Competency matching method and device based on multiple dimensions, equipment and medium

Abstract

The invention discloses a competency matching method and device based on multiple dimensions, equipment and a medium, and relates to the technical field of computers.The method comprises the steps that first introduction information of candidate resumes and second introduction information of target posts are obtained, and the introduction information comprises structured attribute information, semi-structured attribute information and unstructured attribute information; determining a first score of the candidate resume according to the first structured attribute information and the second structured attribute information; determining a second score of the candidate resume according to the first semi-structured attribute information and the second semi-structured attribute information; determining a third score of the candidate resume according to the first unstructured attribute information and the second unstructured attribute information; and determining the matching degree of the candidate resume and the target post according to the first score, the second score and the third score. According to the method, competency matching can be carried out from multiple dimensions, the resumes are screened more comprehensively, the probability of obtaining high-quality resumes is improved, and the probability of obtaining poor-quality resumes is reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a multi-dimensional competency matching method, device, equipment and medium. Background Art

[0002] Currently, the most effective way to obtain candidate resumes is conditional search. However, the inherent limitations of conditional search result in a large workload for screening high-quality resumes, which requires screening in a massive amount of resume search results. After obtaining the search structure, the candidate resumes can be screened again by means of competency matching.

[0003] Traditional competency matching methods often rely on single-dimensional analysis. Due to the incompleteness of competency matching, this limits the comprehensive analysis of candidate resumes, which in turn leads to the screening out of high-quality resumes and the acquisition of low-quality resumes. Summary of the invention

[0004] The present application provides a multi-dimensional competency matching method, device, equipment and medium, which can perform competency matching from multiple dimensions, so as to screen resumes more comprehensively, thereby increasing the probability of obtaining high-quality resumes and reducing the probability of obtaining low-quality resumes.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application provides a multi-dimensional competency matching method, including: The method comprises: Acquire first introduction information of the candidate resume and second introduction information of the target position, wherein the first introduction information includes first structured attribute information, first semi-structured attribute information and first unstructured attribute information, and the second introduction information includes second structured attribute information, second semi-structured attribute information and second unstructured attribute information; Determine a first score of the candidate resume based on the first structured attribute information and the second structured attribute information; determine a second score of the candidate resume based on the first semi-structured attribute information and the second semi-structured attribute information; determine a third score of the candidate resume based on the first unstructured attribute information and the second unstructured attribute information; Determine a matching score of the candidate resume according to the first score, the second score, and the third score; The matching degree between the candidate resume and the target position is determined according to the matching score of the candidate resume.

[0006] Optionally, the first structured attribute information includes a first information segment and a first field value of the first information segment, the second structured attribute information includes a second information segment and a second field value of the second information segment, and determining a first score of the candidate resume according to the first structured attribute information and the second structured attribute information includes: If there is a first field value of the first information segment that is inconsistent with a second field value of the second information segment corresponding to the first information segment, determining that the first score of the candidate resume is 0; If the first field value of each first information segment is consistent with the second field value of the corresponding second information segment, the first score of the candidate resume is determined to be the first numerical value.

[0007] Optionally, the first semi-structured attribute information includes a third information segment and a third field value of the third information segment, and the second semi-structured attribute information includes a fourth information segment and a fourth field value of the fourth information segment, and determining a second score of the candidate resume according to the first semi-structured attribute information and the second semi-structured attribute information includes: According to a preset rule, quantize the third field value of each third information segment to obtain a first quantization result corresponding to each third information segment, and quantize the fourth field value of each fourth information segment to obtain a second quantization result corresponding to each fourth information segment; If there is a first quantization result corresponding to the third information segment that is smaller than a second quantization result corresponding to the fourth information segment corresponding to the third information segment, determining that the second score of the candidate resume is 0; If the first quantization result corresponding to each third information segment is greater than or equal to the second quantization result corresponding to the respective fourth information segment, the second score of the candidate resume is determined to be a second numerical value.

[0008] Optionally, the first unstructured attribute information includes a fifth information segment and a fifth field value of the fifth information segment, the second unstructured attribute information includes a sixth information segment and a sixth field value of the sixth information segment, and determining a third score of the candidate resume according to the first unstructured attribute information and the second unstructured attribute information includes: Performing vectorization processing on the fifth field value of each fifth information segment to obtain a first vector corresponding to each fifth information segment, and performing vectorization processing on the sixth field value of each sixth information segment to obtain a second vector corresponding to each sixth information segment; Determine a first similarity between a fifth field value of the fifth information segment and a sixth field value of the sixth information segment, which correspond to each other, according to a first vector corresponding to the fifth information segment and a second vector corresponding to the sixth information segment, which correspond to each other; Perform keyword extraction on the fifth field value of the fifth information segment and the sixth field value corresponding to the sixth information segment to obtain a keyword set, and determine a first keyword vector of the fifth information segment and a second keyword vector of the sixth information segment according to hit conditions of the keywords in the fifth field value and the keywords in the sixth field value in the keyword set; determining a second similarity between a fifth field value of the fifth information segment and a sixth field value of the sixth information segment according to the first keyword vector of the fifth information segment, the second keyword vector of the sixth information segment, and a term similarity matrix; A third score of the candidate resume is determined according to a weighted sum of the first similarity and the second similarity.

