CN118691331B - A digital enterprise service resource management system and method based on industry support - Google Patents

Abstract

The invention relates to the technical field of resource management, and discloses a digital enterprise service resource management system and method based on industry support. According to the method, a sample set is constructed by collecting historical service resource data supported by industry and historical demand data corresponding to a digital enterprise, the accuracy of the collected service resource data and demand data is guaranteed in a mode of preprocessing the historical service resource data supported by industry and the historical demand data corresponding to the digital enterprise in the constructed sample set, meanwhile, a resource decision model is built in a data analysis processing mode, the built resource decision model is trained in a particle swarm optimization algorithm, a trained resource decision model is obtained, and finally, the efficiency and the accuracy of service resource management are improved through the trained resource decision model.

Description

A digital enterprise service resource management system and method based on industry support

Technical Field

The present invention relates to the technical field of resource management, and in particular to a digital enterprise service resource management system and method based on industry support.

Background Art

With the development of the economy, users' requirements for service resource management are increasing day by day. However, as the demand for resources continues to increase, the matching management of service resources is becoming more and more difficult. A business system with more personalized needs is needed to provide enterprise services.

The existing Chinese patent application CN118052528A, this method sets a talent resume unit through the talent management module in the system, collects resume data sets in real time, and generates talent label data groups through classification by label classification units to complete the classification of talents. At the same time, the enterprise management module is used to collect position data sets and classify them to generate demand label data groups, and the positions are batch classified and marked through unified labels. At the same time, the resource matching module matches resumes and positions according to the number of labels, and calculates and generates matching sets to complete the management of resources. However, since resources are managed only through resource matching, the detailed analysis of resources is ignored, which has certain limitations.

Summary of the invention

1. Technical issues to be resolved

In view of the deficiencies in the prior art, the present invention provides a digital enterprise service resource management system and method based on industry support, which has the advantages of high efficiency, real-time and accuracy, and solves the problem that the matching management of service resources is becoming increasingly difficult when the demand for resources continues to increase.

(II) Technical solution

In order to solve the technical problem that the matching management of service resources becomes increasingly difficult when the demand for resources continues to increase, the present invention provides the following technical solutions:

The present invention discloses a digital enterprise service resource management method based on industry support, which specifically includes the following steps:

S1. Collect historical service resource data of industry support and historical demand data of corresponding digital enterprises, and build a sample set based on the collected historical service resource data of industry support and historical demand data of corresponding digital enterprises;

S2. Preprocess the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain the preprocessed historical service resource data and the corresponding historical demand data;

S3, based on the obtained pre-processed historical service resource data and the corresponding historical demand data, a resource decision model is established through data analysis and processing;

S4, based on the established resource decision model, the established resource decision model is trained by using a particle swarm optimization algorithm, and a trained resource decision model is obtained;

S5. Perform service resource allocation management on the service resource data collected in real time and the corresponding demand data based on the trained resource decision model.

The present invention constructs a sample set by collecting historical service resource data supported by industries and historical demand data of corresponding digital enterprises, and pre-processes the historical service resource data supported by industries and the historical demand data of corresponding digital enterprises in the constructed sample set to ensure the accuracy of the collected service resource data and demand data. At the same time, a resource decision model is established through data analysis and processing, and the established resource decision model is trained through a particle swarm optimization algorithm to obtain a trained resource decision model. Finally, the trained resource decision model is used to improve the efficiency and accuracy of service resource management.

Preferably, the preprocessing of the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set includes the following steps:

S21. Filter the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain filtered historical service resource data and corresponding historical demand data;

S22. Set the filtered historical service resource data and the corresponding historical demand data as the pre-processed historical service resource data and the corresponding historical demand data.

