An expert database management system and method based on talent big data analysis

Abstract

The present invention discloses an expert database management system and method based on talent big data analysis, the system comprising a data acquisition unit, a data sorting unit, a data storage unit, and a query retrieval unit; the data acquisition unit is used to receive talent big data information, and screen the talent data information, screen out the talent data information whose relevance meets preset conditions, and send it to the data sorting unit; the data sorting unit sorts all the received talent data information, obtains the sorted standardized expert database data, and sends it to the data storage unit; the query retrieval unit is used to provide retrieval to users, and obtain retrieval results from the standardized expert database data stored in the data storage unit.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and specifically relates to an expert database management system and method based on talent big data analysis. Background Art

[0002] With the continuous advancement of data storage technology, the storage media cost of massive big data is lower and the storage performance is higher. The existing human resources database system requires a lot of manual configuration, and it is difficult to efficiently cope with the storage and retrieval of massive human resources information big data.

[0003] How to provide more efficient and accurate technical means to collect and screen human resources data, and analyze and mine the data based on the advantages of big data has become an urgent problem to be solved in this field. Summary of the invention

[0004] The present invention provides an expert database management system and method based on talent big data analysis, which specifically adopts the following technical solutions:

[0005] A talent information processing system based on big data analysis, the system comprising a data collection unit, a data sorting unit, a data storage unit, and a query retrieval unit;

[0006] The data collection unit is used to receive talent big data information, and screen the talent data information, screen out talent data information whose relevance meets preset conditions, and send it to the data sorting unit;

[0007] The data sorting unit sorts all the received talent data information, obtains the sorted standardized expert database data, and sends it to the data storage unit;

[0008] The query retrieval unit is used to provide retrieval for the user and obtain retrieval results from the standardized expert database data stored in the data storage unit.

[0009] The present invention also relates to a talent information processing method based on big data analysis, which is applied to the talent information processing system based on big data analysis described above, and comprises the following steps:

[0010] S1. The data collection unit receives talent big data information, and screens the talent data information, screens out talent data information whose relevance meets preset conditions, and sends it to the data sorting unit;

[0011] S2. The data sorting unit sorts all the talent data information received, obtains standardized expert database data after data sorting, and sends it to the data storage unit;

[0012] S3. The query retrieval unit is used to provide retrieval for the user and obtain retrieval results from the standardized expert database data stored in the data storage unit.

[0013] The present invention also relates to a computer program product, which includes a computer program. The computer program is executed by a processor to execute the above-mentioned talent information processing method based on big data analysis.

[0014] The present invention also relates to a computer-readable storage medium, which is used to store a computer program. The computer program is executed by a processor to execute the above-mentioned talent information processing method based on big data analysis.

[0015] The technical solution of the present invention can collect and screen human resource data more efficiently and accurately based on the advantages of big data, and provide users with accurate target query information. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a block diagram of an expert database management system based on talent big data analysis of the present invention DETAILED DESCRIPTION

[0017] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the scope of protection of the present invention. It should be pointed out that the following detailed description is exemplary and is intended to provide further explanation of the present invention.

[0018] Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those generally understood by those of ordinary skill in the art to which the present invention belongs. It should be noted that the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0019] As attached Figure 1 As shown, Embodiment 1 of the present invention relates to an expert database management system based on talent big data analysis, and the system includes a data collection unit, a data sorting unit, a data storage unit, and a query retrieval unit.

[0020] The data collection unit is used to receive talent big data information, and screen the talent data information, screen out the talent data information whose relevance meets the preset conditions, and send it to the data sorting unit.

[0021] Specifically, the data collection unit receives the talent big data information, performs semantic word segmentation and vectorization processing on each piece of talent data information in the talent big data information, and obtains the i-th talent data information d among the m pieces of talent data information. i The corpus vector matrix W i ,

[0022] W i =[w i1 , w i2 ,…w in ]

[0023] Among them, w in is the i-th talent data information d i The vector of the nth word in .

[0024] The data acquisition unit obtains the corpus vector matrix U of the preset condition information,

[0025] U=[u1,u2,…u n ]

[0026] Among them, u n is the vector of the nth word in the preset condition information.

