Multi-source data collaborative tourist road facility ant colony intelligent layout method and system

Abstract

The invention relates to the technical field of industrial engineering. The tourism highway facility ant colony intelligent layout method and system based on multi-source data collaboration are provided, and the method comprises the steps that collaborative fusion processing is carried out on multi-source heterogeneous data, and a dynamic demand field model is generated; performing topology constraint network construction processing based on the facility coordination rule to generate a topology constraint network; carrying out facility layout candidate solution set generation processing under the dynamic demand field model and the topology constraint network through an improved ant colony algorithm, and generating a facility layout candidate solution set; and carrying out multi-objective optimization and man-machine collaborative decision processing on the facility layout candidate solution set, and outputting a facility layout scheme so as to achieve the technical effects of improving the collaborative linkage capability among facilities, shortening the algorithm convergence time, reducing the local optimal trap occurrence rate and enhancing the multi-objective collaborative optimization efficiency.

Description

Technical Field

[0001] This invention relates to the field of industrial engineering technology, and in particular to a method and system for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration. Background Technology

[0002] With the deepening integration of smart tourism and transportation, the intelligent layout of tourism highway service facilities (such as charging piles, rest stations, and viewing platforms) has become a key link in improving tourist experience and resource utilization efficiency.

[0003] However, existing tourism highway facility layout technologies suffer from spatial disconnect in the collaborative optimization of multiple facilities, making it difficult for facilities such as charging piles, rest stations, and rescue points to form a service network linkage mechanism. At the same time, intelligent optimization algorithms face three problems in complex scenarios: slow convergence speed, high incidence of local optimum traps, and insufficient multi-objective collaborative optimization capabilities. Summary of the Invention

[0004] Based on this, it is necessary to provide a method and system for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration to address the above-mentioned technical problems, so as to improve the collaborative linkage capability between facilities, shorten the algorithm convergence time, reduce the occurrence rate of local optimal traps, and enhance the technical effect of multi-objective collaborative optimization.

[0005] Firstly, this application provides a method for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration, the method comprising:

[0006] Collaborative fusion processing of multi-source heterogeneous data generates a dynamic demand field model;

[0007] The topology constraint network is generated by constructing a topology constraint network based on facility coordination rules.

[0008] By improving the ant colony algorithm, a candidate solution set for facility layout is generated under the dynamic demand field model and topological constraint network.

[0009] The candidate solution set for facility layout is subjected to multi-objective optimization and human-machine collaborative decision-making to output the facility layout scheme.

[0010] Furthermore, by improving the ant colony algorithm under the dynamic demand field model and topological constraint network, a candidate solution set for facility layout is generated, including:

[0011] The ant colony individuals are bound with facility type tags to generate ant colony individuals carrying facility type tags;

[0012] Based on the demand intensity distribution of the dynamic demand field model, probabilistic path selection is performed to drive individual ants carrying facility type labels to move between road network nodes, generating ant movement paths.

[0013] Based on the edge weights of the topologically constrained network, pheromone updates are used to collaboratively strengthen the ant movement path, generating an optimized path.

[0014] The optimized paths generated iteratively are aggregated to generate candidate solution sets for facility layout.

[0015] Furthermore, based on the demand intensity distribution of the dynamic demand field model, probabilistic path selection is performed to drive individual ants carrying facility type labels to move between road network nodes, generating ant movement paths, including:

[0016] Based on the demand intensity distribution of the dynamic demand field model, the movement direction decision processing of ant colony individuals carrying facility type labels is performed to generate a set of candidate moving nodes.

[0017] The set of candidate mobile nodes is evaluated for facility type matching degree, and a node matching degree weight distribution is generated.

[0018] A dynamic selection probability distribution is generated by performing fusion probability calculation based on the demand intensity distribution and the node matching degree weight distribution.

[0019] The roulette wheel selection process is performed based on a dynamic selection probability distribution to determine the next moving node;

[0020] Based on the next mobile node, the location of individual ants carrying facility type tags is updated and their trajectory is recorded to generate ant movement paths.

[0021] Furthermore, based on the edge weights of the topologically constrained network, pheromone updates are applied to the ant movement path for collaborative reinforcement, generating an optimized path, including:

[0022] Perform facility coordination rule compliance judgment on the ant movement path and generate path compliance identifier;

[0023] Based on the edge weights and path compliance identifiers of the topologically constrained network, pheromone incremental superposition processing is performed on compliant path segments to generate an enhanced pheromone distribution.

[0024] Based on path compliance identification, pheromone punitive volatilization is applied to non-compliant path segments to generate pheromone suppression measures.

[0025] Based on enhancing pheromone distribution and inhibiting pheromone distribution, a path optimization evaluation process is performed on the ant movement path to generate an optimized path.

