Artificial intelligence-based talent market data management system

Abstract

The invention relates to the technical field of information processing, in particular to a talent market data management system based on artificial intelligence, which comprises a personnel data acquisition module used for acquiring personnel registration information and personnel job application states, an enterprise data acquisition module used for acquiring enterprise registration information and position demand information, a position trend analysis module used for analyzing the position demand information, and a management module used for managing the position demand information. The system comprises a position type analysis module used for analyzing the change state of each position type and the number state of each position type and calculating the trend index of each position type, a personnel characteristic analysis module used for analyzing personnel characteristics, an enterprise characteristic analysis module used for analyzing enterprise characteristics, a characteristic matching module used for matching the characteristics of each position type, and a calculation module used for calculating the trend index of each position type. The matching degree calculation module is used for calculating the matching degree between the enterprise and the personnel according to the enterprise feature analysis result and the personnel feature analysis result, and the position recommendation module is used for calculating position recommendation coefficients and recommending positions to the personnel. The talent market data processing efficiency is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a talent market data management system based on artificial intelligence. Background Art

[0002] With the rapid development of the economy and the intensification of market competition, enterprises have an increasing demand for talent. Traditional talent market data management systems often rely on manual input and simple queries, with low data processing efficiency, and are unable to meet the needs of modern enterprises for accurate and efficient talent management. In recent years, the development of artificial intelligence technology has provided new ideas for solving these problems. By introducing technologies such as natural language processing, machine learning, and data mining, it is possible to achieve intelligent management of talent market data and provide enterprises with more accurate talent recommendations and services.

[0003] Chinese patent publication number CN116452163A discloses a talent recruitment management system and method based on big data, the method comprising: S1, preset data is set by a manager; the preset data comprises screening parameter items, the weight of each screening parameter item, the minimum standard and the maximum standard of each screening parameter item, the number of matching resumes, the number of recruitments and the screening completion time; S2, based on big data, the division level of each screening parameter item is obtained, the time period is divided according to the preset conditions according to the screening completion time, and the setting level of the screening parameter item for each divided time period is dynamically adjusted according to the minimum standard and the maximum standard of each screening parameter item, the weight of each screening parameter item, the number of matching resumes and the division level of each screening parameter item; it can be seen that the invention does not analyze the needs of job seekers, and also recommends positions to personnel according to the development trend of the profession and the degree of matching between personnel and enterprises, and there is a problem of low efficiency in processing talent market data. Summary of the invention

[0004] The purpose of the present invention is to provide a talent market data management system based on artificial intelligence to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] Personnel data collection module, used to collect personnel registration information and personnel job-seeking status;

[0007] Enterprise data collection module, used to collect enterprise registration information and job demand information;

[0008] The position trend analysis module is used to analyze the change status of each position type and the quantity status of each position type according to the position demand information, and calculate the trend index of each position type according to the change status analysis results and the quantity status analysis results of each position type;

[0009] Personnel characteristics analysis module, used to analyze personnel characteristics based on personnel registration information;

[0010] Enterprise characteristics analysis module, used to analyze enterprise characteristics based on enterprise registration information;

[0011] Feature matching module, used to calculate the compatibility between enterprises and personnel based on the results of enterprise feature analysis and personnel feature analysis;

[0012] The job recommendation module is used to calculate the recommendation coefficient of each job based on the calculation results of the compatibility between the enterprise and the personnel and the trend index calculation results of each job type, and to recommend jobs to personnel based on the recommendation coefficient of each job and the job-seeking status of the personnel, and to send the recommendation results to the personnel.

[0013] Furthermore, the position trend analysis module includes a demand quantity analysis unit, which counts a demand quantity set S for each position type, and compares the statistical result with the preset position demand quantity to determine the quantity status of each position type, and the quantity status of each position type includes a low demand state, a medium demand state and a high demand state.

