CN114493027A - Future talent demand prediction method and system based on Markov model - Google Patents

Future talent demand prediction method and system based on Markov model Download PDF

Info

Publication number
CN114493027A
CN114493027A CN202210117560.XA CN202210117560A CN114493027A CN 114493027 A CN114493027 A CN 114493027A CN 202210117560 A CN202210117560 A CN 202210117560A CN 114493027 A CN114493027 A CN 114493027A
Authority
CN
China
Prior art keywords
talent
data
sequence
markov model
model
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.)
Pending
Application number
CN202210117560.XA
Other languages
Chinese (zh)
Inventor
杜登伟
杜登斌
杜乐
杜小军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Donghu Big Data Trading Center Co ltd
Original Assignee
Wuhan Donghu Big Data Trading Center Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Donghu Big Data Trading Center Co ltd filed Critical Wuhan Donghu Big Data Trading Center Co ltd
Priority to CN202210117560.XA priority Critical patent/CN114493027A/en
Publication of CN114493027A publication Critical patent/CN114493027A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Development Economics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Computation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a future talent demand prediction method and a system based on a Markov model, wherein the method comprises the following steps: acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in an industrial park in a preset stage; calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence; establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model; and acquiring the future career unit, the occupation type and the forecast year to be forecasted in the industrial park, taking the future career unit, the occupation type and the forecast year as forecast data, and inputting the forecast data into the talent demand forecasting model to obtain a forecast result. The invention realizes accurate prediction of future talent demands of various positions in each enterprise and public institution in the industrial park through the gray-Markov model.