[0009] Optionally, the method further includes: If the matching degree between the candidate resume and the target position is greater than or equal to a preset threshold, a pass mark is added to the candidate resume; If the matching degree between the candidate resume and the target position is less than the preset threshold, a failure mark is added to the candidate resume.

[0010] Optionally, the method further includes: Invitation information is pushed to the owners of the candidate resumes that have been marked as passed.

[0011] Optionally, determining the degree of matching between the candidate resume and the target position according to the matching score of the candidate resume includes: Determine the score range in which the matching score of the candidate resume falls; The matching degree corresponding to the score range is determined as the matching degree between the candidate resume and the target position.

[0012] In a second aspect, the present application provides a multi-dimensional competency matching device, comprising: An acquisition module, configured to acquire first introduction information of a candidate resume and second introduction information of a target position, wherein the first introduction information includes first structured attribute information, first semi-structured attribute information and first unstructured attribute information, and the second introduction information includes second structured attribute information, second semi-structured attribute information and second unstructured attribute information; A determination module is used to determine a first score of the candidate resume based on the first structured attribute information and the second structured attribute information; determine a second score of the candidate resume based on the first semi-structured attribute information and the second semi-structured attribute information; determine a third score of the candidate resume based on the first unstructured attribute information and the second unstructured attribute information; determine a matching score of the candidate resume based on the first score, the second score and the third score; and determine a degree of matching between the candidate resume and the target position based on the matching score of the candidate resume.

[0013] In a third aspect, the present application provides a computing device, including a memory and a processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method as described in any one of the first aspects.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method as described in any one of the first aspects.

[0015] It can be seen from the above technical solution that the present application has at least the following beneficial effects: The present application provides a competency matching method based on multiple dimensions, in which the first introduction information of the candidate resume and the second introduction information of the target position are first obtained, and then the first structured attribute information, the first semi-structured attribute information and the first unstructured attribute information in the first introduction information are respectively determined, and the second structured attribute information, the second semi-structured attribute information and the second unstructured attribute information in the second introduction information are determined. Different attribute information corresponds to different dimensions. Then, from the above three dimensions, comparisons are performed respectively, that is, based on the first structured attribute information and the second structured attribute information, the first score of the candidate resume is determined based on the first semi-structured attribute information and the second semi-structured attribute information, the second score of the candidate resume is determined based on the first unstructured attribute information and the second unstructured attribute information, and the third score of the candidate resume is determined based on the first unstructured attribute information and the second unstructured attribute information. Then, based on these three scores, the matching score of the candidate resume is determined, and finally, based on the matching score, the degree of matching between the candidate resume and the target position is determined. It can be seen that this method analyzes the matching degree between candidate resumes and target positions from multiple dimensions. Compared with single-dimensional analysis, the technical solution of this application can improve the comprehensiveness of the analysis, and thus can screen resumes more accurately, thereby increasing the probability of obtaining high-quality resumes and reducing the probability of obtaining low-quality resumes. Therefore, through this method, more high-quality resumes and fewer low-quality resumes can be obtained.

[0016] It should be understood that the description of technical features, technical solutions, beneficial effects or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it is understood that the description of features or beneficial effects means that specific technical features, technical solutions or beneficial effects are included in at least one embodiment. Therefore, the description of technical features, technical solutions or beneficial effects in this specification does not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions and beneficial effects described in the present embodiment can also be combined in any appropriate manner. Those skilled in the art will understand that the embodiment can be realized without one or more specific technical features, technical solutions or beneficial effects of a specific embodiment. In other embodiments, additional technical features and beneficial effects can also be identified in a specific embodiment that does not embody all embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a multi-dimensional competency matching method provided in an embodiment of the present application; Figure 2 A schematic diagram of a multi-dimensional competency matching device provided in an embodiment of the present application; Figure 3 A schematic diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The terms "first", "second", "third", etc. in the specification of this application and the accompanying drawings are used to distinguish different objects rather than to limit a specific order.

