Method and device for identifying travel characteristics of metropolitan area residents

Abstract

The application provides a metropolitan area resident travel feature identification method and device, the method comprising: obtaining mobile phone signaling data of each resident in a target metropolitan area; for each resident, based on the resident's mobile phone signaling data, drawing the resident's trajectory points, clustering the trajectory points to obtain a travel starting point, a travel stay point and a travel ending point; determining a metropolitan area travel result based on the travel starting point, the travel stay point and the travel ending point; determining a metropolitan area travel time based on the trajectory points and the metropolitan area travel result; determining a travel path and a travel mode based on the resident's mobile phone signaling data; determining a travel purpose based on the trajectory points, the travel starting point and the travel ending point; aggregating the above results to obtain the resident's travel feature; and aggregating the travel features of each resident in the target metropolitan area to obtain the travel features of the target metropolitan area. The application can provide an adjustment scheme for formulating a traffic facility plan and adjusting the allocation of traffic resources.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology, and in particular relates to a method and device for identifying travel characteristics of urban residents. Background Art

[0002] A metropolitan area is centered around a central city with a clear primacy advantage and encompasses commuting areas, rather than the administrative boundaries of a single city. As an extended form of a city, a metropolitan area typically encompasses two or more cities, and residents in a metropolitan area often travel across cities and regions. Intercity travel in metropolitan areas differs significantly from the travel needs of urban residents. For example, the relatively low number of trips and the large scope of surveys make it difficult to capture comprehensive information on intercity travel using traditional survey methods.

[0003] Existing urban circle traffic surveys mostly use traditional methods such as manual surveys to collect travel information within the city and aggregate travel flow between major channels and modes. It is difficult to comprehensively portray the travel characteristics of urban circles in the long term, and it is difficult to provide adjustment plans for the reasonable and efficient adjustment of traffic resource allocation in urban circles. Summary of the Invention

[0004] The embodiments of the present application provide a method and device for identifying the travel characteristics of urban circle residents, so as to obtain the travel characteristics of urban circle residents in a more comprehensive and efficient manner and provide solutions for adjusting transportation facility planning and resource allocation.

[0005] This application is achieved through the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for identifying travel characteristics of residents in a metropolitan area, comprising:

[0007] Obtain mobile phone signaling data for every resident in the target metropolitan area.

[0008] For each resident, based on the resident's mobile phone signaling data, the resident's trajectory points are drawn, and the trajectory points are clustered to obtain the travel starting point, travel stop point and travel end point; based on the travel starting point, travel stop point and travel end point, the metropolitan area travel results are determined; based on the trajectory points and metropolitan area travel results, the metropolitan area travel time is determined; based on the resident's mobile phone signaling data, the travel path and travel mode are determined; based on the trajectory points, travel starting point and travel end point, the travel purpose is determined; the travel starting point, travel end point, metropolitan area travel results, travel path, travel mode and travel purpose are summarized to obtain the travel characteristics of the resident.

[0009] Summarize the travel characteristics of each resident in the target metropolitan area to obtain the travel characteristics of the target metropolitan area.

[0010] In combination with the first aspect, in some possible implementation manners, the trajectory points are clustered to obtain a trip starting point, a trip stay point and a trip ending point, including:

[0011] The trajectory points of the resident are clustered by using a space-time clustering algorithm, and a clustering cluster obtained by the clustering is taken as a resident stay area.

[0012] The number of trajectory points in each resident stay area and the time stamp of each trajectory point are obtained, and each resident stay area is sorted according to the number of trajectory points. Two resident stay areas with the first and second number of trajectory points are taken as a trip starting area and a trip ending area. The area with a time sequence earlier in the time stamp of the trajectory points in the area is the trip starting area.

[0013] The center point of all trajectory points in the trip starting area is calculated to obtain a first center point, and the first center point is taken as a trip starting point.

[0014] The center point of all trajectory points in the trip ending area is calculated to obtain a second center point, and the second center point is taken as a trip ending point.

[0015] The time difference between the first trajectory point and the last trajectory point in each resident stay area according to the time sequence after the trip starting area and the trip ending area are removed is calculated.

[0016] For each time difference, if the time difference is greater than or equal to a time threshold, the resident stay area corresponding to the time difference is taken as a trip stay point area. The center point of all trajectory points in the trip stay point area is calculated to obtain a third center point, and the third center point is taken as a trip stay point.

[0017] In combination with the first aspect, in some possible implementation manners, based on the trip starting point, the trip stay point and the trip ending point, a metropolitan circle trip result is determined, including:

[0018] The spatial positions of the trip starting point, the trip stay point and the trip ending point are obtained, and are spatially matched with traffic cells to obtain a traffic cell corresponding to the trip starting point, a traffic cell corresponding to the trip stay point and a traffic cell corresponding to the trip ending point.

[0019] The traffic cell corresponding to the trip starting point, the traffic cell corresponding to the trip stay point and the traffic cell corresponding to the trip ending point are connected according to the time sequence to obtain a plurality of trip segments.

[0020] For each trip segment, whether the trip segment crosses a city urban area boundary is determined according to the traffic cells at two ends of the trip segment. If the trip segment crosses the city urban area boundary, the points at two ends of the trip segment are taken as two end points of a metropolitan circle trip OD. The metropolitan circle trip OD represents a trip traffic crossing the city urban area.

[0021] If there is at least one travel segment whose two endpoints are the two endpoints of the metropolitan area travel OD, the metropolitan area travel result is that there is cross-city travel behavior.

[0022] If the two endpoints of a non-existent travel segment are the two endpoints of the metropolitan area travel OD, the result of the metropolitan area travel is that there is no cross-city travel behavior.

[0023] In conjunction with the first aspect, in some possible implementations, determining the metropolitan area travel time based on the trajectory points and the metropolitan area travel results includes:

[0024] When the metropolitan area travel result indicates that there is cross-city travel behavior, the two endpoints of the metropolitan area travel OD are obtained based on the metropolitan area travel result.

[0025] Get the trajectory points at the two endpoints of the metropolitan area travel OD.

[0026] Based on the trajectory points in the two endpoints of the metropolitan area travel OD, a first endpoint and a second endpoint are obtained; wherein the first endpoint is the endpoint with the earlier timing in the two endpoints of the metropolitan area travel OD.

[0027] The trajectory points in the first endpoint are sorted to obtain the trajectory point with the largest timing in the first endpoint.

[0028] The trajectory points in the second endpoint are sorted to obtain the trajectory point with the smallest timing in the second endpoint.

[0029] The difference between the timestamp of the trajectory point with the smallest time sequence in the second endpoint and the timestamp of the trajectory point with the largest time sequence in the first endpoint is calculated to obtain the urban circle travel time of the resident.

[0030] When the metropolitan area travel result shows that there is no cross-city travel behavior, the metropolitan area travel time is zero.

[0031] In conjunction with the first aspect, in some possible implementations, determining a travel route based on the resident's mobile phone signaling data includes:

[0032] Based on the resident's mobile phone signaling data, the base stations to which the resident's mobile phone is sequentially connected are determined, and based on the sequentially connected base stations, a first path buffer sequence is determined; wherein the path buffer includes multiple base stations; the first path buffer is a collection of path buffers where the sequentially connected base stations are located.

[0033] A second path buffer sequence and a third path buffer sequence are obtained; wherein the second path buffer sequence is a set of path buffers passing along the railway, and the third path buffer sequence is a set of path buffers passing along the highway.

[0034] The similarity between the first path buffer sequence and the second path buffer sequence is calculated to obtain a first similarity.

[0035] The similarity between the first path buffer sequence and the third path buffer sequence is calculated to obtain a second similarity.

[0036] The first similarity and the second similarity are compared, and the path corresponding to the larger similarity value is used as the travel path.

