Urban traffic demand prediction method and device, equipment and storage medium

Abstract

The invention provides an urban traffic demand prediction method and device, equipment and a storage medium. The method comprises the following steps: acquiring all mobile phone signaling data of an operation end in a preset time period in any target residence, wherein all the mobile phone signaling data are mobile phone signaling data of a preset number of users in the target residence acquired by the operation end in the preset time period; extracting traffic data of each user according to the mobile phone signaling data of each user; according to the traffic data of each user, a job and residence place model of each user is constructed, and the job and residence place model comprises a residence place and a working place of each user, commuting time and a track line; constructing an OD matrix according to the occupational and residential place models of all users, wherein the OD matrix is used for representing travel flow from one area to another area; and according to the OD matrix and the residual network, an urban traffic demand prediction model is constructed, obtained traffic data is real and credible, and travel data such as resident commuting in a large-scale city can be comprehensively fed back.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic planning and analysis, and in particular to a method, device, equipment and storage medium for predicting urban traffic demand. Background Art

[0002] The rapid development of intelligent transportation systems has made urban traffic demand forecasting a focus of attention. The further development of intelligent and refined transportation management has put forward higher requirements for the accuracy and timeliness of traffic demand forecasting. Due to the difficulty in obtaining basic survey data on urban traffic demand, the problem of urban traffic demand forecasting has always been a challenging research topic.

[0003] In the existing urban traffic demand forecast, urban traffic demand is mainly counted through sampling surveys at traffic entrances and exits, important hubs and other locations.

[0004] However, the existing methods of conducting statistical surveys on urban traffic demand are time-consuming, labor-intensive, and inefficient. In addition, the validity and authenticity of the survey data are difficult to guarantee, and it is difficult to fully feedback travel data such as commuting of residents in large cities. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for predicting urban traffic demand, which are used to solve the technical problems that the means of urban traffic demand statistical survey in the prior art are time-consuming, labor-intensive, inefficient, and the validity and authenticity of the survey data are difficult to ensure, and the constructed urban traffic demand prediction model has poor training effect, low training accuracy, and poor model versatility.

[0006] In a first aspect, the present application provides a method for predicting urban traffic demand, comprising:

[0007] Acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all the mobile phone signaling data is the mobile phone signaling data of a preset number of users in the target residence collected by the operator within the preset time period;

[0008] Extract traffic data of each user based on the mobile phone signaling data of each user;

[0009] Constructing a work-residence model for each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, as well as the commuting time and trajectory between the residence and workplace;

[0010] Constructing an origin-destination OD matrix based on the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area;

[0011] According to the OD matrix and the residual network, an urban traffic demand prediction model is constructed.

[0012] Optionally, the method as described above, constructing a city traffic demand prediction model based on the OD matrix and the residual network, includes: determining a road network topology structure based on the OD matrix, wherein the road network topology structure includes road characteristic data, wherein the road characteristic data includes flow matrix data and date data; performing data processing on the flow matrix data in the road characteristic data to obtain spatial dimension characteristic data; performing data processing on the date data in the road characteristic data to obtain time dimension characteristic data; and constructing a city traffic demand prediction model based on the spatial dimension characteristic data, the time dimension characteristic data and the residual network.

[0013] Optionally, the method as described above, constructing a city traffic demand prediction model based on the spatial dimension feature data, the time dimension feature data and the residual network, includes: iteratively training the residual network according to the spatial dimension feature data and the time dimension feature data until the city traffic demand prediction error of the residual network meets a preset condition, thereby obtaining a trained city traffic demand prediction model.

[0014] Optionally, the method as described above, constructing a city traffic demand prediction model based on the spatial dimension feature data, the temporal dimension feature data and the residual network, also includes: obtaining external environment feature data; iteratively training the residual network based on the external environment feature data, and the spatial dimension feature data and the temporal dimension feature data, until the city traffic demand prediction error of the residual network meets preset conditions, thereby obtaining a trained city traffic demand prediction model.

[0015] Optionally, in the method as described above, the external environment characteristic data includes one or more of weather data, temperature data and air quality data.

[0016] In a second aspect, the present application provides a device for predicting urban traffic demand, comprising:

[0017] A data acquisition module, used to acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all the mobile phone signaling data are mobile phone signaling data of a preset number of users in the residence collected by the operator within the preset time period;

[0018] A data extraction module is used to extract the traffic data of each user based on the mobile phone signaling data of each user;

[0019] A first construction module is used to construct a work-residence model of each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, and the commuting time and trajectory between the residence and workplace;

[0020] The second construction module is used to construct an origin-destination OD matrix according to the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area;

[0021] The third building module is used to build an urban traffic demand prediction model according to the OD matrix and the residual network.

