A Construction Method, Device and Medium for an Autonomous Transportation System Evolution Model

Abstract

The present invention discloses a method, device and medium for constructing an evolutionary model of an autonomous transportation system. The method includes: determining system elements and element attributes according to the architecture of the autonomous transportation system; determining the association relationships of the system elements according to the element attributes; building a multi-layer complex network structure according to the association relationships and inputting a configuration package into the multi-layer complex network structure; establishing an evolutionary model of the complex network of the autonomous transportation system facing the target layer according to the multi-layer complex network structure and in combination with a first preset standard, and determining the attribute of the evolutionary state value of the evolutionary model; determining the initial state value and attribute value of the evolutionary model according to a second preset standard, and driving the evolutionary model to evolve according to the initial state value and attribute value; outputting the evolutionary data of the evolutionary model and performing feature analysis according to the evolutionary data. The beneficial effect of the present invention is that it can scientifically describe and predict the evolutionary characteristics and development laws of the autonomous transportation system, which is beneficial to the sustainable development of the transportation system.

Description

Technical Field

[0001] The present invention relates to the field of traffic system data processing, and in particular to a method, device and medium for constructing an evolutionary model of an autonomous traffic system. Background Art

[0002] With the development of contemporary society, the traffic demand has been further improved. Users hope to obtain active services, and decision-makers also hope that the system can improve its autonomous response ability. Moreover, with the exponential growth of information volume and the accelerating update and iteration, the complexity of the traffic system has been continuously increasing. Relying on humans to command the traffic system can no longer meet the needs, which will promote the accelerated upgrade of the intelligent transportation system (ITS: Intelligent Transportation System) in our country and its development towards a more intelligent autonomous traffic system (ATS: Autonomous Transportation System). The autonomous traffic system is an open and complex giant system with self-organization properties and evolves along the direction of "assisted autonomy - high autonomy - full autonomy".

[0003] Currently, the research on evolutionary models in the domestic and foreign traffic fields mainly focuses on internal levels such as traffic flow, transportation capacity, and transportation modes. There is less research on evolutionary models for the entire traffic system, and there is a lack of systematic theoretical research, and the evolutionary characteristics are not intuitively presented. Summary of the Invention

[0004] In view of this, the embodiments of the present invention provide a method, device and medium for constructing an evolutionary model of an autonomous traffic system, which can scientifically describe and predict the evolutionary characteristics and development laws of the autonomous traffic system, and is beneficial to the sustainable development of the traffic system.

[0005] The first aspect of the embodiments of the present invention provides a method for constructing an evolutionary model of an autonomous traffic system, including:

[0006] Determine system elements and element attributes according to the autonomous traffic system architecture;

[0007] Determine the association relationships of the system elements according to the element attributes;

[0008] Build a multi-layer complex network structure according to the association relationships, and input a configuration package into the multi-layer complex network structure;

[0009] Establish an evolutionary model of the complex network of the autonomous traffic system facing the target layer according to the multi-layer complex network structure, and determine the attribute of the evolutionary state value of the evolutionary model;

[0010] Determine the initial state value and attribute value of the evolution model according to the second preset standard, and drive the evolution of the evolution model according to the initial state value and the attribute value;

[0011] Output the evolution data of the evolution model, and perform feature analysis according to the evolution data.

[0012] Optionally, the determining of system elements and element attributes according to the autonomous transportation system architecture includes:

[0013] Determine the system elements according to the construction requirements of the autonomous transportation system architecture combined with the characteristics of the autonomous transportation system. The system elements include technology, requirements, services, functions, and components.

[0014] Optionally, the determining of system elements and element attributes according to the autonomous transportation system architecture further includes:

[0015] Determine the linkage mechanism of the system elements, and construct an attribute complex network according to the linkage mechanism of the system elements;

[0016] Construct an attribute model according to the attribute complex network;

[0017] Determine the element attributes according to the attribute model combined with the preset dimension.

[0018] Optionally, the determining of the association relationship of the system elements according to the element attributes includes:

[0019] Determine the linkage mechanism of the element attributes by associating the element attributes;

[0020] Determine the association relationship of the system elements according to the linkage mechanism of the element attributes.