[0026] Furthermore, multi-objective optimization and human-machine collaborative decision-making are performed on the candidate solution set for facility layout to output facility layout schemes, including:

[0027] A multi-objective function evaluation process is performed on the candidate solution set for facility layout to generate a Pareto non-dominated solution set;

[0028] Based on generative adversarial networks, operational performance is extrapolated from Pareto non-dominated solution sets to generate risk prediction reports;

[0029] The system interactively optimizes the expert decision-making weights and risk prediction reports to output a facility layout plan.

[0030] Furthermore, a multi-objective function evaluation process is performed on the candidate solution set for facility layout to generate a Pareto non-dominated solution set, including:

[0031] The objective function set is defined for the candidate solution set of facility layout;

[0032] Based on the objective function set, conflict quantification analysis is performed on the candidate solution set of facility layout to generate the objective conflict matrix;

[0033] The candidate solution set for facility layout is subjected to non-dominance relation filtering to generate a set of non-dominance relation identifiers;

[0034] Based on the target conflict matrix and the set of non-dominated relation identifiers, a hierarchical processing of the solution set is performed to generate a Pareto non-dominated solution set.

[0035] Furthermore, based on facility coordination rules, a topology constraint network is constructed to generate a topology constraint network, including:

[0036] Define and process the rules for association between facility types to generate a set of facility coordination constraint rules;

[0037] Topology node modeling is performed based on the facility collaboration constraint rule set to generate a topology node set;

[0038] The coordination relationship between facilities is quantified based on the facility coordination constraint rule set to generate an edge weight matrix;

[0039] A topologically constrained network is generated by performing graph structure generation processing based on the topological node set and edge weight matrix.

[0040] Secondly, this application also provides a multi-source data collaborative intelligent layout system for tourism highway facilities using ant colonies, the system comprising:

[0041] The collaborative fusion module is used to perform collaborative fusion processing on multi-source heterogeneous data to generate a dynamic demand field model.

[0042] The topology construction module is used to construct topology-constrained networks based on facility coordination rules, generating such networks.

[0043] The ant colony optimization module is used to generate a set of candidate solutions for facility layout under dynamic demand field models and topological constraint networks by improving the ant colony algorithm.

[0044] The decision optimization module is used to perform multi-objective optimization and human-machine collaborative decision-making on the candidate solution set for facility layout, and output the facility layout scheme.

[0045] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods in the first aspect of this application.

[0046] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the methods in the first aspect of this application.

[0047] This application provides a method and system for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration. The method includes: collaboratively fusing multi-source heterogeneous data to generate a dynamic demand field model; constructing a topological constraint network based on facility collaboration rules; generating a candidate solution set for facility layout under the dynamic demand field model and topological constraint network by improving the ant colony algorithm; and performing multi-objective optimization and human-machine collaborative decision-making on the candidate solution set to output a facility layout scheme. This achieves the technical effects of improving the collaborative linkage capability between facilities, shortening the algorithm convergence time, reducing the occurrence rate of local optimum traps, and enhancing the efficiency of multi-objective collaborative optimization. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart of a multi-source data collaborative intelligent layout method for tourism highway facilities using an ant colony in one embodiment of the present invention;

[0050] Figure 2 In one embodiment of the present invention, a probability path selection process is performed on the demand intensity distribution based on the dynamic demand field model to drive individual ants carrying facility type labels to move between road network nodes, generating a flowchart of the ant movement path.

[0051] Figure 3 This is a structural diagram of a multi-source data collaborative intelligent layout system for tourism highway facilities, as shown in one embodiment of the present invention. Detailed Implementation

[0052] To make the above-mentioned objects, features, and advantages of this application more apparent and understandable, the specific implementation methods of this application will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0053] like Figure 1 As shown, this application provides a multi-source data collaborative intelligent ant colony layout method for tourism highway facilities, which includes:

[0054] S101: Perform collaborative fusion processing on multi-source heterogeneous data to generate a dynamic demand field model.

[0055] Specifically, multi-source heterogeneous data includes traffic flow data, tourist interest point data, tourist behavior data, natural geographic environment data, and existing service facility data. The above data undergoes collaborative fusion processing, which includes acquiring various types of raw data from different data sources and transmitting them to the data processing platform. Subsequently, the raw data is cleaned, transformed, and standardized to remove noise and errors, and to unify data format and units. Association algorithms are used to uncover potential relationships between different data sets; for example, combining traffic flow data with the popularity of tourist interest points can help analyze the spatiotemporal distribution characteristics of tourist traffic.