[0019] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0020] In order to make the description of the following embodiments clear and concise, a brief introduction to the related technology is first given: Competence is a concept widely used in many fields such as human resource management and organizational psychology. It is important for assessing employee capabilities, predicting job performance, and developing training and development plans. In this application, competence is characterized by the degree of match between resumes and positions.

[0021] In the traditional way, candidate resumes are screened through competency matching, but the traditional competency matching method often only relies on a single-dimensional analysis and lacks a comprehensive analysis of resumes and positions, which leads to the screening out of high-quality resumes and obtaining low-quality resumes.

[0022] In view of this, an embodiment of the present application provides a competency matching method based on multiple dimensions, which can be executed by a processing device, which can be a terminal or a server. Terminals include but are not limited to smart phones, tablet computers, laptops, personal digital assistants, or smart wearable devices. The server can be a cloud server, such as a central server in a central cloud computing cluster, or an edge server in an edge cloud computing cluster. Of course, the server can also be a server in a local data center. A local data center refers to a data center directly controlled by a user. Compared with single-dimensional analysis, the technical solution of the present application can improve the comprehensiveness of the analysis, and thus can more accurately screen resumes, thereby increasing the probability of obtaining high-quality resumes and reducing the probability of obtaining low-quality resumes. Therefore, through this method, more high-quality resumes and fewer low-quality resumes can be obtained.

[0023] In order to make the technical solution of the present application clearer and easier to understand, the technical solution of the present application is introduced below in conjunction with the accompanying drawings. Figure 1 As shown in FIG. 1 , the figure is a flow chart of a multi-dimensional competency matching method provided in an embodiment of the present application, the method comprising: S101. A processing device obtains first introduction information of a candidate resume and second introduction information of a target position.

[0024] The first introduction information refers to information used to introduce the candidate resume, and the second introduction information refers to information used to introduce the target position. After receiving the candidate resume, the processing device can obtain the first introduction information of the candidate resume, wherein the second introduction information of the target position can be pre-configured, and the processing device obtains the pre-configured second introduction information.

[0025] The first introduction information includes first structured attribute information, first semi-structured attribute information and first unstructured attribute information, and the second introduction information includes second structured attribute information, second semi-structured attribute information and second unstructured attribute information.

[0026] Structured attribute information refers to data with a clear definition and fixed format, which is usually stored in a relational database and strictly follows the data format and length specifications. For the application scenarios of the embodiments of the present application, the structured attribute information can be gender, city, major, etc. For example, gender can be male or female, city can be Tianjin or Beijing, and major can be electronic information engineering or communication function.

[0027] Semi-structured attribute information refers to data that is not strictly structured in organization, but has a certain degree of labeling and hierarchy. For the application scenarios of the embodiments of the present application, semi-structured attribute information may be education level, years of work experience, age, etc.

[0028] Unstructured attribute information refers to data without a clear structure or organization, which is usually not easy to store and process in the form of a table or database. For the application scenario of the embodiment of the present application, the unstructured attribute information can be project experience, personal skills, etc.

[0029] It should be noted that, for the application scenarios of the embodiments of the present application, it is possible to pre-configure which information segments belong to structured attribute information, which information segments belong to semi-structured attribute information, and which information segments belong to unstructured attribute information.

[0030] S102: The processing device determines a first score for the candidate resume based on the first structured attribute information and the second structured attribute information.

[0031] After the processing device obtains the first introduction information, since the processing device knows which information segments in the first introduction information belong to structured attribute information, the first structured attribute information can be extracted. Similarly, the processing device can also extract the second structured attribute information from the second introduction information, and then determine the first score of the candidate resume based on the first structured attribute information and the second structured attribute information.

[0032] In some embodiments, the first structured attribute information includes a first information segment and a first field value of the first information segment, and the second structured attribute information includes a second information segment and a second field value of the second information segment. If there is a first field value of the first information segment that is inconsistent with the second field value of the second information segment corresponding to the first information segment, the processing device determines that the first score of the candidate resume is 0; if the first field value of each first information segment is consistent with the second field value of the second information segment corresponding to each, the processing device determines that the first score of the candidate resume is a first numerical value, for example, the first numerical value is 1, and the first numerical value may also be other numerical values.

[0033] For example, the first information segment includes a gender information segment and a city information segment, the field value of the gender information segment is "male", and the field value of the city information segment is "Tianjin", and the second information segment includes a gender requirement information segment and a work city information segment, the field value of the gender requirement information segment is "male", and the field value of the work city information segment is "Chengdu". In this example, the gender information segment corresponds to the gender requirement information segment, and the city information segment corresponds to the work city information segment.

