Urban travel activity prediction method and device based on artificial neural network

Abstract

The present invention relates to the technical field of urban construction planning, and particularly relates to a method and device for predicting urban travel activities based on an artificial neural network, including: constructing an initial urban travel activity prediction model based on the feature relationship between urban basic elements and urban travel activity data in combination with a topological model; calculating the full amount of data of urban travel activities according to a backstepping fitting algorithm to obtain the urban activity travel probability; training the initial urban travel activity prediction model according to the urban activity travel probability, urban travel activity data, and urban construction and renewal plan data to obtain an urban travel activity prediction model; the present invention can more accurately predict the future urban activity travel probability through the urban travel activity prediction model. It can observe the impact of the future urban planning and design plan on urban travel activities according to the future urban activity travel probability, so as to assist in the auxiliary adjustment of the future urban planning and design plan and optimize urban development decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of urban construction planning, and particularly to a method and device for predicting urban travel activities based on an artificial neural network. Background Art

[0002] According to the seventh national population census, the urbanization rate of China's population has exceeded 63%. With the advancement of the urbanization process, the construction and renewal of cities will bring changes to urban travel activities. For example, overly concentrated urban development will lead to the aggregation of travel activities, which will in turn cause problems such as traffic congestion and shortage of service facilities. Therefore, correctly predicting and analyzing the impact of the urban development process on urban travel activities is an important part of the decision-making process for urban planning, construction, and renewal.

[0003] Existing urban travel activity predictions mainly calculate based on theoretical formulas of traditional experience, which can neither grasp the objective data of urban development nor reflect the personalized travel characteristics of different cities. As a result, the traditional approach can no longer meet the increasingly refined urban governance requirements and has also led to frequent occurrences of urban diseases. The existing technology mainly relies on population census data and on-site surveys, and uses empirical theoretical formulas as models to predict urban travel activities. Its deficiencies mainly include:

[0004] 1. Insufficient data coverage: The population census data is sampling survey data and cannot cover all travel activities.

[0005] 2. Inaccurate on-site surveys: On-site surveys are restricted by factors such as human interference, on-site errors, and sampling time, resulting in inaccurate survey data.

[0006] 3. Inaccurate prediction results: Traditional predictions calculate based on theoretical formulas of traditional experience, which can neither grasp the objective laws of urban development nor reflect the personalized travel characteristics of different cities, resulting in inaccurate prediction results.

[0007] 4. Incomplete prediction elements: Traditional predictions only rely on infrastructure data such as land use attributes and building areas, but ignore the significant impact of service facilities (such as catering and education) in the city on travel activities, resulting in prediction results that cannot reflect the objective laws of urban development. Summary of the Invention

[0008] The present invention provides a method and device for predicting urban travel activities based on an artificial neural network to optimize urban development strategies.

[0009] The embodiments of this specification provide a method for predicting urban travel activities based on an artificial neural network, including:

[0010] Collect urban travel activity data;

[0011] Build a topological model of urban basic elements, associate traffic elements, plot elements, and service elements as additional attributes to the topological model, and assign the urban travel activity data to the corresponding cross-section of the topological model;

[0012] Based on the characteristic relationship between urban basic elements and the urban travel activity data, construct an initial urban travel activity prediction model in combination with the topological model;

[0013] Based on the urban travel activity data, calculate the full amount of urban travel activity data by combining the inverse extrapolation fitting algorithm, and process the full amount of urban travel activity data to obtain the urban activity travel probability;

[0014] Obtain urban construction and renewal plan data, and train the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the urban construction and renewal plan data to obtain an urban travel activity prediction model;

[0015] Obtain the current urban travel activity data and urban future planning and design plan data, input the current urban travel activity data and the urban future planning and design plan data into the urban travel activity prediction model to obtain the future urban activity travel probability;

[0016] Auxiliary adjust the urban future planning and design plan according to the future urban activity travel probability.

[0017] Preferably, the collecting of urban travel activity data includes:

[0018] Set the cruising time and cruising points of the drone;

[0019] Collect urban travel activity data within the urban area through the set drone, and the urban travel activity data includes but is not limited to community entrances and exits, main road cross-sections, intersections, traffic road networks, pedestrian flow operation data, vehicle flow operation data, and cross-section calibration data.

[0020] Preferably, the building of the topological model of urban basic elements includes:

[0021] Build a topological model of urban basic elements based on the lines formed by each node and the connections between each node. The nodes include the first type of nodes and the second type of nodes, and the lines include the first type of lines and the second type of lines.

[0022] Preferably, the constructing of the initial urban travel activity prediction model based on the characteristic relationship between urban basic elements and the urban travel activity data and in combination with the topological model includes:

[0023] Abstract the urban basic elements into the characteristic attributes of the first type of nodes and the first type of lines on the topological model, where the first type of nodes are the positions from the travel origin to the travel destination, and the first type of lines are the connections from the travel origin to the travel destination;

[0024] Extract the travel origin-destination characteristics and spatial characteristics from the urban travel activity data;

[0025] Construct an initial urban travel activity prediction model according to the correlation between the travel origin-destination characteristics, the spatial characteristics and the urban activity travel probability.