[0056] Simultaneously, tourist behavior data is correlated with natural geographic environment data to analyze the impact of topography and climate conditions on tourist activities. Then, based on geospatial information, the processed data is mapped onto the geographic space along the tourist highway, dividing it into different analysis units. The demand intensity of each unit is calculated, comprehensively considering the influence weights of factors such as transportation convenience, tourist attractiveness, tourist preferences, and environmental factors on the demand for service facilities. Subsequently, through fusion processing, a dynamic demand field model is generated. This model can reflect the service facility demand in various areas along the tourist highway at different time periods in real time, providing a more accurate basis for subsequent facility layout decisions.

[0057] S102: Based on facility coordination rules, perform topology constraint network construction processing to generate a topology constraint network.

[0058] Specifically, the collaborative rules for various facilities along the tourist highway are analyzed and defined in depth. The relationships and constraints between different facility types (such as charging stations, rest stops, and viewing platforms) in terms of functional complementarity, spatial distance, and service processes are clarified, generating a set of facility collaborative constraint rules. Then, based on this rule set, topological node modeling is performed for each facility, abstracting the facilities into nodes with specific attributes (such as location, function, and capacity). The node information of all relevant facilities is collected and organized to generate a set of topological nodes, which are the basic units constituting the network.

[0059] Then, the facility collaboration constraint rule set is used again to quantitatively evaluate the collaboration relationship between each pair of facilities. Taking into account factors such as whether the distance between facilities meets the service radius requirements, whether the functional connection is smooth, and traffic connectivity, the edge weight between each pair of nodes is calculated. The edge weight reflects the tightness and rationality of the collaboration between facilities, thus generating an edge weight matrix. This matrix records the strength of the connection between nodes in detail.

[0060] Then, using the set of topological nodes and the edge weight matrix as input, a graph structure generation algorithm is used to connect the nodes according to their spatial location and edge weights, constructing a topological constraint network that can fully represent the collaborative relationship between facilities along the tourist highway. This network presents the logical connections and interactions between facilities in a graphical way, providing spatial constraints and collaborative guidance for subsequent facility layout optimization.

[0061] S103: By improving the ant colony algorithm, a candidate solution set for facility layout is generated under the dynamic demand field model and topological constraint network.

[0062] Specifically, the traditional ant colony algorithm is improved to adapt to the complexity and unique characteristics of tourism highway facility layout problems. In the improved algorithm, each ant is assigned a relevant facility type label, allowing each ant to represent different types of facilities (such as charging stations and rest stops), thus achieving coordinated layout of different facility types. Then, based on a dynamic demand field model, which reflects the demand intensity and spatiotemporal variation characteristics of various areas along the tourism highway in real time, dynamic directional guidance is provided for the ants' movement. Ants choose their movement direction based on the demand intensity distribution and the facility type labels they carry, tending to move towards areas with high demand intensity and facilities matching their own type.

[0063] Simultaneously, a topological constraint network is used, which includes cooperative constraints and spatial location information between facilities. During movement, ants must adhere to the edge weights and topological structure of the network to ensure that the generated layout path conforms to facility cooperation rules and spatial feasibility. After an ant completes a move, the pheromone along the path is updated based on its movement path and the nodes it traversed. For paths that conform to facility cooperation rules and have a high degree of demand matching, the pheromone intensity is increased to enhance the probability of selecting a high-quality path; for paths that do not conform to the rules or have a low degree of demand matching, the pheromone is evaporated to reduce the likelihood of them being selected subsequently.

[0064] Through multiple iterations, the ant continuously explores and optimizes the path, generating multiple candidate solutions for facility layout. Each candidate solution represents a possible facility layout scheme, including the specific location and distribution of different facility types along the tourist highway. Then, the candidate solutions obtained through iterative optimization are aggregated to generate a set of candidate facility layout solutions, providing diverse options for subsequent multi-objective optimization and decision-making.

[0065] S104: Perform multi-objective optimization and human-machine collaborative decision-making on the candidate solution set for facility layout, and output the facility layout scheme.

[0066] Specifically, a multi-objective function set is defined, including several key indicators for facility layout, such as maximizing service coverage, maximizing inter-facility collaboration efficiency, and minimizing construction costs. Each objective function quantitatively evaluates the merits of the facility layout from different dimensions. Then, for each candidate solution in the facility layout candidate solution set, the respective objective functions are substituted into the calculations to obtain the performance values ​​of each candidate solution on different objectives, constructing an objective value matrix. Based on this matrix, a conflict quantification analysis algorithm is used to calculate the degree of conflict between the objectives, generating an objective conflict matrix. This matrix intuitively displays the mutual constraints between different objectives.

