Traffic route generation method, device, electronic device and storage medium

Abstract

This application relates to a method, device, electronic device, and storage medium for generating a traffic route. The method comprises: obtaining historical portrait images corresponding to a plurality of targets to be measured; performing portrait clustering processing on the historical portrait images to obtain historical clustering information; obtaining the longest travel distance corresponding to the target to be measured based on the historical clustering information; and determining a public transportation stop based on the longest travel distance; and generating a target traffic route based on at least the public transportation stop. This application solves the problem of low accuracy in traffic route generation and implements a method for planning traffic routes based on archival trajectories.

Description

Technical Field

[0001] The present application relates to the field of transportation technology, and in particular to a method, device, electronic device and storage medium for generating a transportation route. Background Art

[0002] As my country's urbanization continues to accelerate, urban populations are expanding, and more and more people are commuting to work and live. This has led to a severe challenge for urban public transportation: rapidly increasing demand and a severe shortage of resources. Therefore, designing bus routes that can meet the travel and activity needs of the majority of people while also balancing operating revenue and expenditure by carrying a sufficient number of passengers has become a key issue.

[0003] Generally speaking, determining the location of bus stops is a prerequisite for urban bus route planning. Related technologies typically use small-scale sampling surveys of residents' travel intentions or time-consuming and ineffective census results to analyze residents' travel needs, obtain bus passenger flow, and then design bus stops and routes. These methods have been proven feasible and effective in practice, but they primarily consider environmental factors such as population density and traffic conditions, and fail to consider the travel patterns of urban residents. As a result, they are time-consuming, labor-intensive, and inefficient, and are unable to adapt to the frequently changing urban road structure and traffic demand, resulting in low accuracy in the generated traffic routes.

[0004] Currently, no effective solution has been proposed to address the problem of low accuracy in traffic route generation in related technologies. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, electronic device, and storage medium for generating a public transportation route, so as to at least solve the problem of low accuracy in generating a public transportation route in the related art.

[0006] In a first aspect, an embodiment of the present application provides a method for generating a traffic route, the method comprising:

[0007] Obtaining historical portrait images corresponding to multiple targets to be measured;

[0008] Performing portrait clustering processing on the historical portrait images to obtain historical clustering information, obtaining the farthest travel distance corresponding to the target to be measured according to the historical clustering information, and determining a public transportation station based on the farthest travel distance;

[0009] A target transportation route is generated at least according to the public transportation station.

[0010] In some embodiments, performing portrait clustering processing on the historical portrait images to obtain historical clustering information includes:

[0011] Performing portrait clustering processing on the historical portrait images to obtain clustering results of the historical portrait images, and performing target recognition for non-public transportation targets based on the clustering results to obtain target recognition results;

[0012] The aggregation result is filtered according to the target recognition result to obtain the historical aggregation information.

[0013] In some embodiments, obtaining the longest travel distance corresponding to the target to be measured according to the historical archive information includes:

[0014] Calculating the travel trajectory of the target to be measured within a preset time period according to the historical archive information, and determining the landing point of the target to be measured based on the travel trajectory, according to a preset activity range and a preset activity time;

[0015] The maximum travel distance is obtained according to the landing point.

[0016] In some embodiments, generating a target transportation route based at least on the public transportation station includes:

[0017] Determine a travel trajectory based on the historical archive information to determine the longest transfer distance in the travel trajectory;

[0018] A shared vehicle placement site is determined according to the longest travel distance and the longest transfer distance, and a target traffic route is generated according to the shared vehicle placement site and the public transportation site.

[0019] In some embodiments, determining a shared vehicle placement site based on the longest travel distance and the longest transfer distance includes:

[0020] When the maximum travel distance is less than a first preset distance, obtaining a gathering point within the first preset range of the maximum travel distance, and determining a first shared vehicle placement site based on the gathering point; wherein the number of shared vehicles corresponding to the first shared vehicle placement site is determined based on the gathering point;

[0021] When the farthest transfer distance is less than a second preset distance, determining an area to be counted within a second preset range of the farthest transfer distance;

[0022] Obtaining a transfer point and a starting point within the area to be counted, and determining a second shared vehicle placement site based on the transfer point and the starting point; wherein the placement volume corresponding to the second shared vehicle placement site is determined based on the number of targets to be measured corresponding to the transfer point;

[0023] The shared vehicle placement site is determined according to the first shared vehicle placement site and the second shared vehicle placement site.

[0024] In some embodiments, determining a public transportation stop based on the maximum travel distance includes:

[0025] When the farthest travel distance is within a preset distance range, determining a single route coverage strategy, and determining the public transportation stops under the single route using the single route coverage strategy;

[0026] In the case that the farthest travel distance exceeds the preset distance range, a combined route coverage strategy is determined, and the public transportation stops under the combined route are determined using the combined route coverage strategy.