[0014] Furthermore, the position trend analysis module further includes a change state analysis unit, which is used to calculate a change coefficient set V of each position type according to a demand quantity set S of each position type and a historical demand quantity set PS of each position type;

[0015] The change state analysis unit compares the change coefficient set V of each position type with each preset change coefficient to determine the change state of each position type. The change state of each position type includes a stable change state, a significantly reduced state and a significantly increased state.

[0016] Furthermore, the position trend analysis module is further provided with a position correlation analysis unit, and the position correlation analysis unit adjusts the change state analysis process of each position type according to the personnel flow quantity matrix between each position type;

[0017] The position association analysis unit calculates the mobility coefficient β(x,y) between the xth position type and the jth position type;

[0018] The position association analysis unit compares β(x, y) with a preset flow coefficient B, and when β(x, y) exceeds the preset flow coefficient B, adjusts the first preset change coefficient to μ1′.

[0019] Furthermore, the job trend analysis module also includes an on-the-job analysis unit, which counts the average on-the-job duration t(x, y) of personnel moving between the x-th job type and the y-th job type, and compares t(x, y) with the preset on-the-job duration G. When t(x, y) is lower than the preset on-the-job duration G, the adjustment process of the change state of each job type is optimized, and the preset mobility coefficient is optimized B'.

[0020] Furthermore, the position trend analysis module is also provided with a position trend analysis unit, which sets a different first offset real number i for the quantity state of the i-th position type, sets a different second offset real number i for the change state of the i-th position type, and calculates the trend index α(i) of the i-th position type based on the first offset real number i and each second offset real number i.

[0021] Further, the personnel feature analysis module includes a vector analysis unit, which performs word segmentation on personnel personal information, personnel work skill description and personnel work experience to obtain personal information phrases, work description phrases and work experience phrases, and performs data cleaning on the personal information phrases, work description phrases and work experience phrases;

[0022] The vector analysis unit performs vector assignment on the personal information phrases, job description phrases and work experience phrases after data cleaning.

[0023] Furthermore, the personnel feature analysis module further includes a personnel feature analysis unit, which analyzes personnel features according to the personal information vector phrase, the job description vector phrase and the work experience vector phrase;

[0024] The personnel feature analysis unit performs entity judgment on the words in the job description phrase and the work experience phrase, and the entity judgment results of the words in the job description phrase and the work experience phrase include entity words and non-entity words;

[0025] The personnel feature analysis unit uses the entity words as personnel description feature phrases;

[0026] The personnel feature analysis unit uses the personal information phrases and the personnel description feature phrases as personnel feature analysis results.

[0027] Furthermore, the feature matching module is used to calculate the compatibility γ(z) between the enterprise and the personnel according to the enterprise feature analysis results and the personnel feature analysis results, and sets γ(z)=(f1×L1+f2×L2) / Q; wherein f1 is the personal information weight, f2 is the job requirement description, f1+f2=1, L1 is the number of word matches between the personal information phrase and the enterprise recruitment information phrase, L2 is the number of word matches between the personnel description feature phrase and the enterprise description feature phrase, and Q is the total number of enterprise features.

[0028] Furthermore, the position recommendation module includes an enterprise position calculation unit, which is used to calculate the position recommendation coefficient η(z,i) of each enterprise according to the compatibility γ(z) between the personnel and each enterprise and the trend index α(i) of each position type;

[0029] The job recommendation module also includes an enterprise job recommendation unit, which sorts the recommendation coefficients η(z,i) of each enterprise job in descending order, and recommends jobs to the personnel according to the sorting results: if the job-seeking status of the personnel is in the employed state, the enterprise job recommendation unit does not recommend a job to the personnel; if the job-seeking status of the personnel is not in the employed state, the enterprise job recommendation unit selects the top 3 enterprise jobs in the sorting results as recommended jobs;

[0030] The enterprise position recommendation unit sends the recommended positions to the personnel.