[0021] Optionally, the building of a multi-layer complex network structure according to the association relationship and inputting a configuration package into the multi-layer complex network structure includes:

[0022] Successively build a three-layer complex network of the autonomous transportation system including a service layer, a function layer, and a component layer according to the association relationship;

[0023] Determine the nodes inside each layer according to the system elements;

[0024] According to the node mapping relationship between layers and within layers, input the requirements into the service layer, input the technology into the function layer, and input the requirements and the technology into the component layer together.

[0025] Optionally, the establishing of an evolution model of the complex network of the autonomous transportation system facing the target layer according to the multi-layer complex network structure and the determination of the evolution state value attribute of the evolution model include:

[0026] Construct the bottom network of the group hierarchy according to the node set;

[0027] Determine the node strategy and node evolution state of the node set according to the element attributes of the component;

[0028] Calculate the node fitness of the node set according to the technology and the requirements;

[0029] Update the node state of the node set according to the first selection.

[0030] Optionally, determining the initial state value and attribute value of the evolution model according to the second preset criterion, and driving the evolution of the evolution model according to the initial state value and the attribute value includes:

[0031] Determine the initial state value of the evolution model according to the first data;

[0032] Determine the attribute value of the evolution model according to the second data.

[0033] The second aspect of the embodiments of the present invention provides a construction device for an evolution model of an autonomous transportation system, including:

[0034] The first module is used to determine system elements and element attributes according to the autonomous transportation system architecture;

[0035] The second module is used to determine the association relationship of the system elements according to the element attributes;

[0036] The third module is used to build a multi-layer complex network structure according to the association relationship and input a configuration package into it;

[0037] The fourth module is used to establish an evolution model of a complex network of an autonomous transportation system facing the target layer according to the multi-layer complex network structure, in combination with the first preset criterion, and determine the evolution state value attribute of the evolution model;

[0038] The fifth module is used to determine the initial state value and related attribute values of the evolution model according to the second preset criterion, and drive the evolution of the evolution model according to the initial state value and the related attribute values;

[0039] The sixth module is used to output the evolution data of the evolution model and perform feature analysis according to the evolution data.

[0040] The third aspect of the embodiments of the present invention provides an electronic device, including a processor and a memory;

[0041] The memory is used to store programs;

[0042] The processor executes the program to implement the method as described above.

[0043] The fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores a program, and the program is executed by a processor to implement the method as described above.

[0044] The embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the method described above.

[0045] The beneficial effects of the embodiments of the present invention are as follows: According to the autonomous transportation system architecture, the present invention determines the system elements and element attributes; it can divide the system elements for a specific traffic scenario to be studied and list the attributes of each element, laying a foundation for the subsequent research on the evolution model; according to the element attributes, the present invention determines the association relationships of the system elements, and based on the association relationships, builds a multi-layer complex network structure and inputs a configuration package into the multi-layer complex network structure; on the basis of determining the association relationships of the traffic scenario elements, a multi-layer complex network structure is built and a configuration package of the evolution model is input, which can clearly realize the mapping between elements; according to the multi-layer complex network structure, in combination with the first preset standard, the present invention establishes an evolution model of the complex network of the autonomous transportation system facing the target layer and determines the attribute of the evolution state value of the evolution model; according to the second preset standard, the present invention determines the initial state value and attribute value of the evolution model, and drives the evolution model to evolve according to the initial state value and the attribute value; an evolution model is constructed based on the multi-layer complex network, and the evolution process of the traffic system is output through the evolution model and its evolution characteristics and development laws are analyzed, forming a complete set of method systems and revealing the evolution mechanism of the constituent elements of the autonomous transportation system; the evolution data of the evolution model is output, and feature analysis is performed according to the evolution data; through feature analysis, the corresponding changes in the system architecture can be scientifically predicted, providing a decision-making basis for traffic managers to formulate long-term effective market regulation means and macro-control plans, which is beneficial to the sustainable development of the traffic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0047] Figure 1The overall flowchart of the method for constructing an autonomous transportation system evolution model provided by an embodiment of the present invention;

[0048] Figure 2 The schematic diagram of the element linkage mechanism of the autonomous transportation system based on element attributes provided by an embodiment of the present invention;