[0034] The processing device compares the field value of the gender information segment with the field value of the gender requirement information segment, and compares the field value of the city information segment with the field value of the work city information segment. After comparison, the field value of the city information segment is inconsistent with the field value of the work city information segment, and then obtains a first score of the candidate resume of 0. If, after comparison, the field value of the gender information segment is consistent with the field value of the gender requirement information segment, and the field value of the city information segment is also consistent with the field value of the work city information segment, the processing device obtains a first score of the candidate resume of 1.

[0035] It should be noted that the above examples are merely illustrative introductions.

[0036] In some examples, after the processing device determines that the first score of a candidate resume is 0, it will no longer execute subsequent matching steps and directly consider the candidate resume as not meeting the requirements, thereby reducing resource waste and improving matching efficiency.

[0037] S103: The processing device determines a second score for the candidate resume according to the first semi-structured attribute information and the second semi-structured attribute information.

[0038] After the processing device obtains the first introduction information, since the processing device knows which information segments in the first introduction information belong to semi-structured attribute information, the first semi-structured attribute information can be extracted. Similarly, the processing device can also extract the second semi-structured attribute information from the second introduction information, and then determine the second score of the candidate resume based on the first semi-structured attribute information and the second semi-structured attribute information.

[0039] In some embodiments, the first semi-structured attribute information includes a third information segment and a third field value of the third information segment, and the second semi-structured attribute information includes a fourth information segment and a fourth field value of the fourth information segment. Then, the processing device can quantize the third field value of the third information segment according to a preset rule to obtain a first quantization result corresponding to each third information segment, and quantize the fourth field value of each fourth information segment to obtain a second quantization result corresponding to each fourth information segment. If there is a first quantization result corresponding to a third information segment that is less than the second quantization result corresponding to the fourth information segment corresponding to the third information segment, the second score of the candidate resume is determined to be 0. If the first quantization result corresponding to each third information segment is greater than or equal to the second quantization result corresponding to the respective fourth information segments, the second score of the candidate resume is determined to be a second numerical value. Exemplarily, the second numerical value can be 1 or other numerical values.

[0040] For example, the third information segment includes an education information segment and a service information segment, the field value of the education information segment is "bachelor's degree", and the field value of the service information segment is "3", and the fourth information segment includes an education requirement information segment and a service requirement information segment, the field value of the education requirement information segment is "master's degree", and the service requirement information segment is "2". In this example, the education information segment corresponds to the education requirement information segment, and the service information segment corresponds to the service requirement information segment.

[0041] Different types of information segments have different corresponding quantization rules; for example, the preset rules may include a first quantization rule, a second quantization rule, etc. The age information segment and the age requirement information segment correspond to the first quantization rule, and the education information segment and the education requirement information segment correspond to the second quantization rule. As an example, the first quantization rule is shown in Table 1 below.

[0042] Table 1:

[0043] As an example, the second quantization rule is shown in Table 2 below.

[0044] Table 2:

[0045] According to Table 1-2 above, the processing device can obtain the quantized value corresponding to the field value of the service information segment as "3", the quantized value corresponding to the field value of the education information segment as "3", the quantized value corresponding to the field value of the service requirement information segment as "2", and the quantized value corresponding to the field value of the education requirement information segment as "4". After obtaining the quantized values, the processing device can compare them respectively to determine whether they meet the job requirements.

[0046] For example, the processing device compares the quantized value of the age information segment with the quantized value of the age requirement information segment, and compares the quantized value of the education information segment with the quantized value of the education requirement information segment. After comparison, the quantized value of the education information segment is less than the quantized value of the education requirement information segment, and the quantized value of the age information segment is greater than the quantized value of the age requirement information segment. At this time, the processing device determines that the second score of the candidate resume is 0. If the quantized value of the education information segment is greater than or equal to the quantized value of the education requirement information segment, and the quantized value of the age information segment is also greater than or equal to the quantized value of the age requirement information segment, the processing device determines that the second score of the candidate resume is the second value, for example, 1.

[0047] It should be noted that the above examples are merely illustrative introductions.

[0048] In some examples, after the processing device determines that the second score of the candidate resume is 0, it will no longer execute the subsequent matching steps and directly consider the candidate resume as not meeting the requirements, thereby reducing resource waste and improving matching efficiency.

[0049] S104: The processing device determines a third score of the candidate resume according to the first unstructured attribute information and the second unstructured attribute information.

[0050] After the processing device obtains the first introduction information, since the processing device knows which information segments in the first introduction information belong to unstructured attribute information, the first unstructured attribute information can be extracted. Similarly, the processing device can also extract the second unstructured attribute information from the second introduction information, and then determine the second score of the candidate resume based on the first unstructured attribute information and the second unstructured attribute information.

