Influence optimization method and system for traffic network key node mining

Abstract

The invention discloses an influence optimization method and system for traffic network key node mining. The method comprises the steps of obtaining a to-be-processed road network data set; performing file preprocessing and text conversion on the road network data set to obtain a text file of a to-be-input network; the text file is input into a target network for influence optimization processing, and the process comprises the steps that first processing is carried out on the text file through a 2-hop neighborhood estimation influence evaluation factor so as to evaluate the repeated influence from one seed node to another seed node in a road network; performing second processing on the text file through an advanced multi-point crossover operator adaptive parameter strategy; and selecting a seed node set method with optimal influence on the basis of an RN-MA algorithm to carry out iterative processing on the text file after the first processing and the second processing, and determining an optimization result of the influence. The key nodes in the composite urban traffic network can be mined, the efficiency is high, and the method can be widely applied to the technical field of computers.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an influence optimization method and system for mining key nodes in a transportation network. Background Art

[0002] Complex networks are a system model that is ubiquitous in the real world and play an important role in people's daily lives and various professional fields. Whether it is social interaction, the layout of urban traffic, or the flow of information on the Internet, they can all be modeled and analyzed with the help of complex network theory. In such a network, individuals or elements are abstracted as nodes in the network, and the interactions between them are represented by edges or links. If these links have no specific directionality, we call this network an undirected network; on the contrary, if the links have a clear directionality, that is, information or relationships can only flow in a specific direction, it is called a directed network. Through this model, we can have a deeper understanding of the characteristics of the network structure and how nodes and links jointly affect the function and stability of the entire network.

[0003] With the acceleration of globalization and urbanization, urban population density continues to increase, and urban traffic issues are increasingly becoming an important factor restricting urban development. As a core component of urban infrastructure, urban transportation networks are key to urban economic vitality and environmental sustainability. However, the large scale and complex structure of urban transportation networks, coupled with the impact of dynamically changing traffic flows and emergencies, pose huge challenges to the management and optimization of urban transportation networks.

[0004] Traditional urban transportation network node importance assessment methods, such as degree centrality and betweenness centrality, are effective in some cases, but often fail to fully capture the impact of key nodes, especially when the network structure changes dynamically. In addition, these methods have low computational efficiency when processing large-scale network data, making it difficult to meet the requirements of real-time performance and accuracy.

[0005] In order to meet these challenges, scholars have proposed a variety of optimization algorithms based on computational intelligence, such as genetic algorithms, simulated annealing algorithms, particle swarm optimization algorithms, etc. These algorithms have shown certain search capabilities and convergence speeds in solving complex network problems. However, the application of these algorithms in mining key nodes in urban transportation networks still has limitations, including but not limited to:

[0006] (1) Computational efficiency: Existing algorithms often require a long computing time when processing large-scale urban traffic networks, making it difficult to meet real-time requirements.

[0007] (2) Solution quality: Existing algorithms may fall into local optimal solutions during the search process, making it difficult to find the global optimal or approximate optimal solution.

[0008] (3) Adaptability: Existing algorithms often lack sufficient adaptability when faced with dynamic changes in urban transportation networks and find it difficult to respond quickly to changes in network status.

[0009] Although the MA algorithm has shown its advantages in many fields, it still has some shortcomings in the application of mining key nodes in urban transportation networks. For example, the computational efficiency of the existing MA algorithm when processing large-scale networks needs to be improved, the algorithm's adaptability to dynamic changes in the network needs to be strengthened, and the structural information of the network may not be fully utilized when evaluating the influence of nodes. Summary of the invention

[0010] The main purpose of the embodiments of the present invention is to propose an efficient and high-performance influence optimization method and system for mining key nodes in a transportation network, which can mine key nodes in a complex urban transportation network.

[0011] To achieve the above purpose, an embodiment of the present invention proposes an influence optimization method for mining key nodes in a transportation network, comprising the following steps:

[0012] Get the road network dataset to be processed;

[0013] Performing file preprocessing and text conversion on the road network data set to obtain a text file to be input into the network;

[0014] The text file is input into the target network for influence optimization, which includes the following steps:

[0015] The text file is first processed by estimating the influence evaluation factor by a 2-hop neighborhood to evaluate the repeated influence from one seed node to another seed node in the road network;

[0016] Performing a second processing on the text file by using an advanced multi-point crossover operator adaptive parameter strategy;

[0017] The method of selecting the seed node set with the best influence based on the RN-MA algorithm is used to iteratively process the text files after the first and second processing, output the optimal solution, and determine the optimization result of the influence.