[0037] In conjunction with the first aspect, in some possible implementations, determining the travel mode based on the resident's mobile phone signaling data includes:

[0038] Based on the resident's mobile phone signaling data, the time difference between the resident's connection to two adjacent base stations on the travel path is obtained.

[0039] Get the distance between two adjacent base stations.

[0040] The quotient of the distance between two adjacent base stations and the time difference between the resident connecting to the two adjacent base stations on the travel path is calculated to obtain the resident's travel speed.

[0041] Filter out the bus routes that are the same as the resident's travel route.

[0042] Obtain a first statistical value; wherein the first statistical value represents the sum of the number of travel starting points, travel stop points, and travel end points within the bus passenger station in the route.

[0043] A first membership value is determined based on the travel speed and a preset automobile K-order parabolic distribution membership function.

[0044] The second membership value is determined based on the travel speed and a preset K-order parabolic distribution membership function of the bus.

[0045] The product of the first statistical value and the first preset value and the sum of the second membership value are calculated to obtain a third membership value.

[0046] The first membership value and the third membership value are compared, and the means of transportation corresponding to the larger membership value is selected as the travel mode.

[0047] The preset car K-order parabolic distribution membership function is:

[0048]

[0049] Wherein, a1, b1, c1 and d1 all represent preset parameters, x represents the travel speed, k represents the parabola power, and A1(x) represents the first membership value.

[0050] The preset K-order parabolic distribution membership function of the bus is:

[0051]

[0052] wherein a2, b2, c2 and d2 represent preset parameters, and A2(x) represents the second membership value.

[0053] With reference to the first aspect, in some possible implementation manners, the travel purpose is determined based on the trajectory point, the travel starting point and the travel ending point, and the method comprises the following steps.

[0054] Based on the trajectory point, the residence and the workplace of the resident are determined according to the POI data and the preset rule.

[0055] The travel purpose of the resident is determined based on the travel starting point, the travel ending point, the residence and the workplace of the resident.

[0056] With reference to the first aspect, in some possible implementation manners, the preset rule comprises the following steps.

[0057] When the number of residents on a first target day in a month exceeds a preset number, and the resident on the first target day stays at a first location for the longest time from 22:00 of the day before the first target day to 7:00 of the first target day and stays at the first location for a time period longer than a preset time period, the first location is determined as the residence of the resident.

[0058] When the number of residents on a second target day in a month exceeds a preset number, and the resident on the second target day stays at a second location for the longest time from 9:00 of the second target day to 18:00 of the second target day and stays at the second location for a time period longer than a preset time period, the second location is determined as the workplace of the resident.

[0059] With reference to the first aspect, in some possible implementation manners, the method further comprises the following steps.

[0060] Based on the travel characteristics of the target metropolitan area, a traffic facility planning and traffic resource allocation scheme is formulated.

[0061] According to the traffic facility planning and traffic resource allocation scheme, the traffic system of the target metropolitan area is optimized and adjusted.

[0062] The second aspect provides a metropolitan area resident travel characteristic identification device, comprising:

[0063] A data acquisition module is configured to acquire mobile phone signaling data of each resident in a target metropolitan area.

[0064] The data processing module is used to draw the trajectory points of each resident based on the resident's mobile phone signaling data, cluster the trajectory points, and obtain the travel starting point, travel stop point and travel end point; determine the urban circle travel results based on the travel starting point, travel stop point and travel end point; determine the urban circle travel time based on the trajectory points and the urban circle travel results; determine the travel path and travel mode based on the resident's mobile phone signaling data; determine the travel purpose based on the trajectory points, travel starting point and travel end point; summarize the travel starting point, travel end point, urban circle travel results, travel path, travel mode and travel purpose to obtain the travel characteristics of the resident.

[0065] The result output module is used to summarize the travel characteristics of each resident in the target metropolitan area and obtain the travel characteristics of the target metropolitan area.

[0066] It can be understood that the beneficial effects of the second aspect mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0067] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0068] This application calculates the travel characteristics of each resident through the mobile phone signaling data of each resident in the target urban circle, summarizes the travel characteristics of each resident, and then obtains the travel characteristics of the target urban circle, providing a basis for the reasonable and efficient adjustment of traffic resources in the target urban circle.

[0069] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0071] Figure 1 This is a flow chart of a method for identifying travel characteristics of metropolitan area residents provided in one embodiment of the present application;

[0072] Figure 2 This is a flowchart of identifying a trip starting point, a trip stop, and a trip destination provided by an embodiment of the present application;

[0073] Figure 3 This is a schematic diagram of the urban circle travel process provided by an embodiment of the present application;

[0074] Figure 4The best matching result of the score matrix, backtracking path and sequence provided in an embodiment of the present application is:

[0075] Figure 5 This is a travel mode identification process provided by an embodiment of the present application;

[0076] Figure 6 This is a schematic diagram of the travel speed calculation principle provided by an embodiment of the present application;

[0077] Figure 7 It is a structural diagram of a device for identifying travel characteristics of urban residents provided in one embodiment of the present application. DETAILED DESCRIPTION

[0078] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0079] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0080] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0081] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0082] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0083] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0084] Existing urban circle traffic surveys mostly use traditional methods such as manual surveys to collect travel information within the city and aggregate travel flow between major channels and modes. It is difficult to comprehensively portray the travel characteristics of urban circles in the long term, and it is difficult to provide adjustment plans for the reasonable and efficient adjustment of traffic resource allocation in urban circles.

[0085] In order to solve the above problems more comprehensively, this solution has the following considerations:

[0086] First: Research and propose the content of the travel survey for urban residents.

[0087] Drawing on domestic and international experience, relevant economic and social development planning requirements, and travel behavior analysis, the metropolitan area resident travel survey primarily includes interval flow surveys, entry and exit surveys, and traffic data surveys. Specifically, it covers indicators such as intercity inflow and outflow characteristics, transit traffic characteristics, traffic flow characteristics on national and provincial highways, employment-residence distribution characteristics, the proportion of migrant workers, population migration, and transportation accessibility (see Table 1 below). Surveys often last longer than one month.

[0088] Table 1

[0089]

[0090] Second: Analysis of the urban circle residents’ travel survey data, and the summary of the multi-source data resource structure of the urban circle residents’ travel survey is shown in Table 2.

[0091] Table 2

[0092]

[0093]

[0094] Third: Build a travel survey process for urban residents based on multi-source data.

[0095] Based on mobile phone signaling data, and integrating multi-source big data such as GPS data, video, coils, and toll collection, as well as basic data such as traditional surveys and road networks, a travel survey process system for urban residents based on multi-source traffic big data was constructed. The system includes the following steps: ① identification of individual travel characteristics, ② analysis of urban circle travel characteristics, and ③ analysis of multi-day travel characteristics. It also combines traffic big data with traditional surveys to identify many characteristics such as intercity travel and highway travel, and verifies them with a variety of evaluation indicators. Finally, a verification and calibration analysis mechanism for multi-source data was established.

[0096] ① Identification of individual travel characteristics

[0097] First, we use signaling data to determine whether the individual travelers are traveling across cities in the metropolitan area. Then, we use basic data such as mobile phone signaling, vehicle GPS, road network, etc. to identify individual travel characteristics such as travel endpoints, OD, paths and methods through clustering, machine learning and other algorithms.

[0098] ② Analysis of travel characteristics in urban areas

[0099] By aggregating and expanding the data, we can identify characteristics such as travel distribution, travel mode breakdown, and traffic flow by mode across the metropolitan area. We then leverage data from highway toll booths, industry statistics, surveillance videos, and loops to analyze actual traffic flow on key sections and across regions. This data is then supplemented and verified with traditional manual survey data, enabling multi-faceted comparison and verification of the metropolitan area's travel characteristics with identification results from signaling and other data.

