A public service radius calculation method for adaptive network evolution

Abstract

The application relates to the technical field of public service network, in particular to a public service radius calculation method of adaptive network evolution, which comprises the following steps: dividing the public service into multiple functional units according to the service content provided by the public service, wherein each functional unit comprises at least one service point; constructing a public service network matched with the public service; setting a network evolution mechanism for the public service network to realize adaptive evolution of capacity, connection and modular growth; setting a dynamic adjustment strategy to realize resource elastic scheduling of the public service and optimization of a service coverage range; obtaining the service coverage range, obtaining the service radius of each service point in the service coverage range based on a multilayer network model, combining the number of demand points covered by each service point and resource consumption under each service radius to form an optimal service radius vector set; and determining the optimal coverage radius and the optimal service radius of each service point.

Description

Technical Field

[0001] This invention relates to the field of public service network technology, and in particular to a method for calculating the public service radius of adaptive network evolution. Background Technology

[0002] Adaptive networks typically refer to network systems that can automatically adjust their parameters or structure to maintain or optimize their functionality based on changes in the external environment or internal state. A key characteristic of public service networks is the involvement of multiple stakeholders. When responding to emergencies or demands, they must be able to quickly adjust and adapt while maintaining high efficiency. This requires effective collaboration among the various stakeholders in the public service network, as well as ensuring the fair and efficient allocation of resources.

[0003] To maintain network efficiency, that is, to ensure the speed and coverage of service delivery, it is necessary to monitor the service range (i.e., coverage radius) in real time. Therefore, we propose an adaptively evolving public service network. Summary of the Invention

[0004] This invention dynamically adjusts the parameters of a public service network based on external environmental factors such as service demand, ensuring service coverage and effective resource utilization.

[0005] The technical solution proposed in this invention is: a method for calculating the public service radius of adaptive network evolution, the method comprising:

[0006] Based on the services provided by the public service providers, the public service is divided into multiple functional units, each of which includes at least one service point.

[0007] Construct a public service network that matches public services, the public service network including a geographical layer, an organizational layer and a resource layer;

[0008] Establish a network evolution mechanism for public service networks to enable their adaptive evolution;

[0009] Set up dynamic adjustment strategies to achieve flexible allocation of public service resources and optimization of service coverage;

[0010] To obtain the service coverage area, based on a multi-layer network model, the service radius of each service point within the service coverage area is obtained. Combining the number of demand points covered by each service point and the resource consumption under each service radius, an optimal service radius vector set is constructed.

[0011] Determine the optimal coverage radius and optimal service radius for each service point.

[0012] Preferably, the construction of a public service network that matches public services includes:

[0013] A public service network is constructed using service content as nodes, connections between nodes as edges, and service resources as thresholds. Specifically, it includes:

[0014] Obtain all service content of the corresponding public service, forming a service content set V = {v1, v2, ..., v...} i ,...v n}, where vi represents the i-th service content; the service content includes service name, geographic coordinate information, and resource capacity information;

[0015] Obtain the demand point information for the corresponding public services. Multiple demand point information sets constitute the demand point set K = {k1, k2, ..., k}. i , ...k n′ The demand point information includes the geographical coordinates of the demand point and the service demand information.

[0016] Using service content as nodes, obtain the resource capacity c of each node. i and current resource usage r i (t);

[0017] Obtain the connection relationships between different nodes to form a node relationship set E = {e ij |i,j≥1}; among them, e ij This indicates the connection relationship between node i and node j;

[0018] With e ij Let w be the edge, where the cooperation efficiency between node i and node j is equal to the edge weight w of the corresponding edge. ij w ij ∈[0,1];

[0019] Obtain the resource threshold for each node and set the edge activation condition, which is the current resource occupancy r of the two endpoints of the edge. i (t)≥θ i r j (t)≥θ j , where θ i and θ j Represents the resource thresholds for nodes i and j;

[0020] Initialize node and edge generation principles to generate an initial public service network.

