Digital talent evaluation system based on data mining

Abstract

The invention relates to the technical field of digital talent evaluation, in particular to a digital talent evaluation system based on data mining, which is characterized in that a demand tag is extracted from an enterprise demand, and a resume related to the demand tag is preliminarily screened out according to the demand tag; the matching degree evaluation of the establishment and the enterprise is calculated according to the number of labels matched with the enterprise demand in a single resume, and each resume is marked according to the matching degree evaluation, so that the resumes with high matching degree with the enterprise demand are screened out, the proportion of each resume is counted, and whether the data mining process is qualified or not is analyzed according to the statistical result. And when the number of the screened resumes is too large, increasing a judgment criterion for analyzing the matching degree of the resumes and the enterprise demands, and judging that the resumes are unqualified under the condition that the total number of the enterprise demand labels is too large and the matching degree evaluation of the labels of the single resumes and the enterprise demand labels is small. Therefore, the matching degree of the screened resumes is further improved, and the resume screening efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of digital talent evaluation, and in particular to a digital talent evaluation system based on data mining. Background Art

[0002] With the rapid development of economy and science and technology, the transformation and upgrading of economic structure, more professional and practical positions have emerged. The demand for applied talents in the economic society of various countries has gradually increased, and higher requirements have been placed on the quality of applied talents. Enterprises are facing greater development opportunities and urgently need innovative breakthroughs to achieve technological upgrades, which has put forward higher requirements on the knowledge, ability and quality of applied talents.

[0003] Digital talent evaluation helps companies to accurately identify and select digital talents. During the recruitment process, through a scientific evaluation system, companies can screen out talents who truly possess the required digital skills and potential. At the same time, it is also important for companies to rationally allocate digital talent resources. According to the evaluation results, companies can arrange digital talents to positions where they can best exert their talents. For example, for digital talents with both programming and design capabilities, they can be assigned to positions such as software interface development to optimize the use of talent resources. The existing technology provides learning videos for a variety of positions through the platform, conducts tests after the learning is completed, and collects those with high comprehensive scores. However, due to the large number of resumes in the early stage, manual screening of resumes is used, which has low work efficiency.

[0004] Chinese Patent Publication No.: CN118552165A discloses a digital talent construction and service platform, specifically a digital talent construction and service platform, including talent planning, talent recruitment, talent identification, talent training, talent evaluation, preferential admission and platform application, the talent planning includes job requirements, number of people required and number of people to be trained; the talent recruitment includes platform registration and tutor recommendation; the talent identification includes talent assessment interview, the platform provides learning videos for a variety of positions, and enterprises provide positions and job teaching online courses on the platform, and verify them during the online course learning process to avoid unqualified people, and make a two-way choice after the learning is completed, and then go to the company for a special interview, and take the ones with high comprehensive scores for inclusion, and then carry out learning of old-to-new and rotation job practice, and then the enterprise can select the best candidates, and those who are not admitted will be recommended for subsequent key recommendations to facilitate their employment, thereby facilitating students and enterprises to go two-way.

[0005] However, the prior art still has the following problems: Due to the large number of resumes in the early stage, manual screening of resumes was used, which resulted in low work efficiency. Summary of the invention

[0006] To this end, the present invention provides a digital talent evaluation system based on data mining, which is used to overcome the problem of low work efficiency in the prior art due to the large number of early resumes and the use of manual resume screening.

[0007] To achieve the above objectives, the present invention provides a digital talent evaluation system based on data mining. It includes: An input terminal, which is used to receive demand information; An extraction end, connected to the input end, for extracting a demand tag from the demand information; A standard construction end, which is connected to the extraction end and is used to determine a preset evaluation benchmark based on the extracted demand tags; A storage terminal, which is used to store some resume information; A retrieval end, which is connected to the extraction end and the storage end, and is used to retrieve the corresponding resume in the storage end based on the demand tag; An evaluation end, which is connected to the extraction end and the search end, is used to calculate a matching evaluation based on the tags in the searched resumes, and to screen the search results based on the matching evaluation, and mark each resume type, including: first level, second level, and third level; An analysis end, which is respectively connected to the input end, the extraction end, the standard construction end, the storage end, the retrieval end and the evaluation end, and is used to analyze whether the data mining is qualified based on the screening result of the evaluation end, to re-determine whether the data mining is qualified based on the number of secondary resumes, to analyze the reasons for the failure of data mining based on the screening ratio, and to determine the corresponding processing method based on the analyzed reasons for the failure of data mining; The output end is connected to the analysis end and is used to output the search results that are qualified for data mining.

