An artificial intelligence-based resource management node deployment method

Abstract

The application discloses a resource management node deployment method based on artificial intelligence, and relates to the technical field of network resource management, and comprises the following steps: S1, constructing a resource node parameter vector set and a state initialization data set; S2, using the resource parameter vector set to perform function vector clustering; S3, using a function area data set to perform node deployment mapping logic construction; S4, using a deployment mapping matrix to determine a node role; S5, using the deployment mapping matrix and a role label set to generate a deployment instruction set; and S6, using a deployment execution data stream to perform multi-scene response verification. Through the setting of the resource feature structured data as the basis, the function similarity clustering analysis mechanism is adopted, the Euclidean distance is used as the measurement mode of the similarity between feature vectors, the function dimensions in the resource parameter vector set are screened and aggregated according to the set similarity threshold value, and thereby, the function area data set is generated.

Description

Technical Field

[0001] This invention relates to the field of network resource management technology, specifically to a method for deploying resource management nodes based on artificial intelligence. Background Technology

[0002] In distributed computing environments, cloud-edge collaborative systems, and large-scale intelligent network platforms, the deployment of resource management nodes has a decisive impact on task scheduling, data transmission efficiency, and service response capabilities. Traditional deployment strategies often rely on static configuration or scheduling mechanisms based on manually set rules, making it difficult to adapt to the dynamic changes in resource demands under diverse application scenarios. With the development of artificial intelligence technology, more and more systems are beginning to adopt methods based on vector representation, similarity calculation, and scenario modeling to optimize node deployment strategies, improve resource utilization efficiency, and enhance system adaptability.

[0003] In existing technologies, the matching strategy between functional requirements and node capabilities during resource deployment often relies on static parameter configuration or fixed resource template mapping methods, lacking the ability to perform dynamic feature analysis from the perspective of functional requirements. In particular, when faced with multi-source heterogeneous resource parameter inputs, it is unable to effectively extract and aggregate the core expressions at the functional level. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an artificial intelligence-based resource management node deployment method to solve the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a resource management node deployment method based on artificial intelligence, comprising the following steps:

[0007] S1. Construct the resource node parameter vector set and state initialization dataset;

[0008] S2. Use the resource parameter vector set to perform functional vector clustering to obtain the functional region dataset;

[0009] S3. Use the functional area dataset to construct the node deployment mapping logic and obtain the deployment mapping matrix;

[0010] S4. Use the deployment mapping matrix to determine the node roles and obtain the node role label set;

[0011] S5. Use the deployment mapping matrix and role tag set to generate a deployment instruction set and obtain the deployment execution data stream;

[0012] S6. Use the deployment execution data stream to perform multi-scenario response verification and obtain a scenario-adaptive deployment model.

[0013] To further optimize this technical solution, in step S1, operating parameters are collected for each resource node in the system, and the collected data is normalized to form a complete vector set. ,in This represents the current number of active nodes.

[0014] In addition, a state initialization dataset is independently established based on the overall resource overview of all nodes, the connectivity topology between nodes, timestamp identifiers, and node online / offline status. It is used to describe the overall operating status of the system, which includes the operating status of each node.

[0015] To further optimize this technical solution, step S2 first constructs a similarity space, then applies a clustering algorithm, followed by state data filtering and clustering result filtering, and finally constructs a functional region dataset.

[0016] In the process of constructing the similarity space, the distance function between nodes The model formula is:

[0017] ;

[0018] in, All are normalized vectors;

[0019] This represents the Euclidean distance, i.e., the L² norm;

[0020] This function measures the similarity between any two nodes in terms of resource features.

[0021] To further optimize this technical solution, in the clustering algorithm application process of step S2, a density-based clustering method is selected. Functional clustering is performed, and the clustering mechanism constructs clusters based on the following conditions:

[0022] ;

[0023] in,

[0024] Distance threshold, used to control the clustering neighborhood;

[0025] Minimum number of samples, used to control the minimum number of neighborhoods required to form a core point;

[0026] Each cluster This represents a set of nodes that are density-connected in the resource feature space.

[0027] To further optimize this technical solution, in the state data filtering and clustering result filtering process in step S2, the state initialization dataset output in step S1 is used. Logical consistency filtering is applied to the initial clustering results by introducing a state mask function:

[0028] ;

[0029] According to the node In the dataset The corresponding state is used to determine whether the current state meets the operational stability requirements of scheduling adaptation for each cluster. Preserve the logically valid subset:

[0030] .

