum value of the similarity. That is, this embodiment takes into account the influence of the attention degree of the position type to the professional keyword when calculating the domain score, so this embodiment can further improve the accuracy of the domain score, thereby further improving the position matching precision.

[0104] In some preferred embodiments, the third preset conversion relationship is a pre-constructed mapping relationship about position type, professional keyword and correction coefficient, and the pre-construction process of the third preset conversion relationship includes the steps of:

[0105] dividing the historical recruitment data into a plurality of position type clusters based on the position description and the skill requirement in the historical recruitment data according to a clustering algorithm, each position type cluster corresponding to a position type;

[0106] calculating a correction coefficient set corresponding to each position type cluster according to the appearance frequency of different professional keywords in all historical recruitment data corresponding to the same position type cluster, each correction coefficient set including a plurality of groups of professional keywords and correction coefficients corresponding thereto, so that each position type corresponds to a correction coefficient set;

[0107] constructing the third preset conversion relationship according to the position type and the corresponding correction coefficient set.

[0108] The historical recruitment data of this embodiment can be the recruitment information published by the enterprise in previous years, and the historical recruitment data includes position description and skill requirements, and the clustering algorithm of this embodiment is preferably a K-means algorithm. Since the higher the frequency of the appearance of a professional keyword in all historical recruitment data corresponding to the same position type cluster, the more important the professional keyword is in the position type corresponding to the position type cluster, therefore, this embodiment can calculate the correction coefficient corresponding to different professional keywords in the same position type cluster based on the frequency of the appearance of different professional keywords in all historical recruitment data corresponding to the same position type cluster, specifically, this embodiment can obtain the correction coefficient corresponding to different professional keywords in the position type cluster by normalizing the frequency of the appearance of different professional keywords in the same position type cluster. After the calculation of the correction coefficient set is completed, each correction coefficient corresponds to a professional keyword and a position type, therefore, this embodiment can construct a third preset mapping relationship according to the position type and the corresponding correction coefficient set based on the existing mapping relationship construction method.

[0109] In some preferred embodiments, the student resume includes internship experience, and step S6 includes:

[0110] S61, respectively calculating the sum of all matching scores corresponding to each recruitment information to obtain a preliminary total score, each preliminary total score corresponding to a recruitment information;

[0111] S62, obtaining a second correction coefficient corresponding to each recruitment information according to the text similarity and a fourth preset conversion relationship, the text similarity being the similarity between the description text of the internship experience and the description text of the recruitment information;

[0112] S63, calculating a matching total score corresponding to each recruitment information according to the preliminary total score and the second correction coefficient corresponding to the recruitment information;

[0113] S64, screening the recruitment information with the highest matching total score from all the recruitment information as the target recruitment information to complete the position matching.

[0114] The fourth preset conversion relationship of this embodiment can be a mapping relationship about the text similarity and the correction coefficient constructed in advance. Step S63 can calculate the matching total score corresponding to the recruitment information by multiplying the preliminary total score corresponding to the recruitment information and the second correction coefficient. The text similarity of this embodiment is the similarity between the description text of the internship experience and the description text of the recruitment information. The higher the text similarity is, the stronger the relevance between the internship experience and the recruitment information is, and the higher the matching degree between the student and the recruitment information is. This embodiment is equivalent to performing position matching from two dimensions of the matching degree between the resume keywords and the recruitment information and the similarity between the internship experience and the recruitment information, and therefore can effectively improve the matching quality between the recruitment information and the student resume, thereby further improving the position matching precision. Specifically, taking the description of the internship experience of a student majoring in business administration as “interning in the marketing department of a well-known Internet company, being responsible for market research and data analysis, and participating in multiple market promotion activities” as an example, for the position of “marketing manager”, the preliminary total score calculated from the resume keywords of the student is 80, and for the position of “financial analyst”, the preliminary total score calculated from the resume keywords of the student is also 80. However, since the similarity between the description text of the internship experience and the description text of the recruitment information corresponding to the marketing manager is greater than the similarity between the description text of the internship experience and the description text of the recruitment information corresponding to the financial analyst, the second correction coefficient corresponding to the marketing manager is greater than the second correction coefficient corresponding to the financial analyst, and the matching total score corresponding to the marketing manager is higher than the matching total score corresponding to the financial analyst, and finally the target recruitment information obtained is the recruitment information corresponding to the marketing manager.