[0008] Furthermore, the evaluation end is used to calculate the matching evaluation based on the tags in the retrieved resume, including: Used to determine the number of tags in a single resume that match the required tags, and get the first feature number, To determine the total number of demand tags extracted by the extraction end, and obtain the second feature quantity, It is used to calculate the ratio of the first feature quantity to the second feature quantity to obtain the matching evaluation. Used to screen search results based on matching evaluation, including: The evaluation end is used to determine whether the current resume is qualified based on the matching evaluation, and mark the resume as a first-level resume; The evaluation end is used to make a secondary determination on whether the current resume is qualified based on the total number of required tags based on the matching evaluation; The evaluation end is used to determine that the current resume is unqualified based on the matching evaluation, and screen out the current resume, marking the current resume as a third-level resume.

[0009] Furthermore, the evaluation end determines whether the current resume is qualified based on the total number of required tags, including: The evaluation end is used to determine whether the current resume is qualified based on the total number of required tags, and mark the resume as a secondary resume; The evaluation end is used to determine that the current resume is unqualified based on the total number of required tags, and screen out the current resume, marking the current resume as a third-level resume.

[0010] Furthermore, the analysis end analyzes whether the data mining is qualified based on the screening result of the evaluation end, including: To determine the number of qualified resumes for screening, The analysis end is used to determine that the data mining is unqualified based on the number of qualified resumes, and to modify the second preset matching evaluation standard threshold; The analysis end is used to determine whether the data mining is qualified based on the number of qualified resumes, and control the output end to output the search result; The analysis end is used to make a secondary determination on whether the data mining is qualified based on the number of secondary resumes based on the number of qualified resumes; The analysis end is used to determine whether the data mining is unqualified based on the number of qualified resumes, and to analyze the reasons for the data mining failure based on the screening ratio.

[0011] Furthermore, the analysis end is used to modify the second preset matching evaluation standard threshold based on the number of qualified resumes, wherein: The increase in the second preset matching evaluation standard threshold is positively correlated with the number of qualified resumes.

[0012] Furthermore, the analysis end is used to obtain high-frequency tags based on historical mining records to obtain new demand tags. To add the newly added demand tags to the search end to perform the search again, Among them, the number of newly added requirement tags is positively correlated with the total number of qualified resumes.

[0013] Furthermore, the analysis end is used to make a secondary determination on whether the data mining is qualified based on the number of secondary resumes, including: To determine the number of secondary resumes, get the first number, To determine the total number of qualified resumes, get the second number, Used to calculate the ratio of the first number to the second number, and get the proportion of secondary resumes, The analysis end is used to determine data mining failure based on the proportion of secondary resumes, and analyze the reasons for data mining failure based on the screening ratio; The analysis end determines that the data mining is qualified based on the proportion of secondary resumes, and controls the output end to output the search result.

[0014] Furthermore, the analysis end is used to analyze the data mining failure based on the screening ratio, including: To determine the number of third-level resumes and obtain the number of first feature screening, To determine the total number of resumes retrieved and obtain the number of second feature screening, It is used to calculate the ratio of the first characteristic screening quantity to the second characteristic screening quantity to obtain the screening ratio, The analysis end is used to determine that the reason for data mining failure is that the time domain segment to be searched is too short based on the screening ratio, and to correct the time interval of the time domain segment to be searched; The analysis end is used to determine the reason for data mining failure based on the screening ratio as a problem with the screening standard, and to recycle the screened resumes.

[0015] Furthermore, the analysis end is used to modify the time interval of the time domain end to be searched based on the screening ratio, wherein: The increase in the time interval is positively correlated with the screening ratio.

