CN117312397B - Talent supply chain management method and system based on big data - Google Patents
Talent supply chain management method and system based on big data Download PDFInfo
- Publication number
- CN117312397B CN117312397B CN202311345295.1A CN202311345295A CN117312397B CN 117312397 B CN117312397 B CN 117312397B CN 202311345295 A CN202311345295 A CN 202311345295A CN 117312397 B CN117312397 B CN 117312397B
- Authority
- CN
- China
- Prior art keywords
- data
- talent
- node
- nodes
- standardized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013068 supply chain management Methods 0.000 title claims abstract description 26
- 238000007726 management method Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000007405 data analysis Methods 0.000 claims abstract description 14
- 239000002131 composite material Substances 0.000 claims abstract description 10
- 238000010586 diagram Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 9
- 238000007667 floating Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000000875 corresponding effect Effects 0.000 description 32
- 238000004364 calculation method Methods 0.000 description 10
- 238000010606 normalization Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
Abstract
The application belongs to the technical field of big data, and discloses a talent supply chain management method and system based on the big data. And carrying out standardization processing on the structured data to obtain standardized data. Performing data analysis based on the relevance between the standardized data to generate talent abstracts; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level. And generating a talent label based on the talent abstract, and transmitting the talent abstract and the talent label to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform. Based on various standardized data, the talents can be comprehensively and automatically evaluated, and talent abstracts with higher confidence can be obtained according to the relevance among different standardized data.
Description
Technical Field
The application relates to the technical field of big data, for example, to a talent supply chain management method and system based on big data.
Background
The development of enterprises needs talents, and the enterprises screen out talents meeting the enterprise needs from a plurality of job seekers during recruitment. Talent data includes capabilities, seniorities, concerns about industry, and industry information gathering capabilities. The capability and the seniority can be evaluated according to the resume basic information, and the attention degree of the industry and the industry information gathering capability can be judged according to the application programs with more use frequency in the resume and the websites with more browsing frequency in the resume.
An existing talent management method, such as CN115907705a, discloses obtaining an enterprise tag of a set of objects to be selected, generating a holographic digitized image according to the enterprise tag, matching the holographic digitized image of the set of objects to be selected by adopting an AI big data technology, and sorting the matching degree. The method specifically comprises the following steps: and analyzing and comparing the evaluation results corresponding to the first evaluation index in the holographic digital image according to the preset weight to obtain the matching degree, and sequencing the matching degree according to the sequence from high to low. The method does not consider the relevance among different labels, and the confidence of the obtained matching degree is not high. Another talent management method, for example CN114971366B, discloses dividing the evaluation period, comparing the social security payment records of different evaluation periods, classifying talents into a first talent list or a second talent list, counting the number of each of the two talents in the two talents list, weighting and summing the weights of the different academies and the number of people to obtain a talent inflow score and a talent outflow score, and evaluating the talent flow condition according to the talent inflow score and the talent outflow score. According to the method, talents cannot be comprehensively and automatically evaluated based on talent data by classifying the talents and carrying out weighted summation on partial data.
In summary, the existing talent evaluation method does not consider the relevance between different labels, and the obtained confidence of the matching degree between the human resource data and the enterprise demand label is not high, and the problem that talents cannot be automatically evaluated comprehensively based on talent data exists.
Disclosure of Invention
The purpose of the application is that: the patent refers to the field of 'electric digital data processing'.
In order to achieve the above object, the present application provides a talent supply chain management method based on big data, including:
the talent data in the database is read, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume;
classifying the talent data to obtain structured data;
carrying out standardization processing on the structured data to obtain standardized data; the standardized data comprises first standardized data and second standardized data;
Performing data analysis based on the relevance between the standardized data to generate talent abstracts; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level;
generating a talent label based on the talent abstract, and sending the talent abstract and the talent label to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform.
Preferably, the data analysis based on the correlation between the standardized data generates a talent summary, including:
extracting all keywords of the standardized data according to a data threshold set to obtain a keyword set;
generating a node diagram according to the keyword set, wherein nodes in the node diagram correspond to the keywords, and connecting edges in the node diagram correspond to weights among different nodes;
calculating the confidence of each node in the node diagram;
taking the node with the confidence coefficient larger than a confidence coefficient threshold value as an effective node;
and connecting all the effective nodes in series according to the connecting edges, and outputting talent abstracts.
Preferably, said calculating a confidence level for each of said nodes in said node map comprises:
calculating the confidence of each node according to the following formula:
wherein c i For the confidence of the ith node, N is the number of nodes connected with the ith node, and w ij Is the weight between the ith and jth nodes.
Preferably, the connecting edges connect all the effective nodes in series to output talent summaries, including:
selecting a starting node from all the valid nodes;
extracting the keywords of the effective nodes according to the connecting edges corresponding to the initial nodes;
and arranging all the keywords according to the extraction sequence to obtain talent abstracts.