[0018] In some embodiments, the performing file preprocessing and text conversion on the road network dataset to obtain a text file to be input into the network comprises the following steps:

[0019] According to the road network data set, the following processes are performed in sequence: simplifying the road network, generating buffer zones, segmenting point elements, generating intersection points through polylines, selecting important nodes through cost, and connecting road spaces;

[0020] Screen out inefficient nodes in the road network and screen out roads with low screening influence;

[0021] Based on the simplified road network dataset, point features are generated through polylines to obtain road network intersections as the node data required in the network:

[0022] Use the degree index to measure and screen out nodes with a degree less than three several times to ensure that the obtained nodes have high influence;

[0023] The resulting nodes are converted into the text file.

[0024] In some embodiments, the expression of the 2-hop neighborhood estimation influence evaluation factor is:

[0025]

[0026] in, represents the 2-hop neighborhood estimated influence evaluation result; C s represents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c, s) is the activation probability of the activated node (s) to the node to be activated (c), and χ represents the repeated influence of the newly activated node (c) and the original seed set (s); is the range of the 1-hop community of node (c); The antecedent of It is used to evaluate the 2-hop influence range of the initial seed node, and the latter two equations evaluate the repeated influence from one seed node to another.

[0027] In some embodiments, the expression of the advanced multi-point crossover operator adaptive parameter strategy is:

[0028] k min =k start +(k end -k start )*(gen / maxGen)

[0029] k∈{i|k min ≤i≤K-1}

[0030] Among them, gen is the current number of iterations, maxGen is the maximum number of iterations; k start and k end are the minimum and maximum number of crossover genes set, k min is the minimum number of randomly generated crossover genes; K is the number of genes contained in an individual in the genetic algorithm; the number of genes to be crossed k is k min Randomly generated between (K-1).

[0031] In some embodiments, the method for selecting the seed node set with the best influence based on the RN-MA algorithm iteratively processes the text files after the first and second processing, outputs the optimal solution, and determines the optimization result of the influence, including the following steps:

[0032] Execute the initialization operator, select candidate nodes according to the fitness index of the input network nodes, treat the node set solution as an individual, and generate an initial population of a certain size;

[0033] Evaluate all individuals in the initial population, perform performance evaluation on the individuals according to the fitness performance index, and obtain a fitness value;

[0034] Executing a crossover operator to exchange gene information between individuals in the initial population, thereby increasing the diversity of individuals in the population and broadening the search solution space;

[0035] Executing a mutation operator to introduce new genes into the initial population to avoid falling into a local optimum;

[0036] Execute the local neighborhood search operator, parallelize the local neighborhood search operator, process all individuals in the population simultaneously in a single search process, combine taboo search to avoid repeated searches, combine the local neighborhood information of individuals in the network, traverse and search all possible solutions in the local neighborhood until the local optimal solution is found;

[0037] Perform global search, parallelize the global search operator, select the individual with the highest fitness among the individuals in the population, compare the selected individuals with the individuals in the population according to the fitness, replace the individuals with smaller fitness, and use them to replace the genes of the individuals in the population;

[0038] Execute the selection operator and elite selection strategy to retain the optimal solution of the current population and simultaneously select suitable individuals to pass on to the next generation;

[0039] Repeat the iterative processing steps until the set number of iterations is met, and output the optimal solution of the population at the end.

[0040] Another aspect of the embodiment of the present invention further provides an influence optimization system for mining key nodes in a transportation network, including:

[0041] The first module is used to obtain the road network dataset to be processed;

[0042] The second module is used to perform file preprocessing and text conversion on the road network dataset to obtain a text file to be input into the network;

[0043] The third module is used to input the text file into the target network for influence optimization processing, and the module includes:

[0044] A first unit is used to perform a first processing on the text file by estimating an influence evaluation factor through a 2-hop neighborhood to evaluate a repeated influence from one seed node to another seed node in the road network;

[0045] A second unit is used for performing a second processing on the text file by using an advanced multi-point crossover operator adaptive parameter strategy;

[0046] The third unit is used to iteratively process the text files after the first and second processing by selecting the seed node set with the best influence based on the RN-MA algorithm, output the optimal solution, and determine the optimization result of the influence.