[0016] Furthermore, the analysis end is used to sort the third-level resumes based on the matching evaluation, select a predetermined number of third-level resumes to update them into first-level resumes, and add them to the screening results, wherein the number of selected third-level resumes is positively correlated with the screening ratio.

[0017] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention extracts demand labels from enterprise needs, preliminarily screens out resumes related to the demand labels based on the demand labels, calculates the matching evaluation with the enterprise based on the number of labels matching the enterprise needs in a single resume, and then marks each resume based on the matching evaluation, thereby screening out resumes with a high matching degree with the enterprise needs, counting the proportion of each type of resume, and analyzing whether the data mining process is qualified based on the statistical results. When the number of screened resumes is too large, the judgment benchmark for analyzing the matching degree between the resumes and the enterprise needs is increased, thereby further improving the matching degree of the screened resumes and improving data mining efficiency.

[0018] Furthermore, in the present invention, when initially determining whether a resume matches enterprise needs, it is considered that when enterprise needs are small, the number of matching resumes will be large. Therefore, a secondary determination is made on whether the resume matches enterprise needs based on the number of enterprise need tags. When the total number of enterprise need tags is large and the matching degree between the tag of a single resume and the tag of the enterprise need is small, the resume is determined to be unqualified, thereby improving the screening accuracy of the resume and thus improving the analysis accuracy of the resume.

[0019] Furthermore, in the present invention, when the number of screened resumes is too large, the standard for evaluating the eligibility of resumes, i.e., the second preset matching evaluation standard threshold, is increased based on the number of qualified resumes, thereby screening out resumes that are more matched with the company's needs, improving the screening accuracy of resumes, and further improving the subsequent screening efficiency.

[0020] Furthermore, in the present invention, when the number of screened resumes is large, considering that if the number of requirement tags is too small, it will affect the screening results, the screening process is further analyzed whether it is qualified according to the number of requirement tags, and when the number of requirement tags is small, new requirement tags are added to the current screening requirements according to the requirement tags entered in the historical data, thereby screening out resumes that are more matched with the company's needs, improving the screening accuracy of the resumes, and further improving the subsequent screening efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is the structural diagram of the digital talent evaluation system based on data mining; Figure 2 It is a flow chart for judging the resume screening; Figure 3 A flowchart for secondary determination of whether the current resume is qualified; Figure 4 The flowchart for secondary determination of whether data mining is qualified. DETAILED DESCRIPTION

[0022] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical data of the system of the present invention in the six months before this determination and the corresponding historical determination results. It can be understood by those skilled in the art that the determination method of the system of the present invention for a single parameter mentioned above can be to select the value with the highest proportion as the preset standard parameter according to the data distribution, use weighted summation to use the obtained value as the preset standard parameter, substitute each historical data into a specific formula and use the value obtained by the formula as the preset standard parameter or other selection methods, as long as the system of the present invention can clearly define different specific situations in the single determination process through the obtained values.

[0024] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0025] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0026] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] See also Figure 1 As shown, it is a structural block diagram of a digital talent evaluation system based on data mining.

[0028] The present invention provides a digital talent evaluation system based on data mining, comprising: An input terminal, which is used to receive demand information; An extraction end, connected to the input end, for extracting a demand tag from the demand information; A standard construction end, which is connected to the extraction end and is used to determine a preset evaluation benchmark based on the extracted demand tags; A storage terminal, which is used to store some resume information; A retrieval end, which is connected to the extraction end and the storage end, and is used to retrieve the corresponding resume in the storage end based on the demand tag; An evaluation end, which is connected to the extraction end and the search end, is used to calculate a matching evaluation based on the tags in the searched resumes, and to screen the search results based on the matching evaluation, and mark each resume type, including: first level, second level, and third level; An analysis end, which is respectively connected to the input end, the extraction end, the standard construction end, the storage end, the retrieval end and the evaluation end, and is used to analyze whether the data mining is qualified based on the screening result of the evaluation end, to re-determine whether the data mining is qualified based on the number of secondary resumes, to analyze the reasons for the failure of data mining based on the screening ratio, and to determine the corresponding processing method based on the analyzed reasons for the failure of data mining; The output end is connected to the analysis end and is used to output the search results that are qualified for data mining.