[0027] The data collection unit calculates the i-th talent data information d i The probability of satisfying the preset condition information P(d i ),

[0028]

[0029] Among them, m is the number of talent data information, w ik is the i-th talent data information d i The kth word vector in N(w ik ,d i ) is the i-th talent data information d i The kth word vector in the i-th talent data information d i The number of occurrences, u n is the vector of the kth word in the preset condition information, N(u k ,d i ) is the vector of the kth word in the preset condition information in the i-th talent data information d i Number of occurrences.

[0030] The data acquisition unit determines the conditional probability P(d i ) is greater than the preset probability value, the i-th talent data information d i And the i-th talent data information d i The corpus vector matrix e iSent to the data sorting unit.

[0031] The data sorting unit sorts all the received talent data information, obtains the sorted standardized expert database data, and sends it to the data storage unit.

[0032] Specifically, the data sorting unit decomposes the received multiple pieces of talent data information into multiple field data, performs data cleaning, and writes the talent data information after data cleaning and the corpus vector matrix corresponding to the talent data information into a standardized data table to form standardized expert database data. The fields include but are not limited to personnel number, age, gender, length of service, education, title, industry, position, work experience, academic experience, awards, due diligence report, etc. Data cleaning includes deleting talent data information with erroneous fields and vacant fields, and deduplicating repeated talent data information.

[0033] The data storage unit is used to store standardized expert database data.

[0034] The query retrieval unit is used to provide retrieval for the user and obtain retrieval results from the standardized expert database data stored in the data storage unit.

[0035] Specifically, the query retrieval unit receives the search segment input by the user, performs semantic segmentation and vectorization processing on it, and obtains the corpus vector matrix T of the search segment.

[0036] T=[t1,t2,…t n ]

[0037] Among them, t n is the vector of the nth word in the search segment.

[0038] The query retrieval unit obtains standardized expert database data from the data storage unit one by one, and extracts the corpus vector matrix W therein i ,

[0039] W i =[w i1 , w i2 ,…w in ]

[0040] Among them, w in is the i-th talent data information d i The vector of the nth word in .

[0041] The query retrieval unit calculates the relationship between the retrieval paragraph and the i-th talent data information d i The degree of closeness S i ,

[0042]

[0043] Among them, n is the corpus vector matrix T of the search segment and the i-th talent data information d i The corpus vector matrix W i The number of vectors in t j is the vector of the jth word in the search segment, w ik is the i-th talent data information d i The vector of the kth word in ||t j || indicates t j The L2 norm of ||w ik || indicates w ik The L2 norm of .

[0044] The query retrieval unit calculates the closeness S i Sort from largest to smallest, and provide the highest-ranked M talent data information to the user, where M is the number of queries set by the user.

[0045] Embodiment 2 of the present invention relates to a talent information processing method based on big data analysis, the method comprising the following steps:

[0046] S1. The data collection unit receives talent big data information, and screens the talent data information, screens out talent data information whose relevance meets preset conditions, and sends it to the data sorting unit. The step S1 includes:

[0047] The data collection unit receives the talent big data information, performs semantic word segmentation and vectorization processing on each piece of talent data information in the talent big data information, and obtains the i-th talent data information d among the m pieces of talent data information. i The corpus vector matrix W i ,

[0048] W i =[w i1 , w i2 ,…w in

[0049] Among them, w in is the i-th talent data information d i The vector of the nth word in ;

[0050] The data acquisition unit obtains the corpus vector matrix U of the preset condition information,

[0051] U=[u1,u2,…u n

[0052] Among them, u n is the vector of the nth word in the preset condition information;

[0053] The data collection unit calculates the i-th talent data information d i The probability of satisfying the preset condition information P(d i ),

[0054]

[0055] Among them, m is the number of talent data information, w ik is the i-th talent data information d i The kth word vector in N(w ik ,d i ) is the i-th talent data information d i The kth word vector in the i-th talent data information d i The number of occurrences, u n is the vector of the kth word in the preset condition information, N(u k ,d i ) is the vector of the kth word in the preset condition information in the i-th talent data information d i Number of occurrences;

[0056] The data acquisition unit determines the conditional probability P(d i ) is greater than the preset probability value, the i-th talent data information d i And the i-th talent data information d i The corpus vector matrix e i Sent to the data sorting unit.

[0057] S2. The data sorting unit sorts all the received talent data information, obtains the sorted standardized expert database data, and sends it to the data storage unit.