[0021] Preferably, the provision of a network evolution mechanism for the public service network includes:

[0022] Configure a node evolution mechanism, specifically including:

[0023] Resources are allocated to the appropriate nodes based on demand. The resource allocation function is as follows:

[0024] Where β is the allocation coefficient, D(t) is the total resource demand within a time period, and N(i) is the set of neighboring nodes of node i; c k and r k (t) represents the node-associated resource capacity and current resource usage of the k-th adjacent node, respectively;

[0025] After the service is completed, release the resources. The resource release function is:

[0026] r i (t+1)=max(0,r i (t)-γ·μ i (t)); where γ is the release rate, μ i (t) represents the amount of service completed within a time period;

[0027] Configure a network topology reconfiguration mechanism, specifically including:

[0028] Configure edge activation and deactivation strategies, including:

[0029] When r i (t)≥θ i And r j (t)≥θ j When, edge e is activated. ij ;

[0030] Otherwise, disconnect edge e. ij A new edge is then generated, and w ij According to w ij ←ηw ij Decrease, where η = 0.9; where the rules for generating new edges include:

[0031] If the service content is v i and v j semantic similarity Then establish edge e i ′ j Where α represents the similarity threshold; and λ′ is the resource impact coefficient.

[0032] Configure node addition and deletion policies, specifically including:

[0033] The principle for adding nodes is as follows: when the existing public service network coverage is insufficient, nodes should be added according to probability. Add a new service node; where Coverage(t) and Demand(t) represent the service coverage rate and service demand rate at time t, respectively.

[0034] Node removal criteria: If the resource utilization rate of node vi is lower than δ for consecutive time periods T, then the node is removed. At that time, remove node vi , where δ is the utilization threshold.

[0035] Preferably, the setting of the dynamic adjustment strategy to achieve flexible resource scheduling and service coverage optimization of public services includes:

[0036] By utilizing all nodes reachable from resource-sufficient nodes through activated edges, an effective service region is formed, where each node on the path satisfies r. i (t)≥θ i ;

[0037] Monitor the real-time status of the public service network, including the current resource consumption of nodes, service demand distribution, and edge connection status;

[0038] The service radius is dynamically adjusted, including:

[0039] Dynamic adjustment is triggered when any of the following conditions are met:

[0040]

[0041] Where, Δr th ΔD represents the threshold for resource changes. th The threshold for the rate of change in aggregate demand, γ topo D represents the topological change rate threshold, i.e., the percentage increase or decrease in edges. k (t) represents the service demand distribution, that is, the total service demand at demand point k, and Δt represents the change over the monitoring time.

[0042] The dynamic adjustment of service scope is transformed into a multi-objective optimization problem, namely...

[0043]

[0044] Where S represents the core point set, i.e., the set of nodes reachable by activated edges; d(v i (k) represents node v i The spatial distance to the demand point k; R represents the service radius, λ represents the resource efficiency weight, and B represents the total amount of available resources;

[0045] Introducing decision variables:

[0046]

[0047] The objective function is:

[0048]

[0049] The constraints are:

[0050]

[0051] Service radius is dynamically adjusted based on resource scarcity. Among them, R base σ represents the basic service radius; σ represents the radius adjustment coefficient.

[0052] Preferably, the setting of a dynamic adjustment strategy to achieve flexible resource scheduling and service coverage optimization for public services further includes:

[0053] The coverage radius of the public service network is calculated using the service radius.

[0054] Where, δ ij Represents the collaboration coefficient, i.e., node v i and v j The intensity of cooperation; R j Represents node v j Service radius, d ij Represents node v i and v j The distance between them;

[0055] If the service radius is dynamically adjusted, then the dynamically adjusted coverage radius is obtained using the dynamically adjusted service radius.

[0056] The service radius is the service distance that each node can provide services for, and the coverage radius is the area actually covered by the node under the service network topology.

[0057] Preferably, the setting of node addition and deletion strategies further includes:

[0058] After determining the service content, the next step is to identify the service equipment, that is, to identify the physical entity unit;

[0059] Use the BERT model to extract semantic feature vectors from the service's description text;

[0060] Use a pre-trained binary classification model to distinguish service content and service equipment;

[0061] Set node admission criteria before adding nodes:

[0062]

[0063] Where, τ sim τ represents the minimum semantic similarity threshold. cls θ represents the content confidence threshold. gap Indicates the threshold for triggering a demand gap; Demands k Indicates the demand for services, Supply k h represents the amount of service provided. i and h jLet v represent the i-th semantic feature vector and the j-th semantic feature vector, respectively; k Let τ represent the service content required at demand point k, where τ sim =0.65, τ cls =0.85, θ gap =1.2;

[0064] Set node elimination conditions: Where δ represents the lower limit of resource utilization, ρ represents the threshold for the proportion of inefficiency, and Utilization i (t) represents the node resource utilization rate;

[0065] The multi-armed slot machine algorithm is used to explore nodes and select the optimal node.