[0049] Figure 3 The schematic diagram of the multi-layer complex network structure provided by an embodiment of the present invention;

[0050] Figure 4 The schematic diagram of the element association relationship in the vehicle collision warning scenario provided by an embodiment of the present invention;

[0051] Figure 5 The schematic diagram of the system dynamic evolution in the vehicle collision warning scenario provided by an embodiment of the present invention;

[0052] Figure 6 The schematic diagram of the user subject evolution curve in the vehicle collision warning scenario provided by an embodiment of the present invention;

[0053] Figure 7 The schematic diagram of the carrier evolution curve in the vehicle collision warning scenario provided by an embodiment of the present invention;

[0054] Figure 8 The schematic diagram of the infrastructure evolution curve in the vehicle collision warning scenario provided by an embodiment of the present invention. Detailed implementation manners

[0055] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The implementation principle of the method of the present invention will be described in detail below with reference to the drawings of the specification:

[0057] Figure 1 As shown, the overall flowchart of the method for constructing an autonomous transportation system evolution model provided by an embodiment of the present invention includes: determining system elements and element attributes according to the autonomous transportation system architecture; determining the association relationship of system elements according to the element attributes; building a multi-layer complex network structure according to the association relationship and inputting a configuration package into the multi-layer complex network structure; establishing an evolution model of the autonomous transportation system complex network facing the target layer according to the multi-layer complex network structure and determining the evolution state value attributes of the evolution model; determining the initial state value and attribute value of the evolution model according to a second preset criterion, and driving the evolution model to evolve according to the initial state value and attribute value; outputting the evolution data of the evolution model and performing feature analysis according to the evolution data.

[0058] In some embodiments, according to the autonomous transportation system architecture, system elements and element attributes are determined, including:

[0059] Based on the construction requirements of the autonomous transportation system architecture combined with the characteristics of the autonomous transportation system, system elements are determined. The system elements include technology, requirements, services, functions, and components.

[0060] Specifically, the five types of elements of the autonomous transportation system are not limited to the physical level, but rather focus more on describing the system operation, and they interact with each other and are indispensable. The definitions and examples of the elements of the autonomous transportation system are shown in Table 1:

[0061] Table 1

[0062]

[0063]

[0064] It should be noted that through direct or indirect association relationships, the various elements form a set of action mechanisms: technology and requirements act as driving forces to promote the continuous innovation of services, functions, and components, thereby driving the development of the transportation system. The overall association relationship of the system elements is as follows: components, as the core elements, generate and undertake requirements, participate in services, provide functions, and are indirectly affected by technology. Technology directly affects functions at the same time, while functions support services based on information systems, and services in turn meet requirements guided by transportation operations. In addition to the associations between different types of elements, with the replacement of requirements and technology, there are also positive promotion and reverse competition relationships within the component elements.

[0065] In some embodiments, according to the autonomous transportation system architecture, determining system elements and element attributes further includes:

[0066] Determine the linkage mechanism of system elements, and construct an attribute complex network based on the system element linkage mechanism;

[0067] Construct an attribute model based on the attribute complex network;

[0068] Determine element attributes according to the attribute model combined with preset dimensions.

[0069] Specifically, in order to accurately connect the system elements of the autonomous transportation system at a small granularity level, clarify the linkage mechanism of each element participating in traffic activities, and construct an attribute complex network with support and dynamic evolution functions, a multi-level and multi-dimensional model for setting system element attributes is proposed. Taking a specific element participating in the transportation system as the research object, starting from two levels of kernel attributes and external connection attributes, combined with the time-space dimension, target dimension, and connection dimension, composite attributes are mapped. The idea of attribute extraction for the multi-level and multi-dimensional model is shown in Table 2:

[0070] Table 2

[0071]

[0072]

[0073] Then, the element attributes extracted according to the multi-level and multi-dimensional model are shown in Table 3:

[0074] Table 3

[0075]

[0076] Based on the above theoretical framework, five types of elements, namely technology, demand, service, function, and component, are divided for the specific traffic scenarios to be studied, and the attributes of each element are listed, laying a foundation for the subsequent research on the evolution model.