[0027] In some embodiments, the historical portrait images are acquired at each image acquisition point; and when the farthest travel distance is within a preset distance range, the method further includes:

[0028] Obtaining a gathering point corresponding to the longest travel distance, and obtaining at least one initial traffic route according to the gathering point and the longest travel distance;

[0029] Acquiring trajectory density information at each of the image acquisition points according to the historical archive information, and dividing all the image acquisition points according to the trajectory density information to obtain a division result of the image acquisition points;

[0030] Based on the trajectory density information and the duplication information of the initial traffic route, the initial traffic route is deduplicated to obtain the single route, and the public transportation stops under the single route are determined according to the division result.

[0031] In some embodiments, when the farthest travel distance exceeds the preset distance range, the method further includes:

[0032] Obtaining a gathering point corresponding to the longest travel distance, and obtaining at least one initial traffic route according to the gathering point and the longest travel distance, so as to determine a maximum single route among the initial traffic routes;

[0033] The combined route is generated according to the maximum single route and the longest travel distance to determine the public transportation station under the combined route.

[0034] In some embodiments, after generating the target transportation route at least according to the public transportation station, the method further includes:

[0035] When a historical traffic route is obtained, the historical traffic route is compared with the target traffic route to obtain a route change result, and the route change result is sent to a display terminal for display;

[0036] In the case that the historical traffic route is missing, the target traffic route is sent to the display terminal for display.

[0037] In a second aspect, an embodiment of the present application provides a traffic route generation device, the device comprising: an acquisition module, a file aggregation module, and a generation module;

[0038] The acquisition module is used to acquire historical portrait images corresponding to multiple targets to be measured;

[0039] The clustering module is configured to perform portrait clustering processing on the historical portrait images to obtain historical clustering information, obtain the longest travel distance corresponding to the target to be measured based on the historical clustering information, and determine a public transportation station based on the longest travel distance;

[0040] The generating module is configured to generate a target transportation route at least according to the public transportation site.

[0041] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for generating a traffic route as described in the first aspect above is implemented.

[0042] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the method for generating a traffic route as described in the first aspect above is implemented.

[0043] Compared with the related art, the traffic route generation method, device, electronic device and storage medium provided in the embodiments of the present application obtain historical portrait images corresponding to multiple targets to be measured; perform portrait clustering processing on the historical portrait images to obtain historical clustering information, obtain the farthest travel distance corresponding to the target to be measured based on the historical clustering information, and determine the public transportation station based on the farthest travel distance; generate the target traffic route at least based on the public transportation station, thereby solving the problem of low accuracy in traffic route generation and realizing a method for planning traffic routes based on archive trajectories.

[0044] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute 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 on the present application. In the drawings:

[0046] Figure 1 This is an application environment diagram of a method for generating a traffic route according to an embodiment of the present application;

[0047] Figure 2 is a flow chart of a method for generating a traffic route according to an embodiment of the present application;

[0048] Figure 3 is a flow chart of a shared vehicle deployment method according to a preferred embodiment of the present application;

[0049] Figure 4 is a schematic diagram of a traffic route according to an embodiment of the present application;

[0050] Figure 5 is a flow chart of a method for generating a traffic route according to a preferred embodiment of the present application;

[0051] Figure 6 This is a structural block diagram of a traffic route generation device according to an embodiment of the present application;

[0052] Figure 7 This is a structural diagram of the interior of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means and should not be understood as the contents disclosed in the present application being insufficient.

[0054] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0055] Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by a person of ordinary skill in the technical field to which this application belongs. The words "one", "a", "the" and the like used in this application do not indicate a limit on quantity and may indicate the singular or plural. The terms "include", "comprise", "have" and any variations thereof used in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units that are inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The word "multiple" used in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in this application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0056] In this embodiment, a method for generating a traffic route is provided. Figure 1 This is an application environment diagram of a method for generating a traffic route according to an embodiment of the present application, such as Figure 1As shown, in this application environment, a display terminal 11 communicates with a server 12 via a network. The server 12 obtains historical portrait images corresponding to multiple targets to be measured, clusters the historical portrait images to obtain historical clustering information, obtains the longest travel distance based on the historical clustering information, and determines public transportation stops based on the longest travel distance. The server 12 generates a target transportation route based on at least the public transportation stops. The display terminal 11 obtains the target transportation route from the server 12 and displays it. For example, the display terminal 11 can display the target transportation route on an electronic map application deployed thereon. The display terminal 11 can be, but is not limited to, various smartphones, personal computers, laptops, and tablet computers. The server 12 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0057] This embodiment provides a method for generating a traffic route. Figure 2 is a flow chart of a method for generating a traffic route according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0058] Step S210: Acquire historical portrait images corresponding to a plurality of targets to be measured.

[0059] The aforementioned targets to be measured refer to people passing through various image collection points. These image collection points are checkpoints distributed throughout squares, parks, and even cities, i.e., hardware devices installed on roadsides and intersections. Each checkpoint is used to capture historical portrait images of each target to be measured using the image collection equipment installed. These historical portrait images may include facial images, body images, and gait sequence images. It should be noted that each image may contain facial images, body images, both facial and body images, or neither.

[0060] Step S220 , performing portrait clustering processing on the historical portrait image to obtain historical clustering information, obtaining the farthest travel distance corresponding to the target to be measured according to the historical clustering information, and determining the public transportation station based on the farthest travel distance.