[0066] Decoupling service equipment and service content specifically involves:

[0067] Physical devices are used as resource providers for service content, i.e., resource providers for nodes.

[0068] By matching service equipment and service content through an auction mechanism, it is ensured that the addition or removal of nodes during the evolution of the public service network only affects the service content and not the service equipment.

[0069] Preferably, the service radius of each service point within the service coverage area is obtained, and combined with the number of demand points covered by each service point and the resource consumption under each service radius, an optimal service radius vector set is constructed, including:

[0070] Set the service radius optimization objective function to obtain the service radius that maximizes coverage requirements and minimizes resource consumption;

[0071] The service radius optimization objective function is:

[0072] in, Indicates coverage requirements, χ represents the resource cost; χ represents the weighted average of resource costs. D represents the lower limit of unit resource utilization rate. j C represents the service demand at demand point j; i (R i ) represents the service radius R i Resource consumption cost at that time, y ij Indicates whether the demand point j has obtained node v. i Service variables;

[0073] Set resource constraints:

[0074] Set radius geographical restrictions in, The maximum service radius of service point vi. The minimum service radius of service point vi;

[0075] Set service uniqueness restrictions Avoid duplicate services;

[0076] A genetic algorithm is used to solve the service radius optimization objective function, with a population size of 50, an iteration count of 200, and a mutation rate of 0.1.

[0077] Obtain multiple optimized service radii to form the optimal service radius set R. * ={R1 * R2 * , ..., R l *}

[0078] Preferably, determining the optimal coverage radius and optimal service radius for each service point includes:

[0079] Obtain the optimal service radius set R * ={R1 * R2 * , ..., R l *};

[0080] according to Obtain the optimal coverage radius set S * ={S1 * S2 * S l *};

[0081] If the dynamically adjusted service radius of a node is greater than the optimal service radius, then the dynamically adjusted service radius will be replaced with the optimal service radius.

[0082] An electronic device includes a controller, a memory connected to the controller, and a communication module, the electronic device being used to execute the aforementioned method for calculating the public service radius of adaptive network evolution.

[0083] A computer-readable storage medium storing a computer program that is executed by a processor to implement the method for calculating the public service radius of an adaptive network evolution.

[0084] The beneficial effects of this invention are:

[0085] 1. This invention constructs a public service network using service content as nodes, the connections between service content as edges, and resource thresholds as constraints. It also establishes a self-evolution mechanism, namely dynamic resource allocation (node ​​evolution), network topology reconstruction (edge ​​evolution), and node addition and deletion. Word2Vec is used to quantify service relevance, avoiding resource waste in connections. Simultaneously, semantic constraints and type validation methods ensure that added nodes are services, not service devices.

[0086] 2. In order to accurately reflect the service range of a public service network, this invention distinguishes between the service radius and the coverage radius. The coverage radius accurately reflects the actual range of services provided by the public service network under the network topology, thereby ensuring the effectiveness of dynamic network adjustments. Attached Figure Description

[0087] Figure 1 This is a flowchart of a method for calculating the public service radius of adaptive network evolution according to the present invention. Detailed Implementation

[0088] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0089] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0090] Example 1:

[0091] refer to Figure 1 The technical solution provided by this invention is: a method for calculating the public service radius of adaptive network evolution, comprising the following steps:

[0092] Step 1: Based on the services provided by the public service, divide the public service into multiple functional units, each of which includes at least one service point;

[0093] Step 2: Construct a public service network that matches public services. This public service network includes a geographical layer, an organizational layer, and a resource layer; it includes the following sub-steps:

[0094] A public service network is constructed using service content as nodes, connections between nodes as edges, and service resources as thresholds. Specifically, it includes:

[0095] Obtain all service content of the corresponding public service, forming a service content set V = {v1, v2, ..., v...} i ,...v n}, where vi represents the i-th service content; the service content includes service name, geographic coordinate information, and resource capacity information;

[0096] Obtain the demand point information for the corresponding public services. Multiple demand point information sets constitute the demand point set K = {k1, k2, ..., k}. i , ...k n′ The demand point information includes the geographical coordinates of the demand point and the service demand information.