[0077] In some embodiments, according to the element attributes, the association relationships of system elements are determined, including:

[0078] By associating the element attributes, the linkage mechanism of the element attributes is determined;

[0079] According to the linkage mechanism of the element attributes, the association relationships of the system elements are determined.

[0080] Specifically, Figure 2 Shown is a schematic diagram of the linkage mechanism of autonomous traffic system elements based on element attributes, which shows the association relationships among the core attributes and external connection attributes of each element in Table 3 and the association relationship between the core attribute and the external connection attribute realized through the autonomous operation logic in the core attribute of the function element and the associated service set in the external connection attribute, achieving the precise connection of system elements at the small particle level. Among them, it should be noted that the internal relationships of services in the external connection attribute of service elements include: promotion, competition, and irrelevance, and the internal relationships of functions in the external connection attribute of function elements include: serial, competition, and parallel.

[0081] In some embodiments, according to the association relationships, a multi-layer complex network structure is built, and a configuration package is input into the multi-layer complex network structure, including:

[0082] According to the association relationships, a three-layer complex network of autonomous traffic systems, namely the service layer, the function layer, and the component layer, is built in sequence;

[0083] According to the system elements, the nodes inside each layer are determined;

[0084] According to the mapping relationships between nodes across layers and within layers, the demand is input into the service layer, the technology is input into the function layer, and the demand and technology are jointly input into the component layer.

[0085] Specifically, based on the correlation relationships between elements and referring to the relevant theories of game theory and its evolutionary dynamics, Figure 3 As shown in Figure 3 , the technical route for determining the multi-layer complex network structure is as follows: construct a three-layer complex network of a service layer, a function layer, and a component layer from top to bottom. Determine the internal nodes of each layer according to the specific traffic scenario elements in the system elements, and determine the node mapping relationships between layers and within layers from the perspective of element correlations; demand and technology, as the internal and external driving forces for the evolution of the traffic system, are respectively input into the service layer and the function layer, and at the same time input into the component layer; through the mapping relationships, the layers play an organizational role from top to bottom and conduct evolutionary feedback from bottom to top. It should be noted that demand and technology first activate the relevant nodes within the service layer and the function layer. The component layer evolves autonomously through games internally, and then feeds back to the function layer and the service layer, driving the evolution of the nodes in the two layers. Therefore, the evolution processes of the service layer and the function layer are not quantitatively represented. On the basis of determining the correlation relationships of traffic scenario elements, build a complex network of the service layer, the function layer, and the component layer, and configure the technology package and demand package input into the evolution model to realize the mapping between elements.

[0086] In some embodiments, according to the multi-layer complex network structure, combined with the first preset criterion, establish an evolution model of the autonomous traffic system complex network for the target layer, and determine the attribute of the evolution state value of the evolution model, including:

[0087] (1) Construct the bottom network of the component layer according to the node set;

[0088] Specifically, construct an undirected weighted signed network as the bottom network of the component layer, denoted by g=(V,ε,W).

[0089] It should be noted that V={v1,v2,…,v n} is the node set, and each node represents a component; ε is the edge set, describing the positive and negative connection relationships between components. Let A=(a ij ) n×n be the adjacency matrix of the component layer network. If there is an association between two components, it is 1; if there is no association, it is 0; the weight matrix is W=(w ij ) n×n , used to characterize the interaction intensity between the component nodes, corresponding to the association intensity in the component attributes; let N i ={v j ∈V|a ij =1} and d i =|N i | respectively represent the neighbor set and the node degree of the component nodes.

[0090] (2) Determine the node strategies and node evolution states of the node set according to the element attributes of the components;

[0091] Specifically, the set of individuals participating in the game forms a population. The only difference among all participating individuals lies in the strategies they use. Therefore, combining with the attribute of component elements, the strategy represents the component type, which is determined by technology and demand, and each node represents a strategy.

[0092] It should be noted that according to the number of individuals participating in the game, it can be divided into finite population game and infinite population game. In the actual traffic scenario, the specific number of each component cannot be accurately counted. Therefore, the evolutionary game of the component layer belongs to the infinite population game. Thus, the node evolutionary state value is defined as the market share of the same type of components.