Preferably, filtering the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain the filtered historical service resource data and the corresponding historical demand data includes the following steps:

S211. Establish data standards and filter historical service resource data for abnormal industry support and historical demand data for corresponding digital enterprises;

Set the length standard of the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises, delete the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises that exceed the length standard, and add zeros to the end of the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises that are less than the length standard;

S212, filtering and removing duplicate historical service resource data of industry support and historical demand data of corresponding digital enterprises;

Filter the historical service resource data of industry support and the historical demand data of corresponding digital enterprises based on the filtering algorithm:

Create an array of length m and select A hash function traverses each set of data in the historical service resource data of industry support and the historical demand data of the corresponding digital enterprise, and saves the traversal results in an array;

In the process of traversing through the hash function, when there are two sets of data with the same traversal results, each bit of the two sets of data is compared;

When the comparison results are consistent, the two sets of data are set to be the same data. Based on the arrival time of the task resources, the historical service resource data of the industry support and the historical demand data of the corresponding digital enterprises that arrived later are deleted;

After the traversal is completed, the historical service resource data of industry support and the historical demand data of corresponding digital enterprises stored in the array during the traversal process are summarized to obtain filtered historical service resource data and corresponding historical demand data.

The present invention filters the historical service resource data of industry support and the historical demand data of corresponding digital enterprises by using a filtering algorithm, and filters each group of data in the historical service resource data of industry support and the historical demand data of corresponding digital enterprises by establishing an array and selecting multiple hash functions, thereby improving the accuracy of the service resource data and the corresponding demand data.

Preferably, the step of establishing a resource decision model by means of data analysis and processing based on the obtained pre-processed historical service resource data and the corresponding historical demand data comprises the following steps:

S31. Time cost analysis;

Calculate the time required from receiving historical demand data to scheduling pre-processed historical service resource data to complete the demand. The calculation formula is as follows:

;

in, It indicates the time required from receiving the historical demand data to scheduling the pre-processed historical service resource data to complete the demand. Indicates the number of required tasks, Indicates the number of service resources. Indicates Select the task The decision variables of service resources are set When Select the task service resources, set When Do not select the task service resources, Indicates The execution time of each service resource;

S32. Production cost analysis;

Calculate the production cost from receiving historical demand data to completing the demand. The calculation formula is as follows:

;

in, It represents the production cost required to complete the demand after receiving the historical demand data. Indicates The production cost of each service resource;

S33, service quality analysis;

Calculate the pass rate from receiving historical demand data to completing the demand. The calculation formula is as follows:

;

in, It indicates the qualified rate from receiving the historical demand data to completing the demand. Indicates Production qualification rate of each service resource;

S34. Establish a resource decision-making model.

Preferably, the establishing of the resource decision model comprises the following steps:

The resource decision model calculation formula is as follows:

;

in, represents the resource decision model, Indicates the resource decision weight.

The present invention establishes a resource decision model by using data analysis and processing methods, and establishes the resource decision model by performing time cost analysis, production cost analysis and service quality analysis on pre-processed historical service resource data and corresponding historical demand data, thereby ensuring the accuracy of establishing the resource decision model.

Preferably, the training of the established resource decision model by using a particle swarm optimization algorithm based on the established resource decision model comprises the following steps:

S41, particle swarm optimization algorithm parameter initialization;

Set the group size and maximum number of iterations , random position of particles , particle speed and the inertia factor ;

S42, calculating the fitness of each particle;

The fitness calculation formula for each particle is as follows:

;

in, represents the particle fitness;

S43, updating of the best position of a single particle;

For each particle calculated, the fitness of its current position is compared with the best position it has passed. If the fitness of the current position is greater than the best position it has passed, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position it has passed The fitness of , then the current best position will not be changed ;

S44, updating of the optimal position of the group;

For each particle calculated, the fitness of its current position is compared with the best position that the particle in its population has passed. If the fitness of the current position is greater than the best position that the particle in the population has passed through, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position that the particle in its population has passed The fitness of , then the current best position will not be changed ;

S45, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor;

S46, repeating steps S42-S45 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position;

The inertia factor corresponding to the optimal position of the output is set as the resource decision weight in the trained resource decision model.