Preferably, the generating a talent tag based on the talent abstract, and sending the talent abstract and the talent tag to a corresponding data requirement end includes:
randomly selecting M keywords from the talent abstract, wherein the talent abstract contains N keywords; wherein M is less than N;
generating M personal talents labels according to the selected M keywords;
and calculating the matching degree of the talent abstract and the data demand end according to the following formula:
Wherein p is i For the matching degree, k, of the talent summary and the ith data demand end i Representing the number of demand labels at the i-th said data demand side, and n represents the intersection-taking operation, M ≡k i Representing the number of talent labels shared by the talent abstract and the ith data demand end;
if the matching degree is greater than or equal to a matching degree threshold, sending the talent abstract and the talent tag to an ith data demand end;
if the matching degree is smaller than the matching degree threshold, randomly selecting M keywords from the talent abstract again, and recalculating the matching degree of the talent abstract and the data demand end according to the selected M keywords.
Preferably, the classifying the talent data to obtain structured data includes:
extracting data with integer or floating point type data in the talent data to obtain first classification data; the first classification data comprises ages in the resume basic information, use frequencies of application programs with more use frequencies in the resume and browsing frequencies of websites with more browsing frequencies in the resume;
Extracting data with the data type of Boolean type from the talent data to obtain second classification data; the second classification data comprises whether industry experience exists, whether industry training is accepted or not, and sex is accepted;
and forming the first classification data and the second classification data into structured data.
Preferably, the normalizing the structured data to obtain normalized data includes:
calculating the mean and variance of each first classification data;
subtracting the corresponding mean value from each first classification data to obtain a first data difference value;
and calculating the ratio of the data difference value to the corresponding variance to obtain the first standardized data.
Preferably, the normalizing the structured data to obtain normalized data includes:
calculating the sum of all data of each second classification data to obtain a second data sum;
and taking the ratio of the second classified data to the second data sum as the second standardized data.
Preferably, the selecting a start node from all the valid nodes includes:
counting the number of the effective nodes adjacent to each effective node to obtain the number of the corresponding adjacent nodes;
And taking the effective node with the minimum number of the adjacent nodes as a starting node.
The application provides a talent supply chain management system based on big data, which comprises:
the talent data reading module is used for reading talent data in the database, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume;
the data classification module is used for classifying the talent data to obtain structured data;
the standardized processing module is used for carrying out standardized processing on the structured data to obtain standardized data; the standardized data comprises first standardized data and second standardized data;
the talent summary generation module is used for carrying out data analysis based on the relevance between the standardized data to generate a talent summary; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level;
and the talent data sending module is used for generating talent labels based on the talent abstracts and sending the talent abstracts and the talent labels to corresponding data demand ends, wherein the data demand ends comprise an enterprise talent management platform or a department talent management platform.
The talent supply chain management method based on big data comprises the steps of reading talent data in a database, wherein the talent data comprises resume basic information, application programs with more use frequency in resume and websites with more browsing frequency in resume. The database stores a large number of delivered resume, the talent data contains all information in the resume, and big data analysis is carried out on the basis of talent data. The talent data is classified, so that the talent data can be better summarized and arranged, and the structured data is obtained. And carrying out standardization processing on the structured data to obtain standardized data, wherein the standardized data comprises first standardized data and second standardized data, and the first standardized data and the second standardized data have different value ranges. Performing data analysis based on the relevance between the standardized data to generate talent abstracts; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level. And generating a talent label based on the talent abstract, and transmitting the talent abstract and the talent label to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform. Based on various standardized data, the talents can be comprehensively and automatically evaluated, and talent abstracts with higher confidence can be obtained according to the relevance among different standardized data. The talent abstract and the talent label are sent to enable the corresponding data demand end to quickly and accurately acquire the talent analysis result.
Drawings
FIG. 1 is a flow chart of a talent supply chain management method based on big data according to the first embodiment;
FIG. 2 is a flow chart of a talent supply chain management method based on big data according to a second embodiment;
FIG. 3 is a schematic block diagram of a big data based talent supply chain management system according to a third embodiment;
fig. 4 is a block diagram schematically illustrating a structure of a computer device according to an embodiment.
The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, modules, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, modules, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any module and all combination of one or more of the associated listed items.
It will be understood by those skilled in the art that all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs unless defined otherwise. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Example 1
Referring to fig. 1, a flow chart of a talent supply chain management method based on big data according to an embodiment of the disclosure is shown, the method includes:
s101: and reading talent data in the database, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume.
The databases may be relational databases such as Oracle, DB2, and SQL, or non-relational databases such as HBase, without limitation.
The resume basic information comprises talent names, ages, talent calendars and working years of the application industry, the resume further comprises application programs which are frequently used in normal times, namely application programs which are frequently used, and the resume further comprises websites which are frequently browsed, namely websites which are frequently browsed.