[0115] In some preferred embodiments, step S6 further comprises a step performed before step S63:

[0116] S65, obtaining the user click volume and the publishing duration of the recruitment information, and calculating the position heat corresponding to each recruitment information based on the time decay function according to the user click volume and the publishing duration;

[0117] S66, obtaining the third correction coefficient corresponding to each recruitment information according to the position heat and the fifth preset conversion relationship;

[0118] Step S63 comprises:

[0119] S631, calculating the matching total score corresponding to each recruitment information according to the preliminary total score corresponding to the recruitment information, the second correction coefficient and the third correction coefficient.

[0120] The user click volume of this embodiment can reflect the browsing volume of the user on the recruitment information and the popularity of the recruitment information, and the publication duration of this embodiment is the time difference between the time node of publishing the recruitment information and the current time node. The user click volume and the publication duration of this embodiment can be obtained by the background data interface of the recruitment website. This embodiment calculates the position heat corresponding to each recruitment information based on the time decay function according to the user click volume and the publication duration. In the case of the same publication duration, the greater the user click volume, the higher the position heat. In the case of the same user click volume, the greater the publication duration, the lower the position heat. The fifth preset conversion relationship of this embodiment can be a mapping relationship about the position heat and the correction coefficient which is constructed in advance. Since the position heat is positively correlated with the competition intensity of the position and the recruitment standard, the change of the competition intensity of the position and the recruitment standard will cause the change of the success rate of the students' job hunting. This embodiment is equivalent to considering the influence of the position heat when performing the position matching. Therefore, this embodiment can make the target recruitment information more consistent with the actual situation and market demand of the students, thereby effectively improving the precision and quality of the position matching.

[0121] In some preferred embodiments, step S6 further comprises a step performed before step S63:

[0122] S67, counting the number of positions required for different position types according to all the recruitment information, and calculating a fourth correction coefficient according to the number of positions required for the position type to which the recruitment information belongs and the number of all positions required.

[0123] Step S631 comprises:

[0124] S6311, calculating the matching total score corresponding to each recruitment information according to the preliminary total score corresponding to the recruitment information, the second correction coefficient, the third correction coefficient and the fourth correction coefficient.

[0125] The fourth correction coefficient of this embodiment can be the ratio of the number of positions required for the position type to which the recruitment information belongs and the number of all positions required. The fourth correction coefficient can reflect the demand proportion of the market for different position types. Since the fourth correction coefficient can reflect the demand proportion of the market for different position types when the matching total score is calculated in this embodiment, i.e., the calculation of the matching total score of this embodiment takes into account the demand amount of the market for different position types, this embodiment can make the position matching result more comprehensive, balanced and consistent with the market supply and demand relationship, thereby effectively improving the rationality of the position matching.

[0126] From the above, the position matching method for business administration majors provided by the application first generates position scores, frequency scores and field scores corresponding to resume keywords, and then filters target recruitment information from all recruitment information based on the position scores, frequency scores and field scores, that is, the application recommends suitable positions from the three aspects of the position of the resume keywords in the recruitment information, the frequency of the resume keywords in the recruitment information and the similarity between the resume keywords and the professional keywords, so the application is equivalent to analyzing whether the recruitment information matches the student resume from multiple angles, thereby effectively solving the problem that high-quality matching of recruitment information and resumes cannot be achieved due to the simple appearance of resume keywords for position matching, and further effectively improving the position matching precision.

[0127] In a second aspect, as shown in the Figure 2 application also provides a position matching device for business administration majors, which comprises:

[0128] The recruitment keyword acquisition module 1 is used for sequentially extracting keywords from a plurality of recruitment information respectively to obtain a plurality of recruitment keyword sets, and performing word segmentation, removing stop words and synonym expansion on the recruitment keyword sets. Each recruitment keyword set corresponds to one recruitment information, and each recruitment keyword set includes a plurality of recruitment keywords.

[0129] The resume keyword acquisition module 2 is used for extracting keywords from a pre-filled student resume based on the recruitment keyword set, so that each recruitment information corresponds to one resume keyword set, and the resume keyword set includes a plurality of resume keywords.

[0130] The position score and frequency score acquisition module 3 is used for generating a position score corresponding to each resume keyword based on the position of the resume keyword in the corresponding recruitment information, and generating a frequency score corresponding to each resume keyword based on the frequency of the resume keyword in the corresponding recruitment information.

[0131] The field score acquisition module 4 is used for generating a field score corresponding to each resume keyword based on the similarity between the resume keyword and the professional keyword in the pre-constructed business administration professional field knowledge base.

[0132] The matching score acquisition module 5 is used for calculating a matching score corresponding to each resume keyword according to the position score, the frequency score and the field score of the resume keyword.