[0100] ③Analysis of multi-day travel characteristics

[0101] The travel characteristics obtained above are compared with relevant indicators of industry published data, special investigation reports, and traffic model results. After verifying the feasibility of the method, the travel characteristics of the urban circle for multiple days are analyzed by accumulating data over time.

[0102] Fourth: Propose an urban area resident travel survey indicator system that integrates multi-source data.

[0103] Based on the survey content of urban area residents' travel, and integrating new big data with traditional transportation survey data, a key technical indicator system for urban area residents' travel surveys has been constructed, integrating multi-source data. The system includes four categories: transportation industry statistical indicators, transportation big data statistical indicators, special survey data indicators, and traffic model technical indicators. Transportation industry statistical indicators include road, rail, water, and air transportation data, railway passenger volume, and civil aviation airport passenger throughput. Transportation big data statistical indicators include urban area travel based on fare collection data, bus, subway, and intercity line card swipe data, and key road sections integrated with multi-source data such as video. Traffic model technical indicators include: total urban trip generation, regional passenger flow, mode choice, urban travel mode choice, urban traffic flow distribution using traditional methods, passenger satisfaction, travel time and space distribution, and energy consumption. Special survey data indicators include: traffic flow characteristics and mode share at key sections, traffic flow characteristics and mode split on entry and exit roads, travel O / D characteristics, mode choice preferences, travel distribution characteristics of migrant population, and passenger bus flow characteristics.

[0104] Based on the above problems and considerations, an embodiment of the present application proposes a method for identifying travel characteristics of urban circle residents. Through the mobile phone signaling data of each resident in the target urban circle, the travel characteristics of each resident are calculated, and the travel characteristics of each resident are summarized to obtain the travel characteristics of the target urban circle, and then a traffic resource allocation plan is obtained, providing an adjustment plan for the reasonable and efficient adjustment of traffic resources in the urban circle.

[0105] Figure 1 This is a schematic diagram of the process of identifying the travel characteristics of urban residents provided by an embodiment of the present application, with reference to Figure 1 , the detailed description of the method for identifying the travel characteristics of residents in the metropolitan area is as follows:

[0106] Step 101: Obtain mobile phone signaling data of each resident in the target metropolitan area.

[0107] Specifically, mobile phone signaling data is generated by the communication between base stations and mobile terminals in a mobile communication system, and is a type of data passively collected from base stations through a mobile communication network.

[0108] Step 102: for each resident, based on the mobile phone signaling data of the resident, draw the trajectory points of the resident, cluster the trajectory points to obtain the travel starting point, travel stop points and travel end point; determine the urban circle travel results based on the travel starting point, travel stop points and travel end point; determine the urban circle travel time based on the trajectory points and the urban circle travel results; determine the travel path and travel mode based on the mobile phone signaling data of the resident; determine the travel purpose based on the trajectory points, travel starting point and travel end point; summarize the travel starting point, travel end point, urban circle travel results, travel path, travel mode and travel purpose to obtain the travel characteristics of the resident.

[0109] For example, clustering the trajectory points to obtain the travel starting point, travel stop point, and travel end point includes:

[0110] The trajectory points of the residents are clustered using a spatiotemporal clustering algorithm, and the clusters obtained are used as the residents' stay areas.

[0111] Obtain the number of trajectory points and the timestamp of each trajectory point in each resident's stay area, and sort each resident's stay area according to the number of trajectory points. The two resident stay areas ranked first and second in the number of trajectory points are used as the travel starting area and travel ending area; among them, the area with the earlier timestamp of the trajectory points in the area is the travel starting area.

[0112] Calculate the center points of all trajectory points in the travel starting area, obtain the first center point, and use the first center point as the travel starting point.

[0113] Calculate the center point of all trajectory points in the travel destination area to obtain a second center point, and use the second center point as the travel destination.

[0114] Calculate the time difference between the first and last trajectory points in each resident's stay area, sorted by time, after excluding the travel start and end areas.

[0115] For each time difference, if the time difference is greater than or equal to the time threshold, the resident stay area corresponding to the time difference is used as the travel stop point area; the center point of all trajectory points in the travel stop point area is calculated to obtain the third center, and the third center point is used as the travel stop point.

[0116] Specifically, the above method can more accurately determine the travel starting point, travel stop point and travel end point, avoid errors caused by signal drift, make the final result more accurate, and ensure the accuracy of traffic resource adjustment.

[0117] Specifically, the spatiotemporal clustering algorithm can be the ST-DBSCAN density-based spatiotemporal clustering algorithm; assuming that there is a sample set X = {x1, x2, x3, ..., x n}, where the parameters (Eps, MinPts) are used to describe the compactness of sample distribution, Eps is the clustering radius parameter, and MinPts is the sample number threshold.

[0118] 1) E-neighborhood: For the sample set X = {x1, x2, x3, ..., x n Any sample x in i , whose E-neighborhood contains the sample set X and x i All samples whose distance is less than Eps satisfy the following formula:

[0119] N E (x i )={x l ∈X|dis(x l ,x i )≤Eps}

[0120] Where, dis(x i ,x l ) is any sample x i 、x l The spatial distance, Eps is the cluster radius parameter, X is the sample set, N E (x i ) is the sample x i The set of all samples in the E-neighborhood of .

[0121] 2) Core point: For sample x i , if the number of points contained in its E-neighborhood is greater than the sample number threshold, that is, N E (x i )≥MinPts, then x i It is the core point (the first center point and the second center point). In actual calculation, since the core point is related to the starting point and the end point of the trip, the number threshold will actually filter out the E-neighborhood of the two points. Then, according to the time sequence, the core point corresponding to the starting point and the core point corresponding to the end point can be distinguished. If it does not meet the requirements, it is a boundary object and needs to be judged later whether it is a travel stop point.

[0122] Specifically, in another specific embodiment, Figure 2 As shown, the steps and processes for identifying the trip starting point, trip stop point, and trip end point specifically include:

[0123] S1: Based on the base station database, the signaling sequence data is matched with the longitude and latitude of the corresponding base station according to the base station cell code CELLID.

[0124] S2: For resident i traveling in the metropolitan area, the signaling sequence set after data preprocessing contains information such as the base station connected when the signaling event occurs and the signaling timestamp. The signaling sequence set is sorted according to the timestamp.

[0125] S3: Prepare the algorithm input data, namely the signaling sequence data sample set X of urban residents traveling, the clustering radius parameter Eps, and the number threshold MinPts.

[0126] S4: Traverse the objects in the data sample set X, for a sample object x ii If the number of trajectory points in its E-neighborhood is less than the number threshold MinPts, the object is marked as a noise point, otherwise a new cluster is established to add it.

[0127] S5: Traverse sample object x i All points in the neighborhood are processed and S4 is executed until all sample objects are processed, that is, they are added to the cluster or marked as noise points;

[0128] S6: Obtain a set of all clusters. Filter out the clusters corresponding to the core points from all clusters as the travel start and end point clusters. Perform a stay time threshold determination on the remaining clusters. Calculate the time difference between the first and last points in the cluster. If the time difference is greater than the time threshold, identify the cluster as a travel stop point cluster.

[0129] S7: Find the centroid of each resident's travel stop cluster and use its location as the coordinates of the travel stop. The same applies to the start and end points of the trip. Sort the trajectory points in chronological order, using the timestamp of the first trajectory point as the start time of the stop and the timestamp of the last trajectory point as the end time of the stop.

[0130] Specifically, in another specific embodiment, the travel starting point, travel stop point and travel end point can also be identified based on the card payment data.

[0131] Toll collection data includes bus and subway card swiping data, highway toll collection data, and road, rail, water, and air ticket data. Passengers often swipe their cards when entering and exiting stations, so inter-city travel endpoints within a metropolitan area can be obtained through corresponding station information, crawlers, or POI data.