Preferably, the updating of the optimal position of a single particle comprises the following steps:

The formula for updating the velocity of a single particle is as follows:

;

in, Represents particles In the The speed during the iteration, Represents particles In the The speed during the iteration, represents the inertia factor, Represents particles In the The position during the iteration, , is the acceleration constant, , represents a random number in the interval [0,1], Represents particles The individual extreme value of Represents the global extreme value of all particles;

The formula for updating the position of a single particle is as follows:

;

in, Represents particles In the The position during the iteration.

The present invention trains the established resource decision model by using a particle swarm optimization algorithm, finds the optimal resource decision model by updating the optimal position of a single particle, setting the number of iterations, and setting the fitness, thereby further improving the accuracy of the resource decision model.

Preferably, the performing service resource allocation management on the service resource data collected in real time and the corresponding demand data based on the obtained trained resource decision model comprises the following steps:

Input the production cost, time cost and production qualification rate of the service resource data collected in real time into the trained resource decision model, and output the resource decision value corresponding to the service resource data collected in real time;

A resource decision value threshold is set, and when the resource decision value corresponding to the service resource data collected in real time is greater than the resource decision value threshold, the service resource data collected in real time is arranged to execute the corresponding demand data;

When the resource decision value corresponding to the service resource data collected in real time is outputted and is less than or equal to the resource decision value threshold, the corresponding demand data is arranged to wait.

The present invention also discloses a digital enterprise service resource management system based on industry support, comprising: a data collection module, a data processing module, a model building module, a model optimization module and a resource decision module;

The data collection module is used to collect service resource data and corresponding demand data;

The data processing module is used to process the collected service resource data and corresponding demand data;

The model building module is used to build a resource decision model based on the processed service resource data and the corresponding demand data;

The model optimization module is used to optimize the resource decision model through a particle swarm optimization algorithm;

The resource decision module is used to calculate the resource decision value corresponding to the service resource data.

(III) Beneficial effects

Compared with the prior art, the present invention provides a digital enterprise service resource management system and method based on industry support, which has the following beneficial effects:

1. The invention constructs a sample set through the historical service resource data of industry support and the historical demand data of corresponding digital enterprises, and pre-processes the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to ensure the accuracy of the collected service resource data and demand data. At the same time, a resource decision model is established through data analysis and processing, and the established resource decision model is trained through a particle swarm optimization algorithm to obtain a trained resource decision model. Finally, the trained resource decision model is used to improve the efficiency and accuracy of service resource management.

2. The invention filters the historical service resource data of industry support and the historical demand data of corresponding digital enterprises by using a filtering algorithm, and filters each group of data in the historical service resource data of industry support and the historical demand data of corresponding digital enterprises by establishing an array and selecting multiple hash functions, thereby improving the accuracy of the service resource data and the corresponding demand data.

3. The invention establishes a resource decision model by using data analysis and processing methods, and establishes a resource decision model by performing time cost analysis, production cost analysis, and service quality analysis on the pre-processed historical service resource data and the corresponding historical demand data, thereby ensuring the accuracy of the established resource decision model.

4. The invention trains the established resource decision model by using a particle swarm optimization algorithm, finds the optimal resource decision model by updating the optimal position of a single particle, setting the number of iterations, and setting the fitness, thereby further improving the accuracy of the resource decision model.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of the flow structure of the digital enterprise service resource management method of the present invention.

DETAILED DESCRIPTION

The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

Example 1

Referring to FIG. 1 , this embodiment discloses a digital enterprise service resource management method based on industry support, which specifically includes the following steps:

S1. Collect historical service resource data of industry support and historical demand data of corresponding digital enterprises, and build a sample set based on the collected historical service resource data of industry support and historical demand data of corresponding digital enterprises;

S2. Preprocess the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain the preprocessed historical service resource data and the corresponding historical demand data;

Preprocessing the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set includes the following steps:

S21. Filter the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain filtered historical service resource data and corresponding historical demand data;

S211. Establish data standards and filter historical service resource data for abnormal industry support and historical demand data for corresponding digital enterprises;

Set the length standard of the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises, delete the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises that exceed the length standard, and add zeros to the end of the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises that are less than the length standard;

S212, filtering and removing duplicate historical service resource data of industry support and historical demand data of corresponding digital enterprises;