As an example, the database is an HBase database, and the personal information in the database includes 6 columns, and the 1 st column to the 6 th column are talent names, ages, talent academies, working years of the recruitment industry, application programs with more frequency of use, and websites with more frequency of browsing. Talent A is on line 4 of personal information, which has 6 line values, from line 1 to line 6, of Zhang three, 35, shuoshi, 6 years, application A, and website B in that order.
S102: and classifying the talent data to obtain structured data.
Because the processing modes of the different types of data are different, the talent data are classified according to the data types, and the different types of talent data can be distinguished to obtain the structured data.
S103: carrying out standardization processing on the structured data to obtain standardized data; the normalized data includes first normalized data and second normalized data.
The first standardized data is data in an integer or floating point number format, the second standardized data is Boolean data, and the value of the second standardized data is 0 or 1.
The value range of the first standardized data is mapped into a first interval through the standardized processing, and the value range of the second standardized data is mapped into a second interval. The first section and the second section may be the same or different, and are not limited herein.
The normalization processing can reduce the value range of the first normalization data and the second normalization data, and one type of normalization data corresponds to one interval, so that the normalization data of different types can be analyzed conveniently.
S104: performing data analysis based on the relevance between the standardized data to generate talent abstracts; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below the average statistical level.
There is a correlation between standardized data, such as an age and an operational age of the application industry are generally positive correlations, the longer the operational age of the application industry, the more likely one or more applications are used frequently, and/or one or more industry-related websites are browsed frequently.
The talent summary includes the related part of standardized data, which can better highlight the data characteristics of talents while reducing the data quantity.
S105: generating a talent label based on the talent abstract, and sending the talent abstract and the talent label to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform.
And extracting part of keywords from the talent abstract to generate a talent label, wherein the talent label can reflect the data characteristics of talents more concisely than the talent abstract. The talent abstract and the talent label are sent to a corresponding enterprise talent management platform or department talent management platform, and enterprise management personnel can browse the talent abstract to obtain comprehensive evaluation of talents and browse the talent label to quickly obtain outstanding data characteristics of the talents.
The talent supply chain management method based on big data comprises the steps of reading talent data in a database, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume. The database stores a large number of delivered resume, the talent data contains all information in the resume, and big data analysis is carried out on the basis of talent data. The talent data is classified, so that the talent data can be better summarized and arranged, and the structured data is obtained. And carrying out standardization processing on the structured data to obtain standardized data, wherein the standardized data comprises first standardized data and second standardized data, and the first standardized data and the second standardized data have different value ranges. Performing data analysis based on the relevance between the standardized data to generate talent abstracts; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level. And generating a talent label based on the talent abstract, and transmitting the talent abstract and the talent label to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform. Based on various standardized data, the talents can be comprehensively and automatically evaluated, and talent abstracts with higher confidence can be obtained according to the relevance among different standardized data. The talent abstract and the talent label are sent to enable the corresponding data demand end to quickly and accurately acquire the talent analysis result.
Example two
Referring to fig. 2, a flow chart of a talent supply chain management method based on big data according to a second embodiment is disclosed, and the method includes:
s201: and reading talent data in the database, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume.
Step S201 is the same as step S101, and will not be described here again.
S202: extracting data with integer or floating point type data in the talent data to obtain first classification data; the first classification data comprises ages in the resume basic information, use frequencies of application programs with more use frequencies in the resume and browsing frequencies of websites with more browsing frequencies in the resume.
The integer data is an integer, the floating point data is an integer or a decimal, and the integer data and the floating point data are processed in the same mode.
Age is integer data, if actual frequency is counted, the use frequency of the application program and the browsing frequency of the website are integer data; if the average frequency of each day in a period of time is calculated, the frequency of use of the application program and the frequency of browsing of the website are both floating point data.
As an example, integer or floating point data in talent data is extracted to obtain data with an age of 35, the usage frequency of an application program with a high usage frequency in a resume is 3.2 times in a day on average, and the browsing frequency of a website with a high browsing frequency in the resume is 4.8 times in a day on average.
S203: extracting data with the data type of Boolean type from the talent data to obtain second classification data; the second classification data includes whether industry experience, whether industry training was accepted, and gender.
The number of the values of the Boolean data is two, one value is 1, the other value is 0, and the processing mode of the Boolean data is different from the processing mode of the integer data. Alternatively, when the boolean data indicates whether the condition is satisfied, if the value is 1, then the indication is yes; if the value is 0, the method indicates no; when the data of the Boolean type indicates sex, if the value is 1, the data indicates male; if the value is 0, the female is indicated.
As an example, boolean data in talent data is extracted to obtain industry experience 1, industry training 0, and gender 1.
S204: and forming the first classification data and the second classification data into structured data.