[0093] (3) Calculate the node fitness of the node set according to the technology and the said demand;

[0094] In the evolutionary game dynamics model, the payoff of an individual in the population game is often converted into fitness, which can be understood as a measure of the superiority or inferiority in the game. The evolutionary dynamics on complex networks is divided into constant selection process and frequency-dependent selection process. The evolution of the component layer belongs to the former, that is, the fitness of the component node is a constant with respect to its own strategy, and does not change with the change of the population evolutionary state value (the market share of other components), but will change with the change of technology and demand.

[0095] Before conducting the evolutionary game through fitness, it is necessary to first calculate the payoff generated by the strategy. Here, it can be understood as the influence of technology and demand on the competitiveness of components. The payoff calculation formula is:

[0096]

[0097] In the formula: β1 and β2 are the technology influence coefficient and demand satisfaction coefficient respectively; β3 is a constant term; u is the fluctuation coefficient; represents the overall influence of the autonomous level of the associated technology set; represents the overall satisfaction of the demand target level of the associated demand set.

[0098] In the evolutionary model, the same type of components form a small network, and various small networks form a large component network. The evolutionary game occurs in the small network respectively, and the mutual influence between different types of components is reflected in the fitness. Therefore, when calculating the node fitness, in addition to its own payoff, the promoting or inhibiting influence of different types of components also needs to be considered.

[0099] After calculating the payoff of each node, combine the association relationship and weight to deduce the fitness of each component node. The formula is as follows:

[0100]

[0101] In the formula: w fis the selection intensity, representing the impact of the benefit on the fitness, generally taken as 1; π i (x) is the benefit of node i; N i’ is the set of different class components among the neighbor nodes of node i; w ij is the weight between nodes, corresponding to the correlation strength attribute of the components.

[0102] (4) Update the node states of the node set according to the first selection.

[0103] Specifically, a birth-death process is selected for game to update the node states among the same class components. The birth-death process belongs to a Markov process. It means that at each step, an individual is first selected from the network with a probability proportional to the fitness. This individual generates a replicated individual with the same strategy as itself and replaces one of its neighbors with this replicated individual. The probability of the neighbor being selected is proportional to the weight of the edge between the two. In this model, each node represents a strategy, so it is generalized: instead of replacing the entire node, it is the transfer of the evolutionary state value.

[0104] The evolutionary state value of each node may increase, decrease, or remain unchanged in the next state. The transition probability of each node is derived according to the definition of the birth-death process. It should be noted that when a new class of components first enters the market, although the evolutionary state value is very low, the growth rate is fast and slows down when approaching 1. On the contrary, the evolutionary state value of components with weak autonomy will become lower and lower, and it is easier to be eliminated when approaching 0. Considering the above characteristics, a control function needs to be constructed. Here, a deformation of the sigmoid function is considered and discussed in different cases. The relevant formulas are as follows:

[0105] ① Increase probability:

[0106] In the formula: r i is the fitness of node i; v x is the node of the same class component, N s is the set of nodes of the same class component; α is the advantage-disadvantage variable, taking 1 for the dominant component and -1 for the inferior component; k is the scaling coefficient, and the sigmoid function is translated and scaled according to the value of k; E i is the evolutionary state value of node i;

[0107] ② Decrease probability:

[0108] In the formula: v j is the neighbor node of the same class of node i, N i is the set of neighbor nodes of the same class of node i; v y is the neighbor node of the same class of node j, N j is the set of neighbor nodes of the same class of node j; p j is the increase probability of node j; wij is the weight between node i and node j, w yj is the weight between node y and node j;

[0109] ③ Stationary probability: I i = 1 - p i - q i

[0110] In the formula: p i is the increase probability of node i; q i is the decrease probability of node i;

[0111] The above is the establishment process of the group layer evolution dynamics model. Programming in Python according to the model formula, a static network can be built with the help of NetworkX and dynamic evolution can be realized

[0112] In some embodiments, according to the second preset criterion, the initial state value and attribute value of the evolution model are determined, and the evolution model is driven to evolve according to the initial state value and attribute value, including:

[0113] Determine the initial state value of the evolution model according to the first data;

[0114] Determine the attribute value of the evolution model according to the second data.