[0067] Next, based on the target conflict matrix and preset non-dominated relation screening rules, the candidate solution set is screened to determine the non-dominated relation identifier for each candidate solution, thereby selecting a set of high-quality solutions with non-dominated relations and generating the Pareto non-dominated solution set. Then, the Pareto non-dominated solution set is input into an operational effect simulation module based on a generative adversarial network. By simulating the performance of different solutions in actual operation, a risk prediction report is generated. This report lists in detail the types of risks each solution may face, the probability of risk occurrence, and the potential impact.

[0068] Simultaneously, the decision preference weights of experts for various facility layout schemes were collected. These weights reflect the experts' emphasis and inclination on different objectives. Then, the risk prediction report was combined with the expert decision weights, and an interactive optimization algorithm was used to comprehensively evaluate and optimize the Pareto non-dominated solution set. Risk factors were adjusted according to the expert weights, gradually narrowing the solution set until the optimal facility layout scheme was obtained. This scheme exhibits the best overall performance and feasibility under multi-objective trade-offs.

[0069] One embodiment of this application provides an intelligent ant colony layout method for tourism highway facilities based on multi-source data collaboration, comprising: collaboratively fusing multi-source heterogeneous data to generate a dynamic demand field model; constructing a topological constraint network based on facility collaboration rules to generate a topological constraint network; generating a candidate solution set for facility layout by improving the ant colony algorithm under the dynamic demand field model and the topological constraint network; performing multi-objective optimization and human-machine collaborative decision-making on the candidate solution set for facility layout, and outputting a facility layout scheme, thereby achieving the technical effects of improving the collaborative linkage capability between facilities, shortening the algorithm convergence time, reducing the occurrence rate of local optimum traps, and enhancing the efficiency of multi-objective collaborative optimization.

[0070] Furthermore, by improving the ant colony algorithm under the dynamic demand field model and topological constraint network, a candidate solution set for facility layout is generated, including:

[0071] The ant colony individuals are bound with facility type tags to generate ant colony individuals carrying facility type tags;

[0072] Based on the demand intensity distribution of the dynamic demand field model, probabilistic path selection is performed to drive individual ants carrying facility type labels to move between road network nodes, generating ant movement paths.

[0073] Based on the edge weights of the topologically constrained network, pheromone updates are used to collaboratively strengthen the ant movement path, generating an optimized path.

[0074] The optimized paths generated iteratively are aggregated to generate candidate solution sets for facility layout.

[0075] Specifically, each ant colony member is tagged with a facility type, distinguishing them from facilities with different functions. Based on the demand intensity distribution in the dynamic demand field model, the demand probability for different facility types at each road network node is calculated, generating a facility demand preference probability map for each node. Using this probability map, ant colony members with facility type tags employ a roulette wheel selection algorithm to choose probabilistic paths among road network nodes, driving them to move towards nodes with higher demand matching degrees, thus generating preliminary ant movement paths.

[0076] Subsequently, based on the edge weights of the topologically constrained network, the rationality of facility coordination in each segment of the ant's movement path is evaluated. Path segments that conform to the facility coordination rules are incrementally superimposed with pheromone to enhance the probability of selecting high-quality paths; path segments that do not conform to the rules are penalized with pheromone evaporation to reduce their likelihood of being selected subsequently, thus generating optimized ant movement paths. After multiple iterations, all optimized paths of the ants are collected, and clustering algorithms are used to aggregate the paths, classifying and merging similar or nearly identical layout schemes to generate diverse candidate solutions for facility layouts.

[0077] like Figure 2 As shown, probabilistic path selection is performed based on the demand intensity distribution of the dynamic demand field model, driving individual ants carrying facility type labels to move between road network nodes, generating ant movement paths, including:

[0078] S201: Based on the demand intensity distribution of the dynamic demand field model, the movement direction decision is made for individual ant colonies carrying facility type labels to generate a set of candidate moving nodes.

[0079] S202: Perform facility type matching degree evaluation on the candidate mobile node set and generate node matching degree weight distribution;

[0080] S203: Based on the demand intensity distribution and the node matching degree weight distribution, perform fusion probability calculation to generate a dynamic selection probability distribution;

[0081] S204: Perform roulette wheel selection based on dynamic selection probability distribution to determine the next moving node;

[0082] S205: Based on the next mobile node, perform location updates and trajectory recording on the ant colony individuals carrying facility type tags to generate ant movement paths.

[0083] Specifically, in S201, based on the demand intensity distribution of each road network node in the dynamic demand field model, the ant colony individual carrying facility type label provides a basis for decision-making on the movement direction. The ant colony individual selects nodes whose demand intensity meets a certain threshold according to the demand intensity of its own node and surrounding nodes, and generates a set of candidate moving nodes containing multiple potential movement directions by combining the facility type label it carries.