[0097] Using service content as nodes, obtain the resource capacity c of each node. i and current resource usage r i (t);

[0098] Obtain the connection relationships between different nodes to form a node relationship set E = {e ij |i,j≥1}; among them, e ij This indicates the connection relationship between node i and node j;

[0099] With e ij Let w be the edge, where the cooperation efficiency between node i and node j is equal to the edge weight w of the corresponding edge. ij w ij ∈[0,1];

[0100] Obtain the resource threshold for each node and set the edge activation condition, which is the current resource occupancy r of the two endpoints of the edge. i (t)≥θ i r j (t)≥θ j , where θ i and θ j Represents the resource thresholds for nodes i and j;

[0101] Initialize node and edge generation principles to generate an initial public service network.

[0102] Step 3: Establish a network evolution mechanism for the public service network to achieve adaptive evolution of its capacity, connectivity, and modular growth; this includes the following sub-steps:

[0103] Configure a node evolution mechanism, specifically including:

[0104] Resources are allocated to the appropriate nodes based on demand. The resource allocation function is as follows:

[0105] Where β is the allocation coefficient, D(t) is the total resource demand within a time period, and N(i) is the set of neighboring nodes of node i; c k and r k (t) represents the node-associated resource capacity and current resource usage of the k-th adjacent node, respectively;

[0106] After the service is completed, release the resources. The resource release function is:

[0107] r i (t+1)=max(0,r i (t)-γ·μ i (t)); where γ is the release rate, μ i (t) represents the amount of service completed within a time period;

[0108] Configure a network topology reconfiguration mechanism, specifically including:

[0109] Configure edge activation and deactivation strategies, including:

[0110] When r i (t)≥θ i And r j (t)≥θ j When, edge e is activated. ij ;

[0111] Otherwise, disconnect edge e. ij A new edge is then generated, and w ij According to w ij ←ηw ij Decrease, where η = 0.9; where the rules for generating new edges include:

[0112] If the service content is v i and v j semantic similarity Then establish edge e i ′ j Where α represents the similarity threshold; and λ′ is the resource impact coefficient.

[0113] Configure node addition and deletion policies, specifically including:

[0114] The principle for adding nodes is as follows: when the existing public service network coverage is insufficient, nodes should be added according to probability. Add a new service node; where Coverage(t) and Demand(t) represent the service coverage rate and service demand rate at time t, respectively.

[0115] Set node elimination criteria: If node v i If the resource utilization rate is lower than δ for a continuous period T, then the node is removed. At that time, remove node vi , where δ is the utilization threshold.

[0116] Taking urban healthcare service networks as an example:

[0117] In this network, hospitals, community clinics, and emergency centers can serve as nodes, while referral channels, ambulance routes, and data communication links can serve as edges.

[0118] The hospital's resource threshold is θ i The resource threshold for community clinics is 60% (with a 20% emergency reserve).

[0119] When a sudden medical emergency occurs in a certain area, the resources of surrounding clinics quickly exceed the threshold, automatically establishing a temporary referral channel with a higher-level hospital (adding an edge) or a makeshift hospital (adding a node). After the stress test, the newly added edges and nodes, along with the resources they occupied, are released, and the resources are redistributed to regular services.

[0120] Step 4: Set up dynamic adjustment strategies to achieve flexible resource allocation and optimized service coverage for public services; including:

[0121] By utilizing all nodes reachable from resource-sufficient nodes through activated edges, an effective service region is formed, where each node on the path satisfies r. i (t)≥θ i ;

[0122] Monitor the real-time status of the public service network, including the current resource consumption of nodes, service demand distribution, and edge connection status;

[0123] The service radius is dynamically adjusted, including:

[0124] Dynamic adjustment is triggered when any of the following conditions are met:

[0125]

[0126] Where, Δr th ΔD represents the threshold for resource changes. th The threshold for the rate of change in aggregate demand, γ topo D represents the topological change rate threshold, i.e., the percentage increase or decrease in edges. k (t) represents the service demand distribution, that is, the total service demand at demand point k, and Δt represents the change over the monitoring time.

[0127] The dynamic adjustment of service scope is transformed into a multi-objective optimization problem, namely...