Filter the historical service resource data of industry support and the historical demand data of corresponding digital enterprises based on the filtering algorithm:

Create an array of length m and select A hash function traverses each set of data in the historical service resource data of industry support and the historical demand data of the corresponding digital enterprise, and saves the traversal results in an array;

In the process of traversing through the hash function, when there are two sets of data with the same traversal results, each bit of the two sets of data is compared;

When the comparison results are consistent, the two sets of data are set to be the same data. Based on the arrival time of the task resources, the historical service resource data of the industry support and the historical demand data of the corresponding digital enterprises that arrived later are deleted;

After the traversal is completed, the historical service resource data of the industry support and the historical demand data of the corresponding digital enterprises stored in the array during the traversal process are summarized to obtain the filtered historical service resource data and the corresponding historical demand data;

S22, setting the filtered historical service resource data and the corresponding historical demand data as the pre-processed historical service resource data and the corresponding historical demand data;

S3, based on the obtained pre-processed historical service resource data and the corresponding historical demand data, a resource decision model is established through data analysis and processing;

Based on the obtained pre-processed historical service resource data and the corresponding historical demand data, establishing a resource decision model through data analysis and processing includes the following steps:

S31. Time cost analysis;

Calculate the time required from receiving historical demand data to scheduling pre-processed historical service resource data to complete the demand. The calculation formula is as follows:

;

in, It indicates the time required from receiving the historical demand data to scheduling the pre-processed historical service resource data to complete the demand. Indicates the number of required tasks, Indicates the number of service resources. Indicates Select the task The decision variables of service resources are set When Select the task service resources, set When Do not select the task service resources, Indicates The execution time of each service resource;

S32. Production cost analysis;

Calculate the production cost from receiving historical demand data to completing the demand. The calculation formula is as follows:

;

in, It represents the production cost required to complete the demand after receiving the historical demand data. Indicates The production cost of each service resource;

S33, service quality analysis;

Calculate the pass rate from receiving historical demand data to completing the demand. The calculation formula is as follows:

;

in, It indicates the qualified rate from receiving the historical demand data to completing the demand. Indicates Production qualification rate of each service resource;

S34. Establish resource decision-making model;

The resource decision model calculation formula is as follows:

;

in, represents the resource decision model, Indicates resource decision weight;

S4, based on the established resource decision model, the established resource decision model is trained by using a particle swarm optimization algorithm, and a trained resource decision model is obtained;

Based on the established resource decision model, training the established resource decision model by using the particle swarm optimization algorithm includes the following steps:

S41, particle swarm optimization algorithm parameter initialization;

Set the group size and maximum number of iterations , random position of particles , particle speed and the inertia factor ;

S42, calculating the fitness of each particle;

The fitness calculation formula for each particle is as follows:

;

in, represents the particle fitness;

S43, updating of the best position of a single particle;

The formula for updating the velocity of a single particle is as follows:

;

in, Represents particles In the The speed during the iteration, Represents particles In the The speed during the iteration, represents the inertia factor, Represents particles In the The position during the iteration, , is the acceleration constant, , represents a random number in the interval [0,1], Represents particles The individual extreme value of Represents the global extreme value of all particles;

The formula for updating the position of a single particle is as follows:

;

in, Represents particles In the The position during the iteration;

For each particle calculated, the fitness of its current position is compared with the best position it has passed. If the fitness of the current position is greater than the best position it has passed, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position it has passed The fitness of , then the current best position will not be changed ;

S44, updating of the optimal position of the group;

For each particle calculated, the fitness of its current position is compared with the best position that the particle in its population has passed. If the fitness of the current position is greater than the best position that the particle in the population has passed through, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position that the particle in its population has passed The fitness of , then the current best position will not be changed ;

S45, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor;

The inertia factor update formula is as follows:

;

in, represents the inertia factor at the beginning of iteration, represents the inertia factor at the final iteration, Indicates the current iteration number, Indicates the maximum number of iterations;

S46, repeating steps S42-S45 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position;

The inertia factor corresponding to the optimal position of the output is set as the resource decision weight in the trained resource decision model;

S5. Perform service resource allocation management on the service resource data collected in real time and the corresponding demand data based on the trained resource decision model;

Performing service resource allocation management on the service resource data collected in real time and the corresponding demand data based on the trained resource decision model includes the following steps:

Input the production cost, time cost and production qualification rate of the service resource data collected in real time into the trained resource decision model, and output the resource decision value corresponding to the service resource data collected in real time;

A resource decision value threshold is set, and when the resource decision value corresponding to the service resource data collected in real time is greater than the resource decision value threshold, the service resource data collected in real time is arranged to execute the corresponding demand data;

When the resource decision value corresponding to the service resource data collected in real time is outputted and is less than or equal to the resource decision value threshold, the corresponding demand data is arranged to wait;

Example 2

This embodiment also discloses a digital enterprise service resource management system based on industry support, including: a data collection module, a data processing module, a model building module, a model optimization module and a resource decision module;

The data collection module is used to collect service resource data and corresponding demand data;

The data processing module is used to process the collected service resource data and corresponding demand data;

The model building module is used to build a resource decision model based on the processed service resource data and the corresponding demand data;

The model optimization module is used to optimize the resource decision model through a particle swarm optimization algorithm;

The resource decision module is used to calculate the resource decision value corresponding to the service resource data.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims (4)

1. A digital enterprise service resource management method based on industry support, characterized in that it includes the following steps: S1. Collect historical service resource data of industry support and historical demand data of corresponding digital enterprises, and build a sample set based on the collected historical service resource data of industry support and historical demand data of corresponding digital enterprises; S2. Preprocess the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain the preprocessed historical service resource data and the corresponding historical demand data; The preprocessing of the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set includes the following steps: S21. Filter the historical service resource data of industry support and the historical demand data of corresponding digital enterprises in the constructed sample set to obtain filtered historical service resource data and corresponding historical demand data; S22, setting the filtered historical service resource data and the corresponding historical demand data as the pre-processed historical service resource data and the corresponding historical demand data; The filtering of the historical service resource data of the industry support and the historical demand data of the corresponding digital enterprises in the constructed sample set to obtain the filtered historical service resource data and the corresponding historical demand data includes the following steps: S211. Establish data standards and filter historical service resource data for abnormal industry support and historical demand data for corresponding digital enterprises; Set the length standard of the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises, delete the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises that exceed the length standard, and add zeros to the end of the historical service resource data of industry support and the historical demand data of the corresponding digital enterprises that are less than the length standard; S212, filtering and removing duplicate historical service resource data of industry support and historical demand data of corresponding digital enterprises; Filter the historical service resource data of industry support and the historical demand data of corresponding digital enterprises based on the filtering algorithm: Create an array of length m and select A hash function traverses each set of data in the historical service resource data of industry support and the historical demand data of the corresponding digital enterprise, and saves the traversal results in an array; In the process of traversing through the hash function, when there are two sets of data with the same traversal results, each bit of the two sets of data is compared; When the comparison results are consistent, the two sets of data are set to be the same data. Based on the arrival time of the task resources, the historical service resource data of the industry support and the historical demand data of the corresponding digital enterprises that arrived later are deleted; After the traversal is completed, the historical service resource data of the industry support and the historical demand data of the corresponding digital enterprises stored in the array during the traversal process are summarized to obtain the filtered historical service resource data and the corresponding historical demand data; S3, based on the obtained pre-processed historical service resource data and the corresponding historical demand data, a resource decision model is established through data analysis and processing; The method of establishing a resource decision model by means of data analysis and processing based on the obtained pre-processed historical service resource data and the corresponding historical demand data comprises the following steps: S31. Time cost analysis; Calculate the time required from receiving historical demand data to scheduling pre-processed historical service resource data to complete the demand. The calculation formula is as follows: ; in, It indicates the time required from receiving the historical demand data to scheduling the pre-processed historical service resource data to complete the demand. Indicates the number of required tasks, Indicates the number of service resources. Indicates Select the task The decision variables of service resources are set =1, indicating the Select the task service resources, set =0, indicating the Do not select the task service resources, Indicates The execution time of each service resource; S32. Production cost analysis; Calculate the production cost from receiving historical demand data to completing the demand. The calculation formula is as follows: ; in, It represents the production cost required to complete the demand after receiving the historical demand data. Indicates The production cost of each service resource; S33, service quality analysis; Calculate the pass rate from receiving historical demand data to completing the demand. The calculation formula is as follows: ; in, It indicates the qualified rate from receiving the historical demand data to completing the demand. Indicates Production qualification rate of each service resource; S34. Establish resource decision-making model; The establishment of the resource decision model comprises the following steps: The resource decision model calculation formula is as follows: ; in, represents the resource decision model, Indicates resource decision weight; S4, based on the established resource decision model, the established resource decision model is trained by using a particle swarm optimization algorithm, and a trained resource decision model is obtained; S5. Perform service resource allocation management on the service resource data collected in real time and the corresponding demand data based on the trained resource decision model; The service resource allocation management of the service resource data and the corresponding demand data collected in real time based on the trained resource decision model includes the following steps: Input the production cost, time cost and production qualification rate of the service resource data collected in real time into the trained resource decision model, and output the resource decision value corresponding to the service resource data collected in real time; A resource decision value threshold is set, and when the resource decision value corresponding to the service resource data collected in real time is greater than the resource decision value threshold, the service resource data collected in real time is arranged to execute the corresponding demand data; When the resource decision value corresponding to the service resource data collected in real time is outputted and is less than or equal to the resource decision value threshold, the corresponding demand data is arranged to wait. 2. According to the method for digital enterprise service resource management based on industry support in claim 1, it is characterized in that the resource decision model established based on the established resource decision model is trained by using a particle swarm optimization algorithm, comprising the following steps: S41, particle swarm optimization algorithm parameter initialization; Set the group size and maximum number of iterations , random position of particles , particle speed and the inertia factor ; S42, calculating the fitness of each particle; The fitness calculation formula for each particle is as follows: ; in, represents the particle fitness; S43, updating of the best position of a single particle; For each particle calculated, the fitness of its current position is compared with the best position it has passed. If the fitness of the current position is greater than the best position it has passed, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position it has passed The fitness of , then the current best position will not be changed ; S44, updating of the optimal position of the group; For each particle calculated, the fitness of its current position is compared with the best position that the particle in its population has passed. If the fitness of the current position is greater than the best position that the particle in the population has passed through, The current position is taken as the current best position. , if the fitness of the current position is less than or equal to the best position that the particle in its population has passed The fitness of , then the current best position will not be changed ; S45, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor; S46, repeating steps S42-S45 until the maximum number of iterations is reached, and outputting the inertia factor corresponding to the optimal position; The inertia factor corresponding to the optimal position of the output is set as the resource decision weight in the trained resource decision model. 3. According to the method for managing digital enterprise service resources based on industry support in claim 2, it is characterized in that the updating of the optimal position of a single particle comprises the following steps: The formula for updating the velocity of a single particle is as follows: ; in, Represents particles In the The speed during the iteration, Represents particles In the The speed during the iteration, represents the inertia factor, Represents particles In the The position during the iteration, , is the acceleration constant, , represents a random number in the interval [0,1], Represents particles The individual extreme value of Represents the global extreme value of all particles; The formula for updating the position of a single particle is as follows: ; in, Represents particles In the The position during the iteration. 4. A system for implementing the digital enterprise service resource management method based on industry support as described in any one of claims 1 to 3, characterized in that it comprises: a data collection module, a data processing module, a model building module, a model optimization module and a resource decision module; The data collection module is used to collect service resource data and corresponding demand data; The data processing module is used to process the collected service resource data and corresponding demand data; The model building module is used to build a resource decision model based on the processed service resource data and the corresponding demand data; The model optimization module is used to optimize the resource decision model through a particle swarm optimization algorithm; The resource decision module is used to calculate the resource decision value corresponding to the service resource data.