[0084] In S202, for each node in the candidate mobile node set, its matching degree with the facility type carried by the ant colony is evaluated. Different weight values ​​are assigned to each node based on the matching results, generating a node matching degree weight distribution that reflects the degree of fit between the node and the facility type. In S203, the demand intensity distribution of the dynamic demand field model is fused with the node matching degree weight distribution. A weighted fusion algorithm is used to further increase the weight of nodes with high demand intensity, while also considering the matching degree between the facility type and the node, calculating a dynamic selection probability distribution that comprehensively reflects both demand and matching degree.

[0085] In S204, based on the dynamic selection probability distribution, a roulette wheel selection algorithm is used to determine the node with the highest probability as the next moving node. In S205, the ant colony individuals carrying facility type tags update their positions in the road network according to the determined next moving node, record their movement trajectories, and generate an ant movement path containing multiple consecutive nodes. This path represents a possible facility layout path.

[0086] Furthermore, based on the edge weights of the topologically constrained network, pheromone updates are applied to the ant movement path for collaborative reinforcement, generating an optimized path, including:

[0087] Perform facility coordination rule compliance judgment on the ant movement path and generate path compliance identifier;

[0088] Based on the edge weights and path compliance identifiers of the topologically constrained network, pheromone incremental superposition processing is performed on compliant path segments to generate an enhanced pheromone distribution.

[0089] Based on path compliance identification, pheromone punitive volatilization is applied to non-compliant path segments to generate pheromone suppression measures.

[0090] Based on enhancing pheromone distribution and inhibiting pheromone distribution, a path optimization evaluation process is performed on the ant movement path to generate an optimized path.

[0091] Specifically, the ant movement path undergoes facility coordination rule compliance judgment processing, which checks whether the path traversed by the ant conforms to pre-set facility coordination constraints, such as whether the distance between facilities is reasonable and whether their functions are complementary, generating a path compliance identifier. Compliant path segments are marked as valid, while non-compliant path segments are marked as invalid. Then, based on the edge weights of the topological constraint network and the path compliance identifier, pheromone increment superposition processing is applied to the compliant path segments, increasing the pheromone intensity of the compliant path segments to strengthen the paths conforming to the facility coordination rules, generating a reinforced pheromone distribution.

[0092] Simultaneously, based on path compliance indicators, pheromone punitive evaporation is applied to non-compliant path segments, reducing their pheromone intensity to suppress paths that do not conform to facility coordination rules, thus generating a suppressed pheromone distribution. Subsequently, based on both enhanced and suppressed pheromone distribution, path optimization evaluation is performed on ant movement paths. This involves comprehensively considering pheromone increases and decreases to evaluate and correct the ant movement paths, generating optimized paths that better comply with facility coordination rules and topology-constrained network requirements.

[0093] Furthermore, multi-objective optimization and human-machine collaborative decision-making are performed on the candidate solution set for facility layout to output facility layout schemes, including:

[0094] A multi-objective function evaluation process is performed on the candidate solution set for facility layout to generate a Pareto non-dominated solution set;

[0095] Based on generative adversarial networks, operational performance is extrapolated from Pareto non-dominated solution sets to generate risk prediction reports;

[0096] The system interactively optimizes the expert decision-making weights and risk prediction reports to output a facility layout plan.

[0097] Specifically, a multi-objective function evaluation process is performed on the candidate solution set for facility layout. Multiple objective functions are defined, such as maximizing service coverage, maximizing inter-facility coordination efficiency, and minimizing construction costs. These objective functions measure the merits of facility layout from different dimensions. Each solution in the candidate solution set is substituted into each objective function for calculation, obtaining the performance value of each solution on different objectives, and constructing an objective value matrix. Based on this matrix, a conflict quantification analysis algorithm is used to calculate the degree of conflict between each objective, generating an objective conflict matrix to intuitively show the mutual constraints between different objectives. According to the objective conflict matrix and non-dominated relationship screening rules, the candidate solution set is screened to determine the non-dominated relationship identifier for each solution. A set of high-quality solutions with non-dominated relationships is selected to generate a Pareto non-dominated solution set, in which the solutions achieve a relatively optimal balance among multiple objectives.

[0098] Next, the Pareto non-dominated solution set is input into the operation effect simulation module based on generative adversarial networks to simulate the performance of different solutions in actual operation. Based on operational factors such as tourist flow fluctuations, facility usage frequency, and maintenance costs, a risk prediction report is generated. The report lists in detail the types of risks that each solution may face, the probability of occurrence of the risks, and the potential impact.

[0099] Simultaneously, the decision preference weights of experts for various facility layout schemes were collected. These weights reflect the experts' emphasis and inclination on different objectives. The risk prediction report was combined with the expert decision weights, and an interactive optimization algorithm was used to comprehensively evaluate and optimize the Pareto non-dominated solution set. During the optimization process, risk factors were adjusted according to the expert weights, gradually narrowing the solution set until a facility layout scheme with optimal comprehensive performance and feasibility under multi-objective trade-offs was obtained.