[0051] In some embodiments, the first unstructured attribute information includes a fifth information segment and a fifth field value of the fifth information segment, and the second unstructured attribute information includes a sixth information segment and a sixth field value of the sixth information segment. The processing device determines a first similarity between the fifth field value of the corresponding fifth information segment and the sixth field value of the sixth information segment based on the first vector corresponding to the fifth information segment and the second vector corresponding to the sixth information segment. The processing device performs keyword extraction on the fifth field value of the corresponding fifth information segment and the sixth field value of the sixth information segment to obtain a keyword set, and determines a first keyword vector of the fifth information segment and a second keyword vector of the sixth information segment based on the hit conditions of the keywords in the fifth field value and the keywords in the sixth field value in the keyword set. The processing device determines a second similarity between the fifth field value of the fifth information segment and the sixth field value of the sixth information segment based on the first keyword vector of the fifth information segment, the second keyword vector of the sixth information segment and the term similarity matrix. The processing device determines a third score of the candidate resume based on the weighted sum of the first similarity and the second similarity.

[0052] For example, the fifth information segment includes a project information segment, and the field value of the project information segment is "participate in the development and optimization of the big data platform, and apply machine learning models to data analysis." The sixth information segment includes a project requirement information segment, and the field value of the project requirement information segment is "need to have big data processing experience and be able to use machine learning for data modeling." In this example, the project information segment and the project requirement information segment correspond to each other.

[0053] The processing device may use an Embedding algorithm to perform vectorization processing on the field values ​​of the project information segment and the field values ​​of the project requirement information segment to obtain a first vector corresponding to the project information segment and a second vector corresponding to the project requirement information segment. Then, the processing device uses the following formula to calculate the first similarity between the field values ​​of the project information segment and the field values ​​of the project requirement information segment:

[0054] in, represents the first vector, represents the second vector, Indicates the first similarity.

[0055] The processing device may perform keyword extraction on the field values ​​in the project information segment and the field values ​​in the project requirement information segment to obtain a keyword set, for example, the keyword set G = ["big data", "platform development", "optimization", "machine learning", "data analysis", "big data processing", "data modeling"], and then determine a first keyword vector according to the hit situation of the field value in the project information segment in the keyword set. The first keyword vector , according to the hit situation of the field value in the project requirement information segment in the above keyword set, determine the second keyword vector .

[0056] The processing device constructs a term similarity matrix. For example, "big data" and "big data processing" are related words with a similarity of 0.9, "data analysis" and "data modeling" are related words with a similarity of 0.7, and so on. The term similarity matrix shown in Table 3 can be obtained.

[0057] Table 3:

[0058] The processing device may determine the second similarity between the field value of the project information segment and the field value of the project requirement information segment based on the first keyword vector, the second keyword vector and the term similarity matrix: the processing device calculates the second similarity between the field value of the project information segment and the field value of the project requirement information segment using the following formula:

[0059] in, represents the second similarity between the field value of the project information segment and the field value of the project requirement information segment, represents the i-th element in the first keyword vector, represents the jth element in the first keyword vector, represents the i-th element in the second keyword vector, represents the jth element in the second keyword vector, where n represents the number of elements in the first keyword vector, and the number of elements in the first keyword vector is the same as the number of elements in the second keyword vector. Represents the element in the i-th row and j-th column of the term matrix.

[0060] Substitute the values ​​in the above example into the above formula, where, , , ,and then .

[0061] After obtaining the first similarity and the second similarity, the processing device may perform a weighted sum of the first similarity and the second similarity, and determine a third score of the candidate resume based on the result of the weighted sum. In some examples, the weight of the first similarity is 0.7, and the weight of the second similarity is 0.3.

[0062] It should be noted that the above keyword set is a one-dimensional keyword set. In other examples, the keyword set may be multi-dimensional, and the corresponding first keyword vector and second keyword vector are also multi-dimensional, thereby improving the accuracy of the determined second similarity.

[0063] It should be noted that the execution order of the above S102-S104 is not limited in the embodiment of the present application, and S102-S104 can be executed in sequence or simultaneously. For example, S102 is executed first, then S104, and finally S103.

[0064] S105: The processing device determines a matching score of the candidate resume according to the first score, the second score, and the third score.

[0065] In some embodiments, after obtaining the first score, the second score, and the third score, the processing device may use the result of multiplying the first score, the second score, and the third score as the matching score of the candidate resume.

[0066] S106: The processing device determines the matching degree between the candidate resume and the target position according to the matching score of the candidate resume.

[0067] In some examples, the matching degree is ranked from low to high as match failure, low matching degree, medium matching degree, and high matching degree. The processing device can determine the score interval in which the matching score of the candidate resume is located; and determine the matching degree corresponding to the score interval as the matching degree between the candidate resume and the target position.