[0061] Among them, the data of travelers passing through the image collection points are clustered. Specifically, the image collection equipment deployed at the image collection points is used to capture the facial and body data of the travelers passing by, that is, the above-mentioned targets to be measured, to obtain the above-mentioned historical portrait images. The historical portrait images obtained after the capture are used to perform face and body clustering to cluster the targets to be measured, and all images of travelers in the city that appear at the image collection points are clustered together. After the clustering task is completed, the historical clustering information of a single traveler will be formed, and after algorithm processing, the trajectory route of the person will be drawn on the map, and a city movement trajectory map of a single traveler throughout the day can be obtained to determine the starting point, destination, transfer point and end point of the person, and the above-mentioned public transportation station can be determined based on the farthest travel distance obtained by the trajectory route drawing. For example, the two ends of the farthest travel distance corresponding to each target to be measured can be set as public transportation stations, thereby achieving a significant optimization of the public transportation network of the entire city and maximizing resource utilization.

[0062] Step S230: Generate a target transportation route based at least on the public transportation station.

[0063] The map application programming interface (API) may be called to perform path planning on the public transportation stations selected through the above steps, thereby obtaining the above target transportation route.

[0064] The route generation method in the related art takes too long to conduct field research. However, the embodiment of the present application obtains historical clustering information by clustering the acquired historical portrait images through the above-mentioned steps S210 to S230, obtains the longest travel distance based on the historical clustering information to determine the public transportation station, and finally generates the public transportation route based on the public transportation station, thereby realizing the determination of the population flow trajectory based on the portrait clustering algorithm, avoiding the situation where the traditional method of obtaining the residents' travel demand is inaccurate and the site selection of the public transportation station is prone to errors, solving the problem of low accuracy of traffic route generation, and realizing a method for planning traffic routes based on archive trajectories.

[0065] In some embodiments, the above-mentioned portrait clustering processing of the historical portrait image to obtain historical clustering information also includes the following steps: performing portrait clustering processing on the historical portrait image to obtain a clustering result of the historical portrait image, performing target recognition for non-public transportation targets based on the clustering result to obtain a target recognition result; and filtering the clustering result based on the target recognition result to obtain the historical clustering information.

[0066] The main control device can perform image clustering on the historical portrait images based on the portrait features in the multiple historical portrait images to obtain multiple portrait image sets to form the clustering results of the historical portrait images. For example, assuming that portrait clustering is performed on n portrait images, the portrait features of each portrait image are extracted in sequence, and n portrait features can be extracted. Each portrait feature corresponds to a one-dimensional or multi-dimensional feature vector. The Euclidean distance between the n portrait features is calculated as the first distance. Then, a clustering method such as a k-means clustering algorithm, a conditional random field algorithm (CRF), or a mean shift clustering algorithm is used to cluster based on the Euclidean distance, thereby dividing the n portrait images into multiple portrait image sets, and finally storing the same type of portraits in the archive database. Then, based on the clustering results, the data of the travelers after clustering is statistically analyzed, and the clustering results are subjected to target recognition to filter out non-public transportation targets such as electric bicycle users and self-driving people, so as to eliminate the identified non-public transportation targets, and finally the retained data is used as the historical clustering information. Through the above embodiment, by screening and filtering non-public transportation targets such as electric vehicle users and self-driving users during the portrait clustering process, traffic route generation errors caused by taking the travel trajectories of non-public transportation targets into account in the subsequent traffic route process are avoided, thereby effectively improving the accuracy and efficiency of traffic route generation.

[0067] In some embodiments, the above-mentioned obtaining the farthest travel distance corresponding to the target to be measured based on the historical archive information also includes the following steps: calculating the travel trajectory corresponding to the target to be measured within a preset time period based on the historical archive information, and based on the travel trajectory, determining the landing point of the target to be measured according to the preset activity range and the preset activity time; and obtaining the farthest travel distance based on the landing point.

[0068] The preset time period can be pre-set, for example, weekly or bi-weekly. For example, using a weekly preset time period, the travel trajectory of each traveler can be plotted based on the travel data in the historical aggregated information corresponding to each target. The statistical travel trajectory can also be divided into weekdays and weekends to improve the accuracy of subsequent traffic route generation. Based on the statistically obtained travel trajectories of each traveler, the traveler's daily destination can be calculated. This destination may include the traveler's starting point, transit points, and destination. It should be noted that the starting point refers to the first location of each traveler on the map each day, as determined based on the travel trajectory of the historical aggregated information; the transit point refers to a location within the preset activity range, as determined based on the travel trajectory, where the activity time exceeds half an hour and is less than the preset activity time; and the destination refers to a location within the preset activity range, as determined based on the travel trajectory, where the activity time exceeds the preset activity time. The preset activity range and preset activity time can be pre-set. For example, the preset activity range can be set to a circular area with a radius of 500 meters, and the preset activity range can be set to 5 hours. This will not be further explained here. The maximum travel distance can be calculated based on the distance between the starting point and the end point. Through the above embodiment, the travel trajectory within the preset time period is calculated, the landing point of the target to be measured is determined, and the maximum travel distance is obtained, thereby ensuring the accuracy and timeliness of data analysis statistics, thereby improving the accuracy of traffic route generation.