[0133] The position matching module 6 is used for filtering target recruitment information from all recruitment information based on the sum of all matching scores corresponding to the same recruitment information, so as to complete the position matching.

[0134] The embodiment of the application provides a position matching device for a business administration major, which comprises a recruitment keyword acquisition module 1, a resume keyword acquisition module 2, a position score and frequency score acquisition module 3, a field score acquisition module 4, a matching score acquisition module 5 and a position matching module 6. The position matching device for the business administration major is used to execute the steps of the position matching method for the business administration major provided in the first aspect, and the principle of the position matching device for the business administration major is the same as that of the position matching method for the business administration major provided in the first aspect, which will not be described in detail here.

[0135] As can be seen, the position matching method and device for the business administration major are provided, the position score, the frequency score and the field score corresponding to the resume keyword are generated first, and then the target recruitment information is screened from all the recruitment information based on the position score, the frequency score and the field score, that is, the position matching device for the business administration major recommends suitable positions from the three aspects of the position of the resume keyword in the recruitment information, the appearance frequency of the resume keyword in the recruitment information and the similarity between the resume keyword and the professional keyword, so that the position matching device for the business administration major is equivalent to analyze whether the recruitment information matches the student resume from multiple aspects, thereby effectively solving the problem that high-quality matching between the recruitment information and the resume cannot be realized due to the simple appearance of the resume keyword for position matching, and further effectively improving the position matching precision.

[0136] In the embodiments provided in the application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above-described device embodiments are only schematic; for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation; for example, a plurality of units or components can be combined or integrated into another robot, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections between different entities can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

[0137] In addition, each functional module in each embodiment of the application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0138] In this document, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations.

[0139] The above merely provides an example of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A job matching method for business administration professionals, characterized by, The position matching method for business administration majors comprises the following steps: S1, extracting keywords from a plurality of recruitment information in sequence to obtain a plurality of recruitment keyword sets, and performing word segmentation, stop word removal and synonym expansion on the recruitment keyword sets, each of the recruitment keyword sets corresponding to a recruitment information, and each of the recruitment keyword sets comprising a plurality of recruitment keywords; S2, extracting keywords from a pre-filled student resume based on the recruitment keyword sets, so that each of the recruitment information corresponds to a resume keyword set, and the resume keyword set comprises a plurality of resume keywords; S3, generating a position score corresponding to each of the resume keywords based on the position of the resume keyword in the corresponding recruitment information, and generating a frequency score corresponding to each of the resume keywords based on the frequency of the resume keyword in the corresponding recruitment information; S4, generating a domain score corresponding to each of the resume keywords based on the similarity between the resume keyword and a professional keyword in a pre-constructed business administration major domain knowledge base; S5, calculating a matching score corresponding to each of the resume keywords according to the position score, the frequency score and the domain score of the resume keyword; S6, screening target recruitment information from all the recruitment information based on the sum of all the matching scores corresponding to the same recruitment information, to complete the position matching; Step S3 comprises: S31, selecting a resume keyword; S32, obtaining position type information according to the recruitment information corresponding to the selected resume keyword; S33, generating a position score according to the position of the selected resume keyword in the corresponding recruitment information and the position type information corresponding thereto; S34, generating a frequency score according to the frequency of the selected resume keyword in the corresponding recruitment information and the position type information corresponding thereto; S35, analyzing whether there is a resume keyword without a generated position score and a frequency score, if yes, selecting any resume keyword without a generated position score and a frequency score, and returning to step S32, if not, executing step S4.

2. The job matching method for business administration majors as claimed in claim 1, wherein, Step S33 comprises: S331, obtaining a position correction coefficient according to the position of the selected resume keyword in the corresponding recruitment information, the position type information corresponding thereto and a first preset conversion relationship; S332, calculating a position score according to the position correction coefficient and a preset preliminary position score.

3. The job matching method for business administration majors as claimed in claim 1, wherein, Step S4 comprises: S41, selecting a resume keyword; S42, obtaining a domain score according to the maximum value of the similarity between the selected resume keyword and a professional keyword in a pre-constructed business administration major domain knowledge base and a second preset conversion relationship; S43, analyzing whether there is a resume keyword without a generated domain score, if yes, selecting any resume keyword without a generated domain score, and returning to step S42, if not, executing step S5.