[0026] Preferably, based on the urban travel activity data, calculate the full amount of urban travel activity data by combining the backtracking fitting algorithm, including:

[0027] Take the community entrances and exits and the intersections as the second type of nodes, and the traffic road network as the second type of lines connecting the second type of nodes, and construct a data backtracking model in combination with the topological model;

[0028] Based on the cross-section calibration data, assign the target value and target range of the first travel volume to the second type of lines of the key connections in the data backtracking model;

[0029] Randomly initialize the first travel volume between each community in the data backtracking model;

[0030] Distribute the first travel volume into the data backtracking model according to travel habits to obtain the full amount of urban travel activity data.

[0031] Preferably, the step of distributing the first travel volume into the data backtracking model according to travel habits includes:

[0032] Distribute the first travel volume to the optimal path in the data backtracking model according to travel habits, and the optimal path includes the optimal combination of the second type of nodes and the second type of lines;

[0033] Calculate the second travel volume currently assigned to the key path;

[0034] Select the third travel volume based on the target value and target range of the first travel volume, and correct the fourth travel volume and the fifth travel volume in the optimal path according to the second travel volume, the third travel volume and the travel volume correction algorithm, where the fourth travel volume is the travel volume between communities including the key path, and the fifth travel volume is the travel volume involving the key path;

[0035] Calculate the sixth travel volume according to the corrected fourth travel volume and the corrected fifth travel volume;

[0036] Based on the sixth trip volume, the minimum optimal entropy is calculated by combining the optimal entropy algorithm to obtain the third trip volume and the sixth trip volume when the optimal entropy is the smallest;

[0037] The sixth trip volume is redistributed according to travel habits, and the above steps are cycled until the ratio of the corrected fifth trip volume to the corrected fourth trip volume between each community is less than a preset value.

[0038] Preferably, the training of the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the urban construction and renewal plan data includes:

[0039] Feature extraction is performed on the urban construction and renewal plan data to obtain urban construction and renewal features;

[0040] The initial urban travel activity prediction model is trained according to the trip origin-destination features, the travel space features, the urban construction and renewal features, and the urban activity travel probability.

[0041] The embodiments of this specification also provide an urban travel activity prediction device based on an artificial neural network, including:

[0042] An information collection module for collecting urban travel activity data;

[0043] A topology model construction module for establishing a topology model of urban basic elements, associating traffic elements, plot elements, and service elements as additional attributes to the topology model, and assigning the urban travel activity data to the corresponding section of the topology model;

[0044] A prediction model construction module for constructing an initial urban travel activity prediction model based on the feature relationship between urban basic elements and the urban travel activity data, in combination with the topology model;

[0045] An inverse inference fitting module for calculating the full amount of urban travel activity data based on the urban travel activity data, in combination with the inverse inference fitting algorithm, and processing the full amount of urban travel activity data to obtain the urban activity travel probability;

[0046] A prediction model training module for obtaining urban construction and renewal plan data, and training the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the urban construction and renewal plan data to obtain an urban travel activity prediction model;

[0047] An activity travel prediction module, configured to obtain current urban travel activity data and urban future planning and design scheme data, and input the current urban travel activity data and the urban future planning and design scheme data into the urban travel activity prediction model to obtain the future urban activity travel probability;

[0048] A scheme adjustment module, configured to assist in adjusting the urban future planning and design scheme according to the future urban activity travel probability.

[0049] An electronic device, wherein the electronic device includes:

[0050] A processor and a memory storing a computer-executable program, and when the executable program is executed, the processor is caused to execute the method described in any one of the above.

[0051] A computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method described in any one of the above is implemented.

[0052] Through the urban travel activity prediction model of the present invention, the future urban activity travel probability can be predicted more accurately, and the impact of the urban future planning and design scheme on urban travel activities can be observed according to the future urban activity travel probability, so as to assist in the auxiliary adjustment of the urban future planning and design scheme and optimize urban development decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0054] Figure 1 It is a schematic diagram of the principle of the urban travel activity prediction method based on an artificial neural network provided by an embodiment of the present specification;

[0055] Figure 2 It is a schematic diagram of the structure of the urban travel activity prediction device based on an artificial neural network provided by an embodiment of the present specification;

[0056] Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present specification;

[0057] Figure 4 It is a schematic diagram of the principle of a computer-readable medium provided by an embodiment of the present specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0058] Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, providing these exemplary embodiments enables the present invention to be more complete and thorough, and more conveniently conveys the inventive concept to those skilled in the art. Like reference numerals in the figures denote like or similar elements, components, or parts, and thus repetitive descriptions thereof will be omitted.

[0059] On the premise of conforming to the technical concept of the present invention, the features, structures, characteristics, or other details described in a specific embodiment may not be excluded from being combined in a suitable manner in one or more other embodiments.

[0060] In the description of specific embodiments, the features, structures, characteristics, or other details described in the present invention are for enabling those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can practice the technical solutions of the present invention without one or more of the specific features, structures, characteristics, or other details.