[0069] In some embodiments, the above-mentioned generation of the target traffic route at least based on the public transportation station also includes the following steps: determining the travel trajectory based on the historical archive information to determine the farthest transfer distance in the travel trajectory; determining the shared vehicle deployment site based on the farthest travel distance and the farthest transfer distance, and generating the target traffic route based on the shared vehicle deployment site and the public transportation station. Among them, after the above-mentioned travel trajectory is calculated based on the historical archive information, the transfer point and the terminal location corresponding to the target to be measured can be obtained according to the travel trajectory statistics through the above steps, so as to determine the above-mentioned farthest transfer distance based on the distance between the transfer point and the terminal, and finally determine the shared vehicle deployment site based on the farthest travel distance and the farthest transfer distance. It can be understood that the shared vehicle includes a shared bicycle or a shared electric vehicle, etc.

[0070] In some embodiments, determining the shared vehicle placement site based on the longest travel distance and the longest transfer distance further includes the following steps:

[0071] Step S221, when the farthest travel distance is less than the first preset distance, obtain a gathering point within the first preset range of the farthest travel distance, and determine the first shared vehicle deployment site based on the gathering point; wherein the deployment quantity corresponding to the first shared vehicle deployment site is determined based on the gathering point.

[0072] The first preset distance and the first preset range can be pre-set based on actual circumstances. For example, the first preset distance can be set to 3 kilometers based on the size of the urban area, and the first preset range can be set to a circular area with a radius of 1 kilometer. The aforementioned gathering point refers to a location where a large number of travelers gather, such as a residential community, a park, or an office building. When the maximum travel distance, i.e., the distance between the starting point and the end point, is less than the first preset distance, it indicates that the corresponding target's travel distance is not far. In this case, a shared vehicle recommendation can be made for the target's travel route. The presence and number of gathering points, such as residential communities, within the first preset range can be determined. If the number of gathering points detected is less than or equal to two, the gathering point, such as the entrance to the residential community, can be directly identified as the first shared vehicle placement site. The number of shared vehicles assigned to this first shared vehicle placement site can be determined based on the number of travelers present at this gathering point. If the number of gathering points is greater than two, the gathering points can be combined in pairs. The first shared vehicle placement site is determined to be a compromise between the two combined gathering points, and the number of shared vehicles assigned to these two gathering points can be determined based on the number of travelers present at these two gathering points.

[0073] Step S222, when the farthest transfer distance is less than the second preset distance, determine the area to be counted within the second preset range of the farthest transfer distance; obtain the transfer point and starting point within the area to be counted, and determine the second shared vehicle delivery site based on the transfer point and starting point; wherein the delivery volume corresponding to the second shared vehicle delivery site is determined according to the number of targets to be measured corresponding to the transfer point.

[0074] The second preset distance and the second preset range can be set in advance based on actual conditions. For example, the second preset distance can be set to 2 kilometers based on the area of ​​the urban area, and the second preset range can be set to a circular area with a radius of 500 meters, and the area to be counted is within the second preset range. Then, all transfer points and starting points in the area to be counted can be counted; if there is a starting point, the starting point can be directly set as the second shared vehicle delivery site; if there is no starting point in the area to be counted, the center point within the second preset range can be set as the second shared vehicle delivery site; finally, the number of shared vehicles to be delivered to the second shared vehicle delivery site can be determined based on the number of travelers corresponding to the transfer points, so as to achieve accurate delivery of shared vehicles.

[0075] Step S223: determining the shared vehicle placement site according to the first shared vehicle placement site and the second shared vehicle placement site.

[0076] Specifically, the first shared vehicle placement site and the second shared vehicle placement site obtained by the above calculation are summarized to finally determine the above shared vehicle placement site.

[0077] In related technologies, the planning of urban public transportation routes is usually implemented by using a method to determine the location of bus stops based on taxi GPS data; the bus stop site selection method based on taxi GPS data overcomes the defect of inaccurate acquisition of residents' travel needs by traditional methods, and provides a better foundation for the subsequent planning of bus routes. However, the existing bus stop site selection method based on taxi GPS data does not consider the integrity of the division of traffic hotspot areas, or does not consider the service radius of bus stops, so that the planning of traffic routes is usually limited to bus stops, which is very limited. However, through the above-mentioned embodiments, the present application uses the trajectory map of the urban personnel data to perform algorithm-oriented analysis, and realizes the accurate evaluation of the placement location and placement amount of shared vehicles in urban transportation, thereby effectively combining the placement location of shared vehicles with bus stops, greatly alleviating urban traffic congestion and achieving the goal of maximizing social resources.

[0078] The following describes the embodiments of the present application in detail in combination with actual application scenarios, taking the above-mentioned shared vehicle as a shared bicycle as an example. Figure 3 This is a flow chart of a shared vehicle deployment method according to a preferred embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0079] Step S301, obtain clustering results, filter the trajectory data of self-driving people, electric vehicle people, etc. from the clustering results, and obtain historical clustering information.

[0080] Step S302: Analyze each person's daily destination based on historical archive information, and calculate each person's weekly destination.