[0132] The boarding point is the card swiping point. The alighting point is calculated using the Poisson distribution and route matching method. The main steps are as follows:

[0133] (1) Calibration of Poisson distribution parameters.

[0134] For each bus line, a Poisson distribution is set, and the distribution parameter λ is adjusted through analysis of previous bus surveys and inquiries to ensure that the distribution is consistent with the actual number of bus stops taken by passengers on this line.

[0135] (2) Extraction of bus stop data.

[0136] After completing the boarding identification, the alighting station information is identified based on the passenger's card swiping data characteristics on that day, combined with the bus connection travel mode and travel distance characteristics.

[0137] 1) Given a single card swiping data record, the number of bus stops taken by the passenger is randomly obtained using the Poisson probability distribution, thereby inferring the alighting station information.

[0138] 2) If there are multiple card swipe data, inference is made in four cases:

[0139] ① The first and last trips are return trips, i.e., the same route with different up and down routes. The boarding station for the first card swipe data i is the alighting station for the last card swipe data i+n, and the boarding station for the last card swipe data i+n is the alighting station for the first trip i.

[0140] ② The first and last trips form a loop, meaning the stops in the direction of the last data item gradually approach the stop in the direction of the first card swipe data item. The stop in the direction of the last data item i+n, with the shortest distance from the stop in the first card swipe data item i and less than 1500 meters, is the alighting stop, where 1500 meters is determined by the current city's walking distance limit.

[0141] ③ For trips on the same or different lines, if the two adjacent card swipe data have the same route, excluding the first and last swipes, the two trips are considered on the same route; otherwise, they are considered on different lines. For two trips on the same line, the boarding station for the i+1 data item is the alighting station for the i data item. For two trips on different lines, the alighting station is the station with the shortest distance from the i+1 boarding station in the direction of travel of the bus route for the i data item and is less than 1500m away.

[0142] ④ For other travel situations, use Poisson probability distribution to randomly obtain the number of bus stops taken by passengers and infer the alighting station information.

[0143] Identifying the travel starting point, travel stop point and travel end point based on card swiping and charging data is a supplementary method for identifying the travel starting point, travel stop point and travel end point in this scheme. When the method of obtaining the travel starting point, travel stop point and travel end point by clustering based on trajectory points cannot be implemented specifically, the travel starting point, travel stop point and travel end point can be identified based on card swiping and charging data.

[0144] Specifically, in order to ensure the smooth implementation of the plan and reduce the requirements for obtaining initial data (mobile phone signaling information of each resident in the target urban agglomeration), alternative parts were introduced into the overall plan to enhance the feasibility and applicability of the plan, so that it can adapt to more complex and changing situations and ensure the accuracy of the results.

[0145] Exemplarily, determining a metropolitan area travel result based on a travel starting point, a travel stop point, and a travel destination includes:

[0146] The spatial locations of the travel starting point, travel stop point and travel destination are obtained, and spatially matched with the traffic district to obtain the traffic district corresponding to the travel starting point, the traffic district corresponding to the travel stop point and the traffic district corresponding to the travel destination.

[0147] The traffic areas corresponding to the travel starting point, the traffic areas corresponding to the travel stop points, and the traffic areas corresponding to the travel end points are connected in time sequence to obtain multiple travel segments.

[0148] For each travel segment, the traffic zones at both ends of the segment are used to determine whether the segment crosses the city boundary. If the segment crosses the city boundary, the points at both ends of the segment are used as the two endpoints of the metropolitan area travel OD; the metropolitan area travel OD represents travel traffic that crosses the city boundary.

[0149] If there is at least one travel segment whose two endpoints are the two endpoints of the metropolitan area travel OD, the metropolitan area travel result is that there is cross-city travel behavior.

[0150] If the two endpoints of a non-existent travel segment are the two endpoints of the metropolitan area travel OD, the result of the metropolitan area travel is that there is no cross-city travel behavior.

[0151] Specifically, such as Figure 3 As shown, the resident's departure city includes three districts: O1, O2, and O3, and the arrival city includes three districts: D1, D2, and D3. Four endpoints were identified for the resident, resulting in three trips. Trip segment 2 starts at O2, belonging to traffic district 4, and ends at D2, belonging to traffic district 5. Both the starting and ending points cross the city boundary, making this an inter-city trip. Trip segments 1 and 3, with a starting point at O1 and a destination at D1, and a starting point at O3 and a destination at D3, are intra-city trips and not inter-city trips.

[0152] Specifically, in another specific embodiment, the metropolitan area travel results can also be identified based on the card payment data.

[0153] (1) For data on subways, roads, railways, waterways, and airlines that require card swiping at all stations, the identified travel endpoints are arranged in chronological order.

[0154] (2) According to the card swiping attributes of the boarding and alighting stations, each set of boarding and alighting station card swiping records is matched, and the corresponding travel OD information is identified in combination with data such as POI.

[0155] (3) For buses and other vehicles that only use the card swiping data on boarding, the above-mentioned alighting station estimation method is used to obtain the corresponding travel OD information, combined with the actual latitude and longitude of the station and other data.

[0156] Identifying metropolitan area travel results based on card swiping and charging data is a supplementary method for identifying metropolitan area travel results in this solution. When the method of obtaining metropolitan area travel results based on travel starting points, travel stops and travel end points cannot be implemented, identifying metropolitan area travel results based on card swiping and charging data can be used.

[0157] Exemplarily, determining the metropolitan area travel time based on the trajectory points and the metropolitan area travel results includes:

[0158] When the metropolitan area travel result indicates that there is cross-city travel behavior, the two endpoints of the metropolitan area travel OD are obtained based on the metropolitan area travel result.

[0159] Get the trajectory points at the two endpoints of the metropolitan area travel OD.

[0160] Based on the trajectory points in the two endpoints of the metropolitan area travel OD, a first endpoint and a second endpoint are obtained; wherein the first endpoint is the endpoint with the earlier timing in the two endpoints of the metropolitan area travel OD.

[0161] The trajectory points in the first endpoint are sorted to obtain the trajectory point with the largest timing in the first endpoint.

[0162] The trajectory points in the second endpoint are sorted to obtain the trajectory point with the smallest timing in the second endpoint.

[0163] The difference between the timestamp of the trajectory point with the smallest time sequence in the second endpoint and the timestamp of the trajectory point with the largest time sequence in the first endpoint is calculated to obtain the urban circle travel time of the resident.

[0164] When the metropolitan area travel result shows that there is no cross-city travel behavior, the metropolitan area travel time is zero.

[0165] Specifically, in another specific embodiment, the travel time can also be identified based on the card charging data.

[0166] Unlike spatiotemporal trajectory data, card swipe data records the swipe time. Therefore, for subway card swipe data, highway toll collection data, and road, rail, water, and air ticket data, boarding and alighting times can be directly extracted from the data records to calculate travel time. However, bus travel data does not include alighting and alighting data, so this method cannot directly extract travel time. Therefore, it is necessary to integrate bus GPS and station coordinate data to calculate travel time.

[0167] (1) Calculate the bus stop according to the above method.

[0168] (2) Based on the boarding card swiping time and boarding station of the bus trip, combined with all the bus GPS data of the route, the bus schedule to be taken is matched and determined.

[0169] (3) According to the GPS data of the bus, the time when the bus arrives at the get-off station is matched and recorded as the bus get-off station time.

[0170] (4) Calculate the bus travel time based on the boarding card swiping time and the alighting time.

[0171] Identifying travel time based on card swiping and charging data is a supplementary method for identifying travel time in this solution. When the method of determining metropolitan area travel time based on trajectory points and metropolitan area travel results cannot be implemented, identifying travel time based on card swiping and charging data can be used.