[0061] The figures shown in the accompanying drawings are only illustrative and do not necessarily include all the content and operations / steps, nor are they necessarily executed in the described order. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

[0062] The block diagrams shown in the accompanying drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0063] The term "and / or" or "and / or" includes all combinations of any one or more of the associated listed items.

[0064] Refer to Figure 1 The schematic diagram of the principle of the urban travel activity prediction method based on artificial neural network provided for the embodiments of this specification includes:

[0065] S101: Collect urban travel activity data;

[0066] Further, the collecting of urban travel activity data includes:

[0067] Set the cruising time and cruising points of the drone;

[0068] Collect urban travel activity data within the urban area through pre-set drones. The urban travel activity data includes, but is not limited to, community entrances and exits, main road sections, intersections, traffic road networks, pedestrian flow operation data, vehicle flow operation data, and section calibration data.

[0069] In a preferred embodiment of the present invention, the drone is set at a specific cruising point, and the cruising time of the drone is set so that the drone collects urban travel activity data within the urban area at the set time. Among them, the urban travel activity data includes community entrances and exits, main road sections, intersections, traffic road networks, pedestrian flow operation data, vehicle flow operation data, section calibration data, etc. By collecting urban travel activity data at fixed points and fixed times by the drone, the high coverage rate and accuracy of the data within the specified time and specified area are ensured.

[0070] S102: Establish a topological model of urban basic elements, associate traffic elements, plot elements, and service elements as additional attributes to the topological model, and assign the urban travel activity data to the corresponding sections of the topological model;

[0071] Furthermore, the establishment of the topological model of urban basic elements includes:

[0072] Establish a topological model of urban basic elements based on the lines formed by each node and the connections between each node. The nodes include the first type of node and the second type of node, and the lines include the first type of line and the second type of line.

[0073] In a preferred embodiment of the present invention, a topological model with urban basic elements is established, and then traffic elements, plot elements, and service elements are associated as additional attributes to the nodes of the topological model and the lines formed by the connections between each node, and the pedestrian flow operation data, vehicle flow operation data, and section calibration data collected by the drone are assigned to the corresponding sections of the topological model. Through the above method, the three major types of facilities in the city, such as traffic infrastructure, plot infrastructure, and service facilities, are regarded as urban elements, which is convenient for establishing an urban travel activity prediction model between the existing urban elements and urban travel activity data through neural network algorithms, and predicting the impact of newly built urban projects or urban renewal projects on urban travel activities, providing more accurate, comprehensive, and city-personalized prediction results, providing auxiliary support for urban development decision-making, and facilitating the subsequent construction of a data reverse inference model to provide data support for the urban travel activity prediction model.

[0074] S103: Based on the characteristic relationship between urban basic elements and the urban travel activity data, construct an initial urban travel activity prediction model in combination with the topological model;

[0075] Further, constructing an initial urban travel activity prediction model based on the characteristic relationship between the urban basic elements and the urban travel activity data, in combination with the topological model, includes:

[0076] Abstracting the urban basic elements into the characteristic attributes of the first type of nodes and the first type of lines on the topological model, where the first type of nodes is the position from the travel starting point to the travel ending point, and the first type of line is the connection from the travel starting point to the travel ending point;

[0077] Extracting the travel starting and ending point features and spatial features from the urban travel activity data;

[0078] Constructing an initial urban travel activity prediction model according to the correlation relationship between the travel starting and ending point features, the spatial features and the urban activity travel probability.

[0079] In a preferred embodiment of the present invention, a characteristic relationship between urban basic elements and urban travel activity data is modeled based on an artificial neural network model. When modeling, in combination with the topological model, the urban basic elements are abstracted into the characteristic attributes of the first type of nodes and the first type of lines on the topological model. On this basis, the travel starting and ending point features and spatial features from the urban travel activity data are extracted, and an initial urban travel activity prediction model is built according to the correlation relationship between the travel starting and ending point features, the spatial features and the urban activity travel probability. Among them, the first type of nodes is the position from the travel starting point to the travel ending point, and the first type of line is the connection from the travel starting point to the travel ending point. Through the above method, the three major types of facilities such as transportation infrastructure, plot infrastructure, and service facilities in the city are associated as urban elements into the constructed initial urban travel activity prediction model. When the urban travel activity prediction model is officially running, it can provide more accurate, more comprehensive, and more in line with the personalized characteristics of the city prediction results, providing auxiliary support for urban development decision-making.

[0080] Specifically, the characteristic attributes Li and Lj of the travel starting point i and the end node j are used as the input layer parameters of the initial urban travel activity prediction model. At the same time, the spatial feature Lij between the travel starting point i and the end node j is calculated and also used as the input layer parameter of the initial urban travel activity prediction model; the travel volume from the travel starting point i to the end node j as the target is used as T 0 ij, and the travel generation rate Pij between the travel starting point i and the end node j is calculated. The calculation formula of the travel generation rate Pij is shown in formula (1):

[0081] Pij = T 0 ij / ∑Tij (1)

[0082] Where Pij is the travel generation rate, T 0The travel volume with ij as the destination, and ∑Tij is the total travel volume departing from the travel origin i to all destination nodes. Among them, the characteristic attributes Li and Lj both include at least one or more of the municipal basic elements, plot basic elements, and social elements, and the spatial feature Lij includes the straight-line distance, driving time, bus time, etc.