[0022] Optionally, in the method as described above, the second construction module includes: a first processing unit, used to determine the road network topology structure based on the OD matrix, wherein the road network topology structure includes road characteristic data, wherein the road characteristic data includes flow matrix data and date data; a second processing unit, used to perform data processing on the flow matrix data in the road characteristic data to obtain spatial dimension characteristic data; a third processing unit, used to perform data processing on the date data in the road characteristic data to obtain time dimension characteristic data; a fourth processing unit, used to construct an urban traffic demand prediction model based on the spatial dimension characteristic data, the time dimension characteristic data and the residual network.

[0023] Optionally, in the method as described above, the fourth processing unit is specifically used to iteratively train the residual network according to the spatial dimension feature data and the time dimension feature data until the urban traffic demand prediction error of the residual network meets preset conditions, thereby obtaining a trained urban traffic demand prediction model.

[0024] In a third aspect, the present invention provides a service device, comprising: at least one processor and a memory;

[0025] The memory stores computer-executable instructions;

[0026] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the urban traffic demand forecasting method as described in the first aspect and various possible designs of the first aspect.

[0027] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer execution instructions. When a processor executes the computer execution instructions, the method described in the first aspect and various possible designs of the first aspect are implemented.

[0028] The urban traffic demand prediction method, device, equipment and storage medium provided in the present application extract the user's traffic data through the mobile phone signaling data of the operation end, construct the user's work-residence model, construct the start-point and end-point OD matrix through the work-residence model of all users, and construct the urban traffic demand prediction model through the OD matrix and the residual network algorithm. The urban traffic demand statistics are timely and efficient, and the acquired traffic data are authentic and reliable, which can construct comprehensive feedback of travel data such as commuting of residents in large cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0030] Figure 1 A schematic diagram of a scenario of a method for predicting urban traffic demand provided by an embodiment of the present invention;

[0031] Figure 2 A schematic diagram of a flow chart of a method for predicting urban traffic demand provided by an embodiment of the present invention;

[0032] Figure 3 A schematic diagram of a flow chart of a method for predicting urban traffic demand provided by another embodiment of the present invention;

[0033] Figure 4 A schematic diagram of the structure of a device for predicting urban traffic demand provided by an embodiment of the present invention;

[0034] Figure 5 A schematic diagram of the hardware structure of a service device provided in an embodiment of the present invention.

[0035] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0036] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0037] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0038] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0039] Figure 1 A schematic diagram of a scenario of a method for predicting urban traffic demand provided in an embodiment of the present application. Figure 1 As shown, the system provided by this embodiment includes a user terminal 101 and a service device 102 .

[0040] The service device 102 may be a server, or alternatively, may be a single server or a cluster of multiple servers.

[0041] Specifically, the user terminal 101 receives the city traffic demand forecast request input by the user, and transmits the city traffic demand forecast request to the service device 102. After receiving the city traffic demand forecast request, the service device 102 performs city traffic demand forecast and sends the city traffic demand forecast result to the user terminal 101 for display.

[0042] Embodiment 1

[0043] Figure 2 A flow chart of a method for predicting urban traffic demand provided by an embodiment of the present invention. The execution subject of this embodiment may be Figure 1 The service device 102 shown in the figure may also be other computer devices, which is not particularly limited in this embodiment. Figure 2 As shown, the method includes:

[0044] S201: Acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all mobile phone signaling data are mobile phone signaling data of a preset number of users in the target residence collected by the operator within the preset time period.

[0045] In this embodiment, the target residence may be a prefecture-level city area.

[0046] In this embodiment, the preset time period may be 1 month, 6 months or 12 months.

[0047] In this embodiment, the preset number of users may be all users in the target residence.

[0048] In this embodiment, the mobile phone signaling data may include traffic data and at least one of the following: location information, time information, and base station number information.

[0049] S202: Extracting traffic data of each user based on the mobile phone signaling data of each user.

[0050] Specifically, multiple attribute fields in the mobile phone signaling data are identified, and corresponding traffic data are identified and extracted from the multiple attribute fields.