[0029] Specifically, in this embodiment, the tags in the resume include but are not limited to gender, age, education level, years of work experience, and length of work experience.

[0030] Specifically, the present invention extracts demand labels from enterprise needs, preliminarily screens out resumes related to the demand labels based on the demand labels, calculates the matching evaluation with the enterprise based on the number of labels matching the enterprise needs in a single resume, and then marks each resume based on the matching evaluation, thereby screening out resumes with a high matching degree with enterprise needs, and counts the proportion of each type of resume. According to the statistical results, it analyzes whether the data mining process is qualified. When the number of screened resumes is too large, the judgment benchmark for analyzing the matching degree of resumes with enterprise needs is increased, thereby further improving the matching degree of the screened resumes and improving data mining efficiency.

[0031] See also Figure 2 As shown, it is a flow chart for determining the resume screening.

[0032] Specifically, the evaluation end is used to calculate the matching evaluation based on the tags in the retrieved resume, including: Used to determine the number of tags in a single resume that match the required tags, and get the first feature number, To determine the total number of demand tags extracted by the extraction end, and obtain the second feature quantity, It is used to calculate the ratio of the first feature quantity to the second feature quantity to obtain the matching evaluation. Used to screen search results based on matching evaluation, including: If the matching evaluation is greater than or equal to a first preset matching evaluation standard threshold, the evaluation terminal determines that the current resume is qualified and marks the resume as a first-level resume; If the matching evaluation is less than the first preset matching evaluation standard threshold and greater than or equal to the second preset matching evaluation standard threshold, the evaluation end determines whether the current resume is qualified based on the total number of requirement tags; If the matching evaluation is less than the second preset matching evaluation standard threshold, the evaluation end determines that the current resume is unqualified, screens out the current resume, and marks the current resume as a level 3 resume.

[0033] Specifically, in this embodiment, the first preset matching evaluation standard threshold is selected in the interval [0.82, 0.98], and the second preset matching evaluation standard threshold is selected in the interval [0.68, 0.78].

[0034] In the present invention, when preliminarily determining whether a resume matches the enterprise's needs, it is taken into consideration that when the enterprise's needs are small, the number of matching resumes will be large. Therefore, a secondary determination is made on whether the resume matches the enterprise's needs based on the number of enterprise's need tags. When the total number of enterprise's need tags is large and the matching degree between the tag of a single resume and the tag of the enterprise's need is small, the resume is determined to be unqualified, thereby improving the screening accuracy of the resume and thus improving the accuracy of the analysis of the resume.

[0035] See also Figure 3 As shown, it is a flow chart for secondary determination of whether the current resume is qualified.

[0036] Specifically, the evaluation end determines whether the current resume is qualified based on the total number of required tags, including: If the total number of requirement tags is less than or equal to the preset standard threshold of the total number of requirement tags, the evaluation end determines that the current resume is qualified and marks the resume as a secondary resume; If the total number of requirement tags is greater than the preset standard threshold of the total number of requirement tags, the evaluation end determines that the current resume is unqualified, screens out the current resume, and marks the current resume as a level 3 resume.

[0037] Specifically, in this embodiment, the preset standard threshold for the total number of demand tags is obtained in advance, and several company recruitment information is obtained, the company demand tags are extracted, the number of demand tags of each company is counted respectively, and the mean number of demand tags is calculated. The preset standard threshold for the total number of demand tags is 0.9~1.1 times the mean number, the first preset standard threshold for the number is 0.75 times the mean number of demand tags, the second preset standard threshold for the number is 0.65 times the mean number of demand tags, and the third preset standard threshold for the number is 0.55 times the mean number of demand tags.

[0038] Specifically, the analysis end analyzes whether the data mining is qualified based on the screening results of the evaluation end, including: To determine the number of qualified resumes for screening, If the number of qualified resumes is greater than or equal to the first preset number standard threshold, the analysis end determines that the data mining is unqualified and modifies the second preset matching evaluation standard threshold; If the number of qualified resumes is less than the first preset number standard threshold and greater than or equal to the second preset number standard threshold, the analysis end determines that the data mining is qualified and controls the output end to output the search result; If the number of qualified resumes is less than the second preset number standard threshold and greater than or equal to the third preset number standard threshold, the analysis end determines whether the data mining is qualified based on the number of secondary resumes; If the number of qualified resumes is less than the third preset quantity standard threshold, the analysis end determines that the data mining is unqualified.