[0172] Exemplarily, determining a travel route based on the resident's mobile phone signaling data includes:

[0173] Based on the resident's mobile phone signaling data, the base stations to which the resident's mobile phone is sequentially connected are determined, and based on the sequentially connected base stations, a first path buffer sequence is determined; wherein the path buffer includes multiple base stations; the first path buffer is a collection of path buffers where the sequentially connected base stations are located.

[0174] A second path buffer sequence and a third path buffer sequence are obtained; wherein the second path buffer sequence is a set of path buffers passing along the railway, and the third path buffer sequence is a set of path buffers passing along the highway.

[0175] The similarity between the first path buffer sequence and the second path buffer sequence is calculated to obtain a first similarity.

[0176] The similarity between the first path buffer sequence and the third path buffer sequence is calculated to obtain a second similarity.

[0177] The first similarity and the second similarity are compared, and the path corresponding to the larger similarity value is used as the travel path.

[0178] Specifically, in order to avoid the influence of signal drift, multiple base stations are grouped into one path buffer. The travel path is judged by comparing the similarity between the actual passed path buffer list and the path buffer lists of different paths, thereby increasing the accuracy of travel path judgment.

[0179] Specifically, metropolitan area road networks have fewer nodes and a simpler topology. The length of individual road segments is significantly longer than that of urban areas. Furthermore, the distances between parallel or adjacent roads are long, resulting in a low road density. This makes it difficult for a single mobile phone base station to cover two roads. Therefore, a path matching sequence is constructed by setting buffers based on the distribution characteristics of the distance between mobile phone signaling data and base stations. This buffer refers to the geographically defined range of influence of a road segment. Based on the confidence factor for a 95% successful connection to a base station, a strip buffer of 1400m wide and 3-5km long is set for highways and national and provincial highways; and 800m wide and 5-10km long is set for high-speed rail tracks. No buffers are set for special areas such as tunnels, or within 2km of intersections, to avoid difficulties in base station map matching caused by the dense distribution of base stations.

[0180] Each buffer zone covers multiple cell signal base stations, if a passenger has a continuous cell-ID sequence belonging to the same buffer zone, the sequence is replaced by the buffer zone number. Compared with the urban area travel cell-ID sequence, the buffer zone coding sequence is shorter, which can effectively improve the path recognition efficiency and support large-scale group travel path recognition work.

[0181] Specifically, taking the road buffer zone sequence as an example, the preset sequence S of the road buffer zone and the actual sequence T of the actual passing buffer zone are shown in the following table.

[0182] The road buffer zone sequence table is as follows:

[0183] sequence Buffer number sequence Preset sequence S {1，2，3，4，5} Actual sequence T {1，3，5，6}

[0184] The score rule of sequence matching is shown in the following formula, when the elements in the two sequences match, 1 point is obtained, and no score is obtained when mismatching or inserting a space.

[0185]

[0186] In the formula, T is the actual travel buffer zone sequence; S is the preset travel buffer zone sequence; S i is the i-th data in the sequence S; T j is the j-th data in the sequence T; score(S i ,T j ) is the matching score result of any element.

[0187] The iteration formula of the score matrix is as follows:

[0188]

[0189] In the formula, M is the score matrix; M i,j is the score of the i-th row and the j-th column in the matrix M; score(S i ,T j ) is the matching score result of any element.

[0190] According to this rule, fill in the score matrix, after all cells are calculated, start backtracking the best path, and the best matching result is shown in Figure 4 .

[0191] Due to the road geometry relationship of the road network, the passenger travel path or the length of the preset travel path, a longer sequence will be more likely to match more same sequence elements with the passenger travel path sequence, and it is difficult to ensure the reliability of the path matching result by using the number of sequence matching elements as an index to measure the sequence similarity. For this, the project proposes the similarity index as shown in the formula, where Len is the number of sequence elements, and the sequence similarity of S sequence and T sequence is 66.7% by using the above formula.

[0192]

[0193] Where Len(S) is the number of elements in the default row sequence S; Len(T) is the number of elements in the identified row sequence T; score(S, T) is the final matching score of sequences S and T; similarity is the similarity between sequences S and T.

[0194] Exemplarily, determining the travel mode based on the resident's mobile phone signaling data includes:

[0195] Based on the resident's mobile phone signaling data, the time difference between the resident's connection to two adjacent base stations on the travel path is obtained.

[0196] Get the distance between two adjacent base stations.

[0197] The quotient of the distance between two adjacent base stations and the time difference between the resident connecting to the two adjacent base stations on the travel path is calculated to obtain the resident's travel speed.

[0198] Filter out the bus routes that are the same as the resident's travel route.

[0199] Obtain a first statistical value; wherein the first statistical value represents the sum of the number of travel starting points, travel stop points, and travel end points within the bus passenger station in the route.

[0200] A first membership value is determined based on the travel speed and a preset automobile K-order parabolic distribution membership function.

[0201] The second membership value is determined based on the travel speed and a preset K-order parabolic distribution membership function of the bus.

[0202] The product of the first statistical value and the first preset value and the sum of the second membership value are calculated to obtain a third membership value, wherein the first preset value is 0.1.

[0203] The first membership value and the third membership value are compared, and the means of transportation corresponding to the larger membership value is selected as the travel mode.

[0204] The preset car K-order parabolic distribution membership function is:

[0205]

[0206] Wherein, a1, b1, c1 and d1 all represent preset parameters, x represents the travel speed, k represents the parabola power, and A1(x) represents the first membership value.

[0207] The preset K-order parabolic distribution membership function of the bus is:

[0208]

[0209] Wherein, a2, b2, c2 and d2 represent preset parameters, and A2(x) represents the second membership value.

[0210] Specifically, by distinguishing between car travel and bus travel, bus travel schedules can be arranged according to actual conditions to avoid empty seats in the car and waste of resources. At the same time, the number of car trips will also affect the traffic conditions of traffic routes. When the number of car trips is large, staff can be arranged to clear the sections of road that may cause congestion to reduce traffic pressure.

[0211] Specific, combined Figure 5 ,After distinguishing highway and high-speed rail travel based on the ,travel path extraction results, this method builds a fuzzy recognition model, ,first selects individuals with the same travel path as the bus line ,travel, and then discriminates between car and bus travel based on ,their average travel speed and the endpoints of the ,metropolitan circle trip.

[0212] Travel speed is an important basis for distinguishing different travel modes (cars and buses). According to the distance between the projection points of mobile communication base stations on the road and the time when the communication event occurs, the moving speed between two consecutive base stations is calculated, such as Figure 6 As shown. Using mobile phone signal base stations to represent the actual location of mobile phone residents has errors. The closer the distance between the front and rear base stations, the shorter the communication event time, and the greater the calculation error. Therefore, by increasing the number of connected signal base stations and constructing a vertical foot for speed estimation, the speed estimation error can be greatly reduced. Therefore, the calculation formula for travel speed is:

[0213] V i,i+n =D i,i+n / T i,i+n

[0214] Where C i is the foot point of the projection of base station i; D i,i+n Indicates C i and C i+n The distance between the projection feet of i,i+n Indicates the corresponding time difference.

[0215] Specifically, in another specific embodiment, the mode of travel can also be identified based on the card swiping charging data. When traveling by subway, bus, highway, road, rail, water or air, the corresponding metropolitan area inter-city travel mode can be directly queried based on the data source. It should be noted that there may be multiple ways to transfer for inter-city travel in the metropolitan area, so it is necessary to identify the corresponding mode of inter-city travel (the mode with a large time and space interval). On the other hand, when the card swiping data is missing due to a system failure, the timetable of all travel modes in the time period, GPS data, etc. can be combined to assist in determining the travel mode.