[0031] Compared with the prior art, the beneficial effects of the present invention lie in that, by analyzing the changing status of each position type and the quantity status of each position type and calculating the trend index of each position type, the development trend of each position can be judged, high-quality position types can be recommended to personnel, and a high correlation between enterprises and personnel can be achieved by adapting personnel and enterprises. By recommending various occupational types within the enterprise, specific position recommendations can be provided to personnel, thereby improving the efficiency of talent market data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 This is a schematic diagram of the structure of the talent market data management system based on artificial intelligence in this embodiment.

[0034] Figure 2 Schematic diagram of the structure of the position trend analysis module of this embodiment.

[0035] Figure 3 Schematic diagram of the structure of the personnel feature analysis module of this embodiment.

[0036] Figure 4 This is a structural diagram of the job recommendation module in this embodiment. DETAILED DESCRIPTION

[0037] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the scope of protection of the present invention.

[0038] It should be noted that, although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0039] Specifically, the artificial intelligence-based talent market data management system described in this embodiment is applied to the talent market data management of an online Internet platform; the talent market is specifically a talent market in the form of online software; this implementation; It should be noted that the personnel information involved in this application (including but not limited to personnel registration information, personnel job-seeking status, enterprise registration information and position requirement information) are all information and data fully authorized by registered personnel, registered enterprises or all parties, and the collection, use and processing of relevant data need to comply with relevant national and regional laws, regulations and standards.

[0040] See also Figure 1 As shown, it is a structural diagram of the talent market data management system based on artificial intelligence described in this embodiment, including a personnel data collection module, which is used to collect personnel registration information and personnel job-seeking status; the personnel registration information includes personnel personal information, personnel work skill description, and personnel work experience; the personnel job-seeking status includes employed status and non-employed status.

[0041] Specifically, this embodiment does not specifically limit the method of obtaining personnel registration information and personnel job-seeking status. Technical personnel in this field can set it freely. It only needs to meet the requirements for obtaining personnel registration information and personnel job-seeking status. This embodiment obtains it by importing it from the talent market database.

[0042] Please continue reading Figure 1As shown, the system also includes an enterprise data collection module, which is used to collect enterprise registration information and position requirement information; the enterprise registration information includes enterprise recruitment information, enterprise recruitment job skills, and enterprise recruitment work experience; the position requirement information includes the number of requirements for each position type, the historical number of requirements for each position type, the number of personnel flows between each position type, and the length of service of personnel flows between each occupation type; the enterprise recruitment information is specifically personal information such as age and gender required by the enterprise, which corresponds to the personal information of the personnel.

[0043] Specifically, this embodiment does not specifically limit the method for obtaining enterprise registration information and position requirement information, and those skilled in the art can freely set it, and it only needs to meet the requirements for obtaining enterprise registration information and position requirement information, such as obtaining it through the talent market database.

[0044] Please continue reading Figure 1 As shown, the system includes a personnel feature analysis module, which is connected to the personnel data collection module, and the personnel feature analysis module is used to analyze personnel features according to personnel registration information.

[0045] Please continue reading Figure 1 As shown, the system includes a position trend analysis module, which is connected to the enterprise data collection module. The enterprise data collection module is used to analyze the trend of each position type according to position demand information.

[0046] See also Figure 2 As shown, the position trend analysis module includes a demand quantity analysis unit, which counts the demand quantity set S of each position type, and analyzes the quantity status of each position type according to the statistical result: if n(i)<N1, the demand quantity analysis unit determines that the quantity status of the position type is a low demand status; if N1≤n(i)<N2, the demand quantity analysis unit determines that the quantity status of the position type is a medium demand status; if n(i)≥N2, the demand quantity analysis unit determines that the quantity status of the position type is a high demand status;

[0047] Among them, S = [n(1), n(2), ..., n(N)], n(1) represents the demand quantity of the first position type, n(2) represents the demand quantity of the second position type, n(N) represents the demand quantity of the Nth position type, N is the number of position types, n(i) represents the demand quantity of the i-th position type, N1 is the first preset position demand quantity, and N2 is the second preset position demand quantity; the demand quantity analysis unit performs numerical judgment on the demand quantity of the position type to analyze the position demand status of each position type, thereby improving the accuracy of the quantity status analysis of each position type.