[0039] Specifically, when the present invention preliminarily determines whether a resume matches the enterprise's needs, it is considered that when the enterprise's needs are small, the number of matching resumes will be large. Therefore, a secondary judgment is made on whether the resume matches the enterprise's needs based on the number of enterprise's need tags. When the total number of enterprise's need tags is large and the matching degree between the tag of a single resume and the enterprise's need tag is small, the resume is judged as unqualified, thereby improving the screening accuracy of the resume and thus improving the analysis accuracy of the resume.

[0040] Specifically, the analysis end is used to modify the second preset matching evaluation standard threshold based on the number of qualified resumes, wherein: The increase in the second preset matching evaluation standard threshold is positively correlated with the number of qualified resumes.

[0041] In this embodiment, optionally, Compare the number of qualified resumes with the first preset number and the second preset number, If the number of qualified resumes is less than or equal to the first preset number, the second preset matching evaluation standard threshold is increased to 1.05 times the initial value of the second preset matching evaluation standard threshold; If the number of qualified resumes is greater than the first preset number and less than or equal to the second preset number, the second preset matching evaluation standard threshold is increased to 1.1 times the initial value of the second preset matching evaluation standard threshold; If the number of qualified resumes is greater than the second preset number, increasing the second preset matching evaluation standard threshold to 1.15 times the initial value of the second preset matching evaluation standard threshold; The first preset number is 1.05 times the first preset number standard threshold, and the second preset number is 1.12 times the first preset number standard threshold.

[0042] In the present invention, when the number of screened resumes is too large, the standard for evaluating the eligibility of resumes, i.e., the second preset matching evaluation standard threshold, is increased based on the number of qualified resumes, thereby screening out resumes that are more matched with the company's needs, improving the screening accuracy of resumes, and further improving the subsequent screening efficiency.

[0043] Specifically, the analysis end is used to obtain high-frequency tags based on historical mining records to obtain new demand tags. To add the newly added demand tags to the search end to perform the search again, Among them, the number of newly added requirement tags is positively correlated with the total number of qualified resumes.

[0044] In this embodiment, optionally, Compare the number of qualified resumes with the first preset number and the second preset number, If the number of qualified resumes is less than or equal to the first preset number, the first required tag number is increased, and the first required tag number is 0.1 times the initial required tag number; If the number of qualified resumes is greater than the first preset number and less than or equal to the second preset number, then the second required tag number is increased, and the second required tag number is 0.2 times the initial required tag number; If the number of qualified resumes is greater than the second preset number, the third requirement tag number is increased, and the third requirement tag number is 0.3 times the initial requirement tag number.

[0045] In the present invention, when the number of screened resumes is large, it is considered that if the number of requirement tags is too small, it will affect the screening results. Therefore, whether the screening process is qualified is further analyzed according to the number of requirement tags, and when the number of requirement tags is small, new requirement tags are added to the current screening requirements according to the requirement tags input in the historical data, so as to screen out resumes with a higher degree of match with the company's needs, improve the screening accuracy of resumes, and further improve the subsequent screening efficiency.

[0046] See also Figure 4 As shown, it is a flow chart for secondary determination of whether data mining is qualified.

[0047] Specifically, the analysis end is used to make a secondary determination on whether the data mining is qualified based on the number of secondary resumes, including: To determine the number of secondary resumes, get the first number, To determine the total number of qualified resumes, get the second number, Used to calculate the ratio of the first number to the second number, and get the proportion of secondary resumes, If the secondary resume ratio is greater than or equal to the preset secondary resume ratio standard threshold, the analysis end determines that the data mining is unqualified, and analyzes the reasons for the data mining failure based on the screening ratio; If the secondary resume ratio is less than the preset secondary resume ratio standard threshold, the analysis end determines that the data mining is qualified and controls the output end to output the search result.