[0047] In some embodiments, the expression of the 2-hop neighborhood estimation influence evaluation factor is:

[0048]

[0049] in, represents the 2-hop neighborhood estimated influence evaluation result; C s represents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c, s) is the activation probability of the activated node (s) to the node to be activated (c), and χ represents the repeated influence of the newly activated node (c) and the original seed set (s); is the range of the 1-hop community of node (c); The antecedent of It is used to evaluate the 2-hop influence range of the initial seed node, and the latter two equations evaluate the repeated influence from one seed node to another.

[0050] In some embodiments, the expression of the advanced multi-point crossover operator adaptive parameter strategy is:

[0051] k min =k start +(k end -k start )*(gen / maxGen)

[0052] k∈{i|k min ≤i≤K-1}

[0053] Among them, gen is the current number of iterations, maxGen is the maximum number of iterations; k start and k end are the minimum and maximum number of crossover genes set, k min is the minimum number of randomly generated crossover genes; K is the number of genes contained in an individual in the genetic algorithm; the number of genes to be crossed k is k min Randomly generated between (K-1).

[0054] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0055] The memory is used to store programs;

[0056] The processor executes the program to implement the method described above.

[0057] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0058] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0059] The embodiments of the present invention include at least the following beneficial effects: the present invention provides an influence optimization method and system for mining key nodes of a traffic network, the scheme obtains a road network data set to be processed; performs file preprocessing and text conversion on the road network data set to obtain a text file to be input into the network; inputs the text file into the target network for influence optimization processing, the process includes the following steps: first processing the text file through a 2-hop neighborhood estimation influence evaluation factor to evaluate the repeated influence from one seed node to another seed node in the road network; second processing the text file through an advanced multi-point crossover operator adaptive parameter strategy; iteratively processes the text files after the first and second processing based on the RN-MA algorithm to select the seed node set with the best influence, outputs the optimal solution, and determines the optimization result of the influence. The present invention can mine key nodes in a composite urban traffic network, has high efficiency, optimizes the adaptive parameter strategy, and improves processing performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of an implementation environment provided by an embodiment of the present invention;

[0061] Figure 2 is a flow chart of the overall steps provided by an embodiment of the present invention;

[0062] Figure 3 It is a flowchart of a specific implementation process provided by an embodiment of the present invention;

[0063] Figure 4 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present invention. They are only examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the attached claims.

[0065] It is understood that the terms "first", "second", etc. used in the present invention may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0066] The terms "at least one", "multiple", "each", "any", etc. used in the present invention, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0068] The influence optimization method and system for mining key nodes of a traffic network provided by an embodiment of the present invention relate to the field of computer technology. The influence optimization method for mining key nodes of a traffic network provided by an embodiment of the present invention can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a vehicle-mounted terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the influence optimization method for mining key nodes of a traffic network, etc., but is not limited to the above forms.

[0069] The present invention can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present invention can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] like Figure 1 FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention. Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0071] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0072] In addition, the server 101 can also be a node server in the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0073] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal 102 may also be a vehicle-mounted terminal of various device types described above, but is not limited thereto. The terminal 102 and the server 101 may be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment of the present invention.

[0074] Based on the example Figure 1 In the implementation environment shown, an embodiment of the present invention provides an influence optimization method for mining key nodes in a transportation network. The following is an example of applying the influence optimization method for mining key nodes in a transportation network to a server 101. It can be understood that the method can also be applied to a terminal 102.