[0051] In this embodiment, the traffic data may include the user's spatiotemporal trajectory (ie, the mapping relationship between position and time).

[0052] S203: Constructing a work-residence model for each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, as well as the commuting time and trajectory between the residence and workplace.

[0053] Specifically, based on the residence time in different location areas according to traffic data, and taking into account the changes in longitude and time zone, the weight of the location is adjusted, so that a work-residence model for each user can be constructed.

[0054] Specifically, according to the traffic data throughout the day, the area with the longest long-term nighttime stay is the residence (residence), and the area with the longest long-term daytime stay is the workplace (workplace).

[0055] For example, let the commuting OD (Origin-Destination) be the round trip between the workplace and residence every morning and evening. According to data analysis and mining, it is determined that the residents leave their residence and arrive at their workplace from i (such as i=5) to j (such as j=10) in the morning every day, which is a commuting OD. The difference between the arrival time and the departure time is the commuting time, and the line connecting the stop points during the time is the commuting trajectory. Similarly, it is determined that the residents leave their workplace and arrive at their residence from m (such as m=16) to n (such as n=21) in the afternoon, which is a commuting return OD, and the commuting time and trajectory can also be obtained.

[0056] S204: Constructing a start-point and end-point OD matrix according to the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area.

[0057] Specifically, based on the work-residence model of all users, the city is divided into categories such as administrative divisions, longitude and latitude, or points of interest to construct an OD matrix.

[0058] Among them, the OD matrix is ​​used to characterize the travel flow from one area to another. The OD matrix is ​​specifically: the traffic flow from area A to area B is equivalent to the congestion level on the path from area A to area B.

[0059] S205: Construct an urban traffic demand prediction model based on the OD matrix and the residual network.

[0060] Specifically, S205 specifically includes Sa~Sd:

[0061] Sa: Determine the road network topology structure according to the OD matrix, wherein the road network topology structure includes road characteristic data, wherein the road characteristic data includes flow matrix data and date data.

[0062] Among them, the traffic matrix data is the traffic flow demand from the starting point to the end point, that is, the size of the OD flow.

[0063] Specifically, according to the OD matrix and based on the idea of ​​graph theory, according to the three basic elements of nodes, road sections and turns, the main road network of a specific city is abstracted into a weighted directed road network topology structure with turns, and its weight represents the grade and transportation capacity of the road.

[0064] Sb: Process the traffic matrix data in the road feature data to obtain spatial dimension feature data.

[0065] Specifically, data cleaning is performed on the flow matrix data in the road feature data, and spatial features are extracted from the cleaned flow matrix data to obtain spatial dimension feature data.

[0066] Sc: Process the date data in the road feature data to obtain time dimension feature data.

[0067] Specifically, data cleaning is performed on the date data in the road feature data, and time features are extracted from the cleaned date data to obtain time dimension feature data.

[0068] Sd: Construct an urban traffic demand prediction model based on spatial dimension feature data, temporal dimension feature data and residual network.

[0069] Specifically, the residual network is iteratively trained according to the spatial dimension feature data and the temporal dimension feature data until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

[0070] For example, the spatial dimension feature data is input into the residual network to mine the smooth characteristics of urban traffic demand changes; the time dimension feature data is input into the residual network to simulate the periodicity of OD matrix flow changes; the trend of traffic demand changes between urban OD grids is simulated from a longer time dimension; finally, the three results of smoothing, periodicity and trend are integrated and iteratively trained until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

[0071] From the above description, it can be seen that the present invention extracts the user's traffic data through the mobile phone signaling data of the operation end, constructs the user's work-residence model, constructs the start-point and end-point OD matrix through the work-residence model of all users, and constructs the urban traffic demand prediction model through the OD matrix and the residual network algorithm. The urban traffic demand statistics are timely and efficient, and the acquired traffic data are authentic and reliable, which can construct comprehensive feedback on travel data such as commuting of residents in large cities.

[0072] Embodiment 2

[0073] Figure 3 This is a flow chart of a method for predicting urban traffic demand provided by another embodiment of the present invention. The execution subject of this embodiment may be Figure 1 The service device 102 shown in the figure may also be other computer devices, which is not particularly limited in this embodiment. Figure 3 As shown, the method includes:

[0074] S301: Acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all mobile phone signaling data are mobile phone signaling data of a preset number of users in the residence collected by the operator within the preset time period.

[0075] S302: Extracting traffic data of each user according to the mobile phone signaling data of each user.