[0083] Then, the travel generation rate Pij is used as the output layer parameter of the initial urban travel activity prediction model. Multiple neurons are set in each layer of the input layer and are connected to the neurons in the previous layer. The connection weight transmitted from neuron m in the previous layer to neuron n is Wnm, and the weighted sum value Yn of neuron n is calculated. The calculation formula for the weighted sum value Yn of neuron n is shown in formula (2):

[0084] Yn = ∑(Wnm × An) (2)

[0085] Among them, Yn is the weighted sum value of neuron n, Wnm is the connection weight transmitted from neuron m in the previous layer to neuron n, and Am is the output value of neuron m;

[0086] Use LeakyRelu as the activation function, that is

[0087]

[0088] Among them, ai is any fixed parameter in (1, +∞), f(x) is the input value obtained by neuron n, and xm is the weighted sum of the output values of all the neurons in the previous layer output to neuron n. Thus, the calculation formula for the output value An of neuron n is shown in formula (4):

[0089] An = f(Yn) (4)

[0090] Among them, f(Yn) is the final formula of the input value of neuron n.

[0091] Only a single output neuron is set in the output layer, and cross-entropy is used as the loss function, as shown in formula (5):

[0092]

[0093] Among them, Si is the loss value of neuron n in the current iteration, e is a constant, and k is the kth neuron.

[0094] Thus, the output result is normalized to the interval (0, 1). Furthermore, through the established initial urban travel activity prediction model, taking the travel origin-destination characteristics and spatial characteristics as input parameters and the urban activity travel probability as the output parameter, the characteristic relationship between the two is established, realizing the association of three major types of facilities, namely transportation infrastructure, plot infrastructure, and service facilities in the city, as urban elements, into the constructed initial urban travel activity prediction model. When the urban travel activity prediction model is officially running, it can provide more accurate, comprehensive, and city-personalized characteristic prediction results to provide auxiliary support for urban development decision-making.

[0095] S104: Based on the urban travel activity data, combine the backstepping fitting algorithm to calculate the full amount of urban travel activity data, and process the full amount of urban travel activity data to obtain the urban activity travel probability;

[0096] Further, the calculating the full amount of urban travel activity data based on the urban travel activity data and combining the backstepping fitting algorithm includes:

[0097] Taking the community entrances and exits and the intersections as the second type of nodes, and the traffic road network as the second type of lines connecting the second type of nodes, and constructing a data backstepping model in combination with the topological model;

[0098] Based on the cross-section calibration data, assign the target value and target range of the first travel volume to the key-connected second type of lines in the data backstepping model;

[0099] Randomly initialize the first travel volume between each community in the data backstepping model;

[0100] Allocate the first travel volume to the data backstepping model according to travel habits to obtain the full amount of urban travel activity data.

[0101] Further, the allocating the first travel volume to the data backstepping model according to travel habits includes:

[0102] Allocate the first travel volume to the optimal path in the data backstepping model, and the optimal path includes the optimal combination of the second type of nodes and the second type of lines;

[0103] Calculate the second travel volume currently allocated to the key path;

[0104] Select the third traffic volume based on the target value and target range of the first traffic volume, and correct the fourth traffic volume in the optimal path according to the second traffic volume, the third traffic volume, and the traffic volume correction algorithm, and correct the fifth traffic volume in the fourth traffic volume to obtain the corrected fourth traffic volume and the corrected fifth traffic volume. The fourth traffic volume is the traffic volume between communities including the key path, and the fifth traffic volume is the traffic volume involving the key path;

[0105] Calculate the sixth traffic volume according to the corrected fourth traffic volume and the corrected fifth traffic volume;

[0106] According to the sixth traffic volume, calculate the minimum optimal entropy by combining the optimal entropy algorithm to obtain the third traffic volume and the sixth traffic volume when the optimal entropy is the smallest;

[0107] Redistribute the sixth traffic volume according to travel habits, and loop the above steps until the ratio of the corrected fifth traffic volume to the corrected fourth traffic volume between communities is less than the preset value.

[0108] In a preferred embodiment of the present invention, based on the backstepping fitting algorithm, the full amount of urban travel activities is calculated by backstepping using the cross-section calibration data. The calculation steps include:

[0109] Step 1: Take the community entrances and exits and intersections as the second type of nodes, and the traffic road network as the second type of lines connecting the second type of nodes, and construct a data backstepping model in combination with the topological model;

[0110] Step 2: Assign the target value Vt and target range δVt of the traffic volume to the key connections of the second type of lines in the data backstepping model according to the cross-section calibration data;

[0111] Step 3: Randomly initialize the traffic volume between each community and community. If possible, use the historical statistical traffic volume data between each community and community;

[0112] Step 4: Distribute the traffic volume between each community and community to the optimal path in the data backstepping model according to travel habits. The optimal path includes the optimal combination of the second type of nodes and the second type of lines;

[0113] Step 5: After the traffic volume distribution between all communities is completed, calculate the traffic volume Vcur currently assigned to the key path;