[0100] Furthermore, a multi-objective function evaluation process is performed on the candidate solution set for facility layout to generate a Pareto non-dominated solution set, including:

[0101] The objective function set is defined for the candidate solution set of facility layout;

[0102] Based on the objective function set, conflict quantification analysis is performed on the candidate solution set of facility layout to generate the objective conflict matrix;

[0103] The candidate solution set for facility layout is subjected to non-dominance relation filtering to generate a set of non-dominance relation identifiers;

[0104] Based on the target conflict matrix and the set of non-dominated relation identifiers, a hierarchical processing of the solution set is performed to generate a Pareto non-dominated solution set.

[0105] Specifically, the process involves defining a set of objective functions. This includes considering the multi-dimensional requirements of tourism highway infrastructure layout, such as maximizing service coverage, maximizing inter-facilitation efficiency, and minimizing construction costs, to construct a comprehensive and accurate set of objective functions, providing quantitative basis for subsequent evaluation. Then, this set of objective functions is used to conduct in-depth conflict quantification analysis on the candidate solution set for infrastructure layout. By calculating the degree of conflict between different objectives, i.e., the mutual constraints and attrition relationships between the objective function values, an objective conflict matrix is ​​generated. This matrix intuitively presents the degree of mutual influence between the objectives.

[0106] Subsequently, based on the non-dominated relation theory of multi-objective optimization, each solution in the candidate solution set is screened to identify high-quality solutions that are superior in certain objectives and not completely dominated by other solutions, generating a non-dominated relation identifier set to distinguish which solutions have potential advantages under multi-objective trade-offs. Then, based on the objective conflict matrix and the non-dominated relation identifier set, a more comprehensive solution set hierarchical processing is performed on the candidate solution set. According to the performance of each solution in objective conflicts and the non-dominated relation identifiers, the candidate solution set is divided into multiple levels, thus obtaining the Pareto non-dominated solution set. The solutions in this set represent the optimal facility layout selection under comprehensive multi-objective considerations.

[0107] Furthermore, based on facility coordination rules, a topology constraint network is constructed to generate a topology constraint network, including:

[0108] Define and process the rules for association between facility types to generate a set of facility coordination constraint rules;

[0109] Topology node modeling is performed based on the facility collaboration constraint rule set to generate a topology node set;

[0110] The coordination relationship between facilities is quantified based on the facility coordination constraint rule set to generate an edge weight matrix;

[0111] A topologically constrained network is generated by performing graph structure generation processing based on the topological node set and edge weight matrix.

[0112] Specifically, the association rules for facility types are defined and processed to clarify the collaborative constraints between different facilities, such as the distance requirements between charging piles and rest stations, and the visual accessibility between viewing platforms and tourist points of interest, thus generating a set of facility collaborative constraint rules. Based on the above rule set, topological node modeling is performed for each type of facility, abstracting the key attributes of the facility (such as location, function, service radius, etc.), generating topological nodes, and collecting the node information of all related facilities to generate a set of topological nodes.

[0113] Then, using a set of facility collaboration constraint rules, the collaborative relationships between facilities are quantified. For example, by evaluating factors such as distance, functional complementarity, and traffic connectivity between facilities, the edge weights between each pair of nodes are calculated to reflect the tightness and rationality of collaboration between facilities, generating an edge weight matrix. Next, the topological node set and the edge weight matrix are combined, and a graph structure generation algorithm is used to connect nodes according to their positions and edge weights, constructing a topological constraint network that can comprehensively represent the collaborative relationships between facilities. This network graphically presents the logical connections and interactions between facilities.

[0114] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0115] In one embodiment, such as Figure 3 As shown, this application also provides a multi-source data collaborative intelligent layout system for tourism highway facilities using an ant colony 300, which includes:

[0116] The collaborative fusion module 301 is used to perform collaborative fusion processing on multi-source heterogeneous data to generate a dynamic demand field model.

[0117] Topology construction module 302 is used to perform topology constraint network construction processing based on facility coordination rules to generate a topology constraint network;

[0118] Ant colony optimization module 303 is used to generate a set of candidate solutions for facility layout under dynamic demand field model and topological constraint network by improving the ant colony algorithm.

[0119] The decision optimization module 304 is used to perform multi-objective optimization and human-machine collaborative decision-making on the candidate solution set of facility layout, and output the facility layout scheme.

[0120] Specifically, the collaborative fusion module 301 performs collaborative fusion processing on multi-source heterogeneous data to generate a dynamic demand field model, which can reflect the service facility demand in various areas along the tourist highway in real time. The topology construction module 302 performs topology constraint network construction processing based on facility collaboration rules to generate a topology constraint network, which graphically presents the logical connections and interactions between facilities.