[0058] The data sorting unit decomposes the received multiple talent data information into multiple field data, performs data cleaning, writes the talent data information after data cleaning and the corpus vector matrix corresponding to the talent data information into a standardized data table to form standardized expert database data. The fields include but are not limited to personnel number, age, gender, length of service, education, professional title, industry, position, work experience, academic experience, awards, due diligence report, etc. Data cleaning includes deleting talent data information with erroneous fields and vacant fields, and deduplicating repeated talent data information.

[0059] S3. The query retrieval unit is used to provide retrieval to the user and obtain retrieval results from the standardized expert database data stored in the data storage unit. The step S3 includes:

[0060] The query retrieval unit receives the search segment input by the user, performs semantic segmentation and vectorization processing on it, and obtains the corpus vector matrix T of the search segment.

[0061] T=[t1,t2,…t n ]

[0062] Among them, t n is the vector of the nth word in the search segment;

[0063] The query retrieval unit obtains standardized expert database data from the data storage unit one by one, and extracts the corpus vector matrix W therein i ,

[0064] W i =[w i1 , w i2 ,…w in ]

[0065] Among them, w in is the i-th talent data information d i The vector of the nth word in ;

[0066] The query retrieval unit calculates the relationship between the retrieval paragraph and the i-th talent data information d i The degree of closeness S i ,

[0067]

[0068] Among them, n is the corpus vector matrix T of the search segment and the i-th talent data information d i The corpus vector matrix W i The number of vectors in t j is the vector of the jth word in the search segment, w ik is the i-th talent data information d i The vector of the kth word in ||t j || indicates t j The L2 norm of ||w ik || indicates w ik The L2 norm of ;

[0069] The query retrieval unit calculates the closeness S i Sort from largest to smallest, and provide the highest-ranked M talent data information to the user, where M is the number of queries set by the user.

[0070] Embodiment 3 of the present invention relates to a computer program product, which includes a computer program. The computer program is executed by a processor to execute a talent information processing method based on big data analysis according to Embodiment 2.

[0071] Embodiment 4 of the present invention relates to a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program. The computer program is executed by a processor to execute a talent information processing method based on big data analysis of embodiment 2.

[0072] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A talent information processing system based on big data analysis, characterized in that: The system includes a data collection unit, a data sorting unit, a data storage unit, and a query retrieval unit; The data collection unit is used to receive talent big data information, and screen the talent data information, screen out talent data information whose relevance meets preset conditions, and send it to the data sorting unit, specifically including: The data collection unit receives the talent big data information, performs semantic word segmentation and vectorization processing on each piece of talent data information in the talent big data information, and obtains the i-th talent data information d among the m pieces of talent data information. i The corpus vector matrix W i , IN i =[in i1， In i2 ,…In in ] Among them, w in is the i-th talent data information d i The vector of the nth word in ; The data acquisition unit obtains the corpus vector matrix U of the preset condition information, U=[u1,u2,…u n ] Among them, u n is the vector of the nth word in the preset condition information; The data collection unit calculates the i-th talent data information d i The probability of satisfying the preset condition information P(d i ), Among them, m is the number of talent data information, w ik is the i-th talent data information d i The kth word vector in N(w ik ,d i ) is the i-th talent data information d i The kth word vector in the i-th talent data information d i The number of occurrences, u n is the vector of the kth word in the preset condition information, N(u k ,d i ) is the vector of the kth word in the preset condition information in the i-th talent data information d i Number of occurrences; The data acquisition unit determines the conditional probability P(d i ) is greater than the preset probability value, the i-th talent data information d i And the i-th talent data information d i The corpus vector matrix e i Sending to the data sorting unit; The data sorting unit sorts all the received talent data information, obtains the sorted standardized expert database data, and sends it to the data storage unit; The query retrieval unit is used to provide retrieval for the user and obtain retrieval results from the standardized expert database data stored in the data storage unit, specifically including: The query retrieval unit receives the search segment input by the user, performs semantic segmentation and vectorization processing on it, and obtains the corpus vector matrix T of the search segment. T=[t1,t2,…t n ] Among them, t n is the vector of the nth word in the search segment; The query retrieval unit obtains standardized expert database data from the data storage unit one by one, and extracts the corpus vector matrix W therein i , IN i =[in i1， In i2， …In in Among them, w in is the i-th talent data information d i The vector of the nth word in ; The query retrieval unit calculates the relationship between the retrieval paragraph and the i-th talent data information d i The degree of closeness S i , Among them, n is the corpus vector matrix T of the search segment and the i-th talent data information d i The corpus vector matrix W i The number of vectors in t j is the vector of the jth word in the search segment, w ik is the i-th talent data information d i The vector of the kth word in ||t j || indicates t j The L2 norm of ||w ik || indicates w ik The L2 norm of ; The query retrieval unit calculates the closeness S i Sort from largest to smallest, and provide the highest-ranked M talent data information to the user, where M is the number of queries set by the user.