[0075] Reference Figure 2 , Figure 2 The flowchart of the influence optimization method for mining key nodes in a traffic network applied to a server provided in an embodiment of the present invention, the execution subject of the method can be any of the aforementioned computer devices (including servers or terminals). Figure 2 , the method may include the following steps:

[0076] Get the road network dataset to be processed;

[0077] Performing file preprocessing and text conversion on the road network data set to obtain a text file to be input into the network;

[0078] The text file is input into the target network for influence optimization, which includes the following steps:

[0079] The text file is first processed by estimating the influence evaluation factor by a 2-hop neighborhood to evaluate the repeated influence from one seed node to another seed node in the road network;

[0080] Performing a second processing on the text file by using an advanced multi-point crossover operator adaptive parameter strategy;

[0081] The method of selecting the seed node set with the best influence based on the RN-MA algorithm is used to iteratively process the text files after the first and second processing, output the optimal solution, and determine the optimization result of the influence.

[0082] In some embodiments, the performing file preprocessing and text conversion on the road network dataset to obtain a text file to be input into the network comprises the following steps:

[0083] According to the road network data set, the following processes are performed in sequence: simplifying the road network, generating buffer zones, segmenting point elements, generating intersection points through polylines, selecting important nodes through cost, and connecting road spaces;

[0084] Screen out inefficient nodes in the road network and screen out roads with low screening influence;

[0085] According to the simplified road network dataset, the intersection points of the road network are obtained by generating point features through polylines, which are used as the node data required in the network.

[0086] Use the degree index to measure and screen out nodes with a degree less than three several times to ensure that the obtained nodes have high influence;

[0087] The resulting nodes are converted into the text file.

[0088] In some embodiments, the expression of the 2-hop neighborhood estimation influence evaluation factor is:

[0089]

[0090] in, represents the 2-hop neighborhood estimated influence evaluation result; C s represents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c, s) is the activation probability of the activated node (s) to the node to be activated (c), and χ represents the repeated influence of the newly activated node (c) and the original seed set (s); is the range of the 1-hop community of node (c); The antecedent of It is used to evaluate the 2-hop influence range of the initial seed node, and the latter two equations evaluate the repeated influence from one seed node to another.

[0091] In some embodiments, the expression of the advanced multi-point crossover operator adaptive parameter strategy is:

[0092] k min =k start +(kend -k start )*(gen / maxGen)

[0093] k∈{i|k min ≤i≤K-1}

[0094] Among them, gen is the current number of iterations, maxGen is the maximum number of iterations; k start and k end are the minimum and maximum number of crossover genes set, k min is the minimum number of randomly generated crossover genes; K is the number of genes contained in an individual in the genetic algorithm; the number of genes to be crossed k is k min Randomly generated between (K-1).

[0095] In some embodiments, the method for selecting the seed node set with the best influence based on the RN-MA algorithm iteratively processes the text files after the first and second processing, outputs the optimal solution, and determines the optimization result of the influence, including the following steps:

[0096] Execute the initialization operator, select candidate nodes according to the fitness index of the input network nodes, treat the node set solution as an individual, and generate an initial population of a certain size;

[0097] Evaluate all individuals in the initial population, perform performance evaluation on the individuals according to the fitness performance index, and obtain a fitness value;

[0098] Executing a crossover operator to exchange gene information between individuals in the initial population, thereby increasing the diversity of individuals in the population and broadening the search solution space;

[0099] Executing a mutation operator to introduce new genes into the initial population to avoid falling into a local optimum;

[0100] Execute the local neighborhood search operator, parallelize the local neighborhood search operator, process all individuals in the population simultaneously in a single search process, combine taboo search to avoid repeated searches, combine the local neighborhood information of individuals in the network, traverse and search all possible solutions in the local neighborhood until the local optimal solution is found;

[0101] Perform global search, parallelize the global search operator, select the individual with the highest fitness among the individuals in the population, compare the selected individuals with the individuals in the population according to the fitness, replace the individuals with smaller fitness, and use them to replace the genes of the individuals in the population;

[0102] Execute the selection operator and elite selection strategy to retain the optimal solution of the current population and simultaneously select suitable individuals to pass on to the next generation;

[0103] Repeat the iterative processing steps until the set number of iterations is met, and output the optimal solution of the population at the end.

