A method and device for optimizing personnel position configuration based on network model

Abstract

The present invention discloses a personnel post optimization configuration method and device based on a network model, the method comprising: obtaining a post allocation history information set; the post allocation history information set comprises post requirement information and human resource description information; pre-processing the post allocation history information set to obtain a training information set; using the training information set, training a post optimization allocation model to obtain a trained post optimization allocation model; using the trained post optimization allocation model, processing the acquired post requirement information and human resource description information to obtain post allocation result information.

Description

Technical Field

[0001] The present invention relates to the fields of task allocation and artificial intelligence, and in particular to a personnel position optimization configuration method and device based on a network model. Background Art

[0002] In modern technology-intensive industries, efficient operation and task execution of the industrial chain are crucial. However, traditional personnel position allocation methods usually rely on manual experience and historical data, lack of systematic and intelligent analysis tools, resulting in many problems in actual operations. For example, due to insufficient understanding of the complexity of different tasks and actual working environments, it is often difficult to accurately allocate personnel, resulting in low efficiency in task execution. In addition, traditional allocation methods are difficult to respond quickly to task requirements and environmental changes, and cannot adjust personnel positions in real time, increasing the risk and cost of task execution.

[0003] In job allocation in technology-intensive industries, how to quickly respond to task requirements and environmental changes, adjust personnel positions in real time, reduce the risks and costs of task execution, and improve the efficiency and accuracy of job allocation is an issue that needs to be addressed urgently. Summary of the invention

[0004] The present invention mainly solves the problem of how to quickly respond to task requirements and environmental changes, adjust personnel positions in real time, reduce the risk and cost of task execution, and improve the efficiency and accuracy of position allocation in position allocation in technology-intensive industries. The present invention discloses a personnel position optimization configuration method and device based on a network model.

[0005] In a first aspect of the embodiment of the present application, a method for optimizing personnel positions based on a network model is disclosed, comprising:

[0006] S1, obtaining a set of historical information on job assignments; the set of historical information on job assignments includes job requirement information, human resource description information and job assignment information;

[0007] S2, preprocessing the job assignment history information set to obtain a training information set;

[0008] S3, using the training information set, training the job optimization allocation model to obtain a trained job optimization allocation model;

[0009] S4, using the trained job optimization allocation model, processing the acquired job requirement information and human resource description information to obtain job allocation result information.

[0010] The preprocessing of the job assignment history information set to obtain a training information set includes:

[0011] S21, performing outlier elimination processing on the job allocation history information set to obtain a first data set;

[0012] S22, performing boundary check processing on the first data set to obtain a training information set.

[0013] The performing boundary checking on the first data set to obtain a training information set includes:

[0014] S221, for each data attribute of the first data set, preset a corresponding value range; the value range includes an upper limit value of the value range and a lower limit value of the value range;

[0015] S222, for each data of each data attribute of the first data set, judging whether the value of the data is within the value range according to the value range of the data attribute; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data;

[0016] S223, after completing S222 for all data attributes, a training information set is obtained.

[0017] The performing boundary checking on the first data set to obtain a training information set includes:

[0018] S2201, for each type of data attribute of the first data set, using the data collection information of the data as an independent variable and the data value of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes of the class; using the regression model, perform calculation processing on the independent variable to obtain regression data values; determine whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the first data set; if it is less than the first regression discrimination threshold, do not process the data;

[0019] S2202, after completing S2201 for all data attributes, a training information set is obtained.

[0020] The job optimization allocation model includes: a job demand identification network, a human resource identification network and a job matching network;

[0021] The job requirement recognition network includes a first input module, a first convolution module, a depth-separable convolution module, a first dimensionality-increasing convolution module, a second dimensionality-increasing convolution module, a third dimensionality-increasing convolution module, a fourth dimensionality-increasing convolution module, a second convolution module, a first pooling module, a third convolution module and a first fully connected module;