The first classification data and the second classification data may be mixed to form structured data, for example, the 1 st class data to the 6 th class data in the structured data are age, gender, whether industry experience exists, whether industry training is accepted, the use frequency of the application program with more use frequency in the resume, and the browse frequency of the website with more browse frequency in the resume in sequence. The second classification data may be arranged after the first classification data or after the first classification data is arranged after the second classification data, so as to obtain structured data, for example, the 1 st class data to the 6 th class data in the structured data are age, use frequency of application programs with more use frequency in resume, browse frequency of websites with more browse frequency in resume, whether industry experience exists, whether industry training is accepted, and sex.
S205: and calculating the mean value and the variance of each first classification data.
The mean value of the ith first classification data is calculated by the following formula:
wherein A is i Is the mean value of the ith first classification data, N is the data amount of the ith first classification data,the nth value of the ith first classification data.
The variance of the ith first classification data is calculated by the following formula:
Wherein S is i For the variance of the ith first classification data, N is the data amount of the ith first classification data,the value of the nth class data of the ith class is A i Is the mean of the i-th first classification data.
S206: subtracting the corresponding mean value from each first classification data to obtain a first data difference value.
The i-th first data difference is expressed asThe i-th first data difference may be positive or negative.
S207: and calculating the ratio of the data difference value to the corresponding variance to obtain the first standardized data.
The ith first normalized data is calculated by the following formula:
wherein,for the ith first standardized data, S i For the variance of the ith first classification data, +.>Is the i first data difference.
S208: and calculating the sum of all data of each second classification data to obtain a second data sum.
As an example, the second classification data includes 10 data, where 6 data has a value of 1 and 4 data has a value of 0, and the sum of the 10 data is calculated to obtain a second data sum of 6.
S209: and taking the ratio of the second classified data to the second data sum as the second standardized data.
The steps S208-S209 and the steps S205-207 are parallel technical schemes, and the value range of each datum in the second standardized datum is 0-1. As an example, the sum of the second data is 6, the 1 st data, the 2 nd data and the 3 rd data in the second classification data are 1,0,1 respectively, and the 1 st data in the second standardization data has the value ofThe value of the 2 nd data is 0, and the value of the 3 rd data is +.>
S210: and carrying out data analysis based on the relevance between the standardized data to generate a talent abstract.
The talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below the average statistical level.
Step S210 includes the steps of:
s2101: and extracting all keywords of the standardized data according to the data threshold set to obtain a keyword set.
Each normalized data corresponds to one data threshold, and as an example, there are 20 normalized data, 20 data thresholds corresponding to the 20 normalized data, and the 20 data thresholds constitute a data threshold set. And if the average value of the 4 th standardized data is greater than or equal to the 4 th data threshold value, extracting keywords of the 4 th standardized data, such as the working years of the application industry. If the average value of the 5 th standardized data is smaller than the 5 th data threshold value, the keyword of the 5 th standardized data is not extracted. And forming all the extracted keywords into a keyword set.
S2102: and generating a node diagram according to the keyword set, wherein nodes in the node diagram correspond to the keywords, and connecting edges in the node diagram correspond to weights among different nodes.
One node represents one keyword, and different keywords have relevance, so that two interrelated nodes can be connected by a connecting edge, and a node diagram is formed by a plurality of nodes and a plurality of connecting edges.
The length of the connecting edge is proportional to the correlation between the two nodes, i.e. the stronger the correlation between the two nodes, the longer the connecting edge connecting the two nodes. The longer the length of the connecting edge, the larger the weight corresponding to the connecting edge.
For example, node a is associated with node B, and node a is associated with node C. The length of the connecting edge 1 connecting the node A and the node B is L 1 The length of the connecting edge 2 connecting the node A and the node C is L 2 Wherein L is 1 ＞L 2 ，L 1 The corresponding weight is 0.5L 2 The corresponding weight is 0.3, indicating that the association between node a and node B is stronger than the association between node a and node C.
S2103: and calculating the confidence of each node in the node diagram.
Calculating the confidence of each node according to the following formula:
Wherein c i For the confidence of the ith node, N is the number of nodes connected with the ith node, and w ij Is the weight between the ith and jth nodes.
And summing the weights of the node i and N adjacent nodes, and multiplying the weights by the number N of the adjacent nodes to obtain the confidence coefficient of the node i. One keyword in a talent summary typically has an association with a plurality of other keywords, and such association should be evenly distributed. As an example, the keyword of the 4 th node is the working years of the application industry, the keyword of the 5 th node is the age, the keyword of the 6 th node is the total working years, that is, the sum of the working years of the application industry and the working years of other industries, and the keyword of the 7 th nodeThe key word is the age of the child. The weight of the 4 th node and the 5 th node is w 45 The weight of the 4 th node and the 6 th node is w 46 The weight of the 4 th node and the 7 th node is w 47 In practice, the relationship between age, total age and child age and the working years of the application industry should be relatively close, so that w 45 、w 46 And w 47 Is relatively close.