[0104] The specific implementation process of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings:

[0105] refer to Figure 3 In view of the problems existing in the prior art, the present invention proposes an improved Memetic algorithm, called RN-MA (Road Network Memetic Algorithm), which is used to mine key nodes in a complex urban transportation network. The RN-MA algorithm has the following characteristics:

[0106] (1) Advanced multi-point crossover operator: The innovatively designed multi-point crossover operation allows more genes to be randomly selected adaptively according to the number of iterations during the crossover process, thereby increasing the diversity of solutions and helping the algorithm to escape from the local optimum and explore a broad solution space.

[0107] (2) Parallelized local search operator: The introduction of parallelization methods significantly improves the speed of local search. It allows the creation of a process pool equivalent to the population size in a single local search process, and local searches are performed on all individuals in parallel, which significantly speeds up the convergence and training speed of the entire algorithm.

[0108] (3) 2-hop influence evaluation factor: Combined with the 2-hop influence evaluation factor, not only the direct connection between nodes is considered, but also the indirect influence between nodes is deeply analyzed, which significantly improves the evaluation accuracy of the algorithm.

[0109] (4) Taboo search: A taboo search table is used to prevent the algorithm from continuously searching for the same target and falling into local optimality. By recording the new gene information of previous replacements, repeated replacements can be avoided and a broader solution space can be explored.

[0110] (5) Adaptive parameter adjustment strategy: According to the changes in the iterative process, an adaptive parameter adjustment strategy is adopted to optimize the probability settings of crossover, search, and mutation to improve algorithm performance.

[0111] The invention first processes the OSM data file of the road network, including simplifying the road network, generating buffer zones, segmenting point elements, screening important nodes, and connecting road spaces, and the processing is performed based on ArcGis.

[0112] (1) Simplify the road network: retain primary and secondary roads and remove bicycle lanes, small paths and other roads with low impact.

[0113] (2) Generate buffer: Generate buffer using simplified road network. The purpose is to merge two-way roads on one road into one in order to simplify the road network and then vectorize the road.

[0114] (3) Split point elements: Split the road line at the intersection to obtain the road network intersection, that is, the node data required in the network.

[0115] (4) Screening important nodes by degree: Further screening of network nodes is performed to obtain more influential and critical nodes. Degree indicators are used to measure and nodes with a degree less than three are screened several times to ensure that the obtained nodes have high influence.

[0116] (5) Connecting road space: spatially connect point features with road features, and finally export the road network node information to a text file as the input of the algorithm.

[0117] In order to obtain road network nodes with higher influence and optimize and improve the efficiency of the algorithm, it is necessary to filter out the less efficient nodes in the network. A network with inefficient nodes will interfere with the acquisition of network structure information. In order to simplify the network, it is necessary to filter out the interference of trivial information. We call some nodes with lower importance in urban road structured information inefficient nodes. Inefficient nodes come from the following two factors:

[0118] (1) Urban roads are divided into different levels based on indicators such as infrastructure construction level and traffic carrying capacity. Roads of lower levels have low traffic carrying capacity and fewer traffic operation tasks. The intersections of these roads are inefficient nodes and have little impact on traffic.

[0119] (2) Inefficient nodes have poor connectivity, with only a few or no roads connecting them. That is, the degree of the nodes is small, and these nodes have little impact on traffic flow.

[0120] This invention uses an improved RN-MA algorithm to solve the problem of stable influence propagation on the transportation network. Specifically, it includes: according to the network structure of the transportation network, using the 2-hop influence evaluation factor to effectively evaluate the influence level of candidate nodes in the network, designing adaptive parameter adjustment strategies and parallelization methods, combining crossover, mutation, local search and other operators to improve the algorithm's mining performance and search rate. The steps are as follows:

[0121] (1) 2-hop neighborhood estimation influence evaluation factor:

[0122]

[0123] C srepresents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c, s) is the activation probability of the activated node (s) to the node to be activated (c), and χ represents the repeated influence of the newly activated node (c) and the original seed set (s). is the range of the 1-hop community of node (c). The antecedent of The first equation evaluates the 2-hop influence range of the initial seed node, while the second two equations evaluate the repeated influence from one seed node to another.