[0128]

[0129] Where S represents the core point set, i.e., the set of nodes reachable by activated edges; d(v i (k) represents node v i The spatial distance to the demand point k; R represents the service radius, λ represents the resource efficiency weight, and B represents the total amount of available resources;

[0130] Introducing decision variables:

[0131]

[0132] The objective function is:

[0133]

[0134] The constraints are:

[0135]

[0136] Service radius is dynamically adjusted based on resource scarcity. Among them, R base σ represents the basic service radius; σ represents the radius adjustment coefficient; the more scarce the resources, the smaller the service radius. In this embodiment, the basic service radius can be selected as 5km, and the condition coefficient can be -0.5;

[0137] High-demand areas are assigned dynamic weights. The determination of high demand is based on historical demand data and is determined by using a regression model to predict the urgency level. When the predicted urgency level is greater than the preset urgency level threshold, the area is judged to be a high-demand area.

[0138] Based on the branch pricing algorithm, the current candidate core node set is solved to generate a new core point set (a set of potential core points).

[0139] Taking vaccination services as an example, fixed vaccination sites serve 80% of the population. When vaccination demand increases in a certain area (ΔD...),... th ≥15%), trigger the following adjustments:

[0140] Activate mobile vaccination vehicles (add core nodes), shrink the service radius of fixed vaccination points (from 5km to 3km), and generate new service areas.

[0141] Step 5: Obtain the service coverage area. Based on a multi-layer network model, obtain the service radius of each service point within the service coverage area. Combine the number of demand points covered by each service point and the resource consumption under each service radius to construct the optimal service radius vector set; including:

[0142] Set the service radius optimization objective function to obtain the service radius that maximizes coverage requirements and minimizes resource consumption;

[0143] The service radius optimization objective function is:

[0144] in, Indicates coverage requirements, χ represents the resource cost; χ represents the weighted average of resource costs. D represents the lower limit of unit resource utilization rate. j C represents the service demand at demand point j; i (R i ) represents the service radius R i Resource consumption cost at that time, y ij Indicates whether the demand point j has obtained node v. i Service variables;

[0145] Set resource constraints: Where N represents the total number of service radii;

[0146] Set radius geographical restrictions in, Service Point v i Maximum service radius Service Point v i Minimum service radius;

[0147] Set service uniqueness restrictions Avoid duplicate services;

[0148] A genetic algorithm is used to solve the service radius optimization objective function, with a population size of 50, an iteration count of 200, and a mutation rate of 0.1.

[0149] Obtain multiple optimized service radii to form the optimal service radius set R. * ={R1 * R2 * , ..., R l *}

[0150] Step Six: Determine the optimal coverage radius and optimal service radius for each service point. This includes:

[0151] Obtain the optimal service radius set R * ={R1 * R2 * , ..., R l *};

[0152] according to Obtain the optimal coverage radius set S * ={S1 * S2 * S l*};

[0153] If the dynamically adjusted service radius of a node is greater than the optimal service radius, then the dynamically adjusted service radius will be replaced with the optimal service radius.

[0154] Example 2:

[0155] In some cases, during the addition or removal of nodes, we need to add nodes that are services rather than devices. To address this issue, this invention further proposes the following solution based on Embodiment 1:

[0156] Setting node addition and deletion policies also includes:

[0157] After determining the service content, the next step is to identify the service equipment, that is, to identify the physical entity unit;

[0158] Use the BERT model to extract semantic feature vectors from the service's description text;

[0159] Use a pre-trained binary classification model to distinguish service content and service equipment;

[0160] Set node admission criteria before adding nodes:

[0161]

[0162] Where, τ sim τ represents the minimum semantic similarity threshold. cls θ represents the content confidence threshold. gap Indicates the threshold for triggering a demand gap; Demands k Indicates the demand for services, Supply k h represents the amount of service provided. i and h j Let v represent the i-th semantic feature vector and the j-th semantic feature vector, respectively; k In this embodiment, τ represents the service content required by demand point k. sim =0.65, τ cls =0.85, θ gap =1.2;

[0163] Set node elimination conditions: Where δ represents the lower limit of resource utilization, ρ represents the threshold for the proportion of inefficiency, and Utilization i (t) represents the node resource utilization rate;

[0164] The multi-armed slot machine algorithm is used to explore nodes and select the optimal node.

[0165] Decoupling service equipment and service content specifically involves:

[0166] Physical devices are used as resource providers for service content, i.e., resource providers for nodes.

[0167] By matching service equipment and service content through an auction mechanism, it is ensured that the addition or removal of nodes during the evolution of the public service network only affects the service content and not the service equipment.