[0216] Identifying travel modes based on card swiping and charging data is a supplementary method for identifying travel modes in this solution. When the method of determining travel modes based on the resident's mobile phone signaling data cannot be implemented, identifying travel modes based on card swiping and charging data can be used.

[0217] Exemplarily, determining the travel purpose based on the trajectory points, the travel starting point, and the travel end point includes:

[0218] Based on the trajectory points and combined with the POI data of the activity location, the resident’s place of residence and work is determined according to preset rules.

[0219] The starting point of the trip, the end point of the trip, the resident’s place of residence and the resident’s place of work are used to obtain the resident’s travel purpose.

[0220] Specifically, the starting point of the trip, the destination of the trip, the resident's place of residence and the resident's place of work, and the purpose of the resident's trip, including:

[0221] When the starting point of a trip is the resident’s place of residence and the end point of a trip is the resident’s place of work, the purpose of the trip is work.

[0222] When the starting point of a trip is the resident’s workplace and the end point is the resident’s residence, the purpose of the trip is to go home.

[0223] In addition, when the destination of the trip is not the resident’s workplace and the stay duration is greater than 4 hours, it is considered a non-work trip.

[0224] If you want to more accurately determine the purpose of non-work travel, you can extract the POI type of the trip destination.

[0225] (1) Search for all POI types within 200m of the trip destination, perform weighted probability analysis based on the number of POIs and their type weights, and extract the top three major POI types and their distribution ratios. Schools, hospitals, and government agencies have higher weights, while the other types of POIs have lower weights.

[0226] (2) The model constructed using Monte Carlo, support vector machine and other algorithms can directly predict the purpose of the resident's non-work trip based on the time of arrival at the trip destination, the time of departure from the trip destination, the type of POI near the trip destination and the distribution ratio.

[0227] For example, the preset rules are:

[0228] When the number of first target days in a month exceeds the preset number, and the resident on the first target day stays the longest at the first location from 22:00 on the day before the first target day to 7:00 on the first target day, and the stay time is longer than the preset time, the first location will be regarded as the residence of the resident.

[0229] When the number of second target days in a month exceeds a preset number, and a resident on the second target day stays at the second location the longest from 9:00 on the second target day to 18:00 on the second target day and the stay time is longer than the preset time, the second location will be used as the resident's workplace.

[0230] Step 103: Summarize the travel characteristics of each resident in the target metropolitan area to obtain the travel characteristics of the target metropolitan area.

[0231] Exemplarily, the method further includes:

[0232] Based on the travel characteristics of the target metropolitan area, formulate transportation facility planning and transportation resource allocation plans.

[0233] Based on the transportation facilities planning and transportation resource allocation plan, the transportation system of the target urban circle will be optimized and adjusted.

[0234] The above-mentioned method for identifying the travel characteristics of urban circle residents calculates the travel characteristics of each resident through the mobile phone signaling data of each resident in the target urban circle, and summarizes the travel characteristics of each resident to obtain the travel characteristics of the target urban circle, providing a basis for the target urban circle to reasonably and efficiently adjust traffic resources.

[0235] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0236] Corresponding to the method for identifying travel characteristics of metropolitan area residents described in the above embodiment, Figure 7 A structural block diagram of a device for identifying travel characteristics of urban residents provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0237] See also Figure 7 The device for identifying travel characteristics of urban residents in the embodiment of the present application may include: a data acquisition module 201, a data processing module 202 and a result output module 203.

[0238] Data acquisition module 201, used to obtain mobile phone signaling data of each resident in the target metropolitan area;

[0239] Data processing module 202 is configured to plot each resident's trajectory points based on the resident's mobile phone signaling data, cluster the trajectory points to obtain travel starting points, travel stop points, and travel destinations; determine the metropolitan area travel results based on the travel starting points, travel stop points, and travel destinations; determine the metropolitan area travel time based on the trajectory points and the metropolitan area travel results; determine the travel path and travel mode based on the resident's mobile phone signaling data; determine the travel purpose based on the trajectory points, travel starting points, and travel destinations; and summarize the travel starting points, travel destinations, metropolitan area travel results, travel paths, travel modes, and travel purposes to obtain the resident's travel characteristics.

[0240] The result output module 203 is used to summarize the travel characteristics of each resident in the target metropolitan area to obtain the travel characteristics of the target metropolitan area.

[0241] Exemplarily, the data processing module 202 is further configured to:

[0242] The trajectory points of the residents are clustered using a spatiotemporal clustering algorithm, and the clusters obtained are used as the residents' stay areas.

[0243] Obtain the number of trajectory points and the timestamp of each trajectory point in each resident's stay area, and sort each resident's stay area according to the number of trajectory points. The two resident stay areas ranked first and second in the number of trajectory points are used as the travel starting area and travel ending area; among them, the area with the earlier timestamp of the trajectory points in the area is the travel starting area.

[0244] Calculate the center points of all trajectory points in the travel starting area, obtain the first center point, and use the first center point as the travel starting point.

[0245] Calculate the center point of all trajectory points in the travel destination area to obtain a second center point, and use the second center point as the travel destination.

[0246] Calculate the time difference between the first and last trajectory points in each resident's stay area, sorted by time, after excluding the travel start and end areas.

[0247] For each time difference, if the time difference is greater than or equal to the time threshold, the resident stay area corresponding to the time difference is used as the travel stop point area; the center point of all trajectory points in the travel stop point area is calculated to obtain the third center, and the third center point is used as the travel stop point.

[0248] Exemplarily, the data processing module 202 is further configured to:

[0249] The spatial locations of the travel starting point, travel stop point and travel destination are obtained, and spatially matched with the traffic district to obtain the traffic district corresponding to the travel starting point, the traffic district corresponding to the travel stop point and the traffic district corresponding to the travel destination.

[0250] The traffic areas corresponding to the travel starting point, the traffic areas corresponding to the travel stop points, and the traffic areas corresponding to the travel end points are connected in time sequence to obtain multiple travel segments.

[0251] For each travel segment, the traffic zones at both ends of the segment are used to determine whether the segment crosses the city boundary. If the segment crosses the city boundary, the points at both ends of the segment are used as the two endpoints of the metropolitan area travel OD; the metropolitan area travel OD represents travel traffic that crosses the city boundary.

[0252] If there is at least one travel segment whose two endpoints are the two endpoints of the metropolitan area travel OD, the metropolitan area travel result is that there is cross-city travel behavior.

[0253] If the two endpoints of a non-existent travel segment are the two endpoints of the metropolitan area travel OD, the result of the metropolitan area travel is that there is no cross-city travel behavior.

[0254] Exemplarily, the data processing module 202 is further configured to:

[0255] When the metropolitan area travel result indicates that there is cross-city travel behavior, the two endpoints of the metropolitan area travel OD are obtained based on the metropolitan area travel result.

[0256] Get the trajectory points at the two endpoints of the metropolitan area travel OD.

[0257] Based on the trajectory points in the two endpoints of the metropolitan area travel OD, a first endpoint and a second endpoint are obtained; wherein the first endpoint is the endpoint with the earlier timing in the two endpoints of the metropolitan area travel OD.

[0258] The trajectory points in the first endpoint are sorted to obtain the trajectory point with the largest timing in the first endpoint.

[0259] The trajectory points in the second endpoint are sorted to obtain the trajectory point with the smallest timing in the second endpoint.

[0260] The difference between the timestamp of the trajectory point with the smallest time sequence in the second endpoint and the timestamp of the trajectory point with the largest time sequence in the first endpoint is calculated to obtain the urban circle travel time of the resident.

[0261] When the metropolitan area travel result shows that there is no cross-city travel behavior, the metropolitan area travel time is zero.