[0124] (2) Advanced multi-point crossover operator adaptive parameter strategy:

[0125] k min =k start +(k end -k start )*(gen / maxGen)

[0126] k∈{i|k min ≤i≤K-1}

[0127] gen is the current iteration number, maxGen is the maximum iteration number. K is the number of genes contained in an individual in the genetic algorithm, k start and k end are the minimum and maximum number of crossover genes set, k min This is the minimum number of randomly generated crossover genes. The number of genes k to be crossed is k min The adaptive parameter strategy fully considers the impact of algorithm iteration on solution generation. As Gen increases, the crossover operator will be performed on a larger number of genes.

[0128] (3) Method for selecting the seed node set with the best fitness (influence) based on the RN-MA algorithm:

[0129] (3a) Execute the initialization operator, select candidate nodes according to the fitness index of the input network node, treat the node set as an individual, and generate an initial population of a certain size.

[0130] (3b) Evaluate all individuals in the population, perform performance evaluation on the individuals according to the fitness performance index, and obtain the fitness value;

[0131] (3c) Execute the crossover operator to exchange genetic information between individuals in the population, improve the diversity of individuals in the population, and expand the search solution space;

[0132] (3d) Execute the mutation operator to introduce new genes into the population to avoid falling into the local optimum;

[0133] (3e) Execute the local neighborhood search operator, parallelize the local neighborhood search operator, process all individuals in the population simultaneously in a single search process, combine taboo search to avoid repeated searches, combine the local neighborhood information of the individual in the network, traverse and search all possible solutions in the local neighborhood until the local optimal solution is found;

[0134] (3f) Perform global search and parallelize the global search operator. The algorithm selects the individual with the highest fitness among the individuals in the population, compares it with the individuals in the population according to the fitness, and replaces the individuals with smaller fitness to replace the genes of the individuals in the population;

[0135] (3g) Execute the selection operator and elite selection strategy to retain the optimal solution of the current population and simultaneously select suitable individuals to be passed on to the next generation;

[0136] (3h) Repeat operations (3b) to (3g) until the set number of iterations is met, and output the optimal solution of the population at the end.

[0137] Compared with the prior art, the present invention designs an efficient improved RN-MA algorithm for key node mining and optimization research of transportation networks. The method is based on the meme algorithm and improves the crossover and local search operators. It applies advanced multi-point crossover operators based on adaptive parameter adjustment strategies, taboo search methods, and parallel processing of local search operators. Combined with the 2-hop influence evaluation factor, it deeply analyzes the direct and indirect connections of nodes and evaluates the fitness of nodes.

[0138] Secondly, the present invention also proposes a RN-MA algorithm based on the traffic network to solve the problem of mining and optimizing key nodes of the urban network. Compared with the existing methods, this method has the following advantages:

[0139] (a) Significantly improved computational efficiency: Existing algorithms often require a long computational time when processing large-scale urban traffic networks. The data processing and parallelized local search operator methods in the present invention can significantly speed up the algorithm's search speed and improve the algorithm's efficiency based on existing methods.

[0140] (b) The solution has a higher diversity: The application of advanced multi-point crossover operators and taboo search increases the diversity of solutions, which helps to escape from local optimality and find the global optimal solution.

[0141] (c) Optimizing algorithm performance: The adaptive parameter adjustment strategy enables the algorithm to automatically adjust parameters according to changes in the iterative process, thereby optimizing the performance of the algorithm.

[0142] The embodiment of the present invention also provides an influence optimization system for mining key nodes in a transportation network, including:

[0143] The first module is used to obtain the road network dataset to be processed;

[0144] The second module is used to perform file preprocessing and text conversion on the road network dataset to obtain a text file to be input into the network;

[0145] The third module is used to input the text file into the target network for influence optimization processing, and the module includes:

[0146] A first unit is used to perform a first processing on the text file by estimating an influence evaluation factor through a 2-hop neighborhood to evaluate a repeated influence from one seed node to another seed node in the road network;

[0147] A second unit is used for performing a second processing on the text file by using an advanced multi-point crossover operator adaptive parameter strategy;

[0148] The third unit is used to iteratively process the text files after the first and second processing by selecting the seed node set with the best influence based on the RN-MA algorithm, output the optimal solution, and determine the optimization result of the influence.