[0048] Specifically, in this embodiment, the preset standard threshold value of the secondary resume ratio is selected between the interval [0.65, 0.75].

[0049] Specifically, the analysis end is used to analyze the reasons for data mining failure based on the screening ratio, including: To determine the number of third-level resumes and obtain the number of first feature screening, To determine the total number of resumes retrieved and obtain the number of second feature screening, It is used to calculate the ratio of the first characteristic screening quantity to the second characteristic screening quantity to obtain the screening ratio, If the screening ratio is less than or equal to the preset screening ratio standard threshold, the analysis end determines that the reason for data mining failure is that the time domain segment to be searched is too short, and corrects the time interval of the time domain segment to be searched; If the screening ratio is greater than the preset screening ratio standard threshold, the analysis end determines that the reason for the failure of data mining is that there is a problem with the screening standard, and reuses the screened resumes.

[0050] Specifically, in this embodiment, the preset screening ratio standard threshold is selected in the interval [0.2, 0.25].

[0051] Specifically, the analysis end is used to modify the time interval of the time domain end to be searched based on the screening ratio, wherein: The increase in the time interval is positively correlated with the screening ratio.

[0052] In this embodiment, optionally, The screening ratio is compared with the first preset screening ratio and the second preset screening ratio, If the screening ratio is less than or equal to the first preset screening ratio, then the first time interval is increased, and the first time interval is 0.1 times of the initial time interval; If the screening ratio is greater than the first preset screening ratio and less than or equal to the second preset screening ratio, then a second time interval is added, and the second time interval is 0.15 times of the initial time interval; If the screening ratio is greater than the second preset screening ratio, a third time interval is added, and the third time interval is 0.2 times of the initial time interval; Among them, the first preset screening ratio is selected between the interval [0.21, 0.22], and the second preset screening ratio is selected between the interval [0.23, 0.24].

[0053] Specifically, the analysis end is used to sort the third-level resumes based on the matching evaluation, select a predetermined number of third-level resumes to update them into first-level resumes, and add them to the screening results, wherein the number of selected third-level resumes is positively correlated with the screening ratio.

[0054] In this embodiment, optionally, The screening ratio is compared with the first preset screening ratio and the second preset screening ratio, If the screening ratio is less than or equal to the first preset screening ratio, the number of level 3 resumes selected is 0.2 times the total number of level 3 resumes; If the screening ratio is greater than the first preset screening ratio and less than or equal to the second preset screening ratio, the number of level 3 resumes selected is 0.3 times the total number of level 3 resumes; If the screening ratio is greater than the second preset screening ratio, the number of third-level resumes selected is 0.4 times the total number of third-level resumes.

[0055] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0056] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A digital talent evaluation system based on data mining, characterized in that: include: An input terminal, which is used to receive demand information; An extraction end, connected to the input end, for extracting a demand tag from the demand information; A standard construction end, which is connected to the extraction end and is used to determine a preset evaluation benchmark based on the extracted demand tags; A storage terminal, which is used to store some resume information; A retrieval end, which is connected to the extraction end and the storage end, and is used to retrieve the corresponding resume in the storage end based on the demand tag; An evaluation end, which is connected to the extraction end and the search end, is used to calculate a matching evaluation based on the tags in the searched resumes, and to screen the search results based on the matching evaluation, and mark each resume type, which includes: first-level, second-level, and third-level; An analysis end, which is respectively connected to the input end, the extraction end, the standard construction end, the storage end, the retrieval end and the evaluation end, and is used to analyze whether the data mining is qualified based on the screening result of the evaluation end, to re-determine whether the data mining is qualified based on the number of secondary resumes, to analyze the reasons for the failure of data mining based on the screening ratio, and to determine the corresponding processing method based on the analyzed reasons for the failure of data mining; The output end is connected to the analysis end and is used to output the search results that are qualified for data mining.