[0081] Step S303, determine whether the distance from the transfer point to the end point is less than 2 kilometers; if the judgment result is yes, select the shared vehicle deployment quantity and deployment point based on the turnover points within 500 meters; if the judgment result is no, execute the subsequent step S306.

[0082] Step S304: Analyze the longest travel distance with each cell as the starting point for analysis; determine whether the longest travel distance, that is, the distance from the starting point to the terminal, is within 3 kilometers; if the judgment result is yes, execute the subsequent step S305; if the judgment result is no, execute the subsequent step S306.

[0083] Step S305, determine whether there are more than 2 communities within a 1-kilometer radius; if the judgment result is yes, determine the shared bicycle delivery point as the compromise point of each two communities after the combination of two, and the delivery amount is determined according to the number of people in these two communities; if the judgment result is no, determine the shared bicycle delivery point as the community entrance, and the delivery amount is determined according to the travel personnel data of the community.

[0084] Step S306: planning a public transportation route.

[0085] In some embodiments, the above-mentioned determination of the public transportation stop based on the farthest travel distance also includes the following steps: when the farthest travel distance is within a preset distance range, determining a single route coverage strategy, and using the single route coverage strategy to determine the public transportation stop under the single route; when the farthest travel distance exceeds the preset distance range, determining a combined route coverage strategy, and using the combined route coverage strategy to determine the public transportation stop under the combined route.

[0086] Among them, the above-mentioned preset distance range can be set in advance based on actual conditions; for example, the preset distance range can be set to 2 to 20 kilometers. Specifically, if the travel trajectory corresponding to the above-mentioned target to be measured has a starting point and an end point, and the distance between the starting point and the end point is less than 20 kilometers and greater than 2 kilometers, or the distance between the transfer point and the end point is less than 20 kilometers and greater than 2 kilometers, that is, the above-mentioned farthest travel distance is within the preset distance range, then it means that a single route coverage strategy can be determined at this time, that is, an optimal route between the farthest travel distances can be determined as a single route to be covered, and the gathering points passed by the retained single route can be used as the above-mentioned public transportation stops. On the contrary, if the farthest travel distance exceeds the preset distance range, for example, the distance between the starting point and the end point is greater than 20 kilometers, then it means that the travel range corresponding to the target to be measured is large at this time, and a combined route coverage strategy can be determined, that is, the travel range is covered by combining multiple routes, and finally the gathering points passed by the combined routes are used as public transportation stops.

[0087] Through the above embodiment, the corresponding route coverage strategy is determined based on the judgment result of the farthest travel distance range, and the public transportation station is determined based on the corresponding route coverage strategy, which effectively improves the accuracy and comprehensiveness of the public transportation station generation.

[0088] In some embodiments, the historical portrait images are obtained at each image collection point; and when the maximum travel distance is within a preset distance range, the method for generating a traffic route further includes the following steps:

[0089] Obtain a gathering point corresponding to the farthest travel distance, and obtain at least one initial traffic route based on the gathering point and the farthest travel distance; obtain trajectory density information under each image acquisition point based on the historical aggregation information, divide all the image acquisition points according to the trajectory density information to obtain a division result of the image acquisition point; based on the trajectory density information and the duplication information of the initial traffic route, deduplicate the initial traffic route to obtain the single route, and determine the public transportation station under the single route according to the division result.

[0090] The aforementioned gathering points along the longest travel distance are sequentially used as starting points. Based on the corresponding destinations and transfer points, the optimal route corresponding to each gathering point is obtained by calling the map API as the aforementioned initial traffic route. This optimal route can be the route with the shortest distance or the shortest time. The trajectory density information of each image acquisition point is then obtained based on the aforementioned historical gathering information to obtain the aforementioned division results. For example, with each image acquisition point as a division point, the population density at each image acquisition point is determined based on the historical gathering information. If the number of people at the image acquisition point is greater than 10, the score is 10; if the number of people is greater than 5 and less than 10, the score is 10; if the number of people is less than 5 and greater than 2, the score is 2; if the number of people is less than 1, the score is 1. Each score is used as the aforementioned division result. Staff can also pre-set rules such that if the score is 10 or 5, a public transportation stop must be established at this image acquisition point; if the score is less than 5 and the distance to the next checkpoint is no more than 500 meters, a stop is established at the next image acquisition point, so as to subsequently determine the public transportation stop. Based on the above trajectory density information and the duplication information between each initial traffic route, each initial traffic route can be deduplicated; for example, if the duplication rate between a certain initial traffic route and other initial traffic routes is detected to be more than 80%, but based on the trajectory density information, it can be obtained that there are more than 50 people on this initial traffic route for 10 minutes during the peak period, then the initial traffic route is retained. Otherwise, the initial traffic route with the longest distance is retained as the above single route, and the public transportation stations under the single route are determined according to the rules for setting up stations corresponding to the above division results. Through the above embodiment, by using the image acquisition point integral form to determine the public transportation stations, a humanized formulation of the public transportation stations is achieved, thereby further improving the accuracy of traffic route generation and greatly alleviating urban traffic congestion.

[0091] In some embodiments, when the maximum travel distance exceeds the preset distance range, the method for generating a traffic route further includes the following steps:

[0092] Obtain the gathering point corresponding to the longest travel distance, and obtain at least one initial traffic route based on the gathering point and the longest travel distance to determine the largest single route in the initial traffic routes; generate the combined route based on the largest single route and the longest travel distance to determine the public transportation station under the combined route. Specifically, Figure 4 is a schematic diagram of a traffic route according to an embodiment of the present application, such as Figure 4 As shown in the figure, there are four communities, A, B, C, and D. The diagram shows the routes with arrows departing from each community, denoted as Route A, Route B, Route C, and Route D, respectively. Assuming that a traveler from Community A is 30 kilometers from their workplace, and that the initial transportation route corresponding to Community A covers a maximum of 20 kilometers, the remaining 10 kilometers can be covered by the community site near the end of the route. Furthermore, Route C overlaps with Routes A and B by over 80%, so Route C can be removed and covered by Routes A and B.

[0093] In some embodiments, after generating the target traffic route at least according to the public transportation station, the traffic route generation method further includes the following steps:

[0094] Step S241 : When a historical traffic route is obtained, the historical traffic route is compared with the target traffic route to obtain a route change result, and the route change result is sent to a display terminal for display.

[0095] The aforementioned historical traffic route refers to a traffic route generated by the aforementioned steps or other route generation methods prior to generating the aforementioned target traffic route. After the historical traffic route is generated, it can be stored by the aforementioned master control device. If the master control device detects the existence of this historical traffic route, it indicates that this is not the first time the traffic route has been generated. Therefore, the master control device can compare the historical traffic route with the target traffic route to determine route change results. These route change results are then sent to the traffic platform deployed on the display terminal to implement real-time alert processing for traffic route change points.

[0096] Step S242: When the historical traffic route is missing, the target traffic route is sent to the display terminal for display.

[0097] Among them, when the above-mentioned main control device detects that the above-mentioned historical traffic route is missing, it means that this is the first time to generate a traffic route, and the target traffic route generated by the above steps can be directly sent to the traffic platform deployed by the above-mentioned display terminal to display the target traffic route in real time on the traffic platform.

[0098] Through the above steps S241 to S242, different display results are generated when a traffic route is generated for the first time and when a traffic route is not generated for the first time, thereby effectively improving the security and accuracy of the traffic route generation method and enhancing the user experience.

[0099] The following describes the embodiments of this application in detail in conjunction with actual application scenarios. Figure 5 This is a flow chart of a method for generating a traffic route according to a preferred embodiment of the present application. Figure 5 As shown, the process includes the following steps:

[0100] Step S501: capturing data from each checkpoint in the city to obtain historical portrait images.

[0101] Step S502: performing face spatiotemporal clustering and body spatiotemporal clustering according to historical portrait images to obtain historical clustering information after face and body clustering.

[0102] Step S503: Based on the personnel trajectory algorithm model, that is, the above steps analyze the historical archive information, and the analysis cycle is run once a week.

[0103] Step S504, determine the number of public transportation stations, shared bicycle deployment stations and the corresponding number of shared bicycle deployment stations on weekends, and store them in the database; determine the number of public transportation stations, shared bicycle deployment stations and the corresponding number of shared bicycle deployment stations during the week, and store them in the database.

[0104] Step S505, check whether it is the first analysis; if it is not the first analysis, alert the traffic platform of the change point; if it is the first analysis, display the analysis results on the traffic platform.

[0105] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0106] This embodiment also provides a traffic route generation device, which is used to implement the above-mentioned embodiments and preferred embodiments. Details already described will not be repeated here. As used below, terms such as "module," "unit," and "subunit" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0107] Figure 6 This is a structural block diagram of a traffic route generation device according to an embodiment of the present application. Figure 6As shown, the apparatus includes: an acquisition module 61, a clustering module 62, and a generation module 63. The acquisition module 61 is used to acquire a plurality of historical portrait images corresponding to the target to be measured; the clustering module 62 is used to perform portrait clustering processing on the historical portrait images to obtain historical clustering information, obtain the longest travel distance corresponding to the target to be measured based on the historical clustering information, and determine a public transportation station based on the longest travel distance; the generation module 63 is used to generate a target transportation route based on at least the public transportation station.

[0108] Through the above embodiment, the clustering module 62 performs portrait clustering on the acquired historical portrait images to obtain historical clustering information, obtains the farthest travel distance based on the historical clustering information to determine the public transportation station, and the generation module 63 finally generates the public transportation route based on the public transportation station, thereby realizing the determination of the population flow trajectory based on the portrait clustering algorithm, avoiding the situation where the traditional method of obtaining the residents' travel demand is inaccurate and the site selection of the public transportation station is prone to errors, solving the problem of low accuracy of the traffic route generation, and realizing a device for planning the traffic route based on the archive trajectory.

[0109] In some embodiments, the above-mentioned clustering module 62 is also used to perform portrait clustering processing on the historical portrait image to obtain a clustering result of the historical portrait image, and perform target recognition for non-public transportation targets based on the clustering result to obtain a target recognition result; the clustering module 62 filters the clustering result based on the target recognition result to obtain the historical clustering information.

[0110] In some embodiments, the above-mentioned archiving module 62 is also used to calculate the travel trajectory of the target to be measured within a preset time period based on the historical archiving information, and based on the travel trajectory, determine the landing point of the target to be measured according to the preset activity range and the preset activity time; the archiving module 62 obtains the farthest travel distance based on the landing point.

[0111] In some embodiments, the above-mentioned generation module 63 is also used to determine the travel trajectory based on the historical archive information to determine the farthest transfer distance in the travel trajectory; the generation module 63 determines the shared vehicle deployment site based on the farthest travel distance and the farthest transfer distance, and generates a target traffic route based on the shared vehicle deployment site and the public transportation site.

[0112] In some embodiments, the above-mentioned generation module 63 is also used to obtain a gathering point within a first preset range of the farthest travel distance when the farthest travel distance is less than a first preset distance, and determine a first shared vehicle delivery site based on the gathering point; wherein the delivery quantity corresponding to the first shared vehicle delivery site is determined based on the gathering point; the generation module 63 determines the area to be counted within a second preset range of the farthest transfer distance when the farthest transfer distance is less than a second preset distance; the generation module 63 obtains the transfer point and the starting point within the area to be counted, and determines a second shared vehicle delivery site based on the transfer point and the starting point; wherein the delivery quantity corresponding to the second shared vehicle delivery site is determined based on the number of targets to be measured corresponding to the transfer point; the generation module 63 determines the shared vehicle delivery site based on the first shared vehicle delivery site and the second shared vehicle delivery site.

[0113] In some embodiments, the above-mentioned generation module 63 is also used to determine a single route coverage strategy when the longest travel distance is within a preset distance range, and use the single route coverage strategy to determine the public transportation stop under the single route; the generation module 63 is used to determine a combined route coverage strategy when the longest travel distance exceeds the preset distance range, and use the combined route coverage strategy to determine the public transportation stop under the combined route.

[0114] In some embodiments, the above-mentioned historical portrait image is obtained at each image acquisition point; the above-mentioned generation module 63 is also used to obtain the gathering point corresponding to the farthest travel distance, and obtain at least one initial traffic route based on the gathering point and the farthest travel distance; the generation module 63 obtains the trajectory density information at each image acquisition point based on the historical aggregation information, and divides all the image acquisition points according to the trajectory density information to obtain the division result of the image acquisition point; the generation module 63 deduplicates the initial traffic route based on the trajectory density information and the duplication information of the initial traffic route to obtain the single route, and determines the public transportation station under the single route according to the division result.

[0115] In some embodiments, the above-mentioned generation module 63 is also used to obtain the gathering point corresponding to the longest travel distance, and obtain at least one initial traffic route based on the gathering point and the longest travel distance to determine the maximum single route in the initial traffic route; the generation module 63 generates the combined route based on the maximum single route and the longest travel distance to determine the public transportation station under the combined route.

[0116] In some embodiments, the above-mentioned traffic route generation device also includes a display module; the display module is used to compare the historical traffic route with the target traffic route to obtain a route change result when a historical traffic route is obtained, and send the route change result to the display terminal for display; when the historical traffic route is missing, the display module sends the target traffic route to the display terminal for display.

[0117] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0118] This embodiment also provides a portrait image clustering system, which includes: a main control device and various image acquisition devices; wherein, each image acquisition device is correspondingly installed under each image acquisition point; the image acquisition device is used to acquire historical portrait images corresponding to multiple targets to be measured. The main control device is used to execute the steps in any of the above method embodiments. Through the above embodiments, the main control device performs portrait clustering on the acquired historical portrait images to obtain historical clustering information, obtains the farthest travel distance based on the historical clustering information to determine the public transportation station, and finally generates the public transportation route based on the public transportation station, thereby realizing the determination of the population flow trajectory based on the portrait clustering algorithm, avoiding the situation where the traditional method of obtaining the residents' travel demand is inaccurate and the site selection of the public transportation station is prone to errors, solving the problem of low accuracy in the generation of traffic routes, and realizing a system for planning traffic routes based on archive trajectories.

[0119] In some embodiments, a computer device is provided, which may be a server. Figure 7 This is a structural diagram of the internal structure of a computer device according to an embodiment of the present application. Figure 7 As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store a target traffic route. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for generating a traffic route.

[0120] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0121] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0122] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0123] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0124] S1, obtaining historical portrait images corresponding to multiple targets to be measured.

[0125] S2, performing portrait clustering processing on the historical portrait image to obtain historical clustering information, obtaining the farthest travel distance corresponding to the target to be measured according to the historical clustering information, and determining the public transportation station based on the farthest travel distance.

[0126] S3: Generate a target transportation route based on at least the public transportation station.

[0127] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0128] In addition, in conjunction with the traffic route generation method in the above embodiments, embodiments of the present application may provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, it implements any of the traffic route generation methods in the above embodiments.

[0129] Those skilled in the art should understand that the various technical features of the above-described embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-described embodiments are 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.