[0262] Exemplarily, the data processing module 202 is further configured to:

[0263] Based on the resident's mobile phone signaling data, the base stations to which the resident's mobile phone is sequentially connected are determined, and based on the sequentially connected base stations, a first path buffer sequence is determined; wherein the path buffer includes multiple base stations; the first path buffer is a collection of path buffers where the sequentially connected base stations are located.

[0264] A second path buffer sequence and a third path buffer sequence are obtained; wherein the second path buffer sequence is a set of path buffers passing along the railway, and the third path buffer sequence is a set of path buffers passing along the highway.

[0265] The similarity between the first path buffer sequence and the second path buffer sequence is calculated to obtain a first similarity.

[0266] The similarity between the first path buffer sequence and the third path buffer sequence is calculated to obtain a second similarity.

[0267] The first similarity and the second similarity are compared, and the path corresponding to the larger similarity value is used as the travel path.

[0268] Exemplarily, the data processing module 202 is further configured to:

[0269] Based on the resident's mobile phone signaling data, the time difference between the resident's connection to two adjacent base stations on the travel path is obtained.

[0270] Get the distance between two adjacent base stations.

[0271] The quotient of the distance between two adjacent base stations and the time difference between the resident connecting to the two adjacent base stations on the travel path is calculated to obtain the resident's travel speed.

[0272] Filter out the bus routes that are the same as the resident's travel route.

[0273] Obtain a first statistical value; wherein the first statistical value represents the sum of the number of travel starting points, travel stop points, and travel end points within the bus passenger station in the route.

[0274] A first membership value is determined based on the travel speed and a preset automobile K-order parabolic distribution membership function.

[0275] The second membership value is determined based on the travel speed and a preset K-order parabolic distribution membership function of the bus.

[0276] The product of the first statistical value and the first preset value and the sum of the second membership value are calculated to obtain a third membership value.

[0277] The first membership value and the third membership value are compared, and the means of transportation corresponding to the larger membership value is selected as the travel mode.

[0278] The preset car K-order parabolic distribution membership function is:

[0279]

[0280] Wherein, a1, b1, c1 and d1 all represent preset parameters, x represents the travel speed, k represents the parabola power, and A1(x) represents the first membership value.

[0281] The preset K-order parabolic distribution membership function of the bus is:

[0282]

[0283] Wherein, a2, b2, c2 and d2 represent preset parameters, and A2(x) represents the second membership value.

[0284] Exemplarily, the data processing module 202 is further configured to:

[0285] Based on the trajectory points and combined with the POI data of the activity location, the resident’s place of residence and work is determined according to preset rules.

[0286] The starting point of the trip, the end point of the trip, the resident’s place of residence and the resident’s place of work are used to obtain the resident’s travel purpose.

[0287] For example, the preset rules are:

[0288] When the number of first target days in a month exceeds the preset number, and the resident on the first target day stays the longest at the first location from 22:00 on the day before the first target day to 7:00 on the first target day, and the stay time is longer than the preset time, the first location will be regarded as the residence of the resident.

[0289] When the number of second target days in a month exceeds a preset number, and a resident on the second target day stays at the second location the longest from 9:00 on the second target day to 18:00 on the second target day and the stay time is longer than the preset time, the second location will be used as the resident's workplace.

[0290] Exemplarily, the result output module 203 is further configured to:

[0291] Based on the travel characteristics of the target metropolitan area, formulate transportation facility planning and transportation resource allocation plans.

[0292] Based on the transportation facilities planning and transportation resource allocation plan, the transportation system of the target urban circle will be optimized and adjusted.

[0293] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0294] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0295] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it can implement the steps in each embodiment of the above-mentioned method for identifying travel characteristics of urban residents.

[0296] An embodiment of the present application provides a computer program product. When the computer program product is run on a mobile terminal, the mobile terminal can implement the steps in each embodiment of the above-mentioned method for identifying travel characteristics of urban residents.

[0297] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0298] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0299] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0300] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0301] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0302] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for identifying travel characteristics of urban residents, characterized in that: include: Obtain mobile phone signaling data for every resident in the target metropolitan area; For each resident, based on the resident's mobile phone signaling data, the resident's trajectory points are drawn, and the trajectory points are clustered to obtain the travel starting point, travel stop point and travel end point; Determine a metropolitan area travel result based on the travel starting point, the travel stop point, and the travel end point; determine a metropolitan area travel time based on the trajectory points and the metropolitan area travel result; Determine the travel path and travel mode based on the resident's mobile phone signaling data; determine the travel purpose based on the trajectory points, the travel starting point, and the travel destination; Summarizing the travel starting point, the travel destination, the metropolitan area travel results, the travel route, the travel mode and the travel purpose to obtain the travel characteristics of the resident; Summarizing the travel characteristics of each resident in the target metropolitan area to obtain the travel characteristics of the target metropolitan area; The clustering process of the trajectory points to obtain a travel starting point, a travel stop point, and a travel end point includes: The trajectory points of the residents are clustered using a spatiotemporal clustering algorithm, and the clusters obtained are used as the residents' stay areas. Obtain the number of trajectory points and the timestamp of each trajectory point in each resident's stay area, and sort each resident's stay area by the number of trajectory points. The two resident stay areas ranked first and second in the number of trajectory points are used as the travel start area and travel end area; the area with the earlier timestamp of the trajectory points in the area is the travel start area; Calculating the center point of all trajectory points in the travel starting area to obtain a first center point, and using the first center point as the travel starting point; Calculating the center point of all trajectory points in the travel destination area to obtain a second center point, and using the second center point as the travel destination; Calculate the time difference between the first trajectory point and the last trajectory point in each resident stay area sorted by time, excluding the travel start area and the travel end area; For each time difference, if the time difference is greater than or equal to the time threshold, the resident stay area corresponding to the time difference is used as the travel stop point area; the center point of all trajectory points in the travel stop point area is calculated to obtain a third center, and the third center point is used as the travel stop point; The determining of the metropolitan area travel result based on the travel starting point, the travel stop point, and the travel destination includes: Obtaining the spatial locations of the travel starting point, the travel stop point, and the travel destination, and performing spatial matching with the traffic cells to obtain the traffic cell corresponding to the travel starting point, the traffic cell corresponding to the travel stop point, and the traffic cell corresponding to the travel destination; Connecting the traffic area corresponding to the trip starting point, the traffic area corresponding to the trip stop point, and the traffic area corresponding to the trip end point in time sequence to obtain multiple travel segments; For each trip segment, determine whether it crosses a city boundary based on the traffic zones at both ends of the segment. If the segment crosses a city boundary, the points at both ends of the segment are used as the two endpoints of the metropolitan area travel OD; the metropolitan area travel OD represents travel that crosses a city boundary. If there is at least one travel segment whose two endpoints are the two endpoints of the metropolitan area travel OD, then the metropolitan area travel result is that there is cross-city travel behavior; If the two endpoints of no travel segment are the two endpoints of the metropolitan area travel OD, then the metropolitan area travel result is that there is no cross-city travel behavior; The determining of the metropolitan area travel time based on the trajectory point and the metropolitan area travel result includes: When the metropolitan area travel result indicates that there is cross-city travel behavior, two endpoints of the metropolitan area travel OD are obtained based on the metropolitan area travel result; Get the trajectory points at the two endpoints of the metropolitan area travel OD; Based on the trajectory points at the two endpoints of the metropolitan area travel OD, a first endpoint and a second endpoint are obtained; wherein the first endpoint is the endpoint with the earlier time sequence among the two endpoints of the metropolitan area travel OD; Sort the trajectory points in the first endpoint to obtain the trajectory point with the largest time sequence in the first endpoint; Sort the trajectory points in the second endpoint to obtain the trajectory point with the smallest time sequence in the second endpoint; Calculate the difference between the timestamp of the trajectory point with the smallest time sequence in the second endpoint and the timestamp of the trajectory point with the largest time sequence in the first endpoint to obtain the metropolitan area travel time of the resident; When the metropolitan area travel result is that there is no cross-city travel behavior, the metropolitan area travel time is zero.

2. The method for identifying travel characteristics of metropolitan area residents according to claim 1, wherein: The determining of a travel route based on the mobile phone signaling data of the resident includes: Determining, based on the resident's mobile phone signaling data, the base stations to which the resident's mobile phone is sequentially connected, and determining a first path buffer sequence based on the sequentially connected base stations; wherein the path buffer includes multiple base stations; and the first path buffer is a set of path buffers where the sequentially connected base stations are located; Obtain a second path buffer sequence and a third path buffer sequence; wherein the second path buffer sequence is a set of path buffers passing along a railway, and the third path buffer sequence is a set of path buffers passing along a highway; Calculating a similarity between the first path buffer sequence and the second path buffer sequence to obtain a first similarity; Calculating a similarity between the first path buffer sequence and the third path buffer sequence to obtain a second similarity; The first similarity and the second similarity are compared, and the path corresponding to the larger similarity value is used as the travel path.

3. The method for identifying travel characteristics of metropolitan area residents according to claim 2, wherein: The determining of the travel mode based on the mobile phone signaling data of the resident includes: Based on the mobile phone signaling data of the resident, obtaining the time difference between the resident and two adjacent base stations on the travel path; Obtaining the distance between the two adjacent base stations; Calculating the quotient of the distance between the two adjacent base stations and the time difference between the resident connecting to the two adjacent base stations on the travel path to obtain the travel speed of the resident; Filter out the bus routes that are the same as the resident's travel route; Obtaining a first statistical value; wherein the first statistical value represents the sum of the number of travel starting points, travel stop points, and travel end points within the bus passenger station on the route; Determining a first membership value based on the travel speed and a preset automobile K-order parabolic distribution membership function; Determining a second membership value based on the travel speed and a preset K-order parabolic distribution membership function of a bus; Calculating the sum of the product of the first statistical value and the first preset value and the second membership value to obtain a third membership value; the first preset value is 0.1; comparing the first membership value and the third membership value, and selecting a means of transportation corresponding to a larger membership value as the travel mode; The preset automobile K-order parabola distribution membership function is: in, 、 、 and All represent preset parameters. represents the travel speed, represents the parabola power, represents the first membership value; The preset K-order parabolic distribution membership function of the bus is: in, 、 、 and Indicates the preset parameters, represents the second membership value.

4. The method for identifying travel characteristics of metropolitan area residents according to claim 1, wherein: The determining of the travel purpose based on the trajectory point, the travel starting point, and the travel end point includes: Based on the trajectory points and the POI data of the activity location, the residence and workplace of the resident are determined according to preset rules; The trip starting point, the trip end point, the resident's residence and the resident's workplace are used to obtain the resident's travel purpose.

5. The method for identifying travel characteristics of metropolitan area residents according to claim 4, characterized in that: The preset rules are: When the number of first target days in a month exceeds a preset number, and a resident on one of the first target days spends the longest time at a first location between 22:00 on the day before the first target day and 7:00 on the first target day, and the length of stay is greater than the preset length, the first location is deemed to be the resident's place of residence; When the number of second target days in a month exceeds the preset number, and a resident on the second target day stays at the second location the longest from 9:00 on the second target day to 18:00 on the second target day and the stay time is longer than the preset time, the second location will be used as the resident's workplace.

6. The method for identifying travel characteristics of metropolitan area residents according to claim 1, wherein: The method further comprises: Formulate transportation infrastructure planning and transportation resource allocation plans based on the travel characteristics of the target metropolitan area; Based on the transportation facility planning and transportation resource allocation plan, the transportation system of the target metropolitan area is optimized and adjusted.

7. A device for identifying travel characteristics of urban residents, characterized in that: include: The data acquisition module is used to obtain the mobile phone signaling data of each resident in the target metropolitan area; A data processing module is used to draw the trajectory points of each resident based on the resident's mobile phone signaling data, cluster the trajectory points, and obtain the travel starting point, travel stop point, and travel end point; Determine a metropolitan area travel result based on the travel starting point, the travel stop point, and the travel end point; determine a metropolitan area travel time based on the trajectory points and the metropolitan area travel result; Determine the travel path and travel mode based on the resident's mobile phone signaling data; determine the travel purpose based on the trajectory points, the travel starting point, and the travel destination; Summarizing the travel starting point, the travel destination, the metropolitan area travel results, the travel route, the travel mode and the travel purpose to obtain the travel characteristics of the resident; A result output module is used to summarize the travel characteristics of each resident in the target metropolitan area to obtain the travel characteristics of the target metropolitan area; The data processing module is further used to: The trajectory points of the residents are clustered using a spatiotemporal clustering algorithm, and the clusters obtained are used as the residents' stay areas. Obtain the number of trajectory points and the timestamp of each trajectory point in each resident's stay area, and sort each resident's stay area by the number of trajectory points. The two resident stay areas ranked first and second in the number of trajectory points are used as the travel start area and travel end area; the area with the earlier timestamp of the trajectory points in the area is the travel start area; Calculating the center point of all trajectory points in the travel starting area to obtain a first center point, and using the first center point as the travel starting point; Calculating the center point of all trajectory points in the travel destination area to obtain a second center point, and using the second center point as the travel destination; Calculate the time difference between the first trajectory point and the last trajectory point in each resident stay area sorted by time, excluding the travel start area and the travel end area; For each time difference, if the time difference is greater than or equal to the time threshold, the resident stay area corresponding to the time difference is used as the travel stop point area; the center point of all trajectory points in the travel stop point area is calculated to obtain a third center, and the third center point is used as the travel stop point; The data processing module is further used to: Obtaining the spatial locations of the travel starting point, the travel stop point, and the travel destination, and performing spatial matching with the traffic cells to obtain the traffic cell corresponding to the travel starting point, the traffic cell corresponding to the travel stop point, and the traffic cell corresponding to the travel destination; Connecting the traffic area corresponding to the trip starting point, the traffic area corresponding to the trip stop point, and the traffic area corresponding to the trip end point in time sequence to obtain multiple travel segments; For each trip segment, determine whether it crosses a city boundary based on the traffic zones at both ends of the segment. If the segment crosses a city boundary, the points at both ends of the segment are used as the two endpoints of the metropolitan area travel OD; the metropolitan area travel OD represents travel that crosses a city boundary. If there is at least one travel segment whose two endpoints are the two endpoints of the metropolitan area travel OD, then the metropolitan area travel result is that there is cross-city travel behavior; If the two endpoints of no travel segment are the two endpoints of the metropolitan area travel OD, then the metropolitan area travel result is that there is no cross-city travel behavior; The data processing module is further used to: When the metropolitan area travel result indicates that there is cross-city travel behavior, two endpoints of the metropolitan area travel OD are obtained based on the metropolitan area travel result; Get the trajectory points at the two endpoints of the metropolitan area travel OD; Based on the trajectory points at the two endpoints of the metropolitan area travel OD, a first endpoint and a second endpoint are obtained; wherein the first endpoint is the endpoint with the earlier time sequence among the two endpoints of the metropolitan area travel OD; Sort the trajectory points in the first endpoint to obtain the trajectory point with the largest time sequence in the first endpoint; Sort the trajectory points in the second endpoint to obtain the trajectory point with the smallest time sequence in the second endpoint; Calculate the difference between the timestamp of the trajectory point with the smallest time sequence in the second endpoint and the timestamp of the trajectory point with the largest time sequence in the first endpoint to obtain the metropolitan area travel time of the resident; When the metropolitan area travel result is that there is no cross-city travel behavior, the metropolitan area travel time is zero.

Images