[0168] Example 3:

[0169] In some cases, it is necessary to distinguish between the coverage radius and service radius (service range and coverage range) of a public service network. The service radius refers to the service distance that each node can provide, while the coverage radius is the area actually covered by the node under the service network topology. Therefore, based on Embodiments 1 and 2, we propose the following technical solution:

[0170] The coverage radius of the public service network is calculated using the service radius.

[0171] Where, δ ij Represents the collaboration coefficient, i.e., node v i and v j The intensity of cooperation; R j Represents node v j Service radius, d ij Represents node v i and v j The distance between them;

[0172] If the service radius is dynamically adjusted, then the dynamically adjusted coverage radius is obtained using the dynamically adjusted service radius.

[0173] The present invention also provides an electronic device, which includes a controller, a memory connected to the controller, and a communication module, wherein the electronic device is used for the aforementioned method for calculating the public service radius of adaptive network evolution.

[0174] The present invention also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the aforementioned method for calculating the public service radius of adaptive network evolution.

[0175] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0176] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0177] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the principles described, the implementation of the present invention may have any changes or modifications.

Claims

1. A method for calculating the public service radius of adaptive network evolution, characterized in that, The method includes: Based on the services provided by the public service providers, the public service is divided into multiple functional units, each of which includes at least one service point. Constructing a public service network that matches public services, the public service network includes a geographical layer, an organizational layer, and a resource layer; it includes: constructing the public service network with service content as nodes, connections between nodes as edges, and service resources as thresholds, specifically including: Obtain all service content of the corresponding public service, which constitutes the service content set. ,in, Indicates the first Each service content includes service name, geographic coordinate information, and resource capacity information. Obtain information on the demand points for relevant public services; multiple demand point information sets constitute a demand point set. The demand point information includes the geographical coordinates of the demand point and the service demand information. Using service content as nodes, obtain the resource capacity of each node. and current resource usage ; Obtain the connection relationships between different nodes to form a node relationship set. ;in, Represents a node and nodes The connection relationship; by Let the edges be nodes, where nodes are nodes. and nodes The collaboration efficiency between them is equal to the edge weight of the corresponding edge. , ; Obtain the resource threshold for each node and set the edge activation condition, which is the current resource occupancy of the two endpoints of the edge. , ,in, and Represents a node and nodes Resource threshold; Initialize node and edge generation principles to generate an initial public service network; Establish a network evolution mechanism for public service networks to enable their adaptive evolution, including: Configure a node evolution mechanism, specifically including: Resources are allocated to the appropriate nodes based on demand. The resource allocation function is as follows: ,in, For allocation coefficients, The total resource demand over a given period of time. For nodes The set of adjacent nodes; and They represent the first The node-associated resource capacity and current resource usage of each adjacent node; After the service is completed, release the resources. The resource release function is: ;in, For the release rate, The volume of services completed within a given time period; Configure a network topology reconfiguration mechanism, specifically including: Configure edge activation and deactivation strategies, including: when and When, the edge is activated. ; Otherwise, disconnect the edge. A new edge is generated afterward, and according to Attenuation, in which The rules for generating new edges include: If the service content and semantic similarity Then establish an edge ;in, Represents the similarity threshold; where, This is the resource impact coefficient; Configure node addition and deletion policies, specifically including: The principle for adding nodes is as follows: when the existing public service network coverage is insufficient, nodes should be added according to probability. Add a new service node; among them, Representing time respectively Service coverage and service demand rate at the time; Set node elimination criteria: If a node... continuous Resource utilization rate during the period is lower than If the node is removed, then the node is removed. Remove node ,in The utilization threshold; Set up dynamic adjustment strategies to achieve flexible allocation of public service resources and optimization of service coverage; To obtain the service coverage area, based on a multi-layer network model, the service radius of each service point within the service coverage area is obtained. Combining the number of demand points covered by each service point and the resource consumption under each service radius, an optimal service radius vector set is constructed. Determine the optimal coverage radius and optimal service radius for each service point.