[0048] Specifically, this embodiment does not make any specific restrictions on the values ​​of the first preset job requirement number N1 and the second preset job requirement number N2. Technical personnel in this field can set them freely as long as the value requirements of the first preset job requirement number N1 and the second preset job requirement number N2 are met. This embodiment sorts the requirement quantity set S of each job type in descending order, and takes the requirement quantity of the job types with the sorting result being the top 70% as the first preset job requirement number N1, and takes the requirement quantity of the job types with the sorting result being the top 30% as the second preset job requirement number N2.

[0049] Please continue reading Figure 2 As shown, the position trend analysis module also includes a change state analysis unit, which is connected to the demand quantity analysis unit, and the change state analysis unit is used to calculate the change coefficient set V of each position type according to the demand quantity set S of each position type and the historical demand quantity set PS of each position type, and set V = [v(1), v(1), ..., v(N)], PS = [pn(1), pn(2), ..., pn(N)], v(1) = [n(1)-pn(1)] / pn(1), v(2) = [n(2)-pn(2)] / pn(2), ..., v(N) = [n(N)-pn(N)] / pn(N);

[0050] The change state analysis unit compares the change coefficient set V of each position type with each preset change coefficient, and analyzes the change state of each position type according to the comparison result: if μ1≤v(i)<μ2, the change state analysis unit determines that the change state of the position type is a stable change state; if v(i)<μ1, the change state analysis unit determines that the change state of the position type is a significantly reduced state; if v(i)≥μ2, the change state analysis unit determines that the change state of the position type is a significantly increased state; wherein μ1 is the first preset change coefficient, μ2 is the second preset change coefficient, μ1<μ2; the change state analysis unit calculates the change coefficient set of each position type to judge the change state of the position type, and then accurately analyzes the demand change trend of each position type, thereby improving the accuracy of the change state analysis of each position type.

[0051] Specifically, this embodiment does not impose any specific limitations on the values ​​of the first preset change coefficient μ1 and the second preset change coefficient μ2. Technical personnel in this field can set them freely as long as the value requirements of the first preset change coefficient μ1 and the second preset change coefficient μ2 are met. For example, the first preset change coefficient μ1 can be set to -0.3, and the second preset change coefficient μ2 can be set to 0.5.

[0052] Please continue reading Figure 2 As shown, the position trend analysis module is further provided with a position correlation analysis unit, which is connected to the change state analysis unit, and the position correlation analysis unit adjusts the change state analysis process of each position type according to the personnel flow quantity matrix between each position type;

[0053] The data format of the personnel flow matrix T between the positions is a square matrix with equal number of rows and columns, and the elements in the matrix are represented by a(x, y), where a(x, y) represents the element in the xth row and yth column, which in this embodiment means the number of personnel flowing from the xth position type to the jth position type;

[0054] The position correlation analysis unit calculates the mobility coefficient β(x,y) between the x-th position type and the j-th position type, and sets

[0055] Among them, a(x,i) represents the number of personnel moving from the xth position type to the ith position type, and a(y,x) represents the number of personnel moving from the yth position type to the xth position type;

[0056] The position association analysis unit compares β(x, y) with the preset mobility coefficient B, and adjusts the change state analysis process of each position type according to the comparison result. If β(x, y)<B, the position association analysis unit does not make any adjustment; if β(x, y)≥B, the position association analysis unit adjusts the first preset change coefficient to μ1', and sets μ1'=μ1×exp{[β(x, y)-B] / B}; the position association analysis unit analyzes the correlation between each position type to determine the numerical impact of the correlation between each position type on the position change, thereby improving the accuracy of the change state analysis of each position type.

[0057] Specifically, this embodiment does not impose any specific limitation on the value of the preset flow coefficient B, and those skilled in the art can freely set it as long as the value requirement of the preset flow coefficient B is met. For example, the preset flow coefficient B can be set to 0.1.