[0068] For example, if the match score is [0, 0.4), it means the match fails; if the match score is [0.4, 0.6), it means the match is low; if the match score is [0.6, 0.8), it means the match is medium; if the match score is [0.8, 1], it means the match is high. If the processing device determines that the match score of the candidate resume is 0.63, it means that the match between the candidate resume and the target position is medium.

[0069] In some embodiments, if the degree of match between the candidate resume and the target position is greater than or equal to a preset degree threshold, a pass mark is added to the candidate resume; if the degree of match between the candidate resume and the target position is less than the preset degree threshold, a fail mark is added to the candidate resume. The preset degree threshold may be the above-mentioned medium match. If the degree of match between the candidate resume and the target position is medium, the processing device adds a pass mark to the candidate resume; if the degree of match between the candidate resume and the target position is low, the processing device adds a fail mark to the candidate resume.

[0070] In some embodiments, the processing device may also push invitation information to the owners of the candidate resumes that have been marked as passed, thereby inviting these users to interviews, etc.

[0071] The present application provides a competency matching method based on multiple dimensions, in which the first introduction information of the candidate resume and the second introduction information of the target position are first obtained, and then the first structured attribute information, the first semi-structured attribute information and the first unstructured attribute information in the first introduction information are respectively determined, and the second structured attribute information, the second semi-structured attribute information and the second unstructured attribute information in the second introduction information are determined. Different attribute information corresponds to different dimensions. Then, from the above three dimensions, comparisons are performed respectively, that is, based on the first structured attribute information and the second structured attribute information, the first score of the candidate resume is determined based on the first semi-structured attribute information and the second semi-structured attribute information, the second score of the candidate resume is determined based on the first unstructured attribute information and the second unstructured attribute information, and the third score of the candidate resume is determined based on the first unstructured attribute information and the second unstructured attribute information. Then, based on these three scores, the matching score of the candidate resume is determined, and finally, based on the matching score, the degree of matching between the candidate resume and the target position is determined. It can be seen that this method analyzes the matching degree between candidate resumes and target positions from multiple dimensions. Compared with single-dimensional analysis, the technical solution of this application can improve the comprehensiveness of the analysis, and thus can screen resumes more accurately, thereby increasing the probability of obtaining high-quality resumes and reducing the probability of obtaining low-quality resumes. Therefore, through this method, more high-quality resumes and fewer low-quality resumes can be obtained.

[0072] Combination of the above Figure 1The multi-dimensional competency matching method provided in the embodiment of the present application is introduced in detail. The apparatus and device provided in the embodiment of the present application will be introduced in conjunction with the accompanying drawings.

[0073] like Figure 2 As shown in FIG. 1 , the figure is a schematic diagram of a multi-dimensional competency matching device provided in an embodiment of the present application, the device comprising: The acquisition module 201 is used to acquire first introduction information of the candidate resume and second introduction information of the target position, wherein the first introduction information includes first structured attribute information, first semi-structured attribute information and first unstructured attribute information, and the second introduction information includes second structured attribute information, second semi-structured attribute information and second unstructured attribute information; Determination module 202 is used to determine a first score of the candidate resume based on the first structured attribute information and the second structured attribute information; determine a second score of the candidate resume based on the first semi-structured attribute information and the second semi-structured attribute information; determine a third score of the candidate resume based on the first unstructured attribute information and the second unstructured attribute information; determine a matching score of the candidate resume based on the first score, the second score and the third score; and determine a degree of matching between the candidate resume and the target position based on the matching score of the candidate resume.

[0074] Optionally, the first structured attribute information includes a first information segment and a first field value of the first information segment, and the second structured attribute information includes a second information segment and a second field value of the second information segment. The determination module 202 is specifically used to determine that the first score of the candidate resume is 0 if the first field value of the first information segment is inconsistent with the second field value of the second information segment corresponding to the first information segment; if the first field value of each first information segment is consistent with the second field value of the corresponding second information segment, then determine that the first score of the candidate resume is the first numerical value.

[0075] Optionally, the first semi-structured attribute information includes a third information segment and a third field value of the third information segment, and the second semi-structured attribute information includes a fourth information segment and a fourth field value of the fourth information segment. The determination module 202 is specifically used to quantize the third field value of each third information segment according to a preset rule to obtain a first quantization result corresponding to each third information segment, and to quantize the fourth field value of each fourth information segment to obtain a second quantization result corresponding to each fourth information segment; if there is a first quantization result corresponding to a third information segment that is less than the second quantization result corresponding to the fourth information segment corresponding to the third information segment, then the second score of the candidate resume is determined to be 0; if the first quantization result corresponding to each third information segment is greater than or equal to the second quantization result corresponding to the respective fourth information segments, then the second score of the candidate resume is determined to be a second numerical value.