[0031] To further optimize this technical solution, in the process of constructing the functional area dataset in step S2, all clusters that have passed the state filtering are collected. The whole dataset is denoted as the functional area dataset:

[0032] ;

[0033] in The final output represents the grouping structure composed of resource node sets corresponding to each functional area, satisfying the dual constraints of resource feature similarity and operational logic rationality.

[0034] To further optimize this technical solution, step S3 first involves calculating the regional functional center vector, then performing inter-regional functional similarity analysis, followed by constructing a mapping reachability determination function, and finally constructing a deployment mapping matrix. The calculation of the regional functional center vector includes:

[0035] Each functional area The central representation vector The mean of all function vectors within this cluster is calculated using the following formula:

[0036] ;

[0037] in, Indicates the first The number of resource nodes within each cluster region.

[0038] To further optimize this technical solution, the inter-regional functional similarity analysis in step S3 includes:

[0039] By calculating the center vectors of the two regions and The cosine similarity is used to calculate the matching degree between functional center vectors. The similarity calculation formula is as follows:

[0040] ;

[0041] in, Represents the vector dot product. This represents the Euclidean norm.

[0042] To further optimize this technical solution, the construction of the mapping reachability determination function in step S3 includes:

[0043] By setting a decision function Determine the region Is it acceptable to come from the region? The deployment mapping request has the following function formula:

[0044] ;

[0045] in, This similarity threshold is used to control the sensitivity of deployment mapping. The value is determined based on the system's requirements for deployment matching accuracy, either through experience or by optimization using historical data.

[0046] To further optimize this technical solution, the deployment mapping matrix construction in step S3 includes:

[0047] Construct deployment mapping matrix The expression for the matrix elements is:

[0048] ;

[0049] A mapping function for deployment feasibility across regions; this formula is used to determine the feasibility of deployment across regions. Can it be deployed to the region? .

[0050] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of a resource management node deployment method based on artificial intelligence as described in the first aspect of the present invention.

[0051] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of a resource management node deployment method based on artificial intelligence as described in the first aspect of the present invention.

[0052] Compared with existing technologies, this invention provides a resource management node deployment method based on artificial intelligence, which has the following beneficial effects:

[0053] This AI-based resource management node deployment method establishes a mechanism based on structured resource feature data, employs functional similarity clustering analysis, and uses Euclidean distance as a measure of similarity between feature vectors. It filters and aggregates functional dimensions within the resource parameter vector set according to a predefined similarity threshold, generating a functional region dataset. This enables structured clustering and regional division of resource functional attributes before deployment, improving the consistency of functional expression and the accuracy of resource selection during deployment strategy formulation. It addresses the shortcomings of existing technologies, such as the lack of a structured modeling path based on functional clustering, resulting in weak generalization ability and insufficient granularity in resource deployment strategies. Attached Figure Description

[0054] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating a resource management node deployment method based on artificial intelligence proposed in this invention.

[0056] Figure 2 This is a schematic diagram of the functional vector clustering process of a resource management node deployment method based on artificial intelligence proposed in this invention;

[0057] Figure 3 This is a schematic diagram illustrating the node deployment mapping logic construction process of a resource management node deployment method based on artificial intelligence proposed in this invention. Detailed Implementation

[0058] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0059] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0061] Example 1:

[0062] Reference Figures 1-3 This is the first embodiment of the present invention, which provides a resource management node deployment method based on artificial intelligence, including the following steps:

[0063] S1. Construct the resource node parameter vector set and state initialization dataset;

[0064] In step S1, a mature node monitoring and data acquisition system is used to collect operational parameters for each resource node in the system. After collection, the collected data is normalized to unify the dimensions of each parameter, and a feature concatenation mechanism is used to combine the normalized indicators into a vector. ,all Vectors are numbered by node index to form a complete vector set. ,in This represents the number of currently active nodes.

[0065] In addition, a state initialization dataset is independently established based on the overall resource overview of all nodes (total occupancy, average latency, etc.), the connectivity topology between nodes (detected through the heartbeat protocol between nodes), timestamp identifiers, and node online / offline status. It is used to describe the overall operating status of the system, which includes the operating status of each node.

[0066] S2. Use the resource parameter vector set to perform functional vector clustering to obtain the functional region dataset;

[0067] Step S2 is based on the resource parameter vector set obtained in step S1. Node parameter vectors The similarity clustering mechanism is used to divide the nodes into functional areas, thereby generating a functional area dataset. .

[0068] Step S2 first constructs a similarity space, then applies a clustering algorithm, followed by state data filtering and clustering result filtering, and finally constructs a functional region dataset.