4. The job matching method for business administration majors according to claim 3, wherein Step S42 comprises: S421, obtaining position type information according to the recruitment information corresponding to the selected resume keyword; S422, obtaining a first correction coefficient corresponding to different professional keywords according to the position type information and a third preset conversion relationship; S423, respectively calculate the similarity of the selected resume keywords and all professional keywords in the pre-constructed management professional field knowledge base to obtain the preliminary similarity corresponding to each professional keyword; S424, calculate the similarity of each professional keyword and the selected resume keyword based on the preliminary similarity corresponding to the professional keyword and the first correction coefficient, and obtain the field score according to the maximum value of the similarity and the second preset conversion relationship.

5. The job matching method for business administration majors according to claim 4, wherein, The third preset conversion relationship is a pre-constructed mapping relationship about the position type, the professional keyword and the correction coefficient, and the pre-construction process of the third preset conversion relationship includes the steps of: dividing the historical recruitment data into a plurality of position type clusters based on clustering algorithm according to the position description and skill requirement in the historical recruitment data, each of the position type clusters corresponding to a position type; calculating a correction coefficient set corresponding to each position type cluster according to the frequency of occurrence of different professional keywords in all historical recruitment data corresponding to the same position type cluster, each of the correction coefficient set including a plurality of professional keywords and the correction coefficient corresponding thereto, so that each position type corresponds to a correction coefficient set; constructing the third preset conversion relationship according to the position type and the corresponding correction coefficient set.

6. The job matching method for business administration majors of claim 1, wherein, The student resume includes internship experience, and step S6 includes: S61, respectively calculate the sum of all the matching scores corresponding to each of the recruitment information to obtain a preliminary total score, each of the preliminary total score corresponding to one of the recruitment information; S62, obtain the second correction coefficient corresponding to each of the recruitment information according to the text similarity and the fourth preset conversion relationship, the text similarity being the similarity between the description text of the internship experience and the description text of the recruitment information; S63, calculate the matching total score corresponding to each of the recruitment information according to the preliminary total score and the second correction coefficient corresponding to the recruitment information; S64, select the recruitment information with the highest matching total score from all the recruitment information as the target recruitment information to complete the position matching.

7. The job matching method for business administration majors according to claim 6, wherein, Step S6 further includes the steps executed before step S63: S65, obtain the user click volume and the publishing duration of the recruitment information, and calculate the position heat corresponding to each of the recruitment information based on the time decay function according to the user click volume and the publishing duration; S66, obtain the third correction coefficient corresponding to each of the recruitment information according to the position heat and the fifth preset conversion relationship; Step S63 includes: S631, calculate the matching total score corresponding to each of the recruitment information according to the preliminary total score, the second correction coefficient and the third correction coefficient corresponding to the recruitment information.

8. The job matching method for business administration majors according to claim 7, wherein, Step S6 further includes the steps executed before step S63: S67, count the number of positions required for different position types according to all the recruitment information, and calculate the fourth correction coefficient according to the number of positions required corresponding to the position type to which the recruitment information belongs and all the number of positions required; Step S631 includes: S6311、According to the preliminary total score corresponding to the recruitment information, the second correction coefficient, the third correction coefficient and the fourth correction coefficient, the matching total score corresponding to each of the recruitment information is calculated.

9. A position matching device for a business administration major, characterized by, The position matching device for business administration specialty is used for executing the steps in the position matching method for business administration specialty, and comprises: A recruitment keyword acquisition module is configured to sequentially perform keyword extraction on a plurality of recruitment information respectively to obtain a plurality of recruitment keyword sets, and perform word segmentation, stop word removal and synonym expansion on the recruitment keyword sets. Each of the recruitment keyword sets corresponds to one recruitment information, and each of the recruitment keyword sets includes a plurality of recruitment keywords. A resume keyword acquisition module is configured to perform keyword extraction on a pre-filled student resume based on the recruitment keyword sets, so that each of the recruitment information corresponds to one resume keyword set, and the resume keyword set includes a plurality of resume keywords. A position score and frequency score acquisition module is configured to generate a position score corresponding to each of the resume keywords based on the position of the resume keyword in the corresponding recruitment information, and generate a frequency score corresponding to each of the resume keywords based on the frequency of the resume keyword in the corresponding recruitment information. A field score acquisition module is configured to generate a field score corresponding to each of the resume keywords based on the similarity between the resume keyword and a professional keyword in a pre-constructed business administration professional field knowledge base. A matching score acquisition module is configured to calculate a matching score corresponding to each of the resume keywords according to the position score, the frequency score and the field score of the resume keyword. A position matching module is configured to filter out target recruitment information from all the recruitment information based on the sum of all the matching scores corresponding to the same recruitment information, so as to complete the position matching.

Images