Factory digital intelligent management and control system and method based on big data

Abstract

The invention discloses a factory digital intelligent management and control system and method based on big data, relates to the technical field of factory management, and solves the problems that in the prior art, most people are trained and managed according to the same requirements, and the difference between the people is not considered, so that the training and management effects are poor, and the training efficiency is high. Therefore, the technical problem of low efficiency of the factory digital intelligent management and control system is solved. An employee ability portrait is generated according to employee data; generating a personalized training plan according to the employee ability portrait; providing personalized training activities for the employees according to the personalized training plan; calculating employee work indexes according to the employee ability portraits; alarm signals are generated according to the work indexes of the employees, indexes of the employees in the aspect of capability dimensions are quantitatively compared, personalized training plans are provided for the employees, the self development and the sense of belonging of the employees are improved, meanwhile, the overall quality and benefits of factories can be further enhanced, and the economic benefits of the factories are improved. And the efficiency of the digital intelligent management and control system is improved.

Description

Technical Field

[0001] The present application belongs to the field of factory management technology, and specifically is a factory digital intelligent management and control system and method based on big data. Background Art

[0002] Personnel training is a series of planned and organized learning activities conducted by an organization or enterprise to improve employee capabilities and promote individual and team development. It is an important support for enterprise development. Through scientific and reasonable training activities, the ability and quality of employees can be improved and the competitiveness of enterprises can be enhanced. The training content can include basic knowledge, professional knowledge training, safety training and management training. Personnel management and training are crucial in all walks of life in modern society.

[0003] In modern manufacturing, personnel management and training are crucial to improving product quality and production efficiency. The existing personnel training and management methods often adopt the same requirements for training and management for most people, without considering the differences between personnel. Different personnel may need targeted training methods, resulting in poor training and management effects, and in turn, low efficiency of factory digital intelligent management and control systems. Therefore, the factory digital intelligent management and control system still needs further improvement. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a factory digital intelligent management and control system and method based on big data, which is used to solve the technical problem that the prior art often adopts the same requirements for training and management of most people, lacks consideration of the differences between personnel, resulting in poor training and management effects, and further leads to low efficiency of the factory digital intelligent management and control system.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a factory digital intelligent management and control system based on big data, including: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0006] The data collection module is used to obtain employee data through data collection equipment;

[0007] The data analysis module: generates employee capability portraits based on employee data; generates personalized training plans based on employee capability portraits; calculates employee work indexes based on employee capability portraits; and generates alarm signals based on employee work indexes;

[0008] The control module provides personalized training activities for employees according to the personalized training plan;

[0009] The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

[0010] Through the above steps, this application uses employee data to build employee capability portraits, compares various employee indicators, and tailors training plans for them to meet their personalized development needs, enhance their sense of belonging and loyalty, improve overall production efficiency and product quality, and further improve the efficiency of the digital intelligent management and control system.

[0011] Furthermore, generating an employee capability profile based on employee data includes:

[0012] Obtaining employee ID, work performance data, skill level data, and training records from employee data, and performing data preprocessing operations on the employee data to obtain preprocessed work performance data, skill level data, and training records;

[0013] Define work ability dimensions, skill ability dimensions, and learning ability dimensions;

[0014] Calculate the corresponding work ability value, skill ability value and learning ability value based on work performance data, skill level data and training records;

[0015] Construct a capability profile matrix based on employee ID and its corresponding capability values;

[0016] Generate employee capability profiles based on the capability profile matrix.

[0017] Furthermore, the calculation of the corresponding work ability value, skill ability value and learning ability value based on the work performance data, skill level data and training records includes:

[0018] Obtain work performance data, skill level data and training records corresponding to the employee ID; the work performance data includes several items and their corresponding KPIs; the skill level data includes several skill test items and their corresponding test scores KF; the training records include several training scores PF;

[0019] Through the formula GNZ = ∑ j α j ×KPI j Calculate the work capacity value GNZ;

[0020] By formula Calculate the skill ability value JNZ;

[0021] By formula Calculate the learning ability value XNZ; where αj is the weight coefficient, αj∈(0,1), and max{} represents the maximum value.

[0022] Furthermore, the generation of a personalized training plan based on the employee capability profile includes:

[0023] Obtain several capability values ​​in the employee capability profile and their corresponding target capability values;

[0024] Generate training weights based on capability values ​​and target capability values;

[0025] Obtain employee capability profile, learning preferences, and work arrangements corresponding to employee ID;

[0026] The employee's ability profile, learning preference, work arrangement and several training weights are input into the personality recommendation model to obtain a personalized training plan; the personality recommendation model is constructed through an artificial intelligence model; the personalized training plan includes training time, training method, training content and training duration.

[0027] This application obtains personalized training plans for employees through the above steps, calculates the weights of corresponding training contents based on the ability dimensions of various aspects of employees, focuses on targeted training for ability dimensions that are significantly different from target requirements, and dynamically and adaptively allocates weights of training resources to different ability dimensions, thereby enhancing the flexibility and pertinence of the training plan.

[0028] Furthermore, the target capability value is calculated by the capability value corresponding to the user ID, including:

[0029] Get the last capability value SNZi, the current capability value DNZi and the last target capability value SMNZi corresponding to the user ID;

[0030] Determine whether DNZi is greater than SNZi;

[0031] Yes, by the formula NZZ i =DNZ i -SNZ i Calculate the capability growth value NZZi; determine whether SMNZi is less than SNZi; if yes, set DMNZi to the maximum value within its corresponding capability value range; if no, when the capability growth value is less than the growth threshold, set the current target capability value DMNZi = SMNZi; otherwise, when DNZi is less than the capability threshold NYi, set the current target capability value DMNZi = SMNZi; otherwise, by formula DMNZ i =SMNZ i ×(1+g×tan -1 (γ1×NZZ i +γ2×SNZ i )) Calculate the current target capability value DMNZi; where g is the proportional coefficient, g∈(0,π / 2); γ1 and γ2 are weight coefficients, γ1 and γ2∈(0,1);

[0032] No, let the current target capability value DMNZi=SMNZi.

[0033] This application updates the target competency values ​​through the above steps, has higher expectations for employees who have made great progress, adjusts their corresponding target competency values ​​accordingly, provides guarantees for the development of personalized training plans for them, and enhances employee motivation.

[0034] Furthermore, generating training weights according to the capability value and the target capability value includes:

[0035] Obtain several capability values ​​in the employee capability profile and their corresponding target capability values;

[0036] Determine whether the capability value is greater than or equal to the target capability value;

[0037] Yes, the training weight corresponding to the capability value is set to 0;

[0038] No, the ability difference NCr is obtained by performing a difference operation between the target ability value and its corresponding ability value; Calculate the training weights PQr.

[0039] Furthermore, the personalized recommendation model is constructed through an artificial intelligence model, including:

[0040] Obtain several historical employee capability profiles, learning preferences, work arrangements, training weights, and their corresponding personalized recommendation plans;

[0041] Divide several historical employee capability portraits, learning preferences, work arrangements, training weights and their corresponding personalized recommendation plans into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;

[0042] Select an AI model as the base model;

[0043] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0044] By verifying the pre-trained model on the test set, we finally obtained a personalized recommendation model whose input is employee ability profile, learning preference, work arrangement and training weight, and whose output is a personalized recommendation plan.

[0045] Furthermore, the calculation of the employee work index according to the employee capability portrait includes:

[0046] Obtain the work ability value GNZ, skill ability value JNZ and learning ability value XNZ in the employee ability profile;

[0047] The employee work index YGZ is calculated by the formula YGZ=β1×GNZ+β2×JNZ+β3×XNZ; wherein β1, β2 and β3 are weight coefficients, β1, β2 and β3∈(0,1).

[0048] Furthermore, generating an alarm signal according to the employee work index includes:

[0049] Obtain employee work index several times in a row;

[0050] When the employee's work index is less than the unemployment threshold for several consecutive times, an employee unemployment alarm signal is generated to remind the employee to resign;

[0051] Otherwise, when the employee work index is less than the job change threshold for several consecutive times, an employee job change alarm signal is generated, and the employee changes jobs according to the employee's wishes and factory needs, and the employee work index is obtained several times after the job change; when the employee work index is less than the job change threshold for several consecutive times, an employee unemployment alarm signal is generated to remind the employee to resign; otherwise, no operation is performed.

[0052] Another aspect of the present invention provides a factory digital intelligent management and control method based on big data, comprising:

[0053] S0: Get employee data;

[0054] S1: Generate employee capability profiles based on employee data;

[0055] S2: Generate personalized training plans based on employee capability profiles; provide personalized training activities for employees based on personalized training plans;

[0056] S3: Calculate employee work index based on employee capability profile; generate alarm signal based on employee work index;

[0057] S4: Provide prompts based on alarm signals and contact management.

[0058] Compared with the prior art, the beneficial effects of this application are:

[0059] 1. This application generates employee capability portraits based on employee data; generates personalized training plans based on employee capability portraits; provides personalized training activities for employees based on personalized training plans; calculates employee work indexes based on employee capability portraits; generates alarm signals based on employee work indexes, conducts quantitative comparison of indicators in various capability dimensions of employees, and provides personalized training plans for employees, thereby improving employees' own development and sense of belonging, while also further enhancing the overall quality and benefits of the factory and improving the efficiency of the digital intelligent management and control system.

[0060] 2. This application updates the current target capability value by obtaining the previous target capability value, adaptively adjusts the target capability value, and has higher expectations for employees who have made great progress. Therefore, their corresponding target capability values ​​are increased to better train the employees, and support is provided in the process of formulating personalized training plans for them, thereby enhancing their sense of belonging and improving their enthusiasm.

[0061] 3. This application calculates the corresponding training weights through the current ability value and the target ability value. The ability dimensions whose current ability values ​​exceed their corresponding target ability values ​​will not be included in this training plan. The training content will focus on the ability dimensions that have not met the requirements. The greater the gap between the ability dimensions and the target requirements, the higher the proportion of training content will be, making the training plan more targeted, thereby improving the efficiency of the training plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 This is a schematic diagram of the principle of the factory digital intelligent management and control system based on big data of this application;

[0064] Figure 2 A flow chart for generating an alarm signal for this application;

[0065] Figure 3 This is a flow chart of the factory digital intelligent management and control method based on big data in this application. DETAILED DESCRIPTION

[0066] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0067] See also Figure 1 , the first embodiment of the present application provides a factory digital intelligent management and control system based on big data, including: a data acquisition module, a data analysis module, a control module, an early warning module and a database;

[0068] Data collection module: obtain employee data through data collection equipment; data collection equipment includes various sensors, and employee data includes employee ID, work performance data, skill level data, training records, learning preferences and work arrangements, etc.;

[0069] Data analysis module: Generate employee capability portraits based on employee data. Employee capability portraits are data describing the various capability dimensions of employees; generate personalized training plans based on employee capability portraits. Personalized training plans are training plans with their own characteristics generated for each employee; calculate employee work index based on employee capability portraits. Employee work index refers to the coefficient of the employee's overall performance; generate alarm signals based on employee work index;

[0070] Control module: Provide personalized training activities for employees according to personalized training plans;

[0071] Early warning module: Prompts are given based on alarm signals and management personnel are contacted; alarm signals include employee unemployment alarm signals and employee job change alarm signals, etc.

[0072] Generating an employee capability profile based on employee data in this embodiment includes:

[0073] Obtaining employee ID, work performance data, skill level data, and training records from employee data, and performing data preprocessing operations on the employee data to obtain preprocessed work performance data, skill level data, and training records;

[0074] Define work ability dimensions, skill ability dimensions, and learning ability dimensions; ability dimensions are defined based on work performance data, skill level data, and training records;

[0075] Calculate the corresponding work ability value, skill ability value and learning ability value based on work performance data, skill level data and training records;

[0076] Construct a capability profile matrix based on employee ID and its corresponding capability values;

[0077] Generate employee capability profiles based on the capability profile matrix.

[0078] In this embodiment, the corresponding work ability value, skill ability value and learning ability value are calculated based on the work performance data, skill level data and training records, including:

[0079] Obtain work performance data, skill level data and training records corresponding to the employee ID; work performance data includes several items and their corresponding KPIs; skill level data includes several skill test items and their corresponding test scores KF; training records include several training scores PF; the training records in this embodiment can select the most recent two training scores or the most recent three training scores;

[0080] Through the formula GNZ = ∑ j α j ×KPI j Calculate the work capability value GNZ; the higher the KPI corresponding to a number of projects, the higher the work capability value will be;

[0081] By formula Calculate the skill ability value JNZ; the skill ability value increases as the skill test score increases;

[0082] By formula Calculate the learning ability value XNZ; the learning ability value increases with the increase of the training score; where αj is the weight coefficient, αj∈(0,1), the specific value is set according to experience, and max{} represents the maximum value.

[0083] In this embodiment, the personalized training plan is generated according to the employee capability profile, including:

[0084] Obtain several capability values ​​in the employee capability profile and their corresponding target capability values;

[0085] Generate training weights based on capability values ​​and target capability values;

[0086] Obtain employee capability profile, learning preferences, and work arrangements corresponding to employee ID;

[0087] The employee's ability profile, learning preference, work arrangement and several training weights are input into the personalized recommendation model to obtain a personalized training plan; the personalized recommendation model is constructed through an artificial intelligence model; the personalized training plan includes training time, training method, training content and training duration.

[0088] This embodiment obtains a personalized training plan by inputting employee capability profiles, learning preferences, work arrangements, and a number of training weights into a personalized recommendation model. Based on the various capability dimensions of employees, the weight ratios of various aspects in the training plan are generated according to the target capability values. Training is focused on capability dimensions that are significantly different from the target capability values. Weights are adaptively assigned to training plans for various capability dimensions, thereby improving the flexibility and targeting of the training plans.

[0089] In this embodiment, the target capability value is calculated by the capability value corresponding to the user ID, including:

[0090] Get the last capability value SNZi, the current capability value DNZi and the last target capability value SMNZi corresponding to the user ID;

[0091] Determine whether DNZi is greater than SNZi;

[0092] Yes, by the formula NZZ i =DNZ i -SNZ i Calculate the capability growth value NZZi. When SNZi is determined, the capability growth value increases with the increase of DNZi. Determine whether SMNZi is less than SNZi. If yes, set DMNZi to the maximum value within its corresponding capability value range. If no, when the capability growth value is less than the growth threshold, the growth threshold is set according to experience, and the current target capability value DMNZi = SMNZi. Otherwise, when DNZi is less than the capability threshold NYi, the capability threshold is set according to experience. Set the current target capability value DMNZi = SMNZi. Otherwise, by using the formula DMNZi i =SMNZ i ×(1+g×tan -1 (γ1×NZZ i +γ2×SNZ i )) Calculate the current target capability value DMNZi; where g is the proportional coefficient, g∈(0,π / 2); γ1 and γ2 are weight coefficients, γ1 and γ2∈(0,1), and the specific values ​​are set according to experience; when SMNZi is determined, the greater the capability growth value, the greater the employee's progress. At the same time, the greater the SMNZi, the greater the employee's progress on a high basis. Therefore, it is necessary to increase the corresponding current target capability value to achieve the goal of training employees to meet higher requirements; the last target capability value in this embodiment may be the initial target capability value, which is set according to experience;

[0093] No, let the current target capability value DMNZi=SMNZi.

[0094] In this embodiment, the training weight is generated according to the capability value and the target capability value, including:

[0095] Obtain several capability values ​​in the employee capability profile and their corresponding target capability values;

[0096] Determine whether the capability value is greater than or equal to the target capability value;

[0097] Yes, set the training weight corresponding to the capability value to 0;

[0098] No, the ability difference NCr is obtained by performing a difference operation between the target ability value and its corresponding ability value; Calculate the training weight PQr; when the r value range is fixed, the training weight PQr will increase as the ability difference NCr increases.

[0099] This embodiment calculates the ability value and the target ability value to obtain the corresponding training weight. If the ability value exceeds the corresponding target ability value, the training content related to this ability dimension will not be arranged in the current training plan. The focus will be on the training content of other ability dimensions that have not met the requirements, thereby improving the efficiency of the training plan.

[0100] The personalized recommendation model in this embodiment is constructed through an artificial intelligence model, including:

[0101] Obtain several historical employee capability profiles, learning preferences, work arrangements, training weights, and their corresponding personalized recommendation plans;

[0102] Several historical employee capability portraits, learning preferences, work arrangements, training weights and their corresponding personalized recommendation plans are divided into training data, verification data and test data; data preprocessing is performed on the training data, verification data and test data to obtain training sets, verification sets and test sets; the ratio between the training set, the test set and the verification set is 7:2:1;

[0103] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a recommendation algorithm model, etc.;

[0104] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;

[0105] By verifying the pre-trained model on the test set, we finally obtained a personalized recommendation model whose input is employee ability profile, learning preference, work arrangement and training weight, and whose output is a personalized recommendation plan.

[0106] Calculating the employee work index according to the employee capability portrait in this embodiment includes:

[0107] Obtain the work ability value GNZ, skill ability value JNZ and learning ability value XNZ in the employee ability profile;

[0108] The employee work index YGZ is calculated by the formula YGZ=β1×GNZ+β2×JNZ+β3×XNZ; wherein β1, β2 and β3 are weight coefficients, β1, β2 and β3∈(0,1), and the specific values ​​are set according to experience; in this embodiment, the weight coefficient β1 corresponding to the work ability value is set higher, and the weight coefficient β3 corresponding to the learning ability value is set lower, so β1>β2>β3; in other embodiments, it can be set to β1<β2<β3 and so on; the employee work index increases with the increase of GNZ, JNZ and XNZ.

[0109] See also Figure 2 In this embodiment, generating an alarm signal according to the employee work index includes:

[0110] The employee work index is obtained several times in succession; in this embodiment, the employee work index is obtained twice in succession;

[0111] Determine whether the employee's work index is less than the unemployment threshold for several consecutive times. The unemployment threshold is set based on experience. If it is, generate an employee unemployment alarm signal to remind the employee to resign.

[0112] No, it is determined whether the employee's work index is less than the job change threshold for several consecutive times. The job change threshold is set based on experience, and the job change threshold is greater than the unemployment threshold;

[0113] If yes, generate an employee job change alarm signal, change jobs according to employee wishes and factory needs, and obtain employee work index for several consecutive times after the job change; determine whether the employee work index is less than the job change threshold for several consecutive times; if yes, generate an employee unemployment alarm signal to remind the employee to resign; if no, do nothing;

[0114] No, do nothing.

[0115] Through the above steps, this embodiment conducts work evaluation for employees working in the first position. If the work fails to meet the requirements for several consecutive times, the employee will be persuaded to resign or transferred to another position. If the requirements are still not met after the transfer, the employee will be persuaded to resign, thereby ensuring the efficiency of each position in the factory and improving the factory's benefits.

[0116] See also Figure 3 Another aspect of the present application provides a factory digital intelligent management and control method based on big data, including:

[0117] S0: Get employee data;

[0118] S1: Generate employee capability profiles based on employee data;

[0119] S2: Generate personalized training plans based on employee capability profiles; provide personalized training activities for employees based on personalized training plans;

[0120] S3: Calculate employee work index based on employee capability profile; generate alarm signal based on employee work index;

[0121] S4: Provide prompts based on alarm signals and contact management.

[0122] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0123] The working principle of this application is as follows: by obtaining employee data, generating employee capability portraits based on employee data; generating personalized training plans based on employee capability portraits; providing personalized training activities for employees based on personalized training plans; calculating employee work indexes based on employee capability portraits; generating alarm signals based on employee work indexes; making prompts based on alarm signals and contacting management personnel to conduct quantitative comparisons of indicators in various capability dimensions of employees, and providing employees with personalized training plans, so that employees' own development and sense of belonging can be improved, while also further enhancing the overall quality and benefits of the factory, thereby improving the efficiency of the digital intelligent management and control system, and avoiding the problem that the existing technology often adopts the same requirements for training and management of most people, lacks consideration of the differences between personnel, resulting in poor training and management results, and further leading to the problem of low efficiency of the factory's digital intelligent management and control system.

[0124] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. The factory digital intelligent management and control system based on big data is characterized by: include: Data acquisition module, data analysis module, control module, early warning module and database; The data collection module is used to obtain employee data through data collection equipment; The data analysis module generates an employee capability profile based on employee data; generates a personalized training plan based on the employee capability profile; Calculate employee work index based on employee capability profile; generate alarm signal based on employee work index; The control module provides personalized training activities for employees according to the personalized training plan; The early warning module: makes prompts according to the alarm signal and contacts the management personnel.

2. According to the big data-based factory digital intelligent management and control system of claim 1, it is characterized in that: Generating employee capability portraits based on employee data includes: Obtaining employee ID, work performance data, skill level data, and training records from employee data, and performing data preprocessing operations on the employee data to obtain preprocessed work performance data, skill level data, and training records; Define work ability dimensions, skill ability dimensions, and learning ability dimensions; Calculate the corresponding work ability value, skill ability value and learning ability value based on work performance data, skill level data and training records; Construct a capability profile matrix based on employee ID and its corresponding capability values; Generate employee capability profiles based on the capability profile matrix.

3. According to the big data-based factory digital intelligent management and control system of claim 2, it is characterized in that: The calculation of the corresponding work ability value, skill ability value and learning ability value based on the work performance data, skill level data and training records includes: Obtain work performance data, skill level data and training records corresponding to the employee ID; the work performance data includes several items and their corresponding KPIs; the skill level data includes several skill test items and their corresponding test scores KF; the training records include several training scores PF; Through the formula GNZ = ∑ j α j ×KPI j Calculate the work capacity value GNZ; By formula Calculate the skill ability value JNZ; By formula Calculate the learning ability value XNZ; where αj is the weight coefficient, αj∈(0,1), and max{} represents the maximum value.

4. The factory digital intelligent management and control system based on big data according to claim 1 is characterized in that: The generation of a personalized training plan based on employee capability profiles includes: Obtain several capability values ​​in the employee capability profile and their corresponding target capability values; Generate training weights based on capability values ​​and target capability values; Obtain employee capability profile, learning preferences, and work arrangements corresponding to employee ID; The employee's ability profile, learning preference, work arrangement and several training weights are input into the personality recommendation model to obtain a personalized training plan; the personality recommendation model is constructed through an artificial intelligence model; the personalized training plan includes training time, training method, training content and training duration.

5. According to the big data-based factory digital intelligent management and control system of claim 4, it is characterized in that: The target capability value is calculated by the capability value corresponding to the user ID, including: Get the last capability value SNZi, the current capability value DNZi and the last target capability value SMNZi corresponding to the user ID; Determine whether DNZi is greater than SNZi; Yes, by the formula NZZ i =DNZ i -SNZ i Calculate the capability growth value NZZi; determine whether SMNZi is less than SNZi; if yes, set DMNZi to the maximum value within its corresponding capability value range; if no, when the capability growth value is less than the growth threshold, set the current target capability value DMNZi = SMNZi; otherwise, when DNZi is less than the capability threshold NYi, set the current target capability value DMNZi = SMNZi; otherwise, by formula DMNZ i =SMNZ i ×(1+g×tan -1 (γ1×NZZ i +γ2×SNZ i )) Calculate the current target capability value DMNZi; where g is the proportional coefficient, g∈(0,π / 2); γ1 and γ2 are weight coefficients, γ1 and γ2∈(0,1); No, let the current target capability value DMNZi=SMNZi.

6. The factory digital intelligent management and control system based on big data according to claim 4 is characterized in that: Generating the training weight according to the capability value and the target capability value includes: Obtain several capability values ​​in the employee capability profile and their corresponding target capability values; Determine whether the capability value is greater than or equal to the target capability value; Yes, the training weight corresponding to the capability value is set to 0; No, the ability difference NCr is obtained by performing a difference operation between the target ability value and its corresponding ability value; Calculate the training weights PQr.

7. The factory digital intelligent management and control system based on big data according to claim 4 is characterized in that: The personality recommendation model is constructed through an artificial intelligence model, including: Obtain several historical employee capability profiles, learning preferences, work arrangements, training weights, and their corresponding personalized recommendation plans; Divide several historical employee capability portraits, learning preferences, work arrangements, training weights and their corresponding personalized recommendation plans into training data, verification data and test data; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtained a personalized recommendation model whose input is employee ability profile, learning preference, work arrangement and training weight, and whose output is a personalized recommendation plan.

8. The factory digital intelligent management and control system based on big data according to claim 1 is characterized in that: The calculation of employee work index based on employee capability portrait includes: Obtain the work ability value GNZ, skill ability value JNZ and learning ability value XNZ in the employee ability profile; The employee work index YGZ is calculated by the formula YGZ=β1×GNZ+β2×JNZ+β3×XNZ; wherein β1, β2 and β3 are weight coefficients, β1, β2 and β3∈(0,1).

9. The factory digital intelligent management and control system based on big data according to claim 1 is characterized in that: The generating of an alarm signal according to the employee work index comprises: Obtain employee work index several times in a row; When the employee's work index is less than the unemployment threshold for several consecutive times, an employee unemployment alarm signal is generated to remind the employee to resign; Otherwise, when the employee work index is less than the job change threshold for several consecutive times, an employee job change alarm signal is generated, and the employee changes jobs according to the employee's wishes and factory needs, and the employee work index is obtained several times after the job change; when the employee work index is less than the job change threshold for several consecutive times, an employee unemployment alarm signal is generated to remind the employee to resign; otherwise, no operation is performed.

10. A factory digital intelligent management and control method based on big data, applied to a factory digital intelligent management and control system based on big data as claimed in any one of claims 1 to 9, characterized in that: include: S0: Get employee data; S1: Generate employee capability profiles based on employee data; S2: Generate personalized training plans based on employee capability profiles; Provide personalized training activities for employees according to personalized training plans; S3: Calculate employee work index based on employee capability profile; generate alarm signal based on employee work index; S4: Provide prompts based on alarm signals and contact management.

Images