[0069] In the process of constructing the similarity space, the distance function between nodes The model formula is:

[0070] ;

[0071] in, All are normalized vectors;

[0072] This represents the Euclidean distance, i.e., the L² norm;

[0073] This function measures the similarity between any two nodes in terms of resource features.

[0074] In the clustering algorithm application process in step S2, a density-based clustering method is selected. Functional clustering is performed, and the clustering mechanism constructs clusters based on the following conditions:

[0075] ;

[0076] in,

[0077] Distance threshold, used to control the clustering neighborhood;

[0078] Minimum number of samples, used to control the minimum number of neighborhoods required to form a core point;

[0079] Each cluster This represents a set of nodes that are density-connected in the resource feature space.

[0080] In step S2, during the state data filtering and clustering result filtering process, the state initialization dataset output from step S1 is used. Logical consistency filtering is applied to the initial clustering results by introducing a state mask function:

[0081] ;

[0082] According to the node In the dataset The corresponding state is used to determine whether the current state meets the operational stability requirements of scheduling adaptation for each cluster. Preserve the logically valid subset:

[0083] .

[0084] In step S2, during the construction of the functional area dataset, all clusters that pass the state filtering are collected. The whole dataset is denoted as the functional area dataset:

[0085] ;

[0086] in The final output represents the grouping structure composed of resource node sets corresponding to each functional area, satisfying the dual constraints of resource feature similarity and operational logic rationality.

[0087] Unlike most existing resource management methods that rely solely on physical topology or static rule partitioning (such as based on physical location, subnetting, or administrator-preset logic), step S2 introduces a unified resource parameter vector space model for functional similarity analysis; it integrates operational status logic judgments to form a functional region construction mechanism under dual constraints; the resulting functional region dataset... It not only possesses parameter space clustering consistency, but also runtime rationality, and has the structural advantage of being directly mapped to subsequent scheduling systems.

[0088] S3. Use the functional area dataset to construct the node deployment mapping logic and obtain the deployment mapping matrix;

[0089] Step S3, based on the functional regions obtained in Step S2, determines which regions in the system can be used as mapping logical paths for resource deployment. To achieve this, Step S3 first calculates the regional functional center vector, then performs functional similarity analysis between regions, then constructs the mapping reachability determination function, and finally constructs the deployment mapping matrix.

[0090] In step S3, the regional functional center vector is first calculated, then the functional similarity between regions is analyzed, then the mapping reachability determination function is constructed, and finally the deployment mapping matrix is ​​constructed.

[0091] Calculation of regional functional center vector:

[0092] Each functional area The central representation vector The mean of all function vectors within this cluster is calculated using the following formula:

[0093] ;

[0094] in, Indicates the first The number of resource nodes within each cluster region.

[0095] Inter-regional functional similarity analysis:

[0096] By calculating the center vectors of the two regions and The cosine similarity is used to calculate the matching degree between functional center vectors. The similarity calculation formula is as follows:

[0097] ;

[0098] in, Represents the vector dot product. This represents the Euclidean norm.

[0099] Construction of the map reachability determination function:

[0100] By setting a decision function Determine the region Is it acceptable to come from the region? The deployment mapping request has the following function formula:

[0101] ;

[0102] in, This similarity threshold is used to control the sensitivity of deployment mapping. The value is determined based on the system's requirements for deployment matching accuracy, either through experience or by optimization using historical data.

[0103] Deployment mapping matrix construction:

[0104] Construct deployment mapping matrix The expression for the matrix elements is:

[0105] ;

[0106] A mapping function for deployment feasibility across regions; this formula is used to determine the feasibility of deployment across regions. Can it be deployed to the region? .

[0107] Traditional mapping typically relies on preset node capability models or static strategy tables. This step constructs a deployment mapping matrix based on the dynamic similarity between functional region vectors, eliminating the need for additional node sets and forming an adaptive mapping mechanism based on functional expression, thereby improving matching accuracy and adaptability in dynamic resource environments.

[0108] S4. Use the deployment mapping matrix to determine the node roles and obtain the node role label set;

[0109] Step S4 involves statistically deploying the mapping matrix. The number of functional areas mapped by each node is used to obtain the participation degree of each node in the functional deployment. This process adopts the mature sparse matrix non-zero element counting method to traverse and calculate each column (or each row).

[0110] Using the feature labels from the functional region dataset in step S2, combined with The matching item positions are used to calculate the degree of feature overlap between nodes and their mapped functional areas using mature label co-occurrence statistical methods, resulting in the "deployment intensity" index. At the same time, the relationship density between node functions is evaluated using feature coverage graph modeling, resulting in the "functional coupling degree" index. The above three indices, "participation degree", "deployment intensity" and "functional coupling degree", are used as input features, and a mature rule-based hierarchical label classification system is used to classify nodes into different role types, forming role labels.

[0111] Finally, all nodes and their role labels are combined to form a node role label set, with each record identifying a node ID and its role category, which serves as the basis for the next step of network structure mapping.

[0112] S5. Use the deployment mapping matrix and role tag set to generate a deployment instruction set and obtain the deployment execution data stream;

[0113] Step S5 is based on the deployment mapping matrix For each resource management node, extract its corresponding set of functional areas to form a node-function mapping table;

[0114] Using the node role tag set generated in step S4, the role attributes of each node are parsed. Combined with the node function execution table, a mature condition mapping rule model is adopted to determine the correspondence between its deployment method and communication logic.

[0115] By adopting a mature process task descriptor generation method, the deployment method of each node is combined with the functional task to build a standardized deployment instruction structure. The deployment instruction structure is modeled using a mature event-driven process chain (EPC) model. Each task node is organized through a directed graph structure, and the execution node and data input source of each task are determined by the node role label set. Finally, a deployment execution data flow representing the task scheduling process between nodes is constructed.

[0116] The final output deployment execution data flow expression in step S5 is:

[0117] ;

[0118] For node role tag set, ;

[0119] A set of deployment instruction structures generated for the task triggering path. ;

[0120] This is a function for binding and mapping character tags to task commands. .

[0121] S6. Use the deployment execution data stream to perform multi-scenario response verification and obtain a scenario-adaptive deployment model;

[0122] Step S6 executes the deployment data stream. The response performance was verified under various operating scenarios, and a scenario-adaptive deployment model with environmental adaptability was built.

[0123] Multi-scenario environment set construction:

[0124] ;

[0125] ;

[0126] in,

[0127] : Load state vector;

[0128] Network state vector;

[0129] : Service request vector.

[0130] In-scenario deployment of data flow execution simulation:

[0131] For each scene The deployment execution data stream obtained in step S5 is used. Simulation scheduling and execution are performed, during which the execution structure is executed for each deployment instruction. Simulate its performance in the scene Based on key performance indicators such as execution latency, communication cost, and resource consumption, a deployment performance indicator vector for this scenario is obtained: ,in Its dimensions include, but are not limited to, response time, throughput, and stability score.

[0132] Adaptive model building and regression optimization:

[0133] Deployment performance metrics results across multiple scenarios: Combined with scene attribute vector set: We use the mature Support Vector Regression (SVR) model to build an adaptive deployment model: ;

[0134] In this AI-based resource management node deployment method, the adaptive deployment model generated in step S6 is used to achieve automatic deployment decisions for resource management nodes under various dynamic scenarios. This model, by inputting new scenario attribute vectors (such as node performance status, network topology changes, service request density, etc.), matches the optimal deployment execution data flow from the trained deployment strategies, thereby outputting a set of deployment task instructions that can be directly issued. The use of this model no longer relies on manual rule formulation, but rather on the learning results based on historical multi-scenario deployment data, achieving real-time, intelligent, and differentiated node deployment responses, improving the system's adaptive scheduling capabilities and resource utilization efficiency in complex business scenarios.

[0135] Step S6 differs from the traditional approach of deploying and optimizing only in a single scenario. It introduces a multi-scenario joint simulation mechanism and a cross-scenario adaptive regression modeling process to achieve generalized learning capabilities for deployment logic. Traditional methods often formulate deployment strategies based on fixed scenario rules, lacking robust modeling and predictive feedback capabilities under environmental changes. This step, however, establishes a multi-dimensional mapping model between deployment behavior and scenario attributes, serving as a crucial transitional step towards a self-adjusting deployment system.

[0136] Example 2:

[0137] This embodiment also provides a computer device applicable to a resource management node deployment method based on artificial intelligence, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the resource management node deployment method based on artificial intelligence as proposed in the above embodiment.

[0138] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements an artificial intelligence-based resource management node deployment method as proposed in the above embodiments.