The number of nodes connected with the ith node is positively correlated with the confidence of the ith node, namely, the more the number of nodes associated with the ith node is, the higher the confidence of the ith node is.
S2104: and taking the node with the confidence coefficient larger than a confidence coefficient threshold value as an effective node.
Optionally, the confidence threshold is set to 0.6, and the node with the confidence greater than 0.6 is used as the valid node.
S2105: and connecting all the effective nodes in series according to the connecting edges, and outputting talent abstracts.
Selecting a starting node from all the valid nodes;
extracting the keywords of the effective nodes according to the connecting edges corresponding to the initial nodes;
and arranging all the keywords according to the extraction sequence to obtain talent abstracts.
The more the number of effective adjacent nodes of the starting node is, the more complex the initial calculation is; the fewer valid neighbors of the starting node, the simpler the initial calculation. And counting the number of adjacent effective nodes of each effective node to obtain the corresponding number of adjacent nodes. The effective node with the minimum number of adjacent nodes is used as the starting node, so that the calculated amount in the initial calculation can be reduced, and errors in the initial calculation are avoided.
As an example, the number of neighboring nodes of the 2 nd valid node is the smallest, and the 2 nd valid node is taken as the start node. The 2 nd effective node is connected with the 3 rd effective node, and the 3 rd effective node is connected with the 5 th effective node and the 6 th effective node. The key word of the 2 nd effective node is name, the key word of the 3 rd effective node is age, the key word of the 5 th effective node is social security payment years, and the key word of the 6 th effective node is public accumulation payment years. And arranging all keywords according to the extraction sequence, wherein the obtained talent abstract is named as Zhang three, the age is 35 years, the social security payment years are 10 years, and the public accumulation payment years are 8 years.
S211: and generating a talent tag based on the talent abstract, and sending the talent abstract and the talent tag to a corresponding data demand end.
The data demand end comprises an enterprise talent management platform or a department talent management platform, M keywords are randomly selected from the talent abstract, and the talent abstract contains N keywords; wherein M is less than N;
generating M personal talents labels according to the selected M keywords;
and calculating the matching degree of the talent abstract and the data demand end according to the following formula:
wherein p is i For the matching degree, k, of the talent summary and the ith data demand end i Representing the number of demand labels at the i-th said data demand side, and n represents the intersection-taking operation, M ≡k i Representing the number of talent labels shared by the talent abstract and the ith data demand end;
if the matching degree is greater than or equal to a matching degree threshold, sending the talent abstract and the talent tag to an ith data demand end;
if the matching degree is smaller than the matching degree threshold, randomly selecting M keywords from the talent abstract again, and recalculating the matching degree of the talent abstract and the data demand end according to the selected M keywords.
As an example, the talent summary has 5 keywords in total, and 3 keywords are randomly selected from the talent summary, namely name three, age 35 and the scholar's academy. Generation from 3 keywords3 talents are labeled, zhang san, age 35 and Master, respectively. The data demand end, namely the enterprise talent management platform or the department talent management platform, is stored with a plurality of demand labels, wherein the demand labels comprise ages below 40 years old and academic degrees above the family. The 3 personal labels have 2 demand labels matched with the 1 st data demand end, and the matching degree is thatSetting the matching degree threshold to +.>And the matching degree is larger than a matching degree threshold value, and the talent abstract and the 3 talent labels are sent to the 1 st data demand end.
The talent abstract can reflect personal information of talents more comprehensively, and the talent label can highlight data characteristics of the talents. And obtaining the matching degree of the talent abstract and the data demand end by calculating the overlapping condition of the talent label in the talent abstract and the demand label of the data demand end. According to the matching degree, the talent abstract and the talent label can be rapidly pushed to a matched data demand end.
As described above, all keywords of the normalized data are extracted according to the data threshold set, resulting in a keyword set. The set of keywords can represent data characteristics of talents. And generating a node diagram according to the keyword set, wherein the node diagram is used for describing the relevance between different keywords, and the stronger the relevance between two keywords is, the longer the connecting edge connecting the two keywords is, the larger the weight corresponding to the connecting edge is. The different keywords are interrelated, the more the number of other keywords connected with one keyword in the node diagram is, the more the other keywords can verify the authenticity of the keyword, and the higher the confidence of the keyword is. And screening out effective nodes from all the nodes through a confidence threshold, wherein the effective nodes are nodes with higher confidence. The effective node with the smallest number of adjacent nodes is used as the starting node, so that the initial calculation amount can be reduced. Extracting keywords of the effective nodes according to the connecting edges corresponding to the initial nodes to obtain keywords of the effective nodes directly or indirectly connected with the initial nodes, and arranging all the extracted keywords according to the extraction sequence to obtain talent abstracts. The talent abstract can highlight the data characteristics of talents, the matching degree of the talent abstract and the data demand end is calculated according to the talent abstract and part of keywords randomly selected from the talent abstract, the talent abstract and the corresponding part of keywords are provided for the data demand end with higher matching degree, and the pushing efficiency of the data characteristics of talents can be improved.