[0076] S303: Constructing a work-residence model for each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, as well as the commuting time and trajectory between the residence and workplace.

[0077] S304: Constructing a start-point and end-point OD matrix according to the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area.

[0078] In this embodiment, the description of steps S301 to S304 is consistent with the above steps S201 to S204. Please refer to the relevant content for the specific description, which will not be repeated here.

[0079] S305: Constructing an urban traffic demand prediction model based on the OD matrix and the residual network.

[0080] Specifically, S305 specifically includes Se~Sh:

[0081] Se: Determine the road network topology structure according to the OD matrix, wherein the road network topology structure includes road characteristic data, wherein the road characteristic data includes flow matrix data and date data.

[0082] Sf: Process the traffic matrix data in the road feature data to obtain spatial dimension feature data.

[0083] Sg: Process the date data in the road feature data to obtain time dimension feature data.

[0084] In this embodiment, the description of steps Se to Sg is consistent with the above steps Sa to Sc. Please refer to the relevant content for the specific description, which will not be repeated here.

[0085] Sh: Based on spatial dimension feature data, temporal dimension feature data and residual network, an urban traffic demand prediction model is constructed.

[0086] Specifically, Sh includes Sh1 to Sh2:

[0087] Sh1: Obtain external environment characteristic data.

[0088] Among them, the external environment characteristic data includes: one or more of weather data, temperature data and air quality data.

[0089] Exemplarily, data capture technology is used to acquire external environment data from a target environment data platform, and external environment feature data is obtained by extracting key frames from the external environment data.

[0090] Sh2: According to the external environment feature data, spatial dimension feature data and time dimension feature data, the residual network is iteratively trained until the urban traffic demand prediction error of the residual network meets the preset conditions, and a trained urban traffic demand prediction model is obtained.

[0091] From the above description, it can be seen that by obtaining external environmental feature data, the residual network is integrated with the spatial dimension feature data and the temporal dimension feature data as well as the external environmental feature data. The constructed urban traffic demand prediction model fully considers the global impact of external environmental factors on urban traffic demand, making the model training accuracy higher, the model versatility better, and the prediction results more accurate.

[0092] Figure 4 The structure diagram of the urban traffic demand prediction device provided by the embodiment of the present invention is shown in FIG. Figure 4As shown, the urban traffic demand prediction device 40 includes: a data acquisition module 401, a data extraction module 402, a first construction module 403, a second construction module 404 and a third construction module 405.

[0093] The data acquisition module 401 is used to acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all the mobile phone signaling data are mobile phone signaling data of a preset number of users in the residence collected by the operator within the preset time period;

[0094] The data extraction module 402 is used to extract the traffic data of each user according to the mobile phone signaling data of each user;

[0095] A first construction module 403 is used to construct a work-residence model of each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, and the commuting time and trajectory between the residence and workplace;

[0096] The second construction module 404 is used to construct an origin-destination OD matrix according to the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area;

[0097] The third construction module 405 is used to construct a city traffic demand prediction model according to the OD matrix and the residual network.

[0098] In a possible design, the second building module 404 includes:

[0099] A first processing unit 4041 is used to determine a road network topology structure according to the OD matrix, wherein the road network topology structure includes road feature data, wherein the road feature data includes flow matrix data and date data;

[0100] The second processing unit 4042 is used to process the traffic matrix data in the road feature data to obtain spatial dimension feature data;

[0101] The third processing unit 4043 is used to process the date data in the road feature data to obtain time dimension feature data;

[0102] The fourth processing unit 4044 is used to construct a city traffic demand prediction model according to the spatial dimension feature data, the temporal dimension feature data and the residual network.

[0103] In a possible design, the fourth processing unit 4044 is specifically used to iteratively train the residual network according to the spatial dimension feature data and the time dimension feature data until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

[0104] In a possible design, the fourth processing unit 4044 is further specifically used to: obtain external environment characteristic data; iteratively train the residual network according to the external environment characteristic data, the spatial dimension characteristic data and the time dimension characteristic data, until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

[0105] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0106] Figure 5 Schematic diagram of the hardware structure of the service device provided in the embodiment of the present invention. Figure 5 As shown, the service device 50 of this embodiment includes: at least one processor 501 and a memory 502; the memory stores computer-executable instructions; at least one processor executes the computer-executable instructions stored in the memory, so that at least one processor executes the above data transmission method;

[0107] Optionally, the memory 502 may be independent or integrated with the processor 501 .