2. A talent information processing system based on big data analysis according to claim 1, characterized in that: The data sorting unit decomposes the received multiple talent data information into multiple field data, and performs data cleaning, and writes the talent data information after data cleaning and the corpus vector matrix corresponding to the talent data information into a standardized data table to form standardized expert database data.

3. A talent information processing system based on big data analysis according to claim 2, characterized in that: The fields include: personnel number, age, gender, length of service, education background, professional title, industry, position, work experience, academic experience, awards received, and due diligence report.

4. A talent information processing system based on big data analysis according to claim 2, characterized in that: The data cleaning includes deleting talent data information with error fields and vacant fields, and performing deduplication processing on repeated talent data information.

5. A talent information processing method based on big data analysis, the method being applied to the talent information processing system based on big data analysis as claimed in any one of claims 1 to 4, characterized in that: The method comprises the following steps: S1. The data collection unit receives the talent big data information, and screens the talent data information, screens out the talent data information whose relevance meets the preset conditions, and sends it to the data sorting unit, specifically including: The data collection unit receives the talent big data information, performs semantic word segmentation and vectorization processing on each piece of talent data information in the talent big data information, and obtains the i-th talent data information d among the m pieces of talent data information. i The corpus vector matrix W i , IN i =[in i1 ,In i2 ,…In in ] Among them, w in is the i-th talent data information d i The vector of the nth word in ; The data acquisition unit obtains the corpus vector matrix U of the preset condition information, U=[u1,u2,…u n ] Among them, u n is the vector of the nth word in the preset condition information; The data collection unit calculates the i-th talent data information d i The probability of satisfying the preset condition information P(d i ), Among them, m is the number of talent data information, w ik is the i-th talent data information d i The kth word vector in N(w ik ,d i ) is the i-th talent data information d i The kth word vector in the i-th talent data information d i The number of occurrences, u n is the vector of the kth word in the preset condition information, N(u k ,d i ) is the vector of the kth word in the preset condition information in the i-th talent data information d i Number of occurrences; The data acquisition unit determines the conditional probability P(d i ) is greater than the preset probability value, the i-th talent data information d i And the i-th talent data information d i The corpus vector matrix e i Sending to the data sorting unit; S2. The data sorting unit sorts all the talent data information received, obtains standardized expert database data after data sorting, and sends it to the data storage unit; S3. The query retrieval unit is used to provide a search to the user, and obtain the search results from the standardized expert database data stored in the data storage unit, specifically including: The query retrieval unit receives the search segment input by the user, performs semantic segmentation and vectorization processing on it, and obtains the corpus vector matrix T of the search segment. T=[t1,t2,…t n ] Among them, t n is the vector of the nth word in the search segment; The query retrieval unit obtains standardized expert database data from the data storage unit one by one, and extracts the corpus vector matrix W therein i , IN i =[in i1 ,In i2 ,…In in ] Among them, w in is the i-th talent data information d i The vector of the nth word in ; The query retrieval unit calculates the relationship between the retrieval paragraph and the i-th talent data information d i The degree of closeness S i , Among them, n is the corpus vector matrix T of the search segment and the i-th talent data information d i The corpus vector matrix W i The number of vectors in t j is the vector of the jth word in the search segment, w ik is the i-th talent data information d i The vector of the kth word in ||t j || indicates t j The L2 norm of ||w ik || indicates w ik The L2 norm of ; The query retrieval unit calculates the closeness S i Sort from largest to smallest, and provide the highest-ranked M talent data information to the user, where M is the number of queries set by the user.

6. A computer program product, characterized in that The computer program product includes a computer program, which is executed by a processor and is used to execute the talent information processing method based on big data analysis as described in claim 5 above.

7. 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 executed by a processor to execute the talent information processing method based on big data analysis as described in claim 5 above.

Images