2. The method for calculating the public service radius of adaptive network evolution according to claim 1, characterized in that, The aforementioned dynamic adjustment strategy, aimed at achieving flexible resource allocation and optimized service coverage for public services, includes: By utilizing all nodes reachable from resource-sufficient nodes through activated edges, an effective service area is formed, and each node on the path satisfies... ; Monitor the real-time status of the public service network, including the current resource consumption of nodes, service demand distribution, and edge connection status; The service radius is dynamically adjusted, including: Dynamic adjustment is triggered when any of the following conditions are met: ； in, Indicates the threshold for resource changes. threshold for the rate of change in aggregate demand This represents the threshold for the rate of topological change, i.e., the percentage increase or decrease in the number of edges. This represents the distribution of service demand, i.e., demand points. The total demand for services, Indicates the change over monitoring time; The dynamic adjustment of service scope is transformed into a multi-objective optimization problem, namely... ； in, This represents the core set of nodes, i.e., the set of nodes reachable from active edges. Represents a node To the point of demand Spatial distance; Indicates the service radius. Indicates resource efficiency weight. Indicates the total amount of available resources; Introducing decision variables: ， ； The objective function is: ； The constraints are: ； Service radius is dynamically adjusted based on resource scarcity. ;in, Indicates the basic service radius; This represents the radius adjustment coefficient.

3. The method for calculating the public service radius of adaptive network evolution according to claim 2, characterized in that, The aforementioned dynamic adjustment strategy, which aims to achieve flexible resource allocation and optimized service coverage for public services, also includes: The coverage radius of the public service network is calculated using the service radius. ; in, Represents the collaboration coefficient, i.e., the node and The intensity of cooperation; Represents a node service radius, Represents a node and The distance between them; If the service radius is dynamically adjusted, then the dynamically adjusted coverage radius is obtained using the dynamically adjusted service radius. The service radius is the service distance that each node can provide services for, and the coverage radius is the area actually covered by the node under the service network topology.

4. The method for calculating the public service radius of adaptive network evolution according to claim 3, characterized in that, The node addition and deletion strategy also includes: After determining the service content, the next step is to identify the service equipment, that is, to identify the physical entity unit; Use the BERT model to extract semantic feature vectors from the service's description text; Use a pre-trained binary classification model to distinguish service content and service equipment; Set node admission criteria before adding nodes: ； in, This represents the minimum semantic similarity threshold. This represents the content confidence threshold. Indicates the threshold for triggering a demand gap; Indicates the demand for services. Indicates the amount of service provided. and They represent the first The semantic feature vector and the first semantic feature vector One semantic feature vector; Indicate demand points The required service content; Set node elimination conditions: ,in, This indicates the lower limit of resource utilization. This indicates the threshold for the proportion of inefficiency. Indicates node resource utilization rate; The multi-armed slot machine algorithm is used to explore nodes and select the optimal node. Decoupling service equipment and service content specifically involves: Physical devices are used as resource providers for service content, i.e., resource providers for nodes. By matching service equipment and service content through an auction mechanism, it is ensured that the addition or removal of nodes during the evolution of the public service network only affects the service content and not the service equipment.

5. The method for calculating the public service radius of adaptive network evolution according to claim 4, characterized in that, The service radius of each service point within the service coverage area is obtained, and combined with the number of demand points covered by each service point and the resource consumption under each service radius, an optimal service radius vector set is constructed, including: Set the service radius optimization objective function to obtain the service radius that maximizes coverage requirements and minimizes resource consumption; The service radius optimization objective function is: ; in, Indicates coverage requirements, Indicates resource cost; Indicates resource cost weighting, This indicates the lower limit of unit resource utilization rate. Indicate demand points The demand for services; Indicates service radius Resource consumption costs at that time Indicate demand points Have nodes been obtained? Service variables; Set resource constraints: ;in, Indicates the total number of service radii; Set radius geographical restrictions :in, service point Maximum service radius service point Minimum service radius; Set service uniqueness restrictions To avoid duplicate services; A genetic algorithm is used to solve the service radius optimization objective function, with a population size of 50, an iteration count of 200, and a mutation rate of 0.

1. Obtain multiple optimized service radii to form the optimal service radius set. .

6. The method for calculating the public service radius of adaptive network evolution according to claim 5, characterized in that, Determining the optimal coverage radius and optimal service radius for each service point includes: Obtain the optimal service radius set ; according to Obtain the optimal coverage radius set ; If the dynamically adjusted service radius of a node is greater than the optimal service radius, then the dynamically adjusted service radius will be replaced with the optimal service radius.

7. An electronic device, the electronic device comprising a controller, a memory connected to the controller, and a communication module, characterized in that, The electronic device is used to execute the method for calculating the public service radius of adaptive network evolution as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method for calculating the public service radius of adaptive network evolution as described in any one of claims 1-6.

Images