[0115] Specifically, before driving the evolution, according to the input requirements of the evolution model, the initial evolution state value and related attribute values are determined. First, the market share of the components in the current generation is statistically obtained through market research, which is the initial evolution state value. Then, the relevant attribute values of each element are determined through methods such as expert consultation and bibliometrics. The relevant attribute values of element evolution and the determination methods are shown in Table 4:

[0116] Table 4

[0117]

[0118] After determining the initial evolution state value of the components and the relevant attribute values of each element in the corresponding traffic scenario, they are input into the evolution model. First, the evolution of the group layer is driven, and then the evolution of the service layer and the function layer is driven through feedback, realizing the activation, change, and extinction of the nodes in the network.

[0119] In some embodiments, from the specific steps of building the evolution model, the evolution process of the group layer can be quantitatively represented by the evolution state value, and the evolution of the service layer and the function layer can only reflect the activation and extinction of the nodes. First, the corresponding relationship between the number of iterations and the actual time in the evolution game process is determined, and then the state changes of each element are output in real time to predict the evolution process of the traffic system. Through feature analysis, its evolution characteristics and development laws are scientifically described, so as to provide a decision-making basis for traffic managers.

[0120] Taking a specific traffic scenario as an example, the present invention will be further described in detail with reference to the accompanying drawings and specific data. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0121] In the scenario of "vehicle collision warning at signal - free intersections based on V2X", it can be achieved through the following steps:

[0122] (a) The scenario of "vehicle collision warning at signal - free intersections based on V2X" means that when a vehicle enters a signal - free intersection, due to problems such as out - of - sight and non - line - of - sight, there are potential vehicle collision hazards. The vehicle senses its own position and driving state, and through V2X communication technology, realizes interactive communication with other vehicles and roadside devices. By processing the data of surrounding vehicles through relevant algorithms, it judges whether there are threatening vehicles and issues warning information, and the driver adjusts the speed independently to avoid collisions. Based on the basic element theory and scenario process, five types of traffic elements in the current scenario are divided, and the attribute values of the above elements are set according to the multi - level and multi - dimensional model, as shown in Table 5:

[0123] Table 5

[0124]

[0125]

[0126] (b) According to the interaction mechanism between elements, starting from the external connection attributes, the correlation relationship between scenario elements is initially constructed. The correlation relationship between the five types of elements in the vehicle collision warning scenario is shown in Table 6:

[0127] Table 6

[0128]

[0129]

[0130]

[0131] It should be noted that the service object in the table is used for the "positive and negative direction" setting between components, and only the function provider exists in the "associated component set" of each element. Figure 4 The figure shows the schematic diagram of the element correlation relationship in the vehicle collision warning scenario, which details the specific correlation relationship between the five types of elements in this scenario. The correlation between components and technology, and requirements can be transmitted through service functions.

[0132] (c) According to the evolutionary dynamics model on the group - layered complex network, the strategy represents the component type, which is determined by technology and requirements, and each node represents a strategy. The group - layered network nodes and corresponding strategy combinations are shown in Table 7:

[0133] Table 7

[0134]

[0135]

[0136] (d) Determine the initial evolution state value and related attribute values through methods such as market research, bibliometric analysis, and expert demonstration, and input them into the evolution model to drive the evolution of elements at each layer. To intuitively represent the evolution process, program in Python according to the model formula, and build a static network and implement dynamic evolution with the help of NetworkX. Figure 5 The schematic diagram of the system dynamic evolution in this traffic scenario is shown. The nodes on the left represent the input demand and technical elements. The nodes in the middle form the group layering. The function layer and service layer are arranged in sequence to the right. The numbers under the component nodes are the evolution state values, which change continuously with the game.

[0137] (e) Output the state changes of each element in this scenario in real time through Python programming. Since this embodiment only involves five types of elements in this scenario in the current generation, with a relatively large granularity, services and functions will not evolve and die out. The evolution process is mainly reflected in the changes of the evolution state values of each component. Refer to Figure 6 、 Figure 7 and Figure 8 The schematic diagram of the evolution curves of each component node. By analyzing the state values of each component node after 20,000 iterations, it can be found that the evolution state values of each component node fluctuate and change in a certain trend. The evolution state values of components with strong competitiveness are getting higher and higher, and the evolution state values of components with weak competitiveness are getting lower and lower until they die out, which conforms to the objective law.