[0022] The input end of the first input module of the job requirement identification network is used to receive the job requirement information; the output end of the first input module of the job requirement identification network is connected to the input end of the first convolution module of the job requirement identification network; the output end of the first convolution module of the job requirement identification network is connected to the input end of the depthwise separable convolution module of the job requirement identification network; the output end of the depthwise separable convolution module of the job requirement identification network is connected to the input end of the first dimensionality-raising convolution module of the job requirement identification network; the output end of the first dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the second dimensionality-raising convolution module of the job requirement identification network; the output end of the second dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the third dimensionality-raising convolution module of the job requirement identification network. connection; the output end of the third dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the fourth dimensionality-raising convolution module of the job requirement identification network; the output end of the fourth dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the second convolution module of the job requirement identification network; the output end of the second convolution module of the job requirement identification network is connected to the input end of the first pooling module of the job requirement identification network; the output end of the first pooling module of the job requirement identification network is connected to the input end of the third convolution module of the job requirement identification network; the output end of the third convolution module of the job requirement identification network is connected to the input end of the first fully connected module of the job requirement identification network; the output end of the first fully connected module of the job requirement identification network is used to output the job requirement identification information;

[0023] The human resource identification network includes a second input module, a fourth convolution module, a fifth convolution module, a sixth convolution module, a second pooling module, a seventh convolution module, a second fully connected module and a third fully connected module;

[0024] The input end of the second input module of the human resource identification network is used to receive the human resource description information; the output end of the second input module of the human resource identification network is connected to the input end of the fourth convolution module of the human resource identification network; the output end of the fourth convolution module of the human resource identification network is connected to the input end of the fifth convolution module of the human resource identification network; the output end of the fifth convolution module of the human resource identification network is connected to the input end of the sixth convolution module of the human resource identification network; the output end of the sixth convolution module of the human resource identification network is connected to the input end of the second pooling module of the human resource identification network; the output end of the second pooling module of the human resource identification network is connected to the input end of the seventh convolution module of the human resource identification network; the output end of the seventh convolution module of the human resource identification network is connected to the input end of the second fully connected module of the human resource identification network; the output end of the second fully connected module of the human resource identification network is connected to the input end of the third fully connected module of the human resource identification network; the output end of the third fully connected module of the human resource identification network is used to output the human resource identification information;

[0025] The job matching network includes an eighth convolution module, a ninth convolution module, a tenth convolution module, an eleventh convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module;

[0026] The input end of the eighth convolution module is connected to the output end of the first fully connected module of the job requirement identification network to receive the job requirement identification information. The output end of the eighth convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the tenth convolution module; the output end of the tenth convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module;

[0027] The input end of the ninth convolution module is connected to the output end of the third fully connected module of the human resource identification network, and is used to receive the human resource identification information. The output end of the ninth convolution module is respectively connected to the input end of the first fusion module and the input end of the third fusion module; the output end of the second fusion module is connected to the input end of the eleventh convolution module; the output end of the eleventh convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output the job allocation result information.

[0028] The training information set is used to train the job optimization allocation model to obtain a trained job optimization allocation model, including:

[0029] S301, initializing a first training number value;

[0030] S302, obtaining human resource description information from the training information set, and inputting the obtained human resource description information into a human resource identification network of a job optimization allocation model;

[0031] S303, inputting the job requirement information in the training information set into the job requirement identification network in the job optimization allocation model; determining the job allocation information corresponding to the human resource description information and the job requirement information input into the job optimization allocation model as label information;

[0032] S304, using the job optimization allocation model to process the input information to obtain predicted job allocation information;

[0033] S305, using a loss function to calculate the predicted job allocation information and label information to obtain a difference value;

[0034] S306, performing an accumulation operation on the first training times;

[0035] S307, determining whether the first training times value exceeds a preset first training times threshold, and obtaining a first determination result; when the first determination result is yes, executing S308;

[0036] When the first judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a second judgment result;

[0037] When the second judgment result is yes, execute S308; when the second judgment result is no, update the parameters of the job requirement identification network using the update model, and execute S303;

[0038] S308, initializing the second training times value;

[0039] S309, acquiring job requirement information from the training information set, and inputting the acquired job requirement information into a job requirement identification network of a job optimization allocation model;

[0040] S310, inputting the human resource description information in the training information set into the human resource identification network in the job optimization allocation model; determining the job allocation information corresponding to the job requirement information and the human resource description information input into the job optimization allocation model as label information;

[0041] S311, using the job optimization allocation model to process the input information to obtain predicted job allocation information;

[0042] S312, using a loss function to calculate the predicted job assignment information and label information to obtain a difference value;

[0043] S313, performing an accumulation operation on the second training times value;

[0044] S314, determining whether the second training times value exceeds a preset second training times threshold value, and obtaining a third determination result; when the third determination result is yes, completing the training process, and obtaining a trained job optimization allocation model;

[0045] When the third judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a fourth judgment result;

[0046] When the fourth judgment result is yes, the training process is completed to obtain a trained job optimization allocation model; when the fourth judgment result is no, the parameters of the human resource identification network and the job matching network are updated using the update model, and S310 is executed.

[0047] The update model is:

[0048]

[0049] θ←θ+v,

[0050] In the formula, is the difference value calculated after the i-th input information in the training information set is input into the job optimization allocation model, v is the parameter update value, θ is the parameter of the network that needs to be updated, η is the preset initial parameter learning rate, α is the preset momentum angle parameter, 0≤α≤π / 4, It means to find the partial derivative with respect to the variable θ.

[0051] In a second aspect of the embodiment of the present application, a device for optimizing personnel position configuration based on a network model is disclosed, the device comprising:

[0052] A memory storing executable program code;

[0053] a processor coupled to the memory;

[0054] The processor calls the executable program code stored in the memory to execute the personnel position optimization configuration method based on the network model.

[0055] In a third aspect of an embodiment of the present application, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the personnel position optimization configuration method based on the network model.

[0056] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the personnel position optimization configuration method based on the network model.

[0057] The beneficial effects of the present invention are:

[0058] The present invention can quickly respond to task requirements and environmental changes, adjust personnel positions in real time, reduce the risk and cost of task execution, and improve the efficiency and accuracy of position allocation. The present invention automatically generates the optimal personnel position deployment plan through an intelligent optimization model, greatly reduces manual intervention, and improves the efficiency and accuracy of task personnel deployment.

[0059] The present invention enhances the reliability of task execution. The present invention timely analyzes task requirement data and human resource data, adjusts personnel positions according to changes in job requirements, ensures the continuity and effectiveness of task execution, and reduces the risk of task failure.

[0060] The present invention optimizes the personnel post deployment, avoids personnel redundancy and resource waste, and reduces the overall cost of post operation. The present invention improves the emergency response capability of post operation, and the present invention can quickly respond to emergencies during task execution, thereby ensuring the safety of personnel and equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0062] In order to better understand the content of the present invention, an embodiment is given here.

[0063] Figure 1 It is a flow chart for implementing the method of the present invention.

[0064] The development of big data analysis and artificial intelligence technology has provided new possibilities for the intelligent optimization and deployment of personnel positions. Although data cannot be obtained in real time, relevant information of personnel in the process of performing tasks can be obtained through offline ferrying for subsequent analysis and optimization. This method realizes the closed loop of data collection and analysis under existing technical conditions, and improves the scientificity and effectiveness of personnel position deployment.

[0065] In order to quickly respond to task requirements and environmental changes, adjust personnel positions in real time, reduce the risk and cost of task execution, and improve the efficiency and accuracy of position allocation, the present invention discloses a personnel position optimization configuration method and device based on a network model.

[0066] In a first aspect of the embodiment of the present application, a method for optimizing personnel positions based on a network model is disclosed, comprising:

[0067] S1, obtain a set of historical information on job assignments; the set of historical information on job assignments includes job requirement information, human resource description information and job assignment information; in the set of historical information on job assignments, the job requirement information and human resource description information correspond to the job assignment information, and the job assignment information is used to indicate the personnel assigned to each job requirement.

[0068] S2, preprocessing the job assignment history information set to obtain a training information set;

[0069] S3, using the training information set, training the job optimization allocation model to obtain a trained job optimization allocation model;

[0070] S4, using the trained job optimization allocation model, processing the acquired job requirement information and human resource description information to obtain job allocation result information;

[0071] The preprocessing of the job assignment history information set to obtain a training information set includes:

[0072] S221, performing outlier elimination processing on the job allocation history information set to obtain a first data set;

[0073] S222: Perform boundary check processing on the first data set to obtain a training information set.

[0074] The performing boundary checking on the first data set to obtain a training information set includes:

[0075] S2221, for each data attribute of the first data set, preset a corresponding value range; the value range includes an upper limit value of the value range and a lower limit value of the value range;

[0076] S2222, for each data of each data attribute of the first data set, judging whether the value of the data is within the value range according to the value range of the data attribute; if the data is within the value range, not processing the data; if the data is not within the value range, setting the value of the data to the upper limit value or the lower limit value of the value range that is closest to the data;

[0077] S2223, after completing S2222 for all data attributes, a training information set is obtained.

[0078] The performing boundary checking on the first data set to obtain a training information set includes:

[0079] S2221, for each type of data attribute of the first data set, using the data collection information of the data as an independent variable and the data value of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes of the class; using the regression model, perform calculation processing on the independent variable to obtain regression data values; determine whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the first data set; if it is less than the first regression discrimination threshold, do not process the data;

[0080] S2222: After completing S2221 for all data attributes, a training information set is obtained.

[0081] The job optimization allocation model includes: a job demand identification network, a human resource identification network and a job matching network;

[0082] The job requirement recognition network includes a first input module, a first convolution module, a depth-separable convolution module, a first dimensionality-increasing convolution module, a second dimensionality-increasing convolution module, a third dimensionality-increasing convolution module, a fourth dimensionality-increasing convolution module, a second convolution module, a first pooling module, a third convolution module and a first fully connected module;

[0083] The input end of the first input module of the job requirement identification network is used to receive the job requirement information; the output end of the first input module of the job requirement identification network is connected to the input end of the first convolution module of the job requirement identification network; the output end of the first convolution module of the job requirement identification network is connected to the input end of the depthwise separable convolution module of the job requirement identification network; the output end of the depthwise separable convolution module of the job requirement identification network is connected to the input end of the first dimensionality-raising convolution module of the job requirement identification network; the output end of the first dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the second dimensionality-raising convolution module of the job requirement identification network; the output end of the second dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the third dimensionality-raising convolution module of the job requirement identification network. connection; the output end of the third dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the fourth dimensionality-raising convolution module of the job requirement identification network; the output end of the fourth dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the second convolution module of the job requirement identification network; the output end of the second convolution module of the job requirement identification network is connected to the input end of the first pooling module of the job requirement identification network; the output end of the first pooling module of the job requirement identification network is connected to the input end of the third convolution module of the job requirement identification network; the output end of the third convolution module of the job requirement identification network is connected to the input end of the first fully connected module of the job requirement identification network; the output end of the first fully connected module of the job requirement identification network is used to output the job requirement identification information;

[0084] The human resource identification network includes a second input module, a fourth convolution module, a fifth convolution module, a sixth convolution module, a second pooling module, a seventh convolution module, a second fully connected module and a third fully connected module;

[0085] The input end of the second input module of the human resource identification network is used to receive the human resource description information; the output end of the second input module of the human resource identification network is connected to the input end of the fourth convolution module of the human resource identification network; the output end of the fourth convolution module of the human resource identification network is connected to the input end of the fifth convolution module of the human resource identification network; the output end of the fifth convolution module of the human resource identification network is connected to the input end of the sixth convolution module of the human resource identification network; the output end of the sixth convolution module of the human resource identification network is connected to the input end of the second pooling module of the human resource identification network; the output end of the second pooling module of the human resource identification network is connected to the input end of the seventh convolution module of the human resource identification network; the output end of the seventh convolution module of the human resource identification network is connected to the input end of the second fully connected module of the human resource identification network; the output end of the second fully connected module of the human resource identification network is connected to the input end of the third fully connected module of the human resource identification network; the output end of the third fully connected module of the human resource identification network is used to output the human resource identification information;

[0086] The job matching network includes an eighth convolution module, a ninth convolution module, a tenth convolution module, an eleventh convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module;

[0087] The input end of the eighth convolution module is connected to the output end of the first fully connected module of the job requirement identification network, and is used to receive the job requirement identification information. The output end of the eighth convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the tenth convolution module; the output end of the tenth convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; the input end of the ninth convolution module is connected to the output end of the third fully connected module of the human resource identification network, and is used to receive the human resource identification information. The output end of the ninth convolution module is respectively connected to the input end of the first fusion module and the input end of the third fusion module; the output end of the second fusion module is connected to the input end of the eleventh convolution module; the output end of the eleventh convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output the job allocation result information.

[0088] The training information set is used to train the job optimization allocation model to obtain a trained job optimization allocation model, including:

[0089] S301, initializing a first training number value;

[0090] S302, obtaining human resource description information from the training information set, and inputting the obtained human resource description information into the human resource identification network of the job optimization allocation model; the obtained human resource description information remains unchanged in S301 to S307;

[0091] S303, inputting the job requirement information in the training information set into the job requirement identification network in the job optimization allocation model; determining the job allocation information corresponding to the human resource description information and the job requirement information input into the job optimization allocation model as label information; in each execution of S303, the job requirement information input into the job requirement identification network in the job optimization allocation model is different;

[0092] S304, using the job optimization allocation model to process the input information to obtain predicted job allocation information;

[0093] S305, using a loss function to calculate the predicted job allocation information and label information to obtain a difference value;

[0094] S306, performing an accumulation operation on the first training times;

[0095] S307, determining whether the first training times value exceeds a preset first training times threshold, and obtaining a first determination result; when the first determination result is yes, executing S308;

[0096] When the first judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a second judgment result;

[0097] When the second judgment result is yes, execute S308; when the second judgment result is no, update the parameters of the job requirement identification network using the update model, and execute S303;

[0098] S308, initializing the second training times value;

[0099] S309, obtaining job requirement information from the training information set, and inputting the obtained job requirement information into a job requirement identification network of a job optimization allocation model; the obtained job requirement information remains unchanged in S310 to S314;

[0100] S310, inputting the human resource description information in the training information set into the human resource identification network in the job optimization allocation model; determining the job allocation information corresponding to the job requirement information and the human resource description information input into the job optimization allocation model as label information; in each execution of S310, the human resource description information input into the human resource identification network in the job optimization allocation model is different;

[0101] S311, using the job optimization allocation model to process the input information to obtain predicted job allocation information;

[0102] S312, using a loss function to calculate the predicted job assignment information and label information to obtain a difference value;

[0103] S313, performing an accumulation operation on the second training times value;

[0104] S314, determining whether the second training times value exceeds a preset second training times threshold value, and obtaining a third determination result; when the third determination result is yes, completing the training process, and obtaining a trained job optimization allocation model;

[0105] When the third judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a fourth judgment result;

[0106] When the fourth judgment result is yes, the training process is completed to obtain a trained job optimization allocation model; when the fourth judgment result is no, the parameters of the human resource identification network and the job matching network are updated using the update model, and S310 is executed.

[0107] The update model is:

[0108]

[0109] θ←θ+v,

[0110] In the formula, is the difference value calculated after the i-th input information in the training information set is input into the job optimization allocation model, v is the parameter update value, θ is the parameter of the network that needs to be updated, η is the preset initial parameter learning rate, α is the preset momentum angle parameter, 0≤α≤π / 4, It represents the partial derivative of the variable θ. The i-th input information includes human resource description information and job requirement information.

[0111] The loss function may adopt a cross entropy loss function.

[0112] Whether the difference value satisfies the convergence condition refers to whether the difference value is less than a preset error threshold value; when the difference value is less than the preset error threshold value, it is judged that the difference value satisfies the convergence condition; when the difference value is greater than the preset error threshold value, it is judged that the difference value does not satisfy the convergence condition.

[0113] The autoregressive-moving average modeling can be implemented using the ARMA method;

[0114] The job requirement information includes the job requirement information in terms of various capability types; the human resource description information includes the evaluation values ​​of the personnel in terms of various capability types;

[0115] The outlier elimination includes filling missing values, smoothing noise data, smoothing or deleting outlier points; the smoothed noise data is first determined to obtain noise data, and then the noise data is smoothed according to the data before and after the noise data; the noise data is a value whose value is less than the detection sensitivity of the sensor of the observed data, or greater than the measurement upper limit of the sensor of the observed data. The outlier point can be determined by the Kalman filtering method. The filling value of the missing value can be determined by averaging the measured values ​​within a certain sampling interval before and after the missing value.

[0116] The capability types include electrical professional capability, electronic information professional capability, control professional capability, word processing capability, structural design capability, etc. The requirement information can be strong, medium, general, or weak; the evaluation value can be leading, excellent, proficient, general, understood, or not possessed;

[0117] The curve fitting of the curve to be approximated by the function approximation method may be performed by using the best consistent linear approximation method. The best consistent approximation polynomial f(Ix) is expressed as:

[0118] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0119] Where P1 is the order of the best consistent approximation polynomial f(Ix), α0, α1, α2, …, α P1 are the coefficients of the optimal consistent approximation polynomial f(Ix);

[0120] The data collection information includes time information, space information or capability type information corresponding to the data collection; when performing data fitting, any of the above information can be used as an independent variable, and the corresponding data value can be used as a dependent variable.

[0121] The dimension-raising convolution module can be implemented by using the dimension-raising convolution module in the ResNet network;

[0122] The pooling module can be implemented by using a maximum pooling operation.

[0123] The depthwise separable convolution module can be implemented by using the depthwise separable convolution module in the MobileNet network.

[0124] The fusion module is implemented by including N multi-head attention modules connected in series.

[0125] In a second aspect of the embodiment of the present application, a device for optimizing personnel position configuration based on a network model is disclosed, the device comprising:

[0126] A memory storing executable program code;

[0127] a processor coupled to the memory;

[0128] The processor calls the executable program code stored in the memory to execute the personnel position optimization configuration method based on the network model.

[0129] In a third aspect of an embodiment of the present application, a computer-storable medium is disclosed, wherein the computer-storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the personnel position optimization configuration method based on the network model.

[0130] In a fourth aspect of the embodiments of the present application, an information data processing terminal is disclosed, and the information data processing terminal is used to implement the personnel position optimization configuration method based on the network model.

[0131] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for optimizing personnel positions based on a network model, characterized in that: include: S1, obtaining a set of historical information on job assignments; the set of historical information on job assignments includes job requirement information, human resource description information and job assignment information; S2, preprocessing the job assignment history information set to obtain a training information set; S3, using the training information set, training the job optimization allocation model to obtain a trained job optimization allocation model; S4, using the trained job optimization allocation model, processing the acquired job requirement information and human resource description information to obtain job allocation result information; The preprocessing of the job assignment history information set to obtain a training information set includes: S21, performing outlier elimination processing on the job allocation history information set to obtain a first data set; S22, performing boundary check processing on the first data set to obtain a training information set; The performing boundary checking on the first data set to obtain a training information set includes: S2201, for each type of data attribute of the first data set, using the data collection information of the data as an independent variable and the data value of the data as a dependent variable, perform autoregression-sliding average modeling to obtain regression models of the data attributes of the class; using the regression model, perform calculation processing on the independent variable to obtain regression data values; determine whether the absolute value of the difference between the regression data value and the corresponding dependent variable value is greater than a set first regression discrimination threshold; if it is greater than the first regression discrimination threshold, delete the data from the first data set; if it is less than the first regression discrimination threshold, do not process the data; S2202, after completing S2201 for all data attributes, a training information set is obtained; The job optimization allocation model includes: a job demand identification network, a human resource identification network and a job matching network; The job requirement recognition network includes a first input module, a first convolution module, a depth-separable convolution module, a first dimensionality-increasing convolution module, a second dimensionality-increasing convolution module, a third dimensionality-increasing convolution module, a fourth dimensionality-increasing convolution module, a second convolution module, a first pooling module, a third convolution module and a first fully connected module; The input end of the first input module of the job requirement identification network is used to receive the job requirement information; the output end of the first input module of the job requirement identification network is connected to the input end of the first convolution module of the job requirement identification network; the output end of the first convolution module of the job requirement identification network is connected to the input end of the depthwise separable convolution module of the job requirement identification network; the output end of the depthwise separable convolution module of the job requirement identification network is connected to the input end of the first dimensionality-raising convolution module of the job requirement identification network; the output end of the first dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the second dimensionality-raising convolution module of the job requirement identification network; the output end of the second dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the third dimensionality-raising convolution module of the job requirement identification network. connection; the output end of the third dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the fourth dimensionality-raising convolution module of the job requirement identification network; the output end of the fourth dimensionality-raising convolution module of the job requirement identification network is connected to the input end of the second convolution module of the job requirement identification network; the output end of the second convolution module of the job requirement identification network is connected to the input end of the first pooling module of the job requirement identification network; the output end of the first pooling module of the job requirement identification network is connected to the input end of the third convolution module of the job requirement identification network; the output end of the third convolution module of the job requirement identification network is connected to the input end of the first fully connected module of the job requirement identification network; the output end of the first fully connected module of the job requirement identification network is used to output the job requirement identification information; The human resource identification network includes a second input module, a fourth convolution module, a fifth convolution module, a sixth convolution module, a second pooling module, a seventh convolution module, a second fully connected module and a third fully connected module; The input end of the second input module of the human resource identification network is used to receive the human resource description information; the output end of the second input module of the human resource identification network is connected to the input end of the fourth convolution module of the human resource identification network; the output end of the fourth convolution module of the human resource identification network is connected to the input end of the fifth convolution module of the human resource identification network; the output end of the fifth convolution module of the human resource identification network is connected to the input end of the sixth convolution module of the human resource identification network; the output end of the sixth convolution module of the human resource identification network is connected to the input end of the second pooling module of the human resource identification network; the output end of the second pooling module of the human resource identification network is connected to the input end of the seventh convolution module of the human resource identification network; the output end of the seventh convolution module of the human resource identification network is connected to the input end of the second fully connected module of the human resource identification network; the output end of the second fully connected module of the human resource identification network is connected to the input end of the third fully connected module of the human resource identification network; the output end of the third fully connected module of the human resource identification network is used to output the human resource identification information; The job matching network includes an eighth convolution module, a ninth convolution module, a tenth convolution module, an eleventh convolution module, a first fusion module, a second fusion module, a third fusion module, a first normalization module, a second normalization module, and a first activation module; The input end of the eighth convolution module is connected to the output end of the first fully connected module of the job requirement identification network to receive the job requirement identification information. The output end of the eighth convolution module is respectively connected to the input end of the first fusion module and the input end of the second fusion module; the output end of the first fusion module is connected to the input end of the tenth convolution module; the output end of the tenth convolution module is connected to the input end of the first normalization module; the output end of the first normalization module is connected to the input end of the third fusion module; The input end of the ninth convolution module is connected to the output end of the third fully connected module of the human resource identification network, and is used to receive the human resource identification information. The output end of the ninth convolution module is respectively connected to the input end of the first fusion module and the input end of the third fusion module; the output end of the second fusion module is connected to the input end of the eleventh convolution module; the output end of the eleventh convolution module is connected to the input end of the second normalization module; the output end of the second normalization module is connected to the input end of the third fusion module; the output end of the third fusion module is connected to the input end of the first activation module; the output end of the first activation module is used to output the job allocation result information; The training information set is used to train the job optimization allocation model to obtain a trained job optimization allocation model, including: S301, initializing a first training number value; S302, obtaining human resource description information from the training information set, and inputting the obtained human resource description information into a human resource identification network of a job optimization allocation model; S303, inputting the job requirement information in the training information set into the job requirement identification network in the job optimization allocation model; determining the job allocation information corresponding to the human resource description information and the job requirement information input into the job optimization allocation model as label information; S304, using the job optimization allocation model to process the input information to obtain predicted job allocation information; S305, using a loss function to calculate the predicted job allocation information and label information to obtain a difference value; S306, performing an accumulation operation on the first training times; S307, determining whether the first training times value exceeds a preset first training times threshold, and obtaining a first determination result; when the first determination result is yes, executing S308; When the first judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a second judgment result; When the second judgment result is yes, execute S308; when the second judgment result is no, update the parameters of the job requirement identification network using the update model, and execute S303; S308, initializing the second training number value; S309, acquiring job requirement information from the training information set, and inputting the acquired job requirement information into a job requirement identification network of a job optimization allocation model; S310, inputting the human resource description information in the training information set into the human resource identification network in the job optimization allocation model; determining the job allocation information corresponding to the job requirement information and the human resource description information input into the job optimization allocation model as label information; S311, using the job optimization allocation model to process the input information to obtain predicted job allocation information; S312, using a loss function to calculate the predicted job allocation information and label information to obtain a difference value; S313, performing an accumulation operation on the second training times value; S314, determining whether the second training times value exceeds a preset second training times threshold value, and obtaining a third determination result; when the third determination result is yes, completing the training process, and obtaining a trained job optimization allocation model; When the third judgment result is no, judging whether the difference value is less than a set convergence threshold, and obtaining a fourth judgment result; When the fourth judgment result is yes, the training process is completed to obtain a trained job optimization allocation model; when the fourth judgment result is no, the parameters of the human resource identification network and the job matching network are updated using the update model, and S310 is executed.

2. The method for optimizing personnel positions based on a network model as claimed in claim 1, characterized in that: The update model is: θ←θ+v, In the formula, is the difference value calculated after the i-th input information in the training information set is input into the job optimization allocation model, v is the parameter update value, θ is the parameter of the network that needs to be updated, η is the preset initial parameter learning rate, α is the preset momentum angle parameter, 0≤α≤π / 4, It means to find the partial derivative with respect to the variable θ.

3. A device for optimizing personnel positions based on a network model, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the personnel position optimization configuration method based on the network model as described in any one of claims 1 to 2.

4. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the personnel position optimization configuration method based on a network model as described in any one of claims 1 to 2.

5. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the personnel position optimization configuration method based on the network model as described in any one of claims 1 to 2.

Images