[0114] Step 6, select the traffic volume Vtcur, Vtcur ∈ [Vt - δVt, Vt + δVt], and correct the traffic volume T between the communities including the key path in all optimal paths according to the deviation rate of Vtcur / Vcur ij and the traffic volume T between the communities including the key path ijThe traffic volume δT ij involved in this critical path is corrected, and after summation, a new traffic volume T’ ij is obtained. The new traffic volume T’ ij has the calculation formula as shown in formula (6):

[0115] T’ ij = T ij + ∑(δT ij ) (6)

[0116] where T’ ij is the new traffic volume, T ij is the traffic volume between the sub - areas containing the critical path among all the optimal paths after correction, and δT ij is the traffic volume between the sub - areas containing the critical path after correction, which is the traffic volume ij in T that involves this critical path;

[0117] Step 7: Calculate δV, and the calculation formula is as shown in formula (7):

[0118] δV = V’cur – Vt (7)

[0119] where δV is the total deviation between the assigned flow formed in the current iteration and the target flow, and V’cur is the assigned flow obtained in the current iteration.

[0120] Then, square δV and δT ij with weights, calculate the optimal entropy Ecur, and obtain the value of Vtcur when Ecur is the smallest and its corresponding traffic volume T 0 ’ ij ;

[0121] Step 8: Substitute the traffic volume T 0 ’ ij calculated in Step 7 into Step 4 for a new round of traffic volume allocation, and repeat Steps 5 - 7 until δT ij / T ji is less than a preset value (for example: 1%), and the above - mentioned calculation process ends to obtain the final traffic volume group, which is the full - volume data of urban travel activities.

[0122] In the above - mentioned way, the full - volume data of urban travel activities is deduced, providing more accurate, comprehensive and city - personalized data, providing data support for training the initial urban travel activity prediction model, thereby improving the prediction accuracy of the urban travel activity prediction model.

[0123] S105: Obtain the data of the urban construction and renewal plan, and train the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the data of the urban construction and renewal plan to obtain an urban travel activity prediction model;

[0124] Further, the training of the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the data of the urban construction and renewal plan includes:

[0125] Extract features from the data of the urban construction and renewal plan to obtain urban construction and renewal features;

[0126] Train the initial urban travel activity prediction model according to the travel origin-destination features, the travel space features, the urban construction and renewal features, and the urban activity travel probability.

[0127] In a preferred embodiment of the present invention, the data of the urban construction and renewal plan is obtained, features are extracted from the data of the urban construction and renewal plan to obtain urban construction and renewal features, and then the initial urban travel activity prediction model is trained according to the travel origin-destination features, the travel space features, and the urban construction and renewal features, thereby obtaining an urban travel activity prediction model that conforms to urban travel habits and characteristics. Among them, the travel origin-destination features, the travel space features, and the urban construction and renewal features are used as input parameters for training the initial urban travel activity prediction model, and the urban activity travel probability is used as the output parameter for training the initial urban travel activity prediction model. In the above manner, more accurate, comprehensive, and urban-personalized-feature-conforming data support can be provided for the initial urban travel activity prediction model, thereby improving the prediction accuracy of the urban travel activity prediction model.

[0128] S106: Obtain the current urban travel activity data and the urban future planning and design plan data, and input the current urban travel activity data and the urban future planning and design plan data into the urban travel activity prediction model to obtain the future urban activity travel probability;

[0129] In a preferred embodiment of the present invention, a drone is used to collect current urban travel activity data, and data on future urban planning and design solutions is obtained. Then, feature extraction is performed on the current urban travel activity data and the data on future urban planning and design solutions to obtain current origin-destination features of travel, current spatial features of travel, and current urban construction and renewal features. Then, based on the current origin-destination features of travel, the current spatial features of travel, and the current urban construction and renewal features, the urban travel activity prediction model will output the probability of future urban activity travel. By the above method, the impact of newly built urban projects or urban renewal projects on urban travel activities is predicted, providing a more accurate, comprehensive, and city-personalized feature-compliant prediction result for urban development decision-making.

[0130] S107: Assist in adjusting the future urban planning and design solutions according to the probability of future urban activity travel.

[0131] In a preferred embodiment of the present invention, when the predicted probability of future urban activity travel shows a greater impact on urban travel activities, auxiliary adjustment support will be provided for the future urban planning and design solutions according to the degree of impact to reduce the negative impact of the future urban planning and design solutions on future urban travel activities.

[0132] Figure 2 It is a schematic structural diagram of an urban travel activity prediction device based on an artificial neural network provided in an embodiment of this specification, including:

[0133] An information collection module 201, configured to collect urban travel activity data;

[0134] A topological model construction module 202, configured to establish a topological model of urban basic elements, associate traffic elements, plot elements, and service elements as additional attributes to the topological model, and assign the urban travel activity data to the corresponding cross-section of the topological model;

[0135] A prediction model construction module 203, configured to construct an initial urban travel activity prediction model based on the feature relationship between urban basic elements and the urban travel activity data, in combination with the topological model;

[0136] An inverse inference fitting module 204, configured to calculate the full amount of urban travel activity data based on the urban travel activity data in combination with an inverse inference fitting algorithm, and process the full amount of urban travel activity data to obtain the probability of urban activity travel;

[0137] A prediction model training module 205, configured to obtain urban construction and renewal plan data, and train the initial urban travel activity prediction model according to the probability of urban activity travel, the urban travel activity data, and the urban construction and renewal plan data to obtain an urban travel activity prediction model;

[0138] The activity travel prediction module 206 is used to obtain the current urban travel activity data and the urban future planning and design scheme data, input the current urban travel activity data and the urban future planning and design scheme data into the urban travel activity prediction model, and obtain the future urban activity travel probability;

[0139] The scheme adjustment module 207 is used to assist in adjusting the urban future planning and design scheme according to the future urban activity travel probability.