[0138] Through the analysis of the system evolution in this scenario, it can be known that the evolution and development of the autonomous transportation system do not follow a simple linear law, but show a non-linear law of mutual restriction. Obvious characteristics of ecosystem evolution will appear during the development and evolution process. Because it is itself a composite ecosystem with traffic activities as the main body, affected by relevant policies, economic development, resource environment and other factors, and interacting with demand and technical elements within a specific time and space range. Therefore, similar to the evolution of the ecosystem, the development of elements in the transportation system has a law of increasing first and then decreasing scale benefits. Therefore, by enhancing its own demand and technical competitiveness and improving the utilization efficiency of resource environment, sustainable and stable development can be achieved, which also provides a basis for macro decision-making for managers.

[0139] The embodiment of the present invention provides a construction device for an evolution model of an autonomous transportation system, including:

[0140] The first module is used to determine system elements and element attributes according to the autonomous transportation system architecture;

[0141] A second module, configured to determine the association relationship of the system elements according to the element attributes;

[0142] A third module, configured to build a multi-layer complex network structure according to the association relationship and input a configuration package thereto;

[0143] A fourth module, configured to establish an evolution model of the complex network of the autonomous transportation system for the target layer according to the multi-layer complex network structure in combination with a first preset criterion, and determine the evolution state value attribute of the evolution model;

[0144] A fifth module, configured to determine the initial state value and related attribute values of the evolution model according to a second preset criterion, and drive the evolution of the evolution model according to the initial state value and the related attribute values;

[0145] A sixth module, configured to output the evolution data of the evolution model and perform feature analysis according to the evolution data.

[0146] The content of the method embodiment of the present invention is applicable to the apparatus embodiment of the present invention. The functions specifically implemented by the apparatus embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method.

[0147] An embodiment of the present invention provides an electronic device, including a processor and a memory;

[0148] The memory is used for storing a program;

[0149] The processor executes the program to implement a method for constructing an evolution model of an autonomous transportation system.

[0150] The content of the method embodiment of the present invention is applicable to the electronic device embodiment of the present invention. The functions specifically implemented by the electronic device embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method.

[0151] In summary, the above embodiments start from the constituent elements and association relationships of the autonomous transportation system, construct an evolution model based on the game on the complex network and its evolution dynamics theory, output the evolution process of the transportation system, analyze its evolution characteristics and development laws, reveal the evolution mechanism of the constituent elements of the autonomous transportation system, can scientifically describe and predict the evolution characteristics and development laws of the system architecture, provide a basis for macro decision-making for managers, so as to formulate long-term and effective market regulation means and macro-control plans, and are beneficial to the sustainable development of the transportation system.

[0152] Embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned method.

[0153] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order mentioned in the operation diagrams. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated, in which the order of various operations is changed and the sub-operations described as part of a larger operation are executed independently.

[0154] Furthermore, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features described may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It can also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More precisely, considering the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skills of an engineer. Therefore, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It can also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0155] If the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs.

[0156] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0157] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0158] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0159] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0160] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

