Method, device and equipment for generating occupation analysis report based on talent concentration degree

Abstract

The application relates to a method, device and equipment for generating a career analysis report based on talent concentration degree. The method comprises the following steps: obtaining career data sets in an online career network and preprocessing to obtain original career data, constructing a talent concentration degree dimension career flow network model according to the personnel flow relationship between careers caused by the talent concentration degree in the original career data, extracting the personnel flow total amount feature, personnel retention feature and flow hub degree feature of each career in the original career data, and generating a career analysis report. According to the method, the personnel flow features of various careers in multiple dimensions can be extracted according to the talent concentration degree dimension career flow network model, and an analysis report can be generated, so that the comprehensiveness and accuracy of career development analysis are improved, and the method has important significance for guiding job seekers to employment and guiding organization human resource management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method and device for generating a career analysis report based on talent concentration. BACKGROUND

[0002] In the era of knowledge economy, new knowledge and technology emerge and integrate constantly, creating new work methods and career paths. The career is more and more diverse, and the employment market is more and more complex and changeable. Job seekers and organization managers need to understand the development of each career in a timely manner with scientific means and keep up with the employment market situation. At present, the evaluation and analysis of some careers only consider the basic situation of the career itself, without considering the number of personnel flow between careers, so there is a technical problem that job seekers and organization managers lack understanding of the personnel flow relationship between careers and the development of careers, resulting in incomplete and inaccurate career development analysis. SUMMARY

[0003] Therefore, it is necessary to provide a method, device and equipment for generating a career analysis report based on talent concentration to solve the above technical problems.

[0004] A method for generating a career analysis report based on talent concentration, the method comprising:

[0005] Obtaining a career data set in an online career network and preprocessing to obtain original career data; the original career data includes the number of careers, the number of employees, the education of personnel, the flow experience of personnel, the industry of personnel, and the region of personnel;

[0006] According to the personnel flow relationship between careers caused by talent concentration in the original career data, a career flow network model of talent concentration dimension is constructed; wherein the career flow network model of talent concentration dimension includes nodes, edges and weights corresponding to each edge, the nodes represent the careers in the original career data, the edges represent the personnel flow between careers, and the weights corresponding to each edge represent the number of personnel flow between careers based on talent concentration;

[0007] According to the weight of the edge in the career flow network model of talent concentration dimension, the original career data is extracted to obtain the total personnel flow feature, the personnel retention feature and the flow hub feature of each career, and the extracted features of each career are recorded to generate a career analysis report.

[0008] In one embodiment, obtaining a career data set in an online career network and preprocessing to obtain original career data, comprising:

[0009] An occupation dataset in an online occupation network is acquired, the occurrence frequency of each occupation in the occupation dataset is counted, and occupations with an occurrence frequency higher than 100 in the occupation dataset are designated as common occupations;

[0010] The names of the common occupations are calibrated to obtain preliminary standardized occupations, and the non-standardized occupations in the occupation dataset are sequentially subjected to complete matching of occupation names and occupation name stems according to the preliminary standardized occupations to obtain standardized occupations;

[0011] The standardized occupations are mapped with the occupation classification of the occupation information network to obtain original occupation data.

[0012] In one of the embodiments, the occupation flow network model in the talent concentration dimension is represented as wherein, represents a node set, each node represents an occupation, and ε represents an edge set, each edge e(u,v)∈ε represents personnel flow between occupations and at t time, represents a weight set, and each edge corresponds to a weight represents the number of personnel flow between occupations and based on the talent concentration at t time.

[0013] In one of the embodiments, the weight corresponding to each edge in the occupation flow network model in the talent concentration dimension is represented as

[0014]

[0015] wherein, represents a calculation factor of the talent concentration, represents the number of personnel flow between occupations u and v at t time, represents the number of personnel flow between occupation u and another occupation z at t time.

[0016] In one of the embodiments, the total personnel flow feature is represented as

[0017] Total t (v)=IN t (v)+OUT t (v)

[0018] wherein, Total t (v) represents the total personnel flow feature of occupation v at t time, represents the number of personnel flow into occupation v based on the talent concentration at t time,​ represents the number of people flowing out of occupation v at time t due to talent concentration, represents the number of people flowing from occupation u to occupation v at time t due to talent concentration, represents the number of people flowing from occupation v to occupation z at time t due to talent concentration.