[0140] Furthermore, the information collection module 201 includes:

[0141] The configuration setting unit is used to set the cruising time and cruising points of the drone;

[0142] The information collection unit is used to collect the urban travel activity data within the urban area through the set drone, and the urban travel activity data includes but is not limited to the community entrance and exit, the main road section, the intersection, the traffic road network, the pedestrian flow operation data, the vehicle flow operation data, and the section calibration data.

[0143] Furthermore, the topology model construction module 202 includes:

[0144] The topology model construction unit is used to establish a topology model of urban basic elements based on the lines formed by each node and the connections between each node. The nodes include the first type of nodes and the second type of nodes, and the lines include the first type of lines and the second type of lines.

[0145] Furthermore, the prediction model construction module 203 includes:

[0146] The topology unit is used to abstract the urban basic elements into the characteristic attributes of the first type of nodes and the first type of lines on the topology model. The first type of nodes is the position from the travel starting point to the travel ending point, and the first type of line is the connection from the travel starting point to the travel ending point;

[0147] The first feature extraction unit is used to extract the travel starting and ending point features and spatial features in the urban travel activity data;

[0148] The prediction model construction unit is used to construct an initial urban travel activity prediction model according to the correlation relationship between the travel starting and ending point features, the spatial features and the urban activity travel probability.

[0149] Furthermore, the inverse inference fitting module 204 includes:

[0150] A data back - inference model construction unit, which is used to take the cell entrances and exits and the intersections as the second - type nodes, and the traffic road network as the second - type lines connecting the second - type nodes, and construct a data back - inference model in combination with the topological model;

[0151] An assignment unit, which is used to assign a target value and a target range of the first traffic volume to the second - type lines of the key connections in the data back - inference model based on the cross - section calibration data;

[0152] An initialization unit, which is used to randomly initialize the first traffic volume between each cell and other cells in the data back - inference model;

[0153] A full - volume data acquisition unit, which is used to distribute the first traffic volume into the data back - inference model according to travel habits to obtain the full - volume data of urban travel activities.

[0154] Further, the full - volume data acquisition unit includes:

[0155] A traffic - volume distribution sub - unit, which is used to distribute the first traffic volume into the optimal paths in the data back - inference model according to travel habits, and the optimal paths include the optimal combination of the second - type nodes and the second - type lines;

[0156] A second traffic - volume calculation sub - unit, which is used to calculate the second traffic volume currently assigned to the key paths;

[0157] A correction sub - unit, which is used to select a third traffic volume based on the target value and target range of the first traffic volume, and correct the fourth traffic volume in the optimal path according to the second traffic volume, the third traffic volume, and the traffic - volume correction algorithm, and correct the fifth traffic volume in the fourth traffic volume to obtain the corrected fourth traffic volume and the corrected fifth traffic volume. The fourth traffic volume is the traffic volume between cells including the key path, and the fifth traffic volume is the traffic volume involving the key path;

[0158] A sixth traffic - volume calculation sub - unit, which is used to calculate the sixth traffic volume according to the corrected fourth traffic volume and the corrected fifth traffic volume;

[0159] An optimal entropy calculation sub - unit, which is used to calculate the minimum optimal entropy according to the sixth traffic volume in combination with the optimal entropy algorithm to obtain the third traffic volume and the sixth traffic volume when the optimal entropy is the smallest;

[0160] An optimization unit, which is used to perform a new round of distribution of the sixth traffic volume according to travel habits, and loop the above steps until the ratio of the corrected fifth traffic volume to the corrected fourth traffic volume between each cell is less than a preset value.

[0161] Further, the prediction model training module 205 includes:

[0162] A second feature extraction unit, configured to extract features from the urban construction and renewal plan data to obtain urban construction and renewal features;

[0163] A model training unit, configured to train the initial urban travel activity prediction model according to the travel origin-destination features, the travel space features, the urban construction and renewal features, and the urban activity travel probability.

[0164] The functions of the device according to the embodiments of the present invention have been described in the above method embodiments. Therefore, for the details not described in this embodiment, reference may be made to the relevant descriptions in the foregoing embodiments, and details will not be repeated herein.

[0165] Based on the same inventive concept, an embodiment of this specification also provides an electronic device.

[0166] The following describes an embodiment of the electronic device of the present invention. This electronic device can be regarded as a specific physical implementation manner of the above method and device embodiments of the present invention. For the details described in the embodiment of the electronic device of the present invention, it should be regarded as a supplement to the above method or device embodiments; for the details not disclosed in the embodiment of the electronic device of the present invention, reference may be made to the above method or device embodiments for implementation.