Description

Future talent demand prediction method and system based on Markov model
Technical Field
The invention relates to the technical field of data processing, in particular to a future talent demand prediction method and system based on a Markov model.
Background
The essence of scientific and technological competition and economic competition is talent competition, human resources are important conditions for survival and development of enterprises and public institutions in industrial parks, are special economic resources, are active production elements in the production process, and have decisive influence on economic development of industrial parks. However, most of the human resource forecasting of governments, organizations and enterprises at present still stay in the experience management stage, and scientific theories and methods are not guided. How to reasonably allocate various positions in each enterprise and public institution in the industrial park according to the flowing condition of talents depends on whether the effective method can be utilized to predict the human resource supply and demand of each enterprise and public institution, and the talents are reasonably planned and introduced.
The prior art future talent prediction method can only reflect the requirements of various industries in the market on talents generally, but cannot reflect the requirements of various positions in various enterprises and public institutions in an industrial park specifically, and the prior art prediction method is limited to the application of a single mathematical model, so that the prediction result is inaccurate.
Disclosure of Invention
In view of this, the present application provides a method and a system for predicting future talent demand based on a markov model, which are used to solve the problem that the prior art cannot accurately predict the future talent demand of various positions in each enterprise and public institution in an industrial park.
The technical scheme of the invention is realized as follows:
the invention provides a future talent demand prediction method and a system based on a Markov model, wherein the method comprises the following steps:
s1, acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in the industrial park in a preset stage;
s2, calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence;
s3, establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model;
and S4, acquiring the enterprise and public institution, occupation type and forecast year to be forecasted in the future in the industrial park, taking the types and the forecast year as forecast data, and inputting the forecast data into the talent demand forecasting model to obtain a forecast result.
On the basis of the above technical solution, preferably, step S1 specifically includes:
the talent distribution data specifically comprises high-level management personnel, decision-making personnel, operation management personnel and technical personnel of various professions in each enterprise and public institution in an industrial park in a preset stage;
the talent flow data specifically comprises the staff members entering, leaving, rising, falling, stopping and changing staff members of various vocabularies in each enterprise and public institution in the industrial park in the preset stage.
Based on the above technical solution, preferably, in step S2, the talent change data specifically includes:
talent transfer data, talent immigration data and talent emigration data of various occupations in each enterprise and public institution in the industrial park in a preset stage.
Based on the above technical solution, preferably, in step S2, the talent change data as an original sequence specifically includes:
the method comprises the steps of respectively giving weights to talent transfer data, talent immigration data and talent emigration data in a preset stage for various occupations in enterprises and public institutions in an industrial park, then conducting data weighting processing to obtain final data, and combining the final data into an original sequence from small to large.
On the basis of the above technical solution, preferably, step S3 specifically includes:
establishing a gray GM (1,1) model, inputting an original sequence into the gray GM (1,1) model to obtain a predicted sequence, and calculating a residual sequence of the predicted sequence and the original sequence;
and establishing a Markov model, inputting the residual sequence into the Markov model for correction, and obtaining a corrected prediction sequence.
On the basis of the above technical solution, preferably, the specific steps of establishing a gray GM (1,1) model, inputting the original sequence into the gray GM (1,1) model to obtain a predicted sequence, and calculating a residual sequence between the predicted sequence and the original sequence include:
the original sequence is denoted X(0)＝{x(0)(1),x(0)(2),…,x(0)(n), where n is the total number of data in the original sequence, x(0)(t)∈X(0)，t＝1,2,…,n；
Inputting the original sequence into the established gray GM (1,1) model to obtain a predicted sequence
Figure BDA0003497082660000031
The calculation formula for calculating the residual sequence E ═ E (1), E (2), …, E (n) }, E (t) ∈ E, t ═ 1,2, …, n, E (t) between the predicted sequence and the original sequence is as follows:
Figure BDA0003497082660000032
on the basis of the above technical solution, preferably, the specific steps of establishing a markov model, inputting the residual sequence into the markov model for correction, and obtaining a corrected prediction sequence include:
averagely dividing the residual sequence into r states to obtain a state interval wi＝[Pi,Qi]，i＝1,2,…r，PiAnd QiThe expression of (a) is:
Figure BDA0003497082660000041
Figure BDA0003497082660000042
establishing a state transition probability matrix according to the state interval, wherein the expression is as follows:
Figure BDA0003497082660000043
wherein the content of the first and second substances,
Figure BDA0003497082660000044
fijrepresenting the number of transitions from state i to state j, FiRepresents the total number of states i;
the median value of each state interval is taken as the predicted value, i.e.
Figure BDA0003497082660000045
Calculating the predicted value of the future state, wherein the calculation formula is as follows:
Figure BDA0003497082660000046
wherein t is 1,2, …, n, i is 1,2, … r, di(t) a row vector representing the ith row of the state transition probability matrix for the tth data;
the predicted values of all future states form a modified prediction sequence
Figure BDA0003497082660000047
Based on the above technical solution, preferably, step S3 further includes:
the accuracy of the gray-Markov model is detected by adopting a posterior difference detection method, the ratio of the mean square error of an original sequence to the mean square error of a residual sequence is taken as a variance ratio, a small error probability is calculated according to a posterior difference formula, a first threshold value and a second threshold value are set, the prediction accuracy is achieved when the small error probability is larger than the first threshold value and the variance ratio is smaller than the second threshold value, and the gray-Markov model achieving the prediction accuracy is taken as a talent demand prediction model.
On the basis of the above technical solution, it is preferable that step S4 is followed by further including:
comparing the current talent demand of enterprises and public institutions and occupation types needing to be predicted in the future in the industrial park with the prediction result, and formulating a reasonable talent introduction strategy according to the comparison result.
The invention also provides a future talent demand prediction system based on the Markov model, which comprises the following steps:
the data acquisition module is used for acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in an industrial park in a preset stage;
the data processing module is used for calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence;
the model establishing module is used for establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model;
and the prediction module is used for acquiring the enterprise and public institution, the occupation type and the prediction time period which need to be predicted in the future in the industrial park, and inputting the prediction data into the talent demand prediction model to obtain a prediction result.
Compared with the prior art, the future talent demand prediction method and system based on the Markov model have the following beneficial effects:
(1) a gray-Markov model is established based on human resource data of various professions in each enterprise and public institution in the industrial park at the present stage, talent demand conditions of various professions in each enterprise and public institution in the industrial park in the future are predicted, scientific talent culture plans can be purposefully formulated for various professions in each enterprise and public institution in the industrial park, and progress of talent introduction work is promoted.
(2) And correcting the residual error of the traditional gray GM (1,1) model by using the Markov model, reflecting the accuracy of the gray-Markov model by using a posterior error test method, establishing a talent demand prediction model with higher accuracy, and ensuring the stability and reliability of future talent demand prediction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating a future talent demand prediction method based on a Markov model according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a future talent demand prediction system based on a markov model according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, a method for predicting the demand of future talents based on a markov model according to an embodiment of the present invention includes:
and S1, acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in the industrial park in a preset stage.
It should be understood that the talent distribution data specifically includes high-level managers, decision-making personnel, operation managers and technicians of various occupations in each enterprise and public institution in the industrial park in a preset stage; the talent flow data specifically comprises the staff members entering, leaving, rising, falling, stopping and changing staff members of various vocabularies in each enterprise and public institution in the industrial park in the preset stage.
In this embodiment, the talent distribution data includes data of high-level managers, decision makers, operation managers, and technicians, and the technicians include data of recruiters, financers, law enforcement officers, planning and construction staff, and the like. The specific data is set according to various practical situations of profession in each enterprise and public institution in the industrial park, and is not limited herein.
And S2, calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence.
It should be understood that the talent change data specifically includes talent movement data, talent immigration data, and talent immigration data of various vocations in each enterprise and public institution in the industrial park at a preset stage.
The method comprises the steps of respectively giving weights to talent transfer data, talent immigration data and talent emigration data in a preset stage for various occupations in enterprises and public institutions in an industrial park, then conducting data weighting processing to obtain final data, and combining the final data into an original sequence from small to large.
It should be understood that the weight of each item of data is determined according to the proportion of the item in the whole data, and the detailed calculation method of the final data is the sum of the weights of each item of data multiplied by the item of data.
And S3, establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model.
Specifically, a gray GM (1,1) model is established, the original sequence is input into the gray GM (1,1) model to obtain a predicted sequence, and a residual sequence between the predicted sequence and the original sequence is calculated; and establishing a Markov model, inputting the residual sequence into the Markov model for correction, and obtaining a corrected prediction sequence.
Further, establishing a gray GM (1,1) model, inputting the original sequence into the gray GM (1,1) model to obtain a predicted sequence, and calculating a residual sequence between the predicted sequence and the original sequence, including:
the original sequence is denoted X(0)＝{x(0)(1),x(0)(2),…,x(0)(n), where n is the total number of data in the original sequence, x(0)(t)∈X(0)，t＝1,2,…,n；
Inputting the original sequence into the established gray GM (1,1) model to obtain a predicted sequence
Figure BDA0003497082660000081
It should be understood that an accumulation calculation is performed on the original sequence to obtain a new data sequence X(1)＝{x(1)(1),x(1)(2),…,x(1)(n), wherein,
Figure BDA0003497082660000082
obtaining a data matrix B and a data matrix Y according to the original sequence and the new data sequencenThe expression is as follows:
Figure BDA0003497082660000083
based on data matrix B and data matrix YnObtaining a predicted sequence according to a least squares method
Figure BDA0003497082660000084
The least squares method is prior art and will not be described herein.
The calculation formula for calculating the residual sequence E ═ E (1), E (2), …, E (n) }, E (t) ∈ E, t ═ 1,2, …, n, E (t) between the predicted sequence and the original sequence is as follows:
Figure BDA0003497082660000085
it is to be understood that the gray prediction model has the characteristics of less data and high short-term prediction accuracy, the Markov model is suitable for prediction problems with high randomness and volatility, and the Markov model are combined to complement advantages and be suitable for future talent demand prediction of various positions in each enterprise and public institution in an industrial park.
Further, the specific steps of establishing a markov model, inputting the residual sequence into the markov model for correction to obtain a corrected prediction sequence include:
averagely dividing the residual sequence into r states to obtain a state interval wi＝[Pi,Qi]，i＝1,2,…r，PiAnd QiThe expression of (a) is:
Figure BDA0003497082660000091
Figure BDA0003497082660000092
establishing a state transition probability matrix according to the state interval, wherein the expression is as follows:
Figure BDA0003497082660000093
wherein the content of the first and second substances,
Figure BDA0003497082660000094
fijrepresenting the number of transitions from state i to state j, FiRepresents the total number of states i;
it should be understood that the above-described embodiments,
Figure BDA0003497082660000095
r (alpha) is an indicator function of 0-1 defining the existence of a condition, and when alpha is true, R (alpha) is 0, and when alpha is false, R (alpha) is 1.
The median value of each state interval is taken as the predicted value, i.e.
Figure BDA0003497082660000096
And calculating the predicted value of the future state, wherein the calculation formula is as follows:
Figure BDA0003497082660000097
wherein t is 1,2, …, n, i is 1,2, … r, di(t) a row vector representing the ith row of the state transition probability matrix for the tth data;
the predicted values of all future states form a modified prediction sequence
Figure BDA0003497082660000098
The accuracy of the gray-Markov model is detected by adopting a posterior difference detection method, the ratio of the mean square error of an original sequence to the mean square error of a residual sequence is taken as a variance ratio, a small error probability is calculated according to a posterior difference formula, a first threshold value and a second threshold value are set, the prediction accuracy is achieved when the small error probability is larger than the first threshold value and the variance ratio is smaller than the second threshold value, and the gray-Markov model achieving the prediction accuracy is taken as a talent demand prediction model.
It should be understood that, in the future, the obtained talent demand prediction model is more accurate, the accuracy of the gray-markov model obtained by training is calculated by using a posterior difference test method, and the posterior difference formula is the prior art and is not described herein again. The prediction precision grade of the posterior difference inspection method is divided into the following rules that when the small error probability is less than 0.70 and the variance ratio is more than 0.65, the prediction precision grade is unqualified; when the small error probability is more than 0.70 and the variance ratio is less than 0.65, the prediction precision level is marginal; when the small error probability is more than 0.80 and the variance ratio is less than 0.50, the prediction precision is qualified; when the small error probability is greater than 0.95 and the variance ratio is less than 0.35, the prediction accuracy is "good". In the present embodiment, the first threshold value is set to 0.95, the second threshold value is set to 0.35, and when the small error probability is greater than 0.95 and the variance ratio is less than 0.35, the prediction accuracy level of the gray-markov model is "good".
And S4, acquiring the enterprise and public institution, occupation type and forecast year to be forecasted in the future in the industrial park, taking the types and the forecast year as forecast data, and inputting the forecast data into the talent demand forecasting model to obtain a forecast result.
Furthermore, the current talent demand of enterprises and public institutions and occupation types needing to be predicted in the future in the industrial park is compared with the prediction result, and a reasonable talent introduction strategy is formulated according to the comparison result.
In a specific embodiment of the invention, the talent demand in the future five years of all the vocational categories of all the enterprise units and the public institutions in the industrial park is predicted, the prediction result is displayed in a line drawing mode according to the names and the vocational categories of the enterprises and the public institutions, the change of the talent demand in the future five years of each vocational category in each enterprise and the public institutions can be visually seen, and a feasible talent introduction plan and a talent culture scheme are formulated according to demand analysis and have reference value.
As shown in fig. 2, the embodiment of the present invention further provides a future talent demand prediction system based on a markov model, which includes a data acquisition module 10, a data processing module 20, a model building module 30, and a prediction module 40:
the data acquisition module 10 is used for acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in an industrial park in a preset stage;
the data processing module 20 is used for calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence;
the model establishing module 30 is used for establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model;
and the prediction module 40 is used for acquiring the enterprise and public institution, the occupation type and the prediction time period which need to be predicted in the future in the industrial park as prediction data, and inputting the prediction data into the talent demand prediction model to obtain a prediction result.
It can be understood that the future talent demand prediction system based on the markov model provided in the embodiments of the present invention corresponds to the future talent demand prediction method based on the markov model provided in the foregoing embodiments, and details thereof are not repeated herein.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that are within the spirit and principle of the present invention are intended to be included in the scope of the present invention.

Claims (10)

1. A markov model based future talent demand prediction method, the method comprising:
s1, acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in the industrial park in a preset stage;
s2, calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence;
s3, establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model;
and S4, acquiring the enterprise and public institution, occupation type and forecast year to be forecasted in the future in the industrial park, taking the types and the forecast year as forecast data, and inputting the forecast data into the talent demand forecasting model to obtain a forecast result.
2. The markov model-based future talent demand prediction method of claim 1, wherein step S1 specifically comprises:
the talent distribution data specifically comprises high-level management personnel, decision-making personnel, operation management personnel and technical personnel of various professions in each enterprise and public institution in an industrial park in a preset stage;
the talent flow data specifically comprises the staff members entering, leaving, rising, falling, stopping and changing staff members of various vocabularies in each enterprise and public institution in the industrial park in the preset stage.
3. The method for predicting talent demand based on markov model as claimed in claim 1, wherein in step S2, the talent variation data specifically includes:
talent transfer data, talent immigration data and talent emigration data of various occupations in each enterprise and public institution in the industrial park in a preset stage.
4. The method for predicting talent demand based on markov model as claimed in claim 2, wherein the step S2 of using the talent variation data as the original sequence specifically comprises:
the method comprises the steps of respectively giving weights to talent transfer data, talent immigration data and talent emigration data in a preset stage for various occupations in enterprises and public institutions in an industrial park, then conducting data weighting processing to obtain final data, and combining the final data into an original sequence from small to large.
5. The markov model-based future talent demand prediction method of claim 1, wherein step S3 specifically comprises:
establishing a gray GM (1,1) model, inputting an original sequence into the gray GM (1,1) model to obtain a predicted sequence, and calculating a residual sequence of the predicted sequence and the original sequence;
and establishing a Markov model, inputting the residual sequence into the Markov model for correction, and obtaining a corrected prediction sequence.
6. The method of claim 5, wherein the method for predicting the requirement of future talents based on the Markov model comprises the steps of establishing a gray GM (1,1) model, inputting an original sequence into the gray GM (1,1) model to obtain a predicted sequence, and calculating a residual sequence between the predicted sequence and the original sequence, wherein the step of calculating the residual sequence comprises:
the original sequence is denoted X(0)＝{x(0)(1),x(0)(2),…,x(0)(n), where n is the total number of data in the original sequence，x(0)(t)∈X(0)，t＝1,2,…,n；
Inputting the original sequence into the established gray GM (1,1) model to obtain a predicted sequence
Figure FDA0003497082650000021
The calculation formula for calculating the residual sequence E ═ E (1), E (2), …, E (n) }, E (t) ∈ E, t ═ 1,2, …, n, E (t) between the predicted sequence and the original sequence is as follows:
Figure FDA0003497082650000022
7. the markov model-based future talent demand prediction method of claim 6, wherein the step of building a markov model and inputting the residual sequence into the markov model for modification to obtain a modified prediction sequence comprises:
averagely dividing the residual sequence into r states to obtain a state interval wi＝[Pi,Qi]，i＝1,2,…r，PiAnd QiThe expression of (a) is:
Figure FDA0003497082650000031
Figure FDA0003497082650000032
and establishing a state transition probability matrix according to the state interval, wherein the expression is as follows:
Figure FDA0003497082650000033
wherein the content of the first and second substances,
Figure FDA0003497082650000034
fijrepresenting the number of transitions from state i to state j, FiRepresents the total number of states i;
the median value of each state interval is taken as the predicted value, i.e.
Figure FDA0003497082650000035
Calculating the predicted value of the future state, wherein the calculation formula is as follows:
Figure FDA0003497082650000036
wherein t is 1,2, …, n, i is 1,2, … r, di(t) a row vector representing the ith row of the state transition probability matrix for the tth data;
the predicted values of all future states form a modified prediction sequence
Figure FDA0003497082650000037
8. The markov model-based future talent demand prediction method of claim 5, wherein step S3 further comprises:
the accuracy of the gray-Markov model is detected by adopting a posterior difference detection method, the ratio of the mean square error of an original sequence to the mean square error of a residual sequence is taken as a variance ratio, a small error probability is calculated according to a posterior difference formula, a first threshold value and a second threshold value are set, the prediction accuracy is achieved when the small error probability is larger than the first threshold value and the variance ratio is smaller than the second threshold value, and the gray-Markov model achieving the prediction accuracy is taken as a talent demand prediction model.
9. The markov model-based future talent demand prediction method of claim 1, further comprising, after step S4:
comparing the current talent demand of enterprises and public institutions and occupation types needing to be predicted in the future in the industrial park with the prediction result, and formulating a reasonable talent introduction strategy according to the comparison result.
10. A markov model based future talent demand prediction system, the system comprising:
the data acquisition module is used for acquiring talent distribution data and talent flow data of various vocabularies in each enterprise and public institution in an industrial park in a preset stage;
the data processing module is used for calculating talent change data of various vocabularies in each enterprise and public institution in a preset stage according to the talent distribution data and the talent flow data, and taking the talent change data as an original sequence;
the model establishing module is used for establishing a gray-Markov model, inputting the original sequence into the gray-Markov model for repeated training to obtain a talent demand prediction model;
and the prediction module is used for acquiring the enterprise and public institution, the occupation type and the prediction time period which need to be predicted in the future in the industrial park, and inputting the prediction data into the talent demand prediction model to obtain a prediction result.
CN202210117560.XA 2022-02-08 2022-02-08 Future talent demand prediction method and system based on Markov model Pending CN114493027A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210117560.XA CN114493027A (en) 2022-02-08 2022-02-08 Future talent demand prediction method and system based on Markov model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210117560.XA CN114493027A (en) 2022-02-08 2022-02-08 Future talent demand prediction method and system based on Markov model

Publications (1)

Publication Number Publication Date
CN114493027A true CN114493027A (en) 2022-05-13

Family

ID=81478338

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210117560.XA Pending CN114493027A (en) 2022-02-08 2022-02-08 Future talent demand prediction method and system based on Markov model

Country Status (1)

Country Link
CN (1) CN114493027A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116110237A (en) * 2023-04-11 2023-05-12 成都智元汇信息技术股份有限公司 Signal lamp control method, device and medium based on gray Markov chain

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116110237A (en) * 2023-04-11 2023-05-12 成都智元汇信息技术股份有限公司 Signal lamp control method, device and medium based on gray Markov chain

Similar Documents

Publication Publication Date Title
Chen et al. A multi-objective model for multi-project scheduling and multi-skilled staff assignment for IT product development considering competency evolution
Law Room occupancy rate forecasting: a neural network approach
Trivedi et al. The Impact of Artificial Intelligence Integration on Minimizing Patient Wait Time in Hospitals
Tyukhtenko et al. Economic and mathematic models for staff planning at enterprises of all ownership forms
CN116307928A (en) Object supervision management system
CN111738778B (en) User portrait generation method and device, computer equipment and storage medium
CN114493027A (en) Future talent demand prediction method and system based on Markov model
CN108122046A (en) A kind of venture company's performance Forecasting Methodology based on Intelligent data analysis
Li [Retracted] The Use of Machine Learning Model in the Evaluation of College Students’ Employment and Entrepreneurship Level
CN115860562A (en) Software workload rationality evaluation method, device and equipment
CN109544337A (en) A kind of equity estimation method
Zhang et al. Prediction of the Development Scale of Vocational Education Using Markov Algorithm and Countermeasures
Bogdanova et al. Valuating the position of the control object based on a universal complex indicator using structured and unstructured data
Akhmetov et al. Developing and customizing university business intelligence cloud
Brattin et al. A neural network solution for forecasting labor demand of drop-in peer tutoring centers with long planning horizons
Rahajeng et al. Decision Support for New Employee Admissions With Profile Matching And Electre Methods
Faizal et al. Classification of Students Based on Academic Ability Using Profile Matching and Linear Interpolation Weighting
Khmyrov et al. Modern actual problems and prospects of financing of distance learning of personnel of Ukrainian companies on the basis of higher educational institutions
CN111221971B (en) Batch task expert automatic selection method based on scientific and technological vocabulary entries
Amponsah An integrated approach for prioritising road projects for implementation using AHP
GururamaSenthilvel et al. Artificial Intelligence enabled Employee Performance Prediction using Comprehensive Learning Metrics
CN113642834B (en) Task importance evaluation method and system based on task attribute priority mapping
Huu Information Systems In International Human Resource Management (Ihrm)-An Overview.
Amenaghawon et al. Markov manpower planning models: a review
US20230121647A1 (en) Machine learning-enabled system for analyzing immigration petitions

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