[0161] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A construction method for an autonomous traffic system evolution model, characterized in that, including: Determine system elements and element attributes according to the architecture of the autonomous transportation system; Among them, the determining of system elements and element attributes according to the architecture of the autonomous transportation system includes: Determine the system elements according to the construction requirements of the autonomous transportation system architecture combined with the characteristics of the autonomous transportation system. The system elements include technology, requirements, services, functions, and components. The components represent the physical elements participating in passenger and freight transportation activities in the transportation system, including people, goods, vehicles, roads, and the environment; Determine the association relationships of the system elements according to the element attributes; Build a multi-layer complex network structure according to the association relationships and input a configuration package into the multi-layer complex network structure; Among them, the building of a multi-layer complex network structure according to the association relationships and inputting a configuration package into the multi-layer complex network structure includes: Successively build a three-layer complex network of the autonomous transportation system for the service layer, function layer, and component layer according to the association relationships; Determine the nodes inside each layer according to the system elements; According to the node mapping relationships between and within layers, input the requirements into the service layer, input the technology into the function layer, and input the requirements and the technology into the component layer together; Establish an evolution model of the complex network of the autonomous transportation system for the target layer according to the multi-layer complex network structure in combination with the first preset standard, and determine the attribute of the evolution state value of the evolution model; Among them, the establishing of an evolution model of the complex network of the autonomous transportation system for the target layer according to the multi-layer complex network structure in combination with the first preset standard, and determining the attribute of the evolution state value of the evolution model includes: Build the bottom network of the component layer according to the node set; Determine the node strategies and node evolution states of the node set according to the element attributes of the components; Calculate the node fitness of the node set according to the technology and the requirements; Update the node states of the node set according to the first selection; Determine the initial state value and attribute value of the evolution model according to the second preset standard, and drive the evolution model to evolve according to the initial state value and the attribute value; Output the evolution data of the evolution model and perform feature analysis according to the evolution data.

2. The construction method of an autonomous transportation system evolution model according to claim 1, characterized in that The determining of system elements and element attributes according to the architecture of the autonomous transportation system further includes: Determine the linkage mechanism of the system elements and build an attribute complex network according to the linkage mechanism of the system elements; Build an attribute model according to the attribute complex network; Determine the element attributes according to the attribute model in combination with the preset dimension.

3. The construction method of an autonomous traffic system evolution model according to claim 1, characterized in that The determining of the association relationships of the system elements according to the element attributes includes: Determine the element attribute linkage mechanism by associating the element attributes; Determine the association relationships of the system elements according to the element attribute linkage mechanism.

4. The construction method of an autonomous traffic system evolution model according to claim 1, characterized in that, The determining of the initial state value and attribute value of the evolution model according to the second preset standard, and driving the evolution model to evolve according to the initial state value and the attribute value includes: Determine the initial state value of the evolution model according to the first data; Determine the attribute value of the evolution model according to the second data.

5. An apparatus for constructing an evolutionary model of an autonomous transportation system, characterized in that, including: The first module is used to determine system elements and element attributes according to the autonomous transportation system architecture; Among them, determining system elements and element attributes according to the autonomous transportation system architecture includes: Determining the system elements according to the construction requirements of the autonomous transportation system architecture in combination with the characteristics of the autonomous transportation system. The system elements include technology, requirements, services, functions, and components. The components represent each physical element participating in passenger and freight transportation activities in the transportation system, including people, goods, vehicles, roads, and the environment; The second module is used to determine the association relationships of the system elements according to the element attributes; The third module is used to build a multi-layer complex network structure according to the association relationships and input a configuration package into it; Among them, building a multi-layer complex network structure according to the association relationships and inputting a configuration package into the multi-layer complex network structure includes: Sequentially building a three-layer complex network of the autonomous transportation system for the service layer, function layer, and component layer according to the association relationships; Determining the nodes inside each layer according to the system elements; According to the node mapping relationships between and within the layers, inputting the requirements into the service layer, inputting the technology into the function layer, and inputting the requirements and the technology into the component layer together; The fourth module is used to establish an evolution model of the complex network of the autonomous transportation system facing the target layer according to the multi-layer complex network structure in combination with the first preset standard, and determine the evolution state value attributes of the evolution model; Among them, establishing an evolution model of the complex network of the autonomous transportation system facing the target layer according to the multi-layer complex network structure in combination with the first preset standard, and determining the evolution state value attributes of the evolution model includes: Building the bottom network of the component layer according to the node set; Determining the node strategies and node evolution states of the node set according to the element attributes of the components; Calculating the node fitness of the node set according to the technology and the requirements; Updating the node states of the node set according to the first selection; The fifth module is used to determine the initial state value and related attribute values of the evolution model according to the second preset standard, and drive the evolution of the evolution model according to the initial state value and the related attribute values; The sixth module is used to output the evolution data of the evolution model and perform feature analysis according to the evolution data.

6. An electronic device, characterized in that, It includes 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 4.

7. A computer-readable storage medium, characterized in that, The storage medium stores a program, and the program is executed by the processor to implement the method according to any one of claims 1 to 4.

Images