[0167] Refer to Figure 3 which is a schematic structural diagram of an electronic device provided by an embodiment of this specification. The following refers to Figure 3 to describe the electronic device 300 according to this embodiment of the present invention. Figure 3 The shown electronic device 300 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0168] As Figure 3 shown, the electronic device 300 is presented in the form of a general computing device. The components of the electronic device 300 may include but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different device components (including the storage unit 320 and the processing unit 310), a display unit 340, etc.

[0169] Among them, the storage unit stores program codes, and the program codes can be executed by the processing unit 310, so that the processing unit 310 executes the steps according to various exemplary embodiments of the present invention described in the above processing method part of this specification. For example, the processing unit 310 can execute the steps as Figure 1 shown.

[0170] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 3201 and / or a cache storage unit 3202, and may further include a read-only storage unit (ROM) 3203.

[0171] The storage unit 320 may also include a program / utilities 3204 having a set (at least one) of program modules 3205. Such program modules 3205 include, but are not limited to: an operating device, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0172] The bus 330 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0173] The electronic device 300 may also communicate with one or more external devices 400 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 300, and / or may communicate with any device that enables the electronic device 300 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be through an input / output (I / O) interface 350. Also, the electronic device 300 may communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 360. The network adapter 360 may communicate with other modules of the electronic device 300 through the bus 330. It should be understood that although Figure 3 not shown, other hardware and / or software modules may be used in conjunction with the electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID devices, tape drives, and data backup storage devices, etc.

[0174] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described in the present invention can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solution according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above method according to the present invention. When the computer program is executed by a data processing device, the computer-readable medium can implement the above method of the present invention, that is: asFigure 1 The method shown

[0175] Referring to Figure 4 is a schematic diagram of the principle of a computer-readable medium provided by an embodiment of this specification.

[0176] Implement Figure 1 The computer program for implementing the method shown can be stored on one or more computer-readable media. The computer-readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus, or component, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0177] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program used by or in conjunction with an instruction execution device, apparatus, or component. The program code contained on the readable storage medium can be transmitted by any appropriate medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination of the above.

[0178] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0179] In summary, the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that general-purpose data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or device program (e.g., a computer program and a computer program product) for executing some or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0180] The specific embodiments described above further elaborate on the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

[0181] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0182] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for predicting urban travel activities based on an artificial neural network, characterized in that Including: Collecting urban travel activity data; Based on the nodes and the lines formed by the connections between the nodes, establishing a topological model of urban basic elements. The nodes include the first type of nodes and the second type of nodes, and the lines include the first type of lines and the second type of lines; associating traffic elements, plot elements, and service elements as additional attributes to the topological model, and assigning the urban travel activity data to the corresponding cross-sections of the topological model; Based on the characteristic relationship between the urban basic elements and the urban travel activity data, constructing an initial urban travel activity prediction model in combination with the topological model, including: abstracting the urban basic elements into the characteristic attributes of the first type of nodes and the first type of lines on the topological model, where the first type of nodes is the position from the travel starting point to the travel ending point, and the first type of lines is the connection from the travel starting point to the travel ending point; extracting the travel starting and ending point characteristics and spatial characteristics from the urban travel activity data; constructing an initial urban travel activity prediction model according to the correlation relationship between the travel starting and ending point characteristics, the spatial characteristics, and the urban activity travel probability; Based on the urban travel activity data, calculating the full amount of urban travel activity data in combination with the inverse inference fitting algorithm. Specifically, taking the community entrances and exits and intersections as the second type of nodes, and the traffic road network as the second type of lines connecting the second type of nodes, constructing a data inverse inference model in combination with the topological model; randomly initializing the first travel volume between each community in the data inverse inference model; distributing the first travel volume into the data inverse inference model according to travel habits to obtain the full amount of urban travel activity data; The step of distributing the first travel volume into the data inverse inference model according to travel habits to obtain the full amount of urban travel activity data includes: distributing the first travel volume into the optimal path in the data inverse inference model according to travel habits, where the optimal path includes the optimal combination of the second type of nodes and the second type of lines; calculating the second travel volume currently assigned to the critical path; selecting the third travel volume based on the target value and target range of the first travel volume, and correcting the fourth travel volume in the optimal path and the fifth travel volume in the fourth travel volume according to the second travel volume, the third travel volume, and the travel volume correction algorithm, where the fourth travel volume is the travel volume between communities including the critical path, and the fifth travel volume is the travel volume involving the critical path; calculating the sixth travel volume according to the corrected fourth travel volume and the corrected fifth travel volume; calculating the minimum optimal entropy according to the sixth travel volume in combination with the optimal entropy algorithm to obtain the third travel volume and the sixth travel volume when the optimal entropy is the smallest; performing a new round of distribution of the sixth travel volume according to travel habits, and looping to execute the step of distributing the first travel volume into the data inverse inference model according to travel habits until the ratio of the corrected fifth travel volume to the corrected fourth travel volume between each community is less than the preset value; Processing the full amount of urban travel activity data to obtain the urban activity travel probability; Obtain data on urban construction and renewal plans, and train the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the data on urban construction and renewal plans to obtain an urban travel activity prediction model; Obtain current urban travel activity data and urban future planning and design plan data, and input the current urban travel activity data and the urban future planning and design plan data into the urban travel activity prediction model to obtain the future urban activity travel probability; Auxiliary adjust the urban future planning and design plan according to the future urban activity travel probability.