[0076] Optionally, the first unstructured attribute information includes a fifth information segment and a fifth field value of the fifth information segment, and the second unstructured attribute information includes a sixth information segment and a sixth field value of the sixth information segment, and the determination module 202 is specifically configured to perform vectorization processing on the fifth field value of each fifth information segment to obtain a first vector corresponding to each fifth information segment, and perform vectorization processing on the sixth field value of each sixth information segment to obtain a second vector corresponding to each sixth information segment; Determine a first similarity between the fifth field value of the fifth information segment and the sixth field value of the sixth information segment according to the first vector corresponding to the fifth information segment and the second vector corresponding to the sixth information segment; perform keyword extraction on the fifth field value of the fifth information segment and the sixth field value corresponding to the sixth information segment to obtain a keyword set, and determine a first keyword vector of the fifth information segment and a second keyword vector of the sixth information segment according to the hit conditions of the keywords in the fifth field value and the keywords in the sixth field value in the keyword set; determine a second similarity between the fifth field value of the fifth information segment and the sixth field value of the sixth information segment according to the first keyword vector of the fifth information segment, the second keyword vector of the sixth information segment and the term similarity matrix; determine a third score of the candidate resume according to a weighted sum of the first similarity and the second similarity.

[0077] Optionally, the device also includes a marking module, which is used to add a pass mark to the candidate resume if the degree of match between the candidate resume and the target position is greater than or equal to a preset degree threshold; if the degree of match between the candidate resume and the target position is less than the preset degree threshold, then add a fail mark to the candidate resume.

[0078] Optionally, the device further comprises an invitation module, the invitation module being used to push invitation information to owners of candidate resumes to which the pass mark is added.

[0079] Optionally, the determination module 202 is specifically used to determine the score interval within which the matching score of the candidate resume lies; and determine the matching degree corresponding to the score interval as the matching degree between the candidate resume and the target position.

[0080] The multi-dimensional competency matching device according to the embodiment of the present application may correspond to the method described in the embodiment of the present application, and the above-mentioned other operations and / or functions of each module / unit of the multi-dimensional competency matching device are respectively to realize Figure 1 For the sake of brevity, the corresponding processes of each method in the illustrated embodiment are not described in detail here.

[0081] The present application also provides a computing device. Figure 3 As shown, this figure is a schematic diagram of a computing device provided in an embodiment of the present application, and the computing device 300 includes a bus 301, a processor 302, a communication interface 303 and a memory 304. The processor 302, the memory 304 and the communication interface 303 communicate with each other through the bus 301.

[0082] The bus 301 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0083] The processor 302 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0084] The communication interface 303 is used for communicating with the outside.

[0085] The memory 304 may include a volatile memory, such as a random access memory (RAM). The memory 304 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0086] The memory 304 stores executable codes, and the processor 302 executes the executable codes to perform the aforementioned multi-dimensional competency matching method.

[0087] Specifically, in implementing Figure 2 In the case of the embodiment shown, and Figure 2 When each module or unit of the multi-dimensional competency matching device described in the embodiment is implemented by software, the execution Figure 2 The software or program code required for the functions of each module / unit in the system may be partially or completely stored in the memory 304. The processor 302 executes the program code corresponding to each unit stored in the memory 304 to execute the aforementioned multi-dimensional competency matching method.

[0088] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state hard disk). The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned multi-dimensional competency matching method.

[0089] The embodiment of the present application further provides a computer program product, which includes one or more computer instructions. When the computer instructions are loaded and executed on a computing device, the process or function described in the embodiment of the present application is generated in whole or in part.

[0090] The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer or data center to another website, computer or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means.

[0091] When the computer program product is executed by a computer, the computer executes any of the aforementioned multi-dimensional competency matching methods. The computer program product may be a software installation package, and when any of the aforementioned multi-dimensional competency matching methods is needed, the computer program product may be downloaded and executed on a computer.

[0092] The descriptions of the processes or structures corresponding to the above-mentioned figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0093] The above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application.

Claims

1. A multi-dimensional competency matching method, characterized in that: The method comprises: Acquire first introduction information of the candidate resume and second introduction information of the target position, wherein the first introduction information includes first structured attribute information, first semi-structured attribute information and first unstructured attribute information, and the second introduction information includes second structured attribute information, second semi-structured attribute information and second unstructured attribute information; Determine a first score of the candidate resume based on the first structured attribute information and the second structured attribute information; determine a second score of the candidate resume based on the first semi-structured attribute information and the second semi-structured attribute information; determine a third score of the candidate resume based on the first unstructured attribute information and the second unstructured attribute information; Determine a matching score of the candidate resume according to the first score, the second score, and the third score; The matching degree between the candidate resume and the target position is determined according to the matching score of the candidate resume.