[0149] In some embodiments, the expression of the 2-hop neighborhood estimation influence evaluation factor is:

[0150]

[0151] in, represents the 2-hop neighborhood estimated influence evaluation result; C s represents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c, s) is the activation probability of the activated node (s) to the node to be activated (c), and χ represents the repeated influence of the newly activated node (c) and the original seed set (s); is the range of the 1-hop community of node (c); The antecedent of It is used to evaluate the 2-hop influence range of the initial seed node, and the latter two equations evaluate the repeated influence from one seed node to another.

[0152] In some embodiments, the expression of the advanced multi-point crossover operator adaptive parameter strategy is:

[0153] k min =k start +(k end -k start )*(gen / maxGen)

[0154] k∈{i|k min ≤i≤K-1}

[0155] Among them, gen is the current number of iterations, maxGen is the maximum number of iterations; k start and k end are the minimum and maximum number of crossover genes set, k min is the minimum number of randomly generated crossover genes; K is the number of genes contained in an individual in the genetic algorithm; the number of genes to be crossed k is k min Randomly generated between (K-1).

[0156] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0157] The embodiment of the present invention further provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned influence optimization method for mining key nodes of a traffic network when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0158] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0159] See also Figure 4 , Figure 4 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0160] The processor 401 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention;

[0161] The memory 402 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 402 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 402, and the processor 401 calls and executes the influence optimization method for mining key nodes in a transportation network according to the embodiment of the present invention;

[0162] Input / output interface 403, used to implement information input and output;

[0163] Communication interface 404, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0164] Bus 405 , which transmits information between various components of the device (e.g., processor 401 , memory 402 , input / output interface 403 , and communication interface 404 );

[0165] The processor 401 , the memory 402 , the input / output interface 403 and the communication interface 404 are connected to each other in communication within the device via the bus 405 .

[0166] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned influence optimization method for mining key nodes in a transportation network.

[0167] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0168] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The embodiments described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Those skilled in the art can appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0170] Those skilled in the art will appreciate that the technical solutions shown in the figures do not limit the embodiments of the present invention and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0171] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0173] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0174] It should be understood that in the present invention, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0175] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0176] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store programs.

[0179] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the embodiments of the present invention is not limited thereby. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the embodiments of the present invention shall be within the scope of the rights of the embodiments of the present invention.

Claims

1. An influence optimization method for mining key nodes in a transportation network, characterized in that: The following steps are involved: Get the road network dataset to be processed; Performing file preprocessing and text conversion on the road network data set to obtain a text file to be input into the network; The text file is input into the target network for influence optimization, which includes the following steps: The text file is first processed by estimating the influence evaluation factor by a 2-hop neighborhood to evaluate the repeated influence from one seed node to another seed node in the road network; Performing a second processing on the text file by using an advanced multi-point crossover operator adaptive parameter strategy; The method of selecting the seed node set with the best influence based on the RN-MA algorithm is used to iteratively process the text files after the first and second processing, output the optimal solution, and determine the optimization result of the influence.

2. The influence optimization method for mining key nodes in a transportation network according to claim 1 is characterized in that: The process of performing file preprocessing and text conversion on the road network data set to obtain a text file to be input into the network comprises the following steps: According to the road network data set, the following processes are performed in sequence: simplifying the road network, generating buffer zones, segmenting point elements, generating intersection points through polylines, selecting important nodes through cost, and connecting road spaces; Screen out inefficient nodes in the road network and screen out roads with low screening influence; According to the simplified road network dataset, the intersection points of the road network are obtained by generating point features through polylines, which are used as the node data required in the network. Use the degree index to measure and screen out nodes with a degree less than three several times to ensure that the obtained nodes have high influence; The resulting nodes are converted into the text file.

3. The influence optimization method for mining key nodes in a transportation network according to claim 1 is characterized in that: The expression of the 2-hop neighborhood estimation influence evaluation factor is: in, represents the 2-hop neighborhood estimated influence evaluation result; C s represents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c,s) is the activation probability of the activated node s to the node to be activated c, and χ represents the repeated influence of the newly activated node c on the original seed set s; is the range of the 1-hop community of node c; The antecedent of It is used to evaluate the 2-hop influence range of the initial seed node, and the latter two equations evaluate the repeated influence from one seed node to another.

4. The influence optimization method for mining key nodes in a transportation network according to claim 1 is characterized in that: The expression of the advanced multi-point crossover operator adaptive parameter strategy is: k min =k start +(k end -k start )*(gen / maxGen) k∈{i|k min ≤i≤K-1} Among them, gen is the current number of iterations, maxGen is the maximum number of iterations; k start and k end are the minimum and maximum number of crossover genes set respectively; k min is the minimum number of randomly generated crossover genes; K is the number of genes contained in an individual in the genetic algorithm; the number of genes to be crossed k is k min Randomly generated between (K-1).

5. The influence optimization method for mining key nodes in a transportation network according to claim 1 is characterized in that: The method for selecting the seed node set with the best influence based on the RN-MA algorithm iteratively processes the text files after the first and second processing, outputs the optimal solution, and determines the optimization result of the influence, including the following steps: Execute the initialization operator, select candidate nodes according to the fitness index of the input network nodes, treat the node set solution as an individual, and generate an initial population of a certain size; Evaluate all individuals in the initial population, perform performance evaluation on the individuals according to the fitness performance index, and obtain a fitness value; Executing a crossover operator to exchange gene information between individuals in the initial population, thereby increasing the diversity of individuals in the population and broadening the search solution space; Executing a mutation operator to introduce new genes into the initial population to avoid falling into a local optimum; Execute the local neighborhood search operator, parallelize the local neighborhood search operator, process all individuals in the population simultaneously in a single search process, combine taboo search to avoid repeated searches, combine the local neighborhood information of individuals in the network, traverse and search all possible solutions in the local neighborhood until the local optimal solution is found; Perform global search, parallelize the global search operator, select the individual with the highest fitness among the individuals in the population, compare the selected individuals with the individuals in the population according to the fitness, replace the individuals with smaller fitness, and use them to replace the genes of the individuals in the population; Execute the selection operator and elite selection strategy to retain the optimal solution of the current population and simultaneously select suitable individuals to pass on to the next generation; Repeat the iterative processing steps until the set number of iterations is met, and output the optimal solution of the population at the end.

6. An influence optimization system for mining key nodes in a transportation network, characterized in that: include: The first module is used to obtain the road network dataset to be processed; The second module is used to perform file preprocessing and text conversion on the road network dataset to obtain a text file to be input into the network; The third module is used to input the text file into the target network for influence optimization processing, and the module includes: A first unit is used to perform a first processing on the text file by estimating an influence evaluation factor through a 2-hop neighborhood to evaluate a repeated influence from one seed node to another seed node in the road network; The second unit is used for performing a second processing on the text file by using an advanced multi-point crossover operator adaptive parameter strategy; The third unit is used to iteratively process the text files after the first and second processing by selecting the seed node set with the best influence based on the RN-MA algorithm, output the optimal solution, and determine the optimization result of the influence.

7. The influence optimization system for mining key nodes in a transportation network according to claim 6 is characterized in that: The expression of the 2-hop neighborhood estimation influence evaluation factor is: in, represents the 2-hop neighborhood estimated influence evaluation result; C s represents the 1-hop neighbor of seed s, that is, the neighbor directly adjacent to the node, p(c,s) is the activation probability of the activated node (s) to the node to be activated (c), and χ represents the repeated influence of the newly activated node (c) and the original seed set (s); is the range of the 1-hop community of node (c); The antecedent of It is used to evaluate the 2-hop influence range of the initial seed node, and the latter two equations evaluate the repeated influence from one seed node to another.

8. The influence optimization system for mining key nodes in a transportation network according to claim 6 is characterized in that: The expression of the advanced multi-point crossover operator adaptive parameter strategy is: k min =k start +(k end -k start )*(gen / maxGen) k∈{i|k min ≤i≤K-1} Among them, gen is the current number of iterations, maxGen is the maximum number of iterations; k start and k end are the minimum and maximum number of crossover genes set, k min is the minimum number of randomly generated crossover genes; K is the number of genes contained in an individual in the genetic algorithm; the number of genes to be crossed k is k min Randomly generated between (K-1).

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 5.

Images