Example III
Referring to fig. 3, a schematic block diagram of a talent supply chain management system based on big data according to a third embodiment of the present disclosure is shown, where the system includes:
the talent data reading module 10 is configured to read talent data in a database, where the talent data includes basic resume information, an application program with a high frequency of use in resume, and websites with a high frequency of browsing in resume;
the data classification module 20 is configured to perform data classification on the talent data to obtain structured data;
the normalization processing module 30 is configured to perform normalization processing on the structured data to obtain normalized data; the standardized data comprises first standardized data and second standardized data;
a talent summary generation module 40, configured to perform data analysis based on the correlation between the standardized data, and generate a talent summary; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level;
the talent data sending module 50 is configured to generate a talent tag based on the talent abstract, and send the talent abstract and the talent tag to a corresponding data requirement end, where the data requirement end includes an enterprise talent management platform or a department talent management platform.
As described above, the big data based talent supply chain management system can implement the big data based talent supply chain management method.
Preferably, the talent summary generation module 40 includes:
the keyword extraction unit is used for extracting all keywords of the standardized data according to the data threshold set to obtain a keyword set;
a node diagram generating unit, configured to generate a node diagram according to the keyword set, where nodes in the node diagram correspond to the keywords, and connecting edges in the node diagram correspond to weights between different nodes;
a confidence calculating unit configured to calculate a confidence of each of the nodes in the node map;
an effective node definition unit, configured to take the node with the confidence coefficient greater than a confidence coefficient threshold value as an effective node;
and the effective node serial connection unit is used for connecting all the effective nodes in series according to the connecting edges and outputting talent abstracts.
Preferably, the confidence calculating unit includes:
a confidence calculating subunit for calculating a confidence of each of the nodes according to the following formula:
wherein c i For the confidence of the ith node, N is the number of nodes connected with the ith node, and w ij Is the weight between the ith and jth nodes.
Preferably, the active node series unit includes:
a start node selection subunit, configured to select a start node from all the valid nodes; specifically, counting the number of the effective nodes adjacent to each effective node to obtain the corresponding number of adjacent nodes; and taking the effective node with the minimum number of the adjacent nodes as a starting node.
A keyword extraction subunit, configured to extract the keywords of the effective node according to a connection edge corresponding to the starting node;
and the keyword ordering subunit is used for arranging all the keywords according to the extraction sequence to obtain talent abstracts.
Preferably, the talent data transmission module 50 includes:
a keyword selection unit, configured to randomly select M keywords from the talent summary, where the talent summary includes N keywords; wherein M is less than N;
the talent label generating unit is used for generating M talent labels according to the selected M keywords;
the first matching degree calculating unit is used for calculating the matching degree of the talent abstract and the data demand end according to the following formula:
wherein p is i For the matching degree, k, of the talent summary and the ith data demand end i Representing the number of demand labels at the i-th said data demand side, and n represents the intersection-taking operation, M ≡k i Representing the number of talent labels shared by the talent abstract and the ith data demand end;
the summary and label sending unit is used for sending the talent summary and the talent label to the ith data demand end if the matching degree is greater than or equal to a matching degree threshold value;
and the second matching degree calculation unit is used for randomly selecting M keywords from the talent abstract again if the matching degree is smaller than the matching degree threshold value, and recalculating the matching degree of the talent abstract and the data demand end according to the selected M keywords.
Preferably, the data classification module 20 includes:
the first classified data extraction unit is used for extracting data with integer or floating point type data in the talent data to obtain first classified data; the first classification data comprises ages in the resume basic information, use frequencies of application programs with more use frequencies in the resume and browsing frequencies of websites with more browsing frequencies in the resume;
The second classification data extraction unit is used for extracting data with the data type of Boolean type from the talent data to obtain second classification data; the second classification data comprises whether industry experience exists, whether industry training is accepted or not, and sex is accepted;
and the structured data composing unit is used for composing the first classified data and the second classified data into structured data.
Preferably, the standardized processing module 30 includes:
a mean and variance calculation unit configured to calculate a mean and variance of each of the first classification data;
the first data difference value calculation unit is used for subtracting the corresponding mean value from each first classification data to obtain a first data difference value;
and the first normalized data calculation unit is used for calculating the ratio of the data difference value to the corresponding variance to obtain the first normalized data.
Preferably, the standardized processing module 30 includes:
a second classification data summation unit, configured to calculate a sum of all data of each of the second classification data, to obtain a second data sum;
and a second normalized data calculation unit configured to take a ratio of the second classification data to the second data sum as the second normalized data.