[0019] In one embodiment, the personnel retention feature is represented as

[0020]

[0021] where Retain t (v) represents the personnel retention feature of occupation v at time t, and ε0 represents a smoothing factor. In one embodiment, the circulation hub feature is represented as

[0022] Center t (v) = Flow t (v) × Path t (v)

[0023]

[0024]

[0025] where Flow t (v) represents the flow proportion of occupation v at time t, Path t (v) represents the key path proportion of occupation v at time t, represents the number of times occupation v appears in the shortest path from occupation x to occupation y, g xy represents the total number of shortest paths from occupation x to occupation y, and x and y are any occupation.

[0026] An apparatus for generating an occupation analysis report based on talent concentration, the apparatus comprising:

[0027] a data preprocessing module configured to obtain an occupation data set in an online occupation network and perform preprocessing to obtain original occupation data, the original occupation data including the number of occupations, the number of employees, the education of personnel, the flow experience of personnel, the industry of personnel, and the region of personnel;

[0028] A professional flow network construction module is configured to construct a talent concentration dimension professional flow network model according to a relationship of personnel flow between professions caused by talent concentration in original professional data; wherein the talent concentration dimension professional flow network model comprises nodes, edges and weights corresponding to each edge, the nodes represent professions in the original professional data, the edges represent personnel flow between professions, and the weights corresponding to each edge represent the number of personnel flow between professions caused by talent concentration;

[0029] A professional analysis report generation module is configured to perform feature extraction on the original professional data according to the weights of the edges in the talent concentration dimension professional flow network model, to obtain personnel flow total amount features, personnel retention features and flow hub features of each profession, and to generate a professional analysis report by recording the features of each profession extracted.

[0030] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0031] A professional data set in an online professional network is obtained and preprocessed to obtain original professional data; the original professional data comprises the number of professions, the number of employees, the education of personnel, the flow experience of personnel, the industry of personnel and the region of personnel;

[0032] A talent concentration dimension professional flow network model is constructed according to a relationship of personnel flow between professions caused by talent concentration in original professional data; wherein the talent concentration dimension professional flow network model comprises nodes, edges and weights corresponding to each edge, the nodes represent professions in the original professional data, the edges represent personnel flow between professions, and the weights corresponding to each edge represent the number of personnel flow between professions caused by talent concentration;

[0033] Feature extraction is performed on the original professional data according to the weights of the edges in the talent concentration dimension professional flow network model, to obtain personnel flow total amount features, personnel retention features and flow hub features of each profession, and a professional analysis report is generated by recording the features of each profession extracted.

[0034] The method, device and equipment for generating the occupation analysis report based on the talent concentration degree can construct the occupation flow network model of the talent concentration degree dimension according to the personnel flow relationship between occupations caused by the talent concentration degree in the original occupation data obtained through preprocessing, extract the personnel flow total amount feature, the personnel retention feature and the flow hub degree feature of each occupation in the original occupation data, and generate the occupation analysis report. The method can capture the personnel flow situation between occupations by integrating the occupation data to construct the occupation flow network model of the talent concentration degree dimension, avoid the insufficient understanding of the personnel flow relationship between occupations by job seekers and organization managers, extract the multi-dimensional personnel flow features according to the occupation flow network model, and generate the analysis report, so as to improve the comprehensiveness and accuracy of the occupation development analysis, and has important significance for guiding the employment of job seekers and the management of human resources of organizations. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A flowchart of a method for generating an occupation analysis report based on talent concentration in an embodiment;

[0036] Figure 2 A block diagram of an apparatus for generating an occupation analysis report based on talent concentration in an embodiment;

[0037] Figure 3 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0039] In one embodiment, as shown in Figure 1 a method for generating an occupation analysis report based on talent concentration is provided, including the following steps:

[0040] Step S1, obtaining an occupation data set in an online occupation network and preprocessing to obtain original occupation data; the original occupation data includes the number of occupations, the number of employees, the education of the personnel, the flow experience of the personnel, the industry of the personnel, and the area of the personnel.

[0041] It can be understood that, since the occupations in the occupation data set in the online occupation network (such as LinkedIn) are output by users, the occupation names lack a unified standard and the occupation types are various, it is necessary to preprocess the occupation names to obtain the original occupation data with standardized occupation names and unified occupation classification.

[0042] Step S2, constructing a talent concentration dimension occupation flow network model according to the personnel flow relationship between occupations caused by talent concentration in the original occupation data; wherein the talent concentration dimension occupation flow network model includes nodes, edges and the weight corresponding to each edge, the node represents the occupation in the original occupation data, the edge represents the personnel flow between occupations, and the weight corresponding to each edge represents the number of personnel flow between occupations based on talent concentration.

[0043] It can be understood that the talent concentration replaces the number of flows with the proportion of the number of flows, and the relative concentrated talent flow often occurs between occupations with similar responsibilities or in adjacent levels in the occupation sequence, which can exclude the influence of the absolute number of personnel. To some extent, the talent concentration indicates the aggregation of highly specialized knowledge, skills and resources. In highly specialized occupations, there is likely to be a concentration of talent. Therefore, the talent concentration dimension occupation flow network model can not only capture the number of personnel flow between occupations, but also capture the flow of highly specialized human capital.

[0044] Step S3, extracting features from the original occupation data according to the weight of the edge in the talent concentration dimension occupation flow network model, obtaining the total amount of personnel flow feature, personnel retention feature and flow hub degree feature of each occupation, and generating an occupation analysis report by recording the extracted features of each occupation.

[0045] It can be understood that the total amount of personnel flow feature represents the total number of personnel inflow and outflow of a certain occupation, which helps to understand the attractiveness and development opportunities of the occupation, the personnel retention feature represents the ratio of the number of personnel inflow to the number of personnel outflow of a certain occupation, which helps to understand the stability of the occupation, and the flow hub degree feature represents the proportion of key path and flow of a certain occupation in the occupation flow network model, which helps to understand the cross-field ability of the occupation.

[0046] In one of the embodiments, the occupation data set in the online occupation network is obtained and preprocessed to obtain the original occupation data, including:

[0047] The occupation data set in the online occupation network is obtained, the frequency of each occupation in the occupation data set is counted, and the occupation with a frequency higher than 100 in the occupation data set is specified as a common occupation;

[0048] The name of the common occupation is calibrated to obtain a preliminary standardized occupation, and the non-standardized occupation in the occupation data set is sequentially matched with the occupation name and the occupation name stem to obtain a standardized occupation. Specifically, the first step is the complete matching of the occupation name. When the name of the non-standardized occupation contains all the words of the name of the preliminary standardized occupation, the non-standardized occupation is converted into the corresponding preliminary standardized occupation. When the name of the non-standardized occupation matches multiple preliminary standardized names, the non-standardized occupation is converted into the largest complete matching preliminary standardized occupation. The second step is the complete matching of the occupation name stem, that is, the name of the non-standardized occupation is matched with the name of the preliminary standardized occupation after the stemming, and the non-standardized occupation is converted into the largest complete matching preliminary standardized occupation with more than two matching words.

[0049] The standardized occupation is mapped with the occupation classification of the occupation information network to obtain the original occupation data.

[0050] It can be understood that the occupation information network (O*NET) classifies occupations uniformly, and the standardized occupation obtained from LinkedIn is mapped with the O*NET classification, so that the occupation classification information of O*NET can be utilized. A plurality of LinkedIn occupations can correspond to one O*NET occupation classification, and occupations that cannot be mapped to the O*NET classification are excluded. Through the standardization and mapping processing of the occupation data set, some useless data can be removed, the accuracy of the occupation data is improved, and a data basis is provided for the subsequent construction of the occupation flow network model.

[0051] In one embodiment, the occupation flow network model of the talent concentration degree dimension is represented as wherein, represents a node set, each node represents an occupation, and ε represents an edge set, each edge e(u,v)∈ε represents the personnel flow between the occupation and the occupation at t time, represents a weight set, and each edge corresponds to a weight represents the number of personnel flows between the occupation and the occupation at t time based on the talent concentration degree, The formula of

[0052]

[0053] wherein, represents a calculation factor of the talent concentration degree, represents the number of personnel flows between the occupation u and the occupation v at t time, represents the number of personnel flowing from occupation u to another occupation z at time t.

[0054] In one embodiment, the total personnel flow feature of occupation v at time t is represented as

[0055] Total t (v) = IN t (v) + OUT t (v)

[0056] where Total t (v) represents the total personnel flow feature of occupation v at time t, represents the number of personnel flowing into occupation v at time t based on the talent concentration, represents the number of personnel flowing out of occupation v at time t based on the talent concentration, represents the number of personnel flowing from occupation u to occupation v at time t based on the talent concentration, represents the number of personnel flowing from occupation v to occupation z at time t based on the talent concentration.

[0057] In one embodiment, the personnel retention feature of occupation v at time t is represented as

[0058]

[0059] where Retain t (v) represents the personnel retention feature of occupation v at time t, and ε0represents a smoothing factor with a value close to zero.

[0060] It can be understood that when the personnel inflow of an occupation is much greater than the personnel outflow, it can be considered that the occupation has strong retention or attraction ability for human capital, and the stability of the occupation is stronger.

[0061] In one embodiment, the flow hub feature is represented as

[0062] Center t (v) = Flow t (v) x Path t (v)

[0063]

[0064]

[0065] where Flow t (v) represents the flow proportion of occupation v at time t, and Path t (v) represents the key path proportion of occupation v at time t, g represents the number of times that the occupation v appears in the shortest path from the occupation x to the occupation y, g xy g represents the total number of shortest paths from the occupation x to the occupation y, x and y are any occupation.

[0066] It can be understood that the shortest path between two occupations refers to the path with the least number of edges connecting the two occupations in the constructed occupation flow network model. The greater the key path proportion and the flow proportion, the higher the flow hub degree and the stronger the ability of occupation exchange human capital.

[0067] It should be understood that, although Figure 1 the steps in the flowchart of the method are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, Figure 1 at least part of the steps in the method can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or sub-steps or stages of other steps.

[0068] In one embodiment, as shown in Figure 2 , an apparatus for generating an occupation analysis report based on talent concentration degree is provided, comprising: a data preprocessing module 201, an occupation flow network construction module 202, and an occupation analysis report generation module 203, wherein:

[0069] The data preprocessing module 201 is configured to obtain an occupation data set in an online occupation network and preprocess it to obtain original occupation data; the original occupation data includes the number of occupations, the number of employees, the education of personnel, the flow experience of personnel, the industry of personnel, and the region of personnel;

[0070] The occupation flow network construction module 202 is configured to construct a talent concentration degree dimension occupation flow network model according to the personnel flow relationship between occupations caused by talent concentration degree in the original occupation data; wherein the talent concentration degree dimension occupation flow network model includes nodes, edges, and weights corresponding to each edge, the nodes represent occupations in the original occupation data, the edges represent the personnel flow between occupations, and the weights corresponding to each edge represent the number of personnel flows between occupations based on talent concentration degree;

[0071] The occupation analysis report generation module 203 is configured to perform feature extraction on the original occupation data according to the weight of the edge in the occupation flow network model of the talent concentration degree dimension, to obtain the total personnel flow feature, the personnel retention feature and the flow hub degree feature of each occupation, and generate an occupation analysis report by recording the extracted features of each occupation.

[0072] The specific limitations of the device for generating an occupation analysis report based on talent concentration degree can refer to the limitations of the method for generating an occupation analysis report based on talent concentration degree described above, which will not be repeated here. The various modules in the device for generating an occupation analysis report based on talent concentration degree described above can be realized by software, hardware and combinations thereof, in whole or in part. The various modules described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the various modules.

[0073] In one embodiment, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in Figure 3 The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a method for generating an occupation analysis report based on talent concentration degree. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, trackball or touchpad arranged on the shell of the computer device, or can be an external keyboard, touchpad or mouse, etc.

[0074] Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0075] In one embodiment, a computer device is provided, which includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the following steps:

[0076] Obtain a career data set in an online career network and preprocess to obtain original career data; the original career data includes the number of careers, the number of employees, the education of the personnel, the flow experience of the personnel, the industry of the personnel, and the region of the personnel;

[0077] According to the personnel flow relationship between careers caused by talent concentration in the original career data, a career flow network model in the talent concentration dimension is constructed; wherein the career flow network model in the talent concentration dimension includes nodes, edges and weights corresponding to each edge, the nodes represent the careers in the original career data, the edges represent the personnel flow between careers, and the weight corresponding to each edge represents the number of personnel flow between careers based on talent concentration;

[0078] According to the weight of the edge in the career flow network model in the talent concentration dimension, the original career data is feature extracted to obtain the total personnel flow feature, the personnel retention feature and the flow hub degree feature of each career, and by recording the extracted features of each career, a career analysis report is generated.

[0079] The technical features of the above embodiments can be combined arbitrarily, in order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0080] The above-described embodiments only express several implementation manners of the present application, the description is more specific and detailed, but it should not be understood as a limitation on the scope of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for generating a career analysis report based on talent concentration, characterized in that, The method comprises: Obtaining a career data set in an online career network and preprocessing to obtain original career data; the original career data includes the number of careers, the number of employees, the education of personnel, the flow experience of personnel, the industry of personnel, and the region of personnel; According to the personnel flow relationship between occupations caused by talent concentration degree in the original occupation data, a talent concentration degree dimension occupation flow network model is constructed; wherein the talent concentration degree dimension occupation flow network model comprises nodes, edges and weights corresponding to each edge, the nodes represent occupations in the original occupation data, the edges represent personnel flow between occupations, and the weights corresponding to each edge represent the number of personnel flow between occupations caused by talent concentration degree; the talent concentration degree dimension occupation flow network model is represented as wherein, represents a node set, each node represents an occupation, represents an edge set, each edge represents personnel flow between occupation t and occupation at time , represents a weight set, the weight corresponding to each edge represents the number of personnel flow between occupation t and occupation caused by talent concentration degree at time ; According to the weight of the edge in the talent concentration degree dimension career flow network model, the original career data is feature extracted to obtain the total amount of personnel flow, the personnel retention feature and the flow hub degree feature of each career, and the features of each career are recorded and extracted to generate a career analysis report; The total amount of personnel flow is represented as in, Indicate occupation exist t Characteristics of total population movement at any given time. Indicates in t The influx of professionals is always based on the concentration of talent. Number of personnel Indicates in t Outflow of professions based on talent concentration Number of personnel Indicates in t The constant shift from professional to talent concentration To professional The number of people moving between them Indicates in t The constant shift from professional to talent concentration To professional The number of people moving between them; The personnel retention feature is represented as wherein representing a profession in t moment in time, representing a smoothing factor; The flow hub degree feature is represented as wherein, representing a profession In t the proportion of traffic at the moment, representing a profession In t the proportion of critical path at the moment, representing a profession In the profession x the number of times of appearing in the shortest path from the profession y to the profession representing a profession x the total number of the shortest path from the profession y to the profession x , y is any profession.

2. The method of claim 1, wherein, Obtaining a career data set in an online career network and preprocessing to obtain original career data, including: Obtaining a career data set in an online career network, counting the frequency of each career in the career data set, and designating the career with a frequency higher than 100 in the career data set as a common career; Calibrating the name of the common career to obtain a preliminary standardized career, and sequentially performing complete matching of the career name and the career name stem on the non-standardized career in the career data set according to the preliminary standardized career to obtain a standardized career; By mapping the standardized career with the career classification of the career information network, the original career data is obtained.

3. The method of claim 1, wherein, In the professional flow network model of the talent concentration degree dimension, the weight corresponding to each edge is represented as: wherein, represents a calculation factor for the concentration of talents, represents the number of personnel flows from the occupation t to the occupation at the time point , represents the number of personnel flows from the occupation t to another occupation at the time point .

4. An apparatus for generating a career analysis report based on talent concentration degree based on any one of claims 1-3, characterized in that, The device comprises: A data preprocessing module for obtaining a career data set in an online career network and preprocessing to obtain original career data; the original career data includes the number of careers, the number of employees, the education of personnel, the flow experience of personnel, the industry of personnel, and the region of personnel; A career flow network construction module for constructing a talent concentration degree dimension career flow network model according to the personnel flow relationship between careers caused by talent concentration in the original career data; wherein the talent concentration degree dimension career flow network model includes nodes, edges, and the weight corresponding to each edge, the node represents the career in the original career data, the edge represents the personnel flow between careers, and the weight corresponding to each edge represents the number of personnel flows between careers caused by talent concentration; A career analysis report generation module for feature extracting the original career data according to the weight of the edge in the talent concentration degree dimension career flow network model to obtain the total amount of personnel flow, the personnel retention feature and the flow hub degree feature of each career, and generating a career analysis report by recording the extracted features of each career. 5.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-4 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the method in any one of claims 1 to 3.

Images