2. The method for predicting urban travel activities based on an artificial neural network according to claim 1, wherein The collecting of urban travel activity data includes: Set the cruising time and cruising points of the drone; Use the set drone to collect urban travel activity data within the urban area to be collected. The urban travel activity data includes community entrances and exits, main road sections, intersections, traffic road networks, pedestrian flow operation data, vehicle flow operation data, and section calibration data.

3. The urban travel activity prediction method based on artificial neural network according to claim 1, characterized in that The calculating of the full amount of urban travel activity data based on the urban travel activity data in combination with the inverse inference fitting algorithm further includes: Assign the target value and target range of the first travel volume to the second type of line of the key connection in the data inverse inference model based on the section calibration data.

4. The urban travel activity prediction method based on artificial neural network according to claim 1, characterized in that, The training of the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the data on urban construction and renewal plans includes: Extract features from the data on urban construction and renewal plans to obtain urban construction and renewal features; Train the initial urban travel activity prediction model according to the travel origin-destination features, the travel space features, the urban construction and renewal features, and the urban activity travel probability.

5. Urban travel activity prediction device based on artificial neural network, characterized in that, It includes: An information collection module for collecting urban travel activity data; A topology model construction module for establishing a topology model of urban basic elements based on the lines formed by each node and the connections between each node. The nodes include the first type of nodes and the second type of nodes, and the lines include the first type of lines and the second type of lines; associate traffic elements, plot elements, and service elements as additional attributes to the topology model, and assign the urban travel activity data to the corresponding sections of the topology model; A prediction model construction module for constructing an initial urban travel activity prediction model based on the characteristic relationship between urban basic elements and the urban travel activity data in combination with the topology model, including: abstracting the urban basic elements into the characteristic attributes of the first type of nodes and the first type of lines on the topology model. The first type of nodes is the position from the travel origin to the travel destination, and the first type of line is the connection from the travel origin to the travel destination; extract the travel origin-destination features and spatial features from the urban travel activity data; construct an initial urban travel activity prediction model according to the correlation relationship between the travel origin-destination features, the spatial features, and the urban activity travel probability; The reverse inference fitting module is used to calculate the full amount of urban travel activity data based on the urban travel activity data and in combination with the reverse inference fitting algorithm. Specifically, the community entrances and exits and intersections are used as the second type of nodes, and the traffic road network is used as the second type of lines connecting the second type of nodes. A data reverse inference model is constructed in combination with the topological model; the first travel volume between each community in the data reverse inference model is randomly initialized; the first travel volume is allocated to the data reverse inference model according to travel habits to obtain the full amount of urban travel activity data; The step of allocating the first travel volume to the data reverse inference model according to travel habits to obtain the full amount of urban travel activity data includes: allocating the first travel volume to the optimal path in the data reverse inference model according to travel habits, and the optimal path includes the optimal combination of the second type of nodes and the second type of lines; calculating the second travel volume currently allocated to the critical path; selecting the third travel volume based on the target value and target range of the first travel volume, and correcting the fourth travel volume in the optimal path according to the second travel volume, the third travel volume, and the travel volume correction algorithm, and correcting the fifth travel volume in the fourth travel volume to obtain the corrected fourth travel volume and the corrected fifth travel volume, where the fourth travel volume is the travel volume between communities including the critical path, and the fifth travel volume is the travel volume involving the critical path; calculating the sixth travel volume according to the corrected fourth travel volume and the corrected fifth travel volume; calculating the minimum optimal entropy according to the sixth travel volume in combination with the optimal entropy algorithm to obtain the third travel volume and the sixth travel volume when the optimal entropy is the smallest; allocating the sixth travel volume according to travel habits for a new round, and looping to execute the step of allocating the first travel volume to the data reverse inference model according to travel habits until the ratio of the corrected fifth travel volume to the corrected fourth travel volume between each community is less than the preset value; Processing the full amount of urban travel activity data to obtain the urban activity travel probability; The prediction model training module is used to obtain urban construction and renewal plan data, and train the initial urban travel activity prediction model according to the urban activity travel probability, the urban travel activity data, and the urban construction and renewal plan data to obtain an urban travel activity prediction model; The activity travel prediction module is used to obtain the current urban travel activity data and the urban future planning and design plan data, and input the current urban travel activity data and the urban future planning and design plan data into the urban travel activity prediction model to obtain the future urban activity travel probability; The plan adjustment module is used to assist in adjusting the urban future planning and design plan according to the future urban activity travel probability.

6. An electronic device, wherein, The electronic device includes: A processor and a memory storing computer-executable instructions, and the executable instructions, when executed, cause the processor to execute the method according to any one of claims 1-4.

7. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more instructions that, when executed by a processor, implement the method according to any one of claims 1-4.

Images