[0130] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for generating a traffic route, characterized in that: The method comprises: Obtaining historical portrait images corresponding to multiple targets to be measured; Performing portrait clustering processing on the historical portrait images to obtain historical clustering information, obtaining the farthest travel distance corresponding to the target to be measured according to the historical clustering information, and determining a public transportation station based on the farthest travel distance; generating a target transportation route based on at least the public transportation station; The historical portrait images are obtained at each image acquisition point; Determining a public transportation stop based on the longest travel distance includes: When the longest travel distance is within a preset distance range, obtaining a gathering point corresponding to the longest travel distance, and obtaining at least one initial traffic route according to the gathering point and the longest travel distance; Acquiring trajectory density information at each of the image acquisition points according to the historical archive information, and dividing all the image acquisition points according to the trajectory density information to obtain a division result of the image acquisition points; Based on the trajectory density information and the duplication information of the initial traffic route, deduplication processing is performed on the initial traffic route to obtain a single route, and the public transportation station under the single route is determined according to the division result; In the case that the farthest travel distance exceeds the preset distance range, a combined route coverage strategy is determined, and the public transportation stops under the combined route are determined using the combined route coverage strategy.

2. The generation method according to claim 1, characterized in that The performing portrait clustering processing on the historical portrait images to obtain historical clustering information includes: Performing portrait clustering processing on the historical portrait images to obtain clustering results of the historical portrait images, and performing target recognition for non-public transportation targets based on the clustering results to obtain target recognition results; The aggregation result is filtered according to the target recognition result to obtain the historical aggregation information.

3. The generation method according to claim 1, characterized in that The acquiring of the longest travel distance corresponding to the target to be measured according to the historical archive information includes: Calculating the travel trajectory of the target to be measured within a preset time period according to the historical archive information, and determining the landing point of the target to be measured based on the travel trajectory, according to a preset activity range and a preset activity time; The maximum travel distance is obtained according to the landing point.

4. The generation method according to claim 1, characterized in that Generating a target transportation route at least according to the public transportation station comprises: Determine a travel trajectory based on the historical archive information to determine the longest transfer distance in the travel trajectory; A shared vehicle placement site is determined according to the longest travel distance and the longest transfer distance, and a target traffic route is generated according to the shared vehicle placement site and the public transportation site.

5. The generation method according to claim 4, characterized in that Determining the shared vehicle placement site according to the longest travel distance and the longest transfer distance includes: When the maximum travel distance is less than a first preset distance, obtaining a gathering point within the first preset range of the maximum travel distance, and determining a first shared vehicle placement site based on the gathering point; wherein the number of shared vehicles corresponding to the first shared vehicle placement site is determined based on the gathering point; When the farthest transfer distance is less than a second preset distance, determining an area to be counted within a second preset range of the farthest transfer distance; Obtaining a transfer point and a starting point within the area to be counted, and determining a second shared vehicle placement site based on the transfer point and the starting point; wherein the placement volume corresponding to the second shared vehicle placement site is determined based on the number of targets to be measured corresponding to the transfer point; The shared vehicle placement site is determined according to the first shared vehicle placement site and the second shared vehicle placement site.

6. The generation method according to claim 1, characterized in that When the farthest travel distance exceeds the preset distance range, the method further includes: Obtaining a gathering point corresponding to the longest travel distance, and obtaining at least one initial traffic route according to the gathering point and the longest travel distance, so as to determine a maximum single route among the initial traffic routes; The combined route is generated according to the maximum single route and the longest travel distance to determine the public transportation station under the combined route.

7. The generation method according to any one of claims 1 to 6, characterized in that: After generating the target transportation route at least according to the public transportation station, the method further includes: When a historical traffic route is obtained, the historical traffic route is compared with the target traffic route to obtain a route change result, and the route change result is sent to a display terminal for display; In the case that the historical traffic route is missing, the target traffic route is sent to the display terminal for display.

8. A traffic route generation device, characterized in that: The device comprises: an acquisition module, a file aggregation module and a generation module; The acquisition module is used to acquire historical portrait images corresponding to multiple targets to be measured; The clustering module is configured to perform portrait clustering processing on the historical portrait images to obtain historical clustering information, obtain the longest travel distance corresponding to the target to be measured based on the historical clustering information, and determine a public transportation station based on the longest travel distance; The generating module is configured to generate a target transportation route based at least on the public transportation station; The historical portrait images are obtained at each image acquisition point; Determining a public transportation stop based on the longest travel distance includes: When the longest travel distance is within a preset distance range, obtaining a gathering point corresponding to the longest travel distance, and obtaining at least one initial traffic route according to the gathering point and the longest travel distance; Acquiring trajectory density information at each of the image acquisition points according to the historical archive information, and dividing all the image acquisition points according to the trajectory density information to obtain a division result of the image acquisition points; Based on the trajectory density information and the duplication information of the initial traffic route, deduplication processing is performed on the initial traffic route to obtain a single route, and the public transportation station under the single route is determined according to the division result; In the case that the farthest travel distance exceeds the preset distance range, a combined route coverage strategy is determined, and the public transportation stops under the combined route are determined using the combined route coverage strategy.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for generating a traffic route according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method for generating a traffic route according to any one of claims 1 to 7 when running.

Images