2. The method according to claim 1, characterized in that The first structured attribute information includes a first information segment and a first field value of the first information segment, the second structured attribute information includes a second information segment and a second field value of the second information segment, and determining a first score of the candidate resume according to the first structured attribute information and the second structured attribute information includes: If there is a first field value of the first information segment that is inconsistent with a second field value of the second information segment corresponding to the first information segment, determining that the first score of the candidate resume is 0; If the first field value of each first information segment is consistent with the second field value of the corresponding second information segment, the first score of the candidate resume is determined to be the first numerical value.

3. The method according to claim 1, characterized in that The first semi-structured attribute information includes a third information segment and a third field value of the third information segment, the second semi-structured attribute information includes a fourth information segment and a fourth field value of the fourth information segment, and determining a second score of the candidate resume according to the first semi-structured attribute information and the second semi-structured attribute information includes: According to a preset rule, quantize the third field value of each third information segment to obtain a first quantization result corresponding to each third information segment, and quantize the fourth field value of each fourth information segment to obtain a second quantization result corresponding to each fourth information segment; If there is a first quantization result corresponding to the third information segment that is smaller than a second quantization result corresponding to the fourth information segment corresponding to the third information segment, determining that the second score of the candidate resume is 0; If the first quantization result corresponding to each third information segment is greater than or equal to the second quantization result corresponding to the respective fourth information segment, the second score of the candidate resume is determined to be a second numerical value.

4. The method according to claim 1, characterized in that The first unstructured attribute information includes a fifth information segment and a fifth field value of the fifth information segment, the second unstructured attribute information includes a sixth information segment and a sixth field value of the sixth information segment, and determining a third score of the candidate resume according to the first unstructured attribute information and the second unstructured attribute information includes: Performing vectorization processing on the fifth field value of each fifth information segment to obtain a first vector corresponding to each fifth information segment, and performing vectorization processing on the sixth field value of each sixth information segment to obtain a second vector corresponding to each sixth information segment; Determine a first similarity between a fifth field value of the fifth information segment and a sixth field value of the sixth information segment, which correspond to each other, according to a first vector corresponding to the fifth information segment and a second vector corresponding to the sixth information segment, which correspond to each other; Perform keyword extraction on the fifth field value of the fifth information segment and the sixth field value corresponding to the sixth information segment to obtain a keyword set, and determine a first keyword vector of the fifth information segment and a second keyword vector of the sixth information segment according to hit conditions of the keywords in the fifth field value and the keywords in the sixth field value in the keyword set; determining a second similarity between a fifth field value of the fifth information segment and a sixth field value of the sixth information segment according to the first keyword vector of the fifth information segment, the second keyword vector of the sixth information segment, and a term similarity matrix; A third score of the candidate resume is determined according to a weighted sum of the first similarity and the second similarity.

5. The method according to claim 1, characterized in that The method further comprises: If the matching degree between the candidate resume and the target position is greater than or equal to a preset threshold, a pass mark is added to the candidate resume; If the matching degree between the candidate resume and the target position is less than the preset threshold, a failure mark is added to the candidate resume.

6. The method according to claim 5, characterized in that The method further comprises: Invitation information is pushed to the owners of the candidate resumes that have been marked as passed.

7. The method according to claim 1, characterized in that Determining the degree of matching between the candidate resume and the target position according to the matching score of the candidate resume includes: Determine the score range in which the matching score of the candidate resume falls; The matching degree corresponding to the score range is determined as the matching degree between the candidate resume and the target position.

8. A multi-dimensional competency matching device, characterized in that: The device comprises: An acquisition module, configured to acquire first introduction information of a candidate resume and second introduction information of a target position, wherein the first introduction information includes first structured attribute information, first semi-structured attribute information and first unstructured attribute information, and the second introduction information includes second structured attribute information, second semi-structured attribute information and second unstructured attribute information; A determination module is used to determine a first score of the candidate resume based on the first structured attribute information and the second structured attribute information; determine a second score of the candidate resume based on the first semi-structured attribute information and the second semi-structured attribute information; determine a third score of the candidate resume based on the first unstructured attribute information and the second unstructured attribute information; determine a matching score of the candidate resume based on the first score, the second score and the third score; and determine a degree of matching between the candidate resume and the target position based on the matching score of the candidate resume.

9. A computing device, characterized in that including memory and processor; One or more computer programs are stored in the memory, and the one or more computer programs include instructions; when the instructions are executed by the processor, the computing device executes the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 7.

Images