[0121] Ant colony optimization module 303 utilizes an improved ant colony algorithm to generate candidate solutions for facility layout under a dynamic demand field model and topological constraint network, providing diverse solutions for subsequent optimization. Decision optimization module 304 performs multi-objective optimization and human-machine collaborative decision-making on the candidate solutions for facility layout, comprehensively considering multiple objective functions and expert decision weights, and then outputs a facility layout scheme that satisfies multi-objective optimization.

[0122] Ant colony optimization module 303 is also used for:

[0123] The ant colony individuals are bound with facility type tags to generate ant colony individuals carrying facility type tags;

[0124] Based on the demand intensity distribution of the dynamic demand field model, probabilistic path selection is performed to drive individual ants carrying facility type labels to move between road network nodes, generating ant movement paths.

[0125] Based on the edge weights of the topologically constrained network, pheromone updates are used to collaboratively strengthen the ant movement path, generating an optimized path.

[0126] The optimized paths generated iteratively are aggregated to generate candidate solution sets for facility layout.

[0127] Ant colony optimization module 303 is also used for:

[0128] Based on the demand intensity distribution of the dynamic demand field model, the movement direction decision processing of ant colony individuals carrying facility type labels is performed to generate a set of candidate moving nodes.

[0129] The set of candidate mobile nodes is evaluated for facility type matching degree, and a node matching degree weight distribution is generated.

[0130] A dynamic selection probability distribution is generated by performing fusion probability calculation based on the demand intensity distribution and the node matching degree weight distribution.

[0131] The roulette wheel selection process is performed based on a dynamic selection probability distribution to determine the next moving node;

[0132] Based on the next mobile node, the location of individual ants carrying facility type tags is updated and their trajectory is recorded to generate ant movement paths.

[0133] Ant colony optimization module 303 is also used for:

[0134] Perform facility coordination rule compliance judgment on the ant movement path and generate path compliance identifier;

[0135] Based on the edge weights and path compliance identifiers of the topologically constrained network, pheromone incremental superposition processing is performed on compliant path segments to generate an enhanced pheromone distribution.

[0136] Based on path compliance identification, pheromone punitive volatilization is applied to non-compliant path segments to generate pheromone suppression measures.

[0137] Based on enhancing pheromone distribution and inhibiting pheromone distribution, a path optimization evaluation process is performed on the ant movement path to generate an optimized path.

[0138] Decision optimization module 304 is also used for:

[0139] A multi-objective function evaluation process is performed on the candidate solution set for facility layout to generate a Pareto non-dominated solution set;

[0140] Based on generative adversarial networks, operational performance is extrapolated from Pareto non-dominated solution sets to generate risk prediction reports;

[0141] The system interactively optimizes the expert decision-making weights and risk prediction reports to output a facility layout plan.

[0142] Decision optimization module 304 is also used for:

[0143] The objective function set is defined for the candidate solution set of facility layout;

[0144] Based on the objective function set, conflict quantification analysis is performed on the candidate solution set of facility layout to generate the objective conflict matrix;

[0145] The candidate solution set for facility layout is subjected to non-dominance relation filtering to generate a set of non-dominance relation identifiers;

[0146] Based on the target conflict matrix and the set of non-dominated relation identifiers, a hierarchical processing of the solution set is performed to generate a Pareto non-dominated solution set.

[0147] Topology building block 302 is also used for:

[0148] Define and process the rules for association between facility types to generate a set of facility coordination constraint rules;

[0149] Topology node modeling is performed based on the facility collaboration constraint rule set to generate a topology node set;

[0150] The coordination relationship between facilities is quantified based on the facility coordination constraint rule set to generate an edge weight matrix;

[0151] A topologically constrained network is generated by performing graph structure generation processing based on the topological node set and edge weight matrix.

[0152] In one embodiment, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0153] In one embodiment, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0154] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0155] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A multi-source data collaborative intelligent layout method for tourism highway facilities using ant colonies, characterized in that, The method includes: Collaborative fusion processing of multi-source heterogeneous data generates a dynamic demand field model; The topology constraint network is generated by constructing a topology constraint network based on facility coordination rules. By improving the ant colony algorithm, a candidate solution set for facility layout is generated under the dynamic demand field model and the topological constraint network. The candidate solution set for facility layout is subjected to multi-objective optimization and human-machine collaborative decision-making to output the facility layout scheme.