Example IV
The fourth embodiment provides a computer device, and the internal structure of the computer device may be as shown in fig. 4. The computer device includes a computer processor, a storage medium, a memory, a network interface, and an input device, the computer processor exchanging information with the storage medium, the storage medium including an operating system, a computer program, and a database. The computer processor is connected with the memory, the network interface and the input device through a system bus, and the network interface is used for carrying out network communication with external equipment.
Corresponding to the above method embodiment, the present application further provides a computer readable storage medium, on which a computer program is stored, which when executed by a computer processor implements the steps of the above big data based talent supply chain management method.
It should also be noted that in this document relational terms such as first and second are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. A talent supply chain management method based on big data, comprising:
the talent data in the database is read, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume;
classifying the talent data to obtain structured data;
carrying out standardization processing on the structured data to obtain standardized data; the standardized data comprises first standardized data and second standardized data;
performing data analysis based on the relevance between the standardized data to generate talent abstracts; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level;
Generating a talent tag based on the talent abstract, and transmitting the talent abstract and the talent tag to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform;
the step of performing data analysis based on the relativity between the standardized data to generate talent summaries comprises the following steps:
extracting all keywords of the standardized data according to a data threshold set to obtain a keyword set;
generating a node diagram according to the keyword set, wherein nodes in the node diagram correspond to the keywords, and connecting edges in the node diagram correspond to weights among different nodes;
calculating the confidence of each node in the node diagram;
taking the node with the confidence coefficient larger than a confidence coefficient threshold value as an effective node;
and connecting all the effective nodes in series according to the connecting edges, and outputting talent abstracts.
2. The big data based talent supply chain management method of claim 1, wherein said calculating a confidence level for each of said nodes in said node map comprises:
calculating the confidence of each node according to the following formula:
wherein c i For the confidence of the ith node, N is the number of nodes connected with the ith node, and w ij Is the weight between the ith and jth nodes.
3. The big data based talent supply chain management method according to claim 1, wherein said connecting all said valid nodes in series according to said connecting edge, outputting a talent summary, comprises:
selecting a starting node from all the valid nodes;
extracting the keywords of the effective nodes according to the connecting edges corresponding to the initial nodes;
and arranging all the keywords according to the extraction sequence to obtain talent abstracts.
4. The big data based talent supply chain management method according to claim 1, wherein said generating a talent tag based on said talent summary, and transmitting said talent summary and said talent tag to corresponding data demand terminals, comprises:
randomly selecting M keywords from the talent abstract, wherein the talent abstract contains N keywords; wherein M is less than N;
generating M personal talents labels according to the selected M keywords;
and calculating the matching degree of the talent abstract and the data demand end according to the following formula:
Wherein p is i For the matching degree, k, of the talent summary and the ith data demand end i Representing the number of demand labels at the i-th said data demand side, and n represents the intersection-taking operation, M ≡k i Representing the number of talent labels shared by the talent abstract and the ith data demand end;
if the matching degree is greater than or equal to a matching degree threshold, sending the talent abstract and the talent tag to an ith data demand end;
if the matching degree is smaller than the matching degree threshold, randomly selecting M keywords from the talent abstract again, and recalculating the matching degree of the talent abstract and the data demand end according to the selected M keywords.
5. The big data based talent supply chain management method according to claim 1, wherein said classifying the talent data into structured data comprises:
extracting data with integer or floating point type data in the talent data to obtain first classification data; the first classification data comprises ages in the resume basic information, use frequencies of application programs with more use frequencies in the resume and browsing frequencies of websites with more browsing frequencies in the resume;
Extracting data with the data type of Boolean type from the talent data to obtain second classification data; the second classification data comprises whether industry experience exists, whether industry training is accepted or not, and sex is accepted;
and forming the first classification data and the second classification data into structured data.
6. The big data based talent supply chain management method according to claim 5, wherein said normalizing the structured data to obtain normalized data comprises:
calculating the mean and variance of each first classification data;
subtracting the corresponding mean value from each first classification data to obtain a first data difference value;
and calculating the ratio of the data difference value to the corresponding variance to obtain the first standardized data.
7. The big data based talent supply chain management method according to claim 5, wherein said normalizing the structured data to obtain normalized data comprises:
calculating the sum of all data of each second classification data to obtain a second data sum;
and taking the ratio of the second classified data to the second data sum as the second standardized data.
8. The big data based talent supply chain management method of claim 4, wherein said selecting a starting node from all of said valid nodes comprises:
counting the number of the effective nodes adjacent to each effective node to obtain the number of the corresponding adjacent nodes;
and taking the effective node with the minimum number of the adjacent nodes as a starting node.