2. The digital talent evaluation system based on data mining according to claim 1 is characterized in that: The evaluation end is used to calculate the matching evaluation based on the tags in the retrieved resume, including: Used to determine the number of tags in a single resume that match the required tags, and get the first feature number, To determine the total number of demand tags extracted by the extraction end, and obtain the second feature quantity, It is used to calculate the ratio of the first feature quantity to the second feature quantity to obtain the matching evaluation. Used to screen search results based on matching evaluation, including: The evaluation end is used to determine whether the current resume is qualified based on the matching evaluation, and mark the resume as a first-level resume; The evaluation end is used to make a secondary determination on whether the current resume is qualified based on the total number of required tags based on the matching evaluation; The evaluation end is used to determine that the current resume is unqualified based on the matching evaluation, and screen out the current resume, marking the current resume as a third-level resume.

3. The digital talent evaluation system based on data mining according to claim 2 is characterized in that: The evaluation end determines whether the current resume is qualified based on the total number of required tags, including: The evaluation end is used to determine whether the current resume is qualified based on the total number of required tags, and mark the resume as a secondary resume; The evaluation end is used to determine that the current resume is unqualified based on the total number of required tags, and screen out the current resume, marking the current resume as a third-level resume.

4. The digital talent evaluation system based on data mining according to claim 3 is characterized in that: The analysis end analyzes whether the data mining is qualified based on the screening result of the evaluation end, including: To determine the number of qualified resumes for screening, The analysis end is used to determine that the data mining is unqualified based on the number of qualified resumes, and to modify the second preset matching evaluation standard threshold; The analysis end is used to determine whether the data mining is qualified based on the number of qualified resumes, and control the output end to output the search result; The analysis end is used to make a secondary determination on whether the data mining is qualified based on the number of secondary resumes based on the number of qualified resumes; The analysis end is used to determine whether the data mining is unqualified based on the number of qualified resumes, and to analyze the reasons for the data mining failure based on the screening ratio.

5. The digital talent evaluation system based on data mining according to claim 4 is characterized in that: The analysis end is used to modify the second preset matching evaluation standard threshold based on the number of qualified resumes, wherein: The increase in the second preset matching evaluation standard threshold is positively correlated with the number of qualified resumes.

6. The digital talent evaluation system based on data mining according to claim 5 is characterized in that: The analysis end is used to obtain high-frequency tags based on historical mining records to obtain new demand tags. To add the newly added demand tags to the search end to perform the search again, Among them, the number of newly added requirement tags is positively correlated with the total number of qualified resumes.

7. The digital talent evaluation system based on data mining according to claim 4 is characterized in that: The analysis end is used to make a secondary determination on whether the data mining is qualified based on the number of secondary resumes, including: To determine the number of secondary resumes, get the first number, To determine the total number of qualified resumes, get the second number, Used to calculate the ratio of the first number to the second number, and get the proportion of secondary resumes, The analysis end is used to determine data mining failure based on the proportion of secondary resumes, and analyze the reasons for data mining failure based on the screening ratio; The analysis end determines that the data mining is qualified based on the proportion of secondary resumes, and controls the output end to output the search result.

8. The digital talent evaluation system based on data mining according to claim 7 is characterized in that: The analysis end is used to analyze the reasons for data mining failure based on the screening ratio, including: To determine the number of third-level resumes and obtain the number of first feature screening, To determine the total number of resumes retrieved and obtain the number of second feature screening, It is used to calculate the ratio of the first characteristic screening quantity to the second characteristic screening quantity to obtain the screening ratio, The analysis end is used to determine that the reason for data mining failure is that the time domain segment to be searched is too short based on the screening ratio, and to correct the time interval of the time domain segment to be searched; The analysis end is used to determine the reason for data mining failure based on the screening ratio as a problem with the screening standard, and to recycle the screened resumes.

9. The digital talent evaluation system based on data mining according to claim 8 is characterized in that: The analysis end is used to modify the time interval of the time domain end to be searched based on the screening ratio, wherein: The increase in the time interval is positively correlated with the screening ratio.

10. The digital talent evaluation system based on data mining according to claim 9 is characterized in that: The analysis end is used to sort the third-level resumes based on the matching evaluation, select a predetermined number of third-level resumes to update them into first-level resumes, and add them into the screening results, wherein the number of selected third-level resumes is positively correlated with the screening ratio.

Images