2. The method for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration according to claim 1, characterized in that, The process of generating a candidate solution set for facility layout using an improved ant colony algorithm under the dynamic demand field model and the topological constraint network includes: The ant colony individuals are bound with facility type tags to generate ant colony individuals carrying facility type tags; Based on the demand intensity distribution of the dynamic demand field model, a probabilistic path selection process is performed to drive the individual ants carrying facility type labels to move between road network nodes, generating ant movement paths. Based on the edge weights of the topologically constrained network, the ant movement path is subjected to pheromone update and collaborative reinforcement processing to generate an optimized path; The optimized paths generated iteratively are subjected to solution set aggregation processing to generate the candidate solution set for facility layout.

3. The intelligent ant colony layout method for tourism highway facilities based on multi-source data collaboration according to claim 2, characterized in that, The probabilistic path selection process based on the demand intensity distribution of the dynamic demand field model drives the ant colony individuals carrying facility type labels to move between road network nodes, generating ant movement paths, including: Based on the demand intensity distribution of the dynamic demand field model, the ant colony individuals carrying facility type labels are subjected to movement direction decision processing to generate a candidate set of moving nodes. The candidate mobile node set is subjected to facility type matching degree evaluation processing to generate node matching degree weight distribution; Based on the demand intensity distribution and the node matching degree weight distribution, a fusion probability calculation is performed to generate a dynamic selection probability distribution; Based on the dynamic selection probability distribution, a roulette wheel selection process is performed to determine the next moving node; Based on the next mobile node, the location of the ant colony individual carrying the facility type tag is updated and the trajectory is recorded to generate the ant movement path.

4. The intelligent ant colony layout method for tourism highway facilities based on multi-source data collaboration according to claim 2, characterized in that, The step of performing pheromone update and collaborative reinforcement processing on the ant movement path based on the edge weights of the topologically constrained network to generate an optimized path includes: The ant movement path is processed to determine its compliance with facility coordination rules, and a path compliance identifier is generated. Based on the edge weights of the topologically constrained network and the path compliance identifier, pheromone incremental superposition processing is performed on the compliant path segments to generate an enhanced pheromone distribution; Based on the path compliance identifier, pheromone punitive evaporation treatment is applied to the non-compliant path segments to generate pheromone suppression distribution; Based on the enhanced pheromone distribution and the suppressed pheromone distribution, the ant movement path is evaluated and optimized to generate the optimized path.

5. The intelligent ant colony layout method for tourism highway facilities based on multi-source data collaboration according to claim 1, characterized in that, The process of performing multi-objective optimization and human-machine collaborative decision-making on the candidate solution set for facility layout, and outputting a facility layout scheme, includes: The candidate solution set for facility layout is subjected to multi-objective function evaluation to generate a Pareto non-dominated solution set; Based on a generative adversarial network, the operational effect of the Pareto non-dominated solution set is extrapolated, and a risk prediction report is generated. The expert decision-making weights and the risk prediction report are interactively optimized to output the facility layout plan.

6. The method for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration according to claim 5, characterized in that, The process of performing multi-objective function evaluation on the candidate solution set for facility layout to generate a Pareto non-dominated solution set includes: The objective function set is defined for the candidate solution set of the facility layout; Based on the objective function set, conflict quantification analysis is performed on the candidate solution set of the facility layout to generate the target conflict matrix; The candidate solution set for facility layout is subjected to non-dominance relationship filtering to generate a set of non-dominance relationship identifiers; Based on the target conflict matrix and the set of non-dominated relation identifiers, a solution set hierarchical processing is performed to generate the Pareto non-dominated solution set.

7. The method for intelligent ant colony layout of tourism highway facilities based on multi-source data collaboration according to claim 1, characterized in that, The process of constructing a topology-constrained network based on facility coordination rules to generate a topology-constrained network includes: Define and process the rules for association between facility types to generate a set of facility coordination constraint rules; Based on the facility coordination constraint rule set, topology node modeling is performed to generate a topology node set; Based on the facility collaboration constraint rule set, the collaboration relationship between facilities is quantified to generate an edge weight matrix; The topological constraint network is generated by performing graph structure generation processing based on the set of topological nodes and the edge weight matrix.

8. A multi-source data collaborative intelligent layout system for tourism highway facilities, characterized in that: The system includes: The collaborative fusion module is used to perform collaborative fusion processing on multi-source heterogeneous data to generate a dynamic demand field model. The topology construction module is used to construct topology-constrained networks based on facility coordination rules, generating such networks. The ant colony optimization module is used to generate a candidate solution set for facility layout under the dynamic demand field model and the topological constraint network by improving the ant colony algorithm. The decision optimization module is used to perform multi-objective optimization and human-machine collaborative decision-making on the candidate solution set of facility layout, and output the facility layout scheme.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the multi-source data collaborative intelligent layout method for tourism highway facilities using ant colonies, as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the multi-source data collaborative intelligent layout method for tourism highway facilities using ant colonies, as described in any one of claims 1 to 7.

Images