[0139] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0140] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0141] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0142] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0143] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0144] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for deploying resource management nodes based on artificial intelligence, characterized in that, Includes the following steps: S1. Construct the resource node parameter vector set and state initialization dataset; S2. Use the resource node parameter vector set to perform functional vector clustering, adopt the functional similarity clustering analysis mechanism, combine Euclidean distance as the measure of similarity between feature vectors, and filter and aggregate the functional dimensions in the resource node parameter vector set according to the set similarity threshold to obtain the functional region dataset. S3. Use the functional area dataset to construct the node deployment mapping logic and obtain the deployment mapping matrix; S4. Use the deployment mapping matrix to determine the node roles and obtain the node role label set; S5. Use the deployment mapping matrix and role tag set to generate a deployment instruction set and obtain the deployment execution data stream; S6. Use the deployment execution data stream to perform multi-scenario response verification and obtain a scenario-adaptive deployment model.

2. The method for deploying resource management nodes based on artificial intelligence according to claim 1, characterized in that, In step S1, operating parameters are collected for each resource node in the system, and the collected data is normalized to form a complete vector set. ,in This represents the current number of active nodes. In addition, a state initialization dataset is independently established based on the overall resource overview of all nodes, the connectivity topology between nodes, timestamp identifiers, and node online / offline status. It is used to describe the overall operating status of the system, which includes the operating status of each node.

3. The method for deploying resource management nodes based on artificial intelligence according to claim 2, characterized in that, Step S2 first constructs a similarity space, then applies a clustering algorithm, then filters state data and clustering results, and finally constructs a functional region dataset. In the process of constructing the similarity space, the distance function between nodes The model formula is: ； in, All are normalized vectors; This represents the Euclidean distance, i.e., the L² norm; This function measures the similarity between any two nodes in terms of resource features.

4. The method for deploying resource management nodes based on artificial intelligence according to claim 3, characterized in that, In the clustering algorithm application process of step S2, a density-based clustering method is selected. Functional clustering is performed, and the clustering mechanism constructs clusters based on the following conditions: ； in, Distance threshold, used to control the clustering neighborhood; Minimum number of samples, used to control the minimum number of neighborhoods required to form a core point; Each cluster This represents a set of nodes that are density-connected in the resource feature space.

5. The method for deploying resource management nodes based on artificial intelligence according to claim 3, characterized in that, In the state data filtering and clustering result filtering process in step S2, the state initialization dataset output in step S1 is used. Logical consistency filtering is applied to the preliminary clustering results by introducing a state mask function: ； Based on data points In the dataset The corresponding state is used to determine whether the current state meets the operational stability requirements of scheduling adaptation for each cluster. Preserve its logically valid subset : 。 6. The method for deploying resource management nodes based on artificial intelligence according to claim 3, characterized in that, In the process of constructing the functional area dataset in step S2, all subsets that pass the state filtering are included. The whole dataset is denoted as the functional area dataset: ； in The final output represents the grouping structure composed of resource node sets corresponding to each functional area, satisfying the dual constraints of resource feature similarity and operational logic rationality. It represents the total number of functional regions obtained after clustering.

7. The method for deploying resource management nodes based on artificial intelligence according to claim 6, characterized in that, In step S3, the regional functional center vector is first calculated, then the functional similarity between regions is analyzed, then the mapping reachability determination function is constructed, and finally the deployment mapping matrix is ​​constructed. The calculation of the regional functional center vector includes: A subset of each functional area The central representation vector The mean of all function vectors within this cluster is calculated using the following formula: ； in, Indicates the first The number of resource nodes within each cluster region.

8. The method for deploying resource management nodes based on artificial intelligence according to claim 7, characterized in that, The inter-regional functional similarity analysis in step S3 includes: By calculating the center vectors of the two regions and The cosine similarity is used to calculate the matching degree between functional center vectors. The similarity calculation formula is as follows: ； in, Represents the vector dot product. This represents the Euclidean norm.

9. The method for deploying resource management nodes based on artificial intelligence according to claim 8, characterized in that, The construction of the mapping reachability determination function in step S3 includes: By setting a decision function Determine the region Is it acceptable to come from the region? The deployment mapping request has the following function formula: ； in, This similarity threshold is used to control the sensitivity of deployment mapping. The value is determined based on the system's requirements for deployment matching accuracy, either through experience or by optimization using historical data.

10. A resource management node deployment method based on artificial intelligence according to claim 9, characterized in that, The deployment mapping matrix construction in step S3 includes: Construct deployment mapping matrix The expression for the matrix elements is: ； A mapping function for deployment feasibility across regions; this formula is used to determine the feasibility of deployment across regions. Can it be deployed to the region? , It is the total number of functional regions obtained after clustering. Indicates the first Each functional area Indicates the first Each functional area.

Images