9. A talent supply chain management system based on big data, comprising:
the talent data reading module is used for reading talent data in the database, wherein the talent data comprises resume basic information, application programs with more use frequency in the resume and websites with more browsing frequency in the resume;
the data classification module is used for classifying the talent data to obtain structured data;
the standardized processing module is used for carrying out standardized processing on the structured data to obtain standardized data; the standardized data comprises first standardized data and second standardized data;
the talent summary generation module is used for carrying out data analysis based on the relevance between the standardized data to generate a talent summary; the talent summary includes a talent type, a talent composite score, a first talent attribute above an average statistical level, and a second talent attribute below an average statistical level;
The talent data sending module is used for generating a talent label based on the talent abstract and sending the talent abstract and the talent label to a corresponding data demand end, wherein the data demand end comprises an enterprise talent management platform or a department talent management platform;
the talent summary generation module comprises:
the keyword extraction unit is used for extracting all keywords of the standardized data according to the data threshold set to obtain a keyword set;
a node diagram generating unit, configured to generate a node diagram according to the keyword set, where nodes in the node diagram correspond to the keywords, and connecting edges in the node diagram correspond to weights between different nodes;
a confidence calculating unit configured to calculate a confidence of each of the nodes in the node map;
an effective node definition unit, configured to take the node with the confidence coefficient greater than a confidence coefficient threshold value as an effective node;
and the effective node serial connection unit is used for connecting all the effective nodes in series according to the connecting edges and outputting talent abstracts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345295.1A CN117312397B (en) | 2023-10-18 | 2023-10-18 | Talent supply chain management method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311345295.1A CN117312397B (en) | 2023-10-18 | 2023-10-18 | Talent supply chain management method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117312397A CN117312397A (en) | 2023-12-29 |
| CN117312397B true CN117312397B (en) | 2024-03-22 |
Family
ID=89260141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311345295.1A Active CN117312397B (en) | 2023-10-18 | 2023-10-18 | Talent supply chain management method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117312397B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710843A (en) * | 2018-12-17 | 2019-05-03 | 国云科技股份有限公司 | A method of improving search matching degree in big quantity personnel resume |
| CN116308227A (en) * | 2023-05-25 | 2023-06-23 | 北京赛学科技有限公司 | Innovative entrepreneur talent hatching data interaction method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130124268A1 (en) * | 2011-11-10 | 2013-05-16 | James Hatton | Systems and methods for identifying experts |
| US11334836B2 (en) * | 2017-01-04 | 2022-05-17 | MSM Holdings Pte Ltd | System and method for analyzing media for talent discovery |
-
2023
- 2023-10-18 CN CN202311345295.1A patent/CN117312397B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710843A (en) * | 2018-12-17 | 2019-05-03 | 国云科技股份有限公司 | A method of improving search matching degree in big quantity personnel resume |
| CN116308227A (en) * | 2023-05-25 | 2023-06-23 | 北京赛学科技有限公司 | Innovative entrepreneur talent hatching data interaction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117312397A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Becchetti et al. | Efficient semi-streaming algorithms for local triangle counting in massive graphs | |
| US20130054497A1 (en) | Systems and methods for detection of satisficing in surveys | |
| KR101269441B1 (en) | Apparatus and method for assessing patent infringement risks based on semantic patent claim analysis | |
| CN113836131B (en) | Big data cleaning method and device, computer equipment and storage medium | |
| CN110825977A (en) | Data recommendation method and related equipment | |
| CN113032403B (en) | Data insight method, device, electronic equipment and storage medium | |
| CN113722611A (en) | Method, device and equipment for recommending government affair service and computer readable storage medium | |
| CN111899821A (en) | Method for processing medical institution data, method and device for constructing database | |
| CN112507212A (en) | Intelligent return visit method and device, electronic equipment and readable storage medium | |
| Kang et al. | A hybrid approach for paper recommendation | |
| CN110389963A (en) | The recognition methods of channel effect, device, equipment and storage medium based on big data | |
| US20180357227A1 (en) | System and method for analyzing popularity of one or more user defined topics among the big data | |
| CN117312397B (en) | Talent supply chain management method and system based on big data | |
| CN112631889A (en) | Portrayal method, device and equipment for application system and readable storage medium | |
| CN109462635B (en) | Information pushing method, computer readable storage medium and server | |
| CN109144999B (en) | Data positioning method, device, storage medium and program product | |
| CN109376287B (en) | House property map construction method, device, computer equipment and storage medium | |
| CN109902129A (en) | Insurance agent's classifying method and relevant device based on big data analysis | |
| CN113627950B (en) | Method and system for extracting user transaction characteristics based on dynamic diagram | |
| CN112182390B (en) | Mail pushing method, device, computer equipment and storage medium | |
| CN113468421A (en) | Product recommendation method, device, equipment and medium based on vector matching technology | |
| CN113129057A (en) | Software cost information processing method and device, computer equipment and storage medium | |
| CN111522795A (en) | Method and device for processing data | |
| CN111191126A (en) | Keyword-based scientific and technological achievement accurate pushing method and device | |
| CN113239024B (en) | Bank abnormal data detection method based on outlier detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |