Enterprise operation and maintenance resource dynamic scheduling system and method based on artificial intelligence

Abstract

The invention discloses an enterprise operation and maintenance resource dynamic scheduling system and method based on artificial intelligence, relates to the technical field of operation and maintenance resource scheduling, and discloses a project resource analysis module, a project resource distinguishing module and a project resource scheduling module. According to the method, the operation and maintenance resources of each project in an enterprise can be dynamically analyzed, comprehensive and detailed operation and maintenance resource analysis is performed on various types of operation and maintenance resources in each project, the operation and maintenance resource demand condition of each project is accurately judged, the projects are efficiently distinguished and processed, subsequent operation and maintenance resource scheduling between the projects is facilitated, and the operation and maintenance resource scheduling efficiency is improved. A project resource scheduling module is arranged, operation and maintenance resource scheduling can be preferentially carried out on projects with large operation and maintenance resource demands according to project demands, a demand project is matched with a plurality of satisfactory projects, and the optimal satisfactory project is selected through simulation of operation and maintenance resource scheduling to carry out operation and maintenance resource scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of operation and maintenance resource scheduling, and more specifically, to an enterprise operation and maintenance resource dynamic scheduling system and method based on artificial intelligence. Background Art

[0002] With the continuous improvement of the degree of enterprise informatization, the effective management and scheduling of operation and maintenance resources have become key factors in ensuring the continuity of enterprise business and improving operational efficiency. The traditional operation and maintenance resource scheduling method often relies on static resource allocation plans, that is, scheduling idle operation and maintenance resources in the enterprise to projects. This operation and maintenance resource scheduling method is prone to uneven distribution of operation and maintenance resources, project delays, cost overruns and other problems when the enterprise is carrying out multiple projects simultaneously and has no idle operation and maintenance resources. Therefore, how to conduct comprehensive and detailed resource analysis and dynamic resource scheduling under the condition that the enterprise has multiple projects at the same time and has no idle operation and maintenance resources is a problem that needs to be solved urgently. Summary of the invention

[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an enterprise operation and maintenance resource dynamic scheduling system and method based on artificial intelligence.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence, including project resource analysis module, project resource distinction module, and project resource scheduling module;

[0006] The project resource analysis module: obtains resource scheduling difference values ​​of each project in the enterprise per gigabyte of time;

[0007] The project resource distinction module: distinguishes the project into a demand project, a satisfied project or a maintained project based on the comparison result of the resource scheduling distinction value of the project with the resource scheduling distinction upper value and the resource scheduling distinction lower value;

[0008] The project resource scheduling module is used to sort the demand projects and schedule operation and maintenance resources for the demand projects in sequence.

[0009] Furthermore, the resource scheduling distinction value of the project is obtained in the following way: obtain the resource demand value of each operation and maintenance resource in the project, set the high resource demand value and the low resource demand value, when the resource demand value of the operation and maintenance resource is greater than or equal to the high resource demand value, mark the operation and maintenance resource as a demand resource, when the resource demand value of the operation and maintenance resource is less than or equal to the low resource demand value, mark the operation and maintenance resource as a satisfied resource, when the resource demand value of the operation and maintenance resource is between the high resource demand value and the low resource demand value, mark the operation and maintenance resource as a fuzzy resource, mark the total number of demand resources as FGcn, mark the total number of satisfied resources as SDpk, obtain the operation and maintenance resource map, match all fuzzy resources into a group, when two fuzzy resources in a group have a demand association in the operation and maintenance resource map, increase the associated demand quantity by one, mark the associated demand quantity as BAsd, and use the formula The resource scheduling difference value YXdz of the project is obtained, where ca is the demand resource coefficient, cb is the satisfied resource coefficient, and ce is the associated demand coefficient.

[0010] Furthermore, the resource demand value of the operation and maintenance resource is obtained in the following manner: obtain the refined resource category of the operation and maintenance resource, obtain the refined demand value EZj of each refined resource category, j=1, 2, ..., J, J is the total number of refined resource categories, set the refined demand coefficient to BGy, set the refined demand boundary value, when the refined demand value of the refined resource category is greater than or equal to the refined demand boundary value, mark the refined resource category as an over-demand resource category, when the refined demand value of the refined resource category is less than the refined demand boundary value, mark the refined resource category as a boundary resource category, match all boundary resource categories into a group, sum the refined demand values ​​of two boundary resource categories in a group to obtain the boundary demand overlap value, set the boundary demand overlap threshold value, when the boundary demand sum value is greater than or equal to the boundary demand overlap threshold value, increase the overlapped demand quantity by one, mark the overlapped demand quantity as CEs, mark the total number of over-demand resource categories as FCp, and use the formula The resource demand value Xqhp of the operation and maintenance resource is obtained, where vn is the superposition demand coefficient and vm is the excess resource coefficient.

[0011] Furthermore, the refined demand value of the refined resource category is obtained in the following manner: collecting the refined resource work data of the refined resource category within a period of g, obtaining the refined resource analysis model of the refined resource category in the project, preprocessing the refined resource work data, inputting the preprocessed refined resource work data into the refined resource analysis model of the refined resource category, and the refined resource analysis model outputs the refined demand value of the refined resource category.

[0012] Furthermore, based on the comparison results of the project's resource scheduling difference value with the resource scheduling difference upper value and the resource scheduling difference lower value, the project is divided into a demand project, a satisfied project or a maintained project, specifically: the resource scheduling difference upper value and the resource scheduling difference lower value are set, when the project's resource scheduling difference value is greater than or equal to the resource scheduling difference upper value, the project is marked as a demand project, when the project's resource scheduling difference value is less than or equal to the resource scheduling difference lower value, the project is marked as a satisfied project, and when the project's resource scheduling difference value is between the resource scheduling difference upper value and the resource scheduling difference lower value, the project is marked as a maintained project.

[0013] Furthermore, the demand items are sorted and operation and maintenance resources are scheduled for the demand items in order. Specifically, all demand items are sorted in descending order according to the numerical values ​​of resource scheduling distinction values, and operation and maintenance resources are scheduled for the demand item with the highest ranking. After the operation and maintenance resource scheduling is completed for the demand item with the highest ranking, operation and maintenance resources are scheduled for the demand item with the next highest ranking.

[0014] Furthermore, operation and maintenance resources are scheduled for the demand project that ranks first in the ranking, specifically: the demand project is matched with all satisfying projects in pairs into a group, and the reasonable resource scheduling value of each group is obtained. The satisfying project in the group with the largest reasonable resource scheduling value is marked as the target project, and the operation and maintenance resources of the target project are scheduled to the demand project.

[0015] Furthermore, reasonable resource scheduling values ​​are obtained in the following manner: obtaining current project data of the demand project and the satisfied project, setting target project data of the demand project, inputting the current project data of the demand project, the current project data of the satisfied project and the target project data of the demand project into the simulation software, building a resource scheduling model, performing i simulation scheduling on the resource scheduling model, obtaining the scheduling analysis value of each simulation scheduling, and marking the scheduling analysis value with the largest value as the reasonable resource scheduling value.

[0016] Furthermore, the scheduling analysis value of the simulation scheduling is obtained in the following way: when performing simulation scheduling, the total duration of the simulation scheduling is marked as Tim, and the resource scheduling difference value of the demand project and the resource scheduling difference value of the satisfied project are obtained for every k durations, the resource scheduling difference values ​​of the demand project are summed and averaged to obtain the demand scheduling mean SCr, the resource scheduling difference values ​​of the satisfied project are summed and averaged to obtain the satisfied scheduling mean MCr, and the formula is used The scheduling analysis value Rcw of this simulation scheduling is obtained, where pa is the duration coefficient, pb is the demand scheduling coefficient, and pc is the satisfaction scheduling coefficient.

[0017] Furthermore, the method for dynamic scheduling of enterprise operation and maintenance resources based on artificial intelligence includes the following steps:

[0018] Step 1: Regularly obtain resource scheduling difference values ​​of each project within the enterprise;

[0019] Step 2: Based on the comparison result of the resource scheduling difference value of the project with the resource scheduling difference upper value and the resource scheduling difference lower value, the project is classified into a demand project, a satisfying project or a maintaining project;

[0020] Step 3: Sort the demand items and schedule operation and maintenance resources for them in order.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. The method of the present invention can accurately determine the demand for operation and maintenance resources of each project, and can prioritize the operation and maintenance resource scheduling of projects with large demand for operation and maintenance resources according to project requirements, and ensure that operation and maintenance resources can be allocated to the projects that need them most and can bring the most benefits in the most reasonable way;

[0023] 2. Setting up the project resource analysis module and the project resource differentiation module can dynamically analyze the operation and maintenance resources of each project in the enterprise. By conducting a comprehensive and detailed operation and maintenance resource analysis of various types of operation and maintenance resources in each project, the projects can be efficiently differentiated to facilitate the subsequent operation and maintenance resource scheduling between projects. Setting up the project resource scheduling module can match the demand project with multiple satisfying projects, and select the best satisfying project through the simulation of operation and maintenance resource scheduling for operation and maintenance resource scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A method flow chart of a method for dynamic scheduling of enterprise operation and maintenance resources based on artificial intelligence;

[0025] Figure 2 A flowchart for scheduling operation and maintenance resources for demand projects in sequence;

[0026] Figure 3 This is a module diagram of the dynamic scheduling system for enterprise operation and maintenance resources based on artificial intelligence. DETAILED DESCRIPTION

[0027] Example 1: Reference Figure 1 ,The enterprise operation and maintenance resource dynamic scheduling method based on artificial intelligence includes the following steps:

[0028] Step 1: Regularly obtain the resource scheduling difference values ​​of each project within the enterprise.

[0029] Step 2: Based on the comparison result of the resource scheduling difference value of the project with the resource scheduling difference upper value and the resource scheduling difference lower value, the project is classified into a demand project, a satisfying project or a maintaining project.

[0030] Step 3: Sort the demand items and schedule operation and maintenance resources for them in order.

[0031] Through the above method, the operation and maintenance resource requirements of each project can be accurately determined, and operation and maintenance resource scheduling can be prioritized for projects with large operation and maintenance resource requirements based on project requirements, ensuring that operation and maintenance resources can be allocated in the most reasonable way to the projects that need them most and can bring the most benefits.

[0032] Example 2: Reference Figures 2 to 3 , an enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence, including project resource analysis module, project resource differentiation module, and project resource scheduling module.

[0033] Project resource analysis module: obtains resource scheduling difference values ​​of each project within the enterprise per gigabyte of time.

[0034] The resource scheduling distinction value of the project is obtained in the following way: obtain the resource demand value of each operation and maintenance resource in the project (the operation and promotion of the project involves various types of operation and maintenance resources, including but not limited to human resources, hardware resources, software resources, information resources, and security resources. A project needs to meet the requirements of various operation and maintenance resources before the project can be operated and promoted), set the high resource demand value and the low resource demand value (the high resource demand value is greater than the low resource demand value, and the high resource demand value and the low resource demand value are both system preset values, and the size is set according to demand). When the resource demand value of the operation and maintenance resource is greater than or equal to the high resource demand value, mark the operation and maintenance resource as a demand resource , when the resource demand value of the operation and maintenance resource is less than or equal to the low resource demand value, the operation and maintenance resource is marked as a satisfied resource. When the resource demand value of the operation and maintenance resource is between the high resource demand value and the low resource demand value, the operation and maintenance resource is marked as a fuzzy resource. The total number of demand resources is marked as FGcn, and the total number of satisfied resources is marked as SDpk. The operation and maintenance resource map is obtained, and all fuzzy resources are matched into a group. When two fuzzy resources in a group have a demand association in the operation and maintenance resource map, the number of associated demands is increased by one. When two fuzzy resources in a group do not have a demand association in the operation and maintenance resource map, no corresponding processing is performed, and the number of associated demands is marked as BAsd. Using the formula The resource scheduling difference value YXdz of the project is obtained, where ca is the demand resource coefficient, cb is the satisfied resource coefficient, ce is the associated demand coefficient, the value of ca is 1.62, the value of cb is 1.21, and the value of ce is 0.88.

[0035] The operation and maintenance resource map includes all types of operation and maintenance resources in the project, and graphically displays the demand relationship between different types of operation and maintenance resources. For example, the greater the demand for human resources, the greater the demand for hardware resources will be. In this case, there is a demand relationship between human resources and hardware resources in the operation and maintenance resource map. For example, the greater the demand for information resources, the greater the demand for security resources will not be. In this case, there is no demand relationship between information resources and security resources in the operation and maintenance resource map.

[0036] The resource demand value of the operation and maintenance resource is obtained in the following way: obtain the detailed resource category of the operation and maintenance resource (the operation and maintenance resource usually includes multiple categories of detailed resources. Taking hardware resources as an example, the categories of hardware resources include server categories, storage device categories, network device categories, etc. Taking human resources as an example, the categories of human resources include developer categories, tester categories, supervisory personnel categories, etc.), obtain the detailed demand value EZj of each detailed resource category, j=1, 2, ..., J, J is the total number of detailed resource categories, set the detailed demand coefficient to BGy, y=1, 2, 3, ...y; BG1<BG2<BG3<...<BGy, set each detailed demand coefficient to correspond to a detailed demand value range, including (0, EZ1], (EZ1, EZ2], ..., (EZj-1, EZj], when the detailed demand value EZj∈(0, EZ1], the detailed demand coefficient is BG1, set the detailed demand boundary value (the detailed demand boundary value is the system preset value, and the size is set according to the demand). When the detailed demand value of the detailed resource category is greater than or equal to the detailed demand boundary value, mark the detailed resource category as an over-demand resource category. When the detailed demand value of the detailed resource category is less than the detailed demand boundary value, mark the detailed resource category as a boundary resource category. Match all boundary resource categories into a group, sum the detailed demand values ​​of the two boundary resource categories in a group, and get the boundary demand overlap value. Set the boundary demand overlap threshold (the boundary demand overlap threshold is the system preset value, and the size is set according to the demand). When the boundary demand sum is greater than or equal to the boundary demand overlap threshold, increase the number of overlapped demands by one. When the boundary demand sum is less than the boundary demand overlap threshold, do not do the corresponding processing, mark the number of overlapped demands as CEs, and mark the total number of over-demand resource categories as FCp. Use the formula The resource demand value Xqhp of the operation and maintenance resource is obtained, where vn is the superposition demand coefficient, vm is the excess resource coefficient, the value of vn is 2.65, and the value of vm is 1.98.

[0037] The refined demand value of a refined resource category is obtained in the following manner: collecting the refined resource work data of the refined resource category within a time period of g (taking the server category as an example, that is, collecting the work data of the server in the project within a time period of g; taking the developer category as an example, that is, collecting the work data of the developers in the project within a time period of g), obtaining the refined resource analysis model of the refined resource category in the project, preprocessing the refined resource work data (the preprocessing method may be data cleaning or data formatting), inputting the preprocessed refined resource work data into the refined resource analysis model of the refined resource category, and the refined resource analysis model outputs the refined demand value of the refined resource category.

[0038] Different refined resource categories in the same project correspond to different refined resource analysis models. For example, the server category and the developer category in the project correspond to a refined resource analysis model respectively. Due to different project requirements, the same refined resource category in different projects also corresponds to different refined resource analysis models. For example, the server category of project a and project b corresponds to a refined resource analysis model respectively. Different refined resource analysis models use the same training method. The following will take the server category of project a as an example to disclose the training method of the refined resource analysis model: collect multiple refined resource work data of the server category in project a. The collected refined resource work data is virtually set according to the requirements of project a. Preprocess each refined resource work data and convert the preprocessed refined resource work data into a training set. According to the training data used as the deep learning model, a refined demand value is assigned to each training data. The value range of the refined demand value is (2-4). The larger the value of the refined demand value, the more difficult it is for the server in project a to meet the needs of project a. The smaller the value of the refined demand value, the easier it is for the server in project a to meet the needs of project a (if the training data is the developer category of project b, the larger the value of the refined demand value, the more difficult it is for the developers in project b to meet the needs of project b. The smaller the value of the refined demand value, the easier it is for the developers in project b to meet the needs of project b). The training data is divided into 60% training set and 40% validation set. The training set and the validation set are trained. After the training is completed, a refined resource analysis model of the server category of project a is obtained.

[0039] Project resource difference module: Set the upper and lower resource scheduling difference values ​​(both the upper and lower resource scheduling difference values ​​are system preset values, and the size is set according to demand). When the resource scheduling difference value of the project is greater than or equal to the upper resource scheduling difference value, the project is marked as a demand project. When the resource scheduling difference value of the project is less than or equal to the lower resource scheduling difference value, the project is marked as a satisfied project. When the resource scheduling difference value of the project is between the upper and lower resource scheduling difference values, the project is marked as a maintained project.

[0040] By setting up a project resource analysis module and a project resource differentiation module, you can dynamically analyze the operation and maintenance resources of each project in the enterprise. By conducting a comprehensive and detailed operation and maintenance resource analysis of various types of operation and maintenance resources in each project, you can accurately determine the operation and maintenance resource requirements of each project, efficiently differentiate and process projects, and facilitate subsequent operation and maintenance resource scheduling between projects.

[0041] Project resource scheduling module: sort all demand projects in descending order according to the resource scheduling distinction value, and schedule operation and maintenance resources for the demand project with the highest ranking. After completing the operation and maintenance resource scheduling for the demand project with the highest ranking, schedule operation and maintenance resources for the demand project with the next highest ranking.

[0042] The operation and maintenance resources are scheduled for the demand project that ranks first, specifically: the demand project is matched with all the satisfying projects in pairs into a group (for example, there are three satisfying projects in total, namely satisfying project a, satisfying project b and satisfying project c, then the demand project is matched with satisfying project a as a group, the demand project is matched with satisfying project b as a group, and the demand project is matched with satisfying project c as a group, for a total of three groups), the reasonable value of resource scheduling is obtained for each group, the satisfying project in the group with the largest reasonable value of resource scheduling is marked as the target project, and the operation and maintenance resources of the target project are scheduled to the demand project (the specific method of scheduling is not the focus of this application and will not be elaborated).

[0043] The reasonable value of resource scheduling is obtained in the following way: obtain the current project data of the demand project and the satisfied project (project data includes but is not limited to project time, resource quantity, resource capacity), set the target project data of the demand project, input the current project data of the demand project, the current project data of the satisfied project and the target project data of the demand project into the simulation software, build a resource scheduling model, perform i simulation scheduling on the resource scheduling model, obtain the scheduling analysis value of each simulation scheduling, and mark the scheduling analysis value with the largest value as the reasonable value of resource scheduling.

[0044] The scheduling analysis value of the simulation scheduling is obtained in the following way: when performing simulation scheduling, the total duration of the simulation scheduling is marked as Tim, and the resource scheduling difference value of the demand project and the resource scheduling difference value of the satisfied project are obtained for every k durations. The resource scheduling difference values ​​of the demand project are summed and averaged to obtain the demand scheduling mean SCr, and the resource scheduling difference values ​​of the satisfied project are summed and averaged to obtain the satisfied scheduling mean MCr. The formula is used The scheduling analysis value Rcw of this simulation scheduling is obtained, where pa is the duration coefficient, pb is the demand scheduling coefficient, pc is the satisfaction scheduling coefficient, the value of pa is 0.48, the value of pb is 0.59, and the value of pc is 0.57.

[0045] By setting up a project resource scheduling module, you can prioritize the operation and maintenance resource scheduling for projects with high demand for operation and maintenance resources according to project requirements, match the demand projects with multiple satisfying projects, and select the best satisfying project for operation and maintenance resource scheduling through operation and maintenance resource scheduling simulation, ensuring that operation and maintenance resources can be allocated to the projects that need them most and can bring the most benefits in the most reasonable way.

[0046] The above formulas are all dimensionless and numerical calculations are performed, and the preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0047] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0048] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0049] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0050] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0051] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0052] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0053] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence is characterized by: Including project resource analysis module, project resource distinction module, and project resource scheduling module; The project resource analysis module: obtains resource scheduling difference values ​​of each project in the enterprise per gigabyte of time; The project resource distinction module is used to distinguish a project into a demand project, a satisfied project or a maintained project based on a comparison result between the resource scheduling distinction value of the project and the upper resource scheduling distinction value and the lower resource scheduling distinction value; The project resource scheduling module is used to sort the demand projects and schedule operation and maintenance resources for the demand projects in sequence.

2. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 1 is characterized in that: The resource scheduling distinction value of the project is obtained in the following way: obtain the resource demand value of each operation and maintenance resource in the project, set the high resource demand value and the low resource demand value, when the resource demand value of the operation and maintenance resource is greater than or equal to the high resource demand value, mark the operation and maintenance resource as a demand resource, when the resource demand value of the operation and maintenance resource is less than or equal to the low resource demand value, mark the operation and maintenance resource as a satisfied resource, when the resource demand value of the operation and maintenance resource is between the high resource demand value and the low resource demand value, mark the operation and maintenance resource as a fuzzy resource, mark the total number of demand resources as FGcn, mark the total number of satisfied resources as SDpk, obtain the operation and maintenance resource map, match all fuzzy resources into a group, when two fuzzy resources in a group have a demand association in the operation and maintenance resource map, increase the associated demand quantity by one, mark the associated demand quantity as BAsd, and use the formula The resource scheduling difference value YXdz of the project is obtained, where ca is the demand resource coefficient, cb is the satisfied resource coefficient, and ce is the associated demand coefficient.

3. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 2 is characterized in that: The resource demand value of the operation and maintenance resource is obtained in the following way: obtain the detailed resource category of the operation and maintenance resource, obtain the detailed demand value EZj of each detailed resource category, j=1, 2, ..., J, J is the total number of detailed resource categories, set the detailed demand coefficient to BGy, set the detailed demand threshold value, when the detailed demand value of the detailed resource category is greater than or equal to the detailed demand threshold value, mark the detailed resource category as an over-demand resource category, when the detailed demand value of the detailed resource category is less than the detailed demand threshold value, mark the detailed resource category as a boundary resource category, match all boundary resource categories into a group, sum the detailed demand values ​​of two boundary resource categories in a group to obtain the boundary demand overlap value, set the boundary demand overlap threshold value, when the boundary demand sum value is greater than or equal to the boundary demand overlap threshold value, increase the overlap demand quantity by one, mark the overlap demand quantity as CEs, mark the total number of over-demand resource categories as FCp, and use the formula The resource demand value Xqhp of the operation and maintenance resource is obtained, where vn is the superposition demand coefficient and vm is the excess resource coefficient.

4. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 3 is characterized in that: The refined demand value of a refined resource category is obtained in the following manner: collecting the refined resource work data of the refined resource category within a time period of g, obtaining the refined resource analysis model of the refined resource category in the project, preprocessing the refined resource work data, inputting the preprocessed refined resource work data into the refined resource analysis model of the refined resource category, and the refined resource analysis model outputs the refined demand value of the refined resource category.

5. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 1 is characterized in that: Based on the comparison results of the project's resource scheduling difference value with the resource scheduling difference upper value and the resource scheduling difference lower value, the project is divided into a demand project, a satisfied project or a maintained project. Specifically, the resource scheduling difference upper value and the resource scheduling difference lower value are set. When the project's resource scheduling difference value is greater than or equal to the resource scheduling difference upper value, the project is marked as a demand project. When the project's resource scheduling difference value is less than or equal to the resource scheduling difference lower value, the project is marked as a satisfied project. When the project's resource scheduling difference value is between the resource scheduling difference upper value and the resource scheduling difference lower value, the project is marked as a maintained project.

6. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 1 is characterized in that: Sort the demand items and schedule operation and maintenance resources for them in order. Specifically, sort all demand items in descending order according to the resource scheduling distinction values, schedule operation and maintenance resources for the demand item that ranks first, and after completing the operation and maintenance resource scheduling for the demand item that ranks first, schedule operation and maintenance resources for the demand item that ranks next.

7. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 1 is characterized in that: Operation and maintenance resource scheduling is performed on the demand project that ranks first in the ranking. Specifically, the demand project is matched with all satisfying projects in pairs into a group, and the reasonable resource scheduling value of each group is obtained. The satisfying project in the group with the largest reasonable resource scheduling value is marked as the target project, and the operation and maintenance resources of the target project are scheduled to the demand project.

8. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 7 is characterized in that: The reasonable value of resource scheduling is obtained in the following way: obtain the current project data of the demand project and the satisfied project, set the target project data of the demand project, input the current project data of the demand project, the current project data of the satisfied project and the target project data of the demand project into the simulation software, build a resource scheduling model, perform i simulation scheduling on the resource scheduling model, obtain the scheduling analysis value of each simulation scheduling, and mark the scheduling analysis value with the largest value as the reasonable value of resource scheduling.

9. The enterprise operation and maintenance resource dynamic scheduling system based on artificial intelligence according to claim 8 is characterized in that: The scheduling analysis value of the simulation scheduling is obtained in the following way: when performing simulation scheduling, the total duration of the simulation scheduling is marked as Tim, and the resource scheduling difference value of the demand project and the resource scheduling difference value of the satisfied project are obtained every k durations. The resource scheduling difference values ​​of the demand project are summed and averaged to obtain the demand scheduling mean SCr, and the resource scheduling difference values ​​of the satisfied project are summed and averaged to obtain the satisfied scheduling mean MCr. The formula is used The scheduling analysis value Rcw of this simulation scheduling is obtained, where pa is the duration coefficient, pb is the demand scheduling coefficient, and pc is the satisfaction scheduling coefficient.

10. The method for dynamic scheduling of enterprise operation and maintenance resources based on artificial intelligence is applied to the dynamic scheduling system for enterprise operation and maintenance resources based on artificial intelligence as claimed in claim 1, characterized in that: The steps include: Step 1: Regularly obtain resource scheduling difference values ​​of each project within the enterprise; Step 2: Based on the comparison result of the resource scheduling difference value of the project with the resource scheduling difference upper value and the resource scheduling difference lower value, the project is classified into a demand project, a satisfying project or a maintaining project; Step 3: Sort the demand items and schedule operation and maintenance resources for them in order.

Images