[0058] Please continue reading Figure 2 As shown, the position trend analysis module further includes an on-the-job analysis unit, which is connected to the position association analysis unit, and the on-the-job analysis unit optimizes the adjustment process of the change state of each position type according to the on-the-job duration of the mobile personnel between each occupation type;

[0059] The on-the-job analysis unit counts the average length of service t(x,y) of personnel moving between the xth occupational type and the yth occupational type, compares t(x,y) with the preset length of service G, and optimizes the adjustment process of the change status of each position type based on the comparison result: if t(x,y)<G, the on-the-job analysis unit optimizes the preset flow coefficient B', setting B'=B×ln{e-[Gt(x,y)] / G}; if t(x,y)≥G, no optimization is performed; wherein e is the natural logarithm; the on-the-job analysis unit performs a numerical analysis on the length of service of the number of people moving between each position type to determine the actual flow situation of each occupation type, thereby improving the accuracy of the analysis of the change status of each position type.

[0060] Specifically, this embodiment does not impose any specific limitation on the value of the preset duration of service G, and those skilled in the art may freely set it as long as the value requirement of the preset duration of service G is met. For example, the preset duration of service G may be set to 1 year.

[0061] Please continue reading Figure 2 As shown, the position trend analysis module is further provided with a position trend analysis unit, which is connected to the change state analysis unit and the demand quantity analysis unit, and the position trend analysis unit analyzes the trend index of each position type according to the quantity state analysis result of each position type and the change state analysis result of each position type;

[0062] The position trend analysis unit sets a different first offset real number i for the quantity status of the i-th position type, sets a different second offset real number i for the change status of the i-th position type, and calculates the trend index α(i) of the i-th position type based on the first offset real number i and each second offset real number i, and sets α(i) = first offset real number i × second offset real number i; the development trend of each position type is analyzed by the position trend analysis unit, thereby improving the accuracy of the trend index of each position type.

[0063] Specifically, the setting process of the first offset real number i in this embodiment is as follows: when the number status of the position type is a low demand state, the first offset real number i is set to a1, and a1=1+[n(i)-N1] / N1 is set; when the number status of the position type is a medium demand state, the first offset real number i is set to a2, and a2=1+[n(i)-N2] / N1 is set; when the number status of the position type is a high demand state, the first offset real number i is set to a3, and a3=2+[n(i)-N2] / N2 is set. ; The setting process of the second offset real number i in this embodiment is as follows: when the number status of position types is in a significantly decreasing state, the second offset real number i is set to b1, and b1 is set to 1+[v(i)-μ1] / μ1; when the number status of position types is in a steadily changing state, the second offset real number i is set to b2, and b2 is set to 1+[v(i)-μ2] / μ2; when the number status of position types is in a significantly increasing state, the second offset real number i is set to b3, and b3 is set to 2+[v(i)-μ2] / μ2.

[0064] Please continue reading Figure 1 As shown, the system further includes a personnel feature analysis module, which is connected to the personnel data collection module, and is used to analyze personnel features according to personnel registration information and job-seeking status.

[0065] See also Figure 3 As shown, the personnel feature analysis module includes a vector analysis unit, and the vector analysis unit is used to analyze the personnel feature vector according to the personnel registration information;

[0066] The vector analysis unit performs word segmentation on the personal information of the personnel, the description of the personnel's work skills and the personnel's work experience to obtain personal information phrases, work description phrases and work experience phrases, and performs data cleaning on the personal information phrases, work description phrases and work experience phrases;

[0067] The vector analysis unit performs vector assignment on the personal information phrases, job description phrases and work experience phrases after data cleaning to obtain personal information vector phrases, job description vector phrases and work experience vector phrases; the personal information vector phrases, job description vector phrases and work experience vector phrases are analyzed by the vector analysis unit to improve the accuracy of subsequent personnel feature analysis.

[0068] Specifically, the process of "assigning vectors to the personal information phrases, job description phrases and work experience phrases after data cleaning to obtain personal information vector phrases, job description vector phrases and work experience vector phrases" in this embodiment is specifically: assigning word vectors to the personal information phrases, job description phrases and work experience phrases through training word vector files, and the training method of the training word vector files is to input the personnel registration information into the skip-word model of Word2Vec to obtain the training word vector files; it is worth noting that if the moduli of all words in the training word vector files are sorted in descending order, there is a strict boundary between the moduli of entity words and non-entity words, that is, the moduli of entity words are strictly greater than the moduli of non-entity words.

[0069] Specifically, this embodiment does not describe in detail the process of "segmenting personnel personal information, personnel work skill descriptions, and personnel work experience". Those skilled in the art can obtain a stop word list through GitHub, and segment personnel personal information, personnel work skill descriptions, and personnel work experience based on a general word list and a Python word segmentation library; at the same time, the process of "cleaning data on personal information phrases, work description phrases, and work experience phrases" in this embodiment is to obtain a Chinese character resume filtering word list through GitHub, and clean up data on personal information phrases, work description phrases, and work experience phrases based on the Chinese character resume filtering word list.

[0070] Please continue reading Figure 3 As shown, the personnel feature analysis module also includes a personnel feature analysis unit, which analyzes personnel features according to the personal information vector phrase, the job description vector phrase and the work experience vector phrase;

[0071] The personnel feature analysis unit performs entity judgment on the words in the job description phrase and the work experience phrase: if |d(k)|<D, the personnel feature analysis unit determines that the word is a non-entity word; if |d(k)|≥D, the personnel feature analysis unit determines that the word is an entity word, wherein D is a preset entity vector modulus;

[0072] The personnel feature analysis unit uses the entity words as personnel description feature phrases;

[0073] The personnel feature analysis unit uses the personal information phrase and the personnel description feature phrase as the personnel feature analysis result; the personnel features are analyzed by the personnel feature analysis unit, thereby improving the accuracy of the personnel feature analysis.

[0074] Specifically, this embodiment does not impose any specific limitation on the value of the preset entity vector modulus D. Technical personnel in this field can set it freely as long as the value requirement of the preset entity vector modulus D is met. The value of the preset entity vector modulus D in this embodiment is directly related to the training word vector file obtained through training, and its value is the minimum value of the vector modulus of all entity words in the training word vector file.

[0075] Please continue reading Figure 1 As shown, the system further includes an enterprise feature analysis module, which is connected to the enterprise data collection module, and is used to analyze enterprise features according to enterprise registration information.

[0076] Specifically, the process of "analyzing enterprise characteristics based on enterprise registration information" in this embodiment is the same as the process of "analyzing personnel characteristics based on personnel registration information" mentioned above, and this embodiment will not be repeated here; the enterprise characteristics include enterprise recruitment information phrases and enterprise description feature phrases; the analysis process of the enterprise recruitment information phrases is the same as that of the personnel information phrases, and the analysis process of the enterprise description feature phrases is the same as that of the personnel description feature phrases.

[0077] Please continue reading Figure 1 As shown, the system includes a feature matching module, which is connected to the personnel feature analysis module and the position trend analysis module. The feature matching module is used to feature match the enterprise feature analysis results and the personnel feature analysis results, and calculate the compatibility γ(z) between the enterprise and the personnel according to the feature matching results, and set γ(z)=(f1×L1+f2×L2) / Q; wherein f1 is the personal information weight, f2 is the position requirement description, f1+f2=1, L1 is the number of word matches between the personal information phrase and the enterprise recruitment information phrase, L2 is the number of word matches between the personnel description feature phrase and the enterprise description feature phrase, and Q is the total number of enterprise features; the enterprise feature analysis results and the personnel feature analysis results are feature matched by the feature matching module, thereby improving the accuracy of the calculation of the compatibility between the enterprise and the personnel.

[0078] Specifically, the process of "feature matching the enterprise feature analysis results and the personnel feature analysis results" in this embodiment is to count the number of word matches L1 between the personal information phrases and the enterprise recruitment information phrases, and the number of word matches L2 between the personnel description feature phrases and the enterprise description feature phrases; the optimal values ​​of f1 and f2 in this embodiment are f1=0.6 and f2=0.4 respectively.

[0079] Please continue reading Figure 1As shown, the system includes a position recommendation module, which is connected to the feature matching module. The position recommendation module is used to recommend positions to personnel based on the recommendation coefficients of each position and the job-seeking status of the personnel.

[0080] See also Figure 4 As shown, the position recommendation module includes an enterprise position calculation unit, which is used to calculate the enterprise position recommendation coefficient η(z,i) of the i-th position type of the z-th enterprise according to the compatibility degree γ(z) between personnel and each enterprise and the trend index α(i) of each position type, and set η(z,i)=c1×γ(z)+c2×α(i);

[0081] Wherein, c1 is the enterprise weight, c2 is the occupation type weight, c1+c2=1; the enterprise position recommendation coefficient is calculated by the enterprise position calculation unit, thereby improving the accuracy of the enterprise position recommendation coefficient calculation.

[0082] It is worth noting that if the zth enterprise does not have a job demand for the i-th job type, then the enterprise job recommendation coefficient η(z,i) of the i-th job type of the zth enterprise is 0.

[0083] Specifically, this embodiment does not impose specific restrictions on the values ​​of the enterprise weight c1 and the occupation type weight c2. Technical personnel in this field can set them freely as long as the value requirements of the enterprise weight c1 and the occupation type weight c2 are met. In this embodiment, the optimal value of the enterprise weight c1 is 0.4, and the optimal value of the occupation type weight c2 is 0.6.

[0084] Please continue reading Figure 4 As shown, the position recommendation module also includes an enterprise position recommendation unit, which is connected to the enterprise position calculation unit and is used to recommend positions to personnel according to the recommendation coefficients of each position and the job-seeking status of the personnel;

[0085] The enterprise position recommendation unit sorts the enterprise position recommendation coefficients η(z,i) in descending order, and recommends positions to the personnel according to the sorting results: if the job-seeking status of the personnel is in the employed state, the enterprise position recommendation unit does not recommend a position to the personnel; if the job-seeking status of the personnel is not in the employed state, the enterprise position recommendation unit selects the top 3 enterprise positions in the sorting results as recommended positions;

[0086] The enterprise position recommendation unit sends the recommended positions to the personnel; the enterprise position recommendation unit analyzes the recommended positions, thereby improving the accuracy of the recommended position analysis and thus improving user satisfaction.

[0087] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A talent market data management system based on artificial intelligence, characterized in that: include: Personnel data collection module, used to collect personnel registration information and personnel job-seeking status; Enterprise data collection module, used to collect enterprise registration information and job demand information; The position trend analysis module is used to analyze the change status of each position type and the quantity status of each position type according to the position demand information, and calculate the trend index of each position type according to the change status analysis results and the quantity status analysis results of each position type; Personnel characteristics analysis module, used to analyze personnel characteristics based on personnel registration information; Enterprise characteristics analysis module, used to analyze enterprise characteristics based on enterprise registration information; Feature matching module, used to calculate the compatibility between enterprises and personnel based on the results of enterprise feature analysis and personnel feature analysis; The job recommendation module is used to calculate the recommendation coefficient of each job based on the calculation results of the compatibility between the enterprise and the personnel and the trend index calculation results of each job type, and to recommend jobs to personnel based on the recommendation coefficient of each job and the job-seeking status of the personnel, and to send the recommendation results to the personnel.

2. The talent market data management system based on artificial intelligence according to claim 1 is characterized in that: The position trend analysis module includes a demand quantity analysis unit, which counts the demand quantity set S of each position type and compares the statistical result with the preset position demand quantity to determine the quantity status of each position type, which includes a low demand state, a medium demand state and a high demand state.

3. The talent market data management system based on artificial intelligence according to claim 2 is characterized in that: The position trend analysis module further includes a change state analysis unit, which is used to calculate a change coefficient set V of each position type according to a demand quantity set S of each position type and a historical demand quantity set PS of each position type; The change state analysis unit compares the change coefficient set V of each position type with each preset change coefficient to determine the change state of each position type. The change state of each position type includes a stable change state, a significantly reduced state and a significantly increased state.

4. The talent market data management system based on artificial intelligence according to claim 3 is characterized in that: The position trend analysis module is further provided with a position correlation analysis unit, which adjusts the change status analysis process of each position type according to the personnel flow quantity matrix between each position type; The position association analysis unit calculates the mobility coefficient β(x,y) between the xth position type and the jth position type; The position association analysis unit compares β(x, y) with a preset flow coefficient B, and when β(x, y) exceeds the preset flow coefficient B, adjusts the first preset change coefficient to μ1′.

5. The talent market data management system based on artificial intelligence according to claim 4 is characterized in that: The job trend analysis module also includes an on-the-job analysis unit, which counts the average on-the-job duration t(x, y) of personnel moving between the x-th job type and the y-th job type, and compares t(x, y) with the preset on-the-job duration G. When t(x, y) is lower than the preset on-the-job duration G, the adjustment process of the change state of each job type is optimized, and the preset flow coefficient is optimized B'.

6. The talent market data management system based on artificial intelligence according to claim 5 is characterized in that: The position trend analysis module is also provided with a position trend analysis unit, which sets a different first offset real number i for the quantity status of the i-th position type, sets a different second offset real number i for the change status of the i-th position type, and calculates the trend index α(i) of the i-th position type based on the first offset real number i and each second offset real number i.

7. The talent market data management system based on artificial intelligence according to claim 6 is characterized in that: The personnel feature analysis module includes a vector analysis unit, which performs word segmentation on personnel personal information, personnel work skill description and personnel work experience to obtain personal information phrases, work description phrases and work experience phrases, and performs data cleaning on the personal information phrases, work description phrases and work experience phrases; The vector analysis unit performs vector assignment on the personal information phrases, job description phrases and work experience phrases after data cleaning.

8. The talent market data management system based on artificial intelligence according to claim 7 is characterized in that: The personnel feature analysis module further includes a personnel feature analysis unit, which analyzes personnel features according to the personal information vector phrase, the job description vector phrase and the work experience vector phrase; The personnel feature analysis unit performs entity judgment on the words in the job description phrase and the work experience phrase, and the entity judgment results of the words in the job description phrase and the work experience phrase include entity words and non-entity words; The personnel feature analysis unit uses the entity words as personnel description feature phrases; The personnel feature analysis unit uses the personal information phrases and the personnel description feature phrases as personnel feature analysis results.

9. The talent market data management system based on artificial intelligence according to claim 8 is characterized in that: The feature matching module is used to calculate the compatibility γ(z) between the enterprise and the personnel according to the enterprise feature analysis results and the personnel feature analysis results, and sets γ(z)=(f1×L1+f2×L2) / Q; wherein f1 is the personal information weight, f2 is the job requirement description, f1+f2=1, L1 is the number of word matches between the personal information phrase and the enterprise recruitment information phrase, L2 is the number of word matches between the personnel description feature phrase and the enterprise description feature phrase, and Q is the total number of enterprise features.

10. The talent market data management system based on artificial intelligence according to claim 9, characterized in that: The position recommendation module includes an enterprise position calculation unit, which is used to calculate the position recommendation coefficient η(z,i) of each enterprise according to the compatibility γ(z) between the personnel and each enterprise and the trend index α(i) of each position type; The job recommendation module further includes an enterprise job recommendation unit, which sorts the enterprise job recommendation coefficients η(z,i) in descending order and recommends jobs to the personnel according to the sorting result: if the job-seeking status of the personnel is in the employed status, the enterprise job recommendation unit does not recommend a job to the personnel; If the job-seeking status of the person is non-employed, the enterprise position recommendation unit selects the top 3 enterprise positions in the ranking results as recommended positions; The enterprise position recommendation unit sends the recommended positions to the personnel.

Images