[0108] When the memory 502 is independently provided, the service device further includes a bus 503 for connecting the memory 502 and the processor 501 .

[0109] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the urban traffic demand prediction method as described above is implemented.

[0110] An embodiment of the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the urban traffic demand prediction method as described above is implemented.

[0111] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0112] It should be further noted that, although the various steps in the flowchart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0113] It should be understood that the above-mentioned device embodiments are only illustrative, and the device of the present application can also be implemented in other ways. For example, the division of units / modules in the above-mentioned embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0114] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present application may be integrated into one unit / module, each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0115] If the integrated unit / module is implemented in the form of hardware, the hardware may be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. If not specifically stated, the processor may be any appropriate hardware processor, such as a CPU, a GPU, an FPGA, a DSP, an ASIC, etc. If not specifically stated, the storage unit may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc.

[0116] If the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0117] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0119] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for predicting urban traffic demand, characterized in that: Applied to service equipment, including: Acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all the mobile phone signaling data is the mobile phone signaling data of a preset number of users in the target residence collected by the operator within the preset time period; Extract traffic data of each user based on the mobile phone signaling data of each user; Constructing a work-residence model for each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, as well as the commuting time and trajectory between the residence and workplace; Constructing an origin-destination OD matrix based on the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area; According to the OD matrix and the residual network, an urban traffic demand prediction model is constructed.

2. The method according to claim 1, characterized in that The urban traffic demand prediction model is constructed according to the OD matrix and the residual network, including: Determine a road network topology structure according to the OD matrix, wherein the road network topology structure includes road feature data, wherein the road feature data includes flow matrix data and date data; Processing the traffic matrix data in the road characteristic data to obtain spatial dimension characteristic data; Processing the date data in the road feature data to obtain time dimension feature data; An urban traffic demand prediction model is constructed based on the spatial dimension feature data, the temporal dimension feature data and the residual network.

3. The method according to claim 2, characterized in that The step of constructing a city traffic demand prediction model based on the spatial dimension feature data, the temporal dimension feature data and the residual network includes: The residual network is iteratively trained according to the spatial dimension feature data and the temporal dimension feature data until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

4. The method according to claim 2 or 3, characterized in that: The step of constructing a city traffic demand prediction model according to the spatial dimension feature data, the temporal dimension feature data and the residual network further includes: Acquire external environment characteristic data; The residual network is iteratively trained according to the external environment feature data, the spatial dimension feature data and the temporal dimension feature data until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

5. The method according to claim 4, characterized in that The external environment characteristic data includes one or more of weather data, temperature data and air quality data.

6. A device for predicting urban traffic demand, characterized in that: Applied to service equipment, including: A data acquisition module, used to acquire all mobile phone signaling data of the operator within a preset time period in any target residence, wherein all the mobile phone signaling data are mobile phone signaling data of a preset number of users in the residence collected by the operator within the preset time period; A data extraction module is used to extract the traffic data of each user based on the mobile phone signaling data of each user; A first construction module is used to construct a work-residence model of each user based on the traffic data of each user, wherein the work-residence model includes the user's residence and workplace, and the commuting time and trajectory between the residence and workplace; The second construction module is used to construct an origin-destination OD matrix according to the work-residence model of all users, wherein the OD matrix is ​​used to characterize the travel flow from one area to another area; The third building module is used to build an urban traffic demand prediction model according to the OD matrix and the residual network.

7. The device according to claim 6, characterized in that The second building block comprises: A first processing unit is used to determine a road network topology structure according to the OD matrix, wherein the road network topology structure includes road feature data, wherein the road feature data includes flow matrix data and date data; A second processing unit is used to process the traffic matrix data in the road characteristic data to obtain spatial dimension characteristic data; A third processing unit, used for performing data processing on the date data in the road feature data to obtain time dimension feature data; The fourth processing unit is used to construct an urban traffic demand prediction model based on the spatial dimension feature data, the temporal dimension feature data and the residual network.

8. The device according to claim 7, characterized in that The fourth processing unit is specifically used to iteratively train the residual network according to the spatial dimension feature data and the time dimension feature data until the urban traffic demand prediction error of the residual network meets the preset conditions, thereby obtaining a trained urban traffic demand prediction model.

9. A service device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the urban traffic demand forecasting method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the urban traffic demand prediction method according to any one of claims 1 to 5.

Images