Railway passenger identification method and device, electronic equipment and computer readable storage medium

Abstract

The invention provides a railway passenger identification method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of big data. According to the method, the signaling set of the target area within the specified time and the signaling interaction range of the railway station are utilized to preliminarily lock the to-be-determined users which stop in the railway station and generate signaling interaction, and then non-railway passengers which stop in only one railway station are excluded based on the residence information of the to-be-determined users in combination with the travel behavior characteristics of the railway passengers, so that the non-railway passengers are not stopped in the same railway station. And finally, various misjudgment conditions are comprehensively considered to exclude the journey of non-railway travelers, so that each section of railway journey of the railway travelers within the specified time is accurately identified.

Description

Technical Field

[0001] The present invention relates to the technical field of big data, and in particular, to a method, device, electronic device and computer-readable storage medium for identifying railway passengers. Background Art

[0002] With the rapid development of China's railway, the railway has become an important part of the national economy. Moreover, in railway planning, layout and service optimization, railway passenger flow statistics is very important.

[0003] And railway passenger flow statistics depends on accurate railway passenger identification. Therefore, how to accurately identify railway passengers is an urgent problem to be solved. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device, electronic device and computer-readable storage medium for identifying railway passengers to improve the problems existing in the prior art.

[0005] The embodiments of the present invention can be implemented as follows: In a first aspect, an embodiment of the present invention provides a method for identifying railway passengers, including: Obtaining a signaling set within a specified time in a target area; Obtaining a signaling interaction range corresponding to each railway station in the target area; Based on the signaling set and the signaling interaction ranges corresponding to each railway station, determining the residence information of each pending user; the pending user is a user who has performed signaling interaction in any of the signaling interaction ranges; Based on the residence information of each pending user, identifying each candidate user who has performed signaling interaction in at least two signaling interaction ranges from all the pending users, and determining the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey; Based on the inter-station trajectory sequences and travel information of each candidate user on at least one candidate journey, filtering misjudged non-railway journeys from all candidate journeys of all candidate users to obtain each railway journey of each railway passenger.

[0006] In a second aspect, an embodiment of the present invention further provides a device for identifying railway passengers, including: A signaling acquisition module, configured to obtain a signaling set within a specified time in a target area; the signaling set includes multiple signaling data of several users; A range determination module, configured to obtain a signaling interaction range corresponding to each railway station in the target area; A residence determination module, configured to determine the residence information of each pending user based on the signaling set and the signaling interaction ranges corresponding to each railway station; the pending user is a user who has performed signaling interaction within any of the signaling interaction ranges; A first identification module, configured to identify, based on the residence information of each pending user, each candidate user who has performed signaling interaction within at least two signaling interaction ranges from all the pending users, and determine the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey; A second identification module, configured to filter out misjudged non-railway journeys from all the candidate journeys of all the candidate users based on the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey, so as to obtain each railway journey of each railway passenger.

[0007] In a third aspect, an embodiment of the present invention further provides an electronic device, including: a memory and a processor, where the memory stores a software program, and when the electronic device runs, the processor executes the software program to implement the railway passenger identification method as described in the first aspect above.

[0008] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the railway passenger identification method as described in the first aspect above is implemented.

[0009] Compared with the prior art, the embodiment of the present invention provides a railway passenger identification method, device, electronic device and computer-readable storage medium. First, a signaling set within a target area within a specified time is obtained, which includes multiple signaling data of several users; then, the signaling interaction range corresponding to each railway station within the target area is obtained; then, based on the signaling set and the signaling interaction ranges corresponding to each railway station, the residence information of each pending user is determined, and the pending user is a user who has performed signaling interaction within any signaling interaction range, so that all the pending users who have stayed within the signaling interaction range of the railway station can be screened out. Then, based on the residence information of each pending user, each candidate user who has performed signaling interaction within at least two signaling interaction ranges is identified from all the pending users, so that non-railway passengers who have only stayed at one railway station, such as pick-up and drop-off personnel or railway staff, can be excluded from all the pending users. Finally, based on the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey, each railway journey of each railway passenger is identified from all the candidate journeys of all the candidate users, and finally each railway journey of each railway passenger within the specified time is accurately identified. Description of the Drawings

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0011] Figure 1 One of the schematic flowcharts of a railway passenger identification method provided by an embodiment of the present invention.

[0012] Figure 2 A schematic diagram of the process of constructing a Thiessen polygon.

[0013] Figure 3 An example diagram of integrating data of multiple stay points provided by an embodiment of the present invention.

[0014] Figure 4 Another schematic flowchart of a railway passenger identification method provided by an embodiment of the present invention.

[0015] Figure 5 A schematic diagram of the segmentation of a trajectory sequence provided by an embodiment of the present invention.

[0016] Figure 6 A schematic structural diagram of a railway passenger identification device provided by an embodiment of the present invention.

[0017] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and illustrated in the drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0020] Railway passenger flow is an important basis for optimizing transportation network layout, rationally planning and layout of stations, and intermodal transport analysis. It usually includes indicators such as station passenger volume, passenger flow direction and proportion, peak hour passenger volume and peak hour coefficient, maximum number of people gathered at the station, source of departure passenger flow, and destination of arrival passenger flow.

[0021] Railway travel passenger flow depends on accurate railway passenger data. Although the existing railway real-name ticketing data can accurately grasp the transportation volume between station pairs and a small number of passenger attribute records, this data is difficult to obtain and almost impossible to obtain. In addition, it is difficult to obtain richer data such as when departing passengers go to the station, where they go to the station from, how they go to the station, when arriving passengers leave the station, where they go after leaving the station, how they leave the station, as well as the passengers' complete travel trajectory, permanent residence, native place, gender, age, etc.

[0022] Therefore, existing technologies can only achieve railway passenger identification through other means, such as: The first method is to obtain travel information of travelers through the distribution and collection of traditional questionnaires. However, the research space scale applicable to the questionnaire survey method is limited, and it is only applicable to small-scale research. Due to the limitations of manpower and time costs, it is difficult to use the questionnaire survey method for large-scale research. In addition, the sample quality and reliability of the questionnaire survey results largely depend on the personal wishes of the respondents, and it is difficult for the questionnaire distributor to effectively control these factors. Different respondents may have different understandings of the questions, resulting in inconsistent answers. Some respondents may even answer according to social expectations instead of expressing their own ideas, which further affects the authenticity and accuracy of the questionnaire data.

[0023] The second method is to build a railway station basic database and a railway line base station database based on mobile phone signaling data, and extract the spatiotemporal data of passengers' single travel trajectories according to the passenger single travel signaling data, entry, exit, transfer station identification method and travel route matching method. This method makes up for the shortcomings of traditional questionnaire survey methods in terms of low data dimensional scalability, high acquisition cost, long survey period, and small survey samples to a certain extent, but it still has certain shortcomings, mainly including: (1) The identification results of this method are mixed with non-real railway travel samples such as station staff (including staff directly related to station travel and personnel selling goods in the station), pick-up and drop-off station personnel, and passing through the station, which will cause great interference to the results; (2) Passenger identification is not closely combined with the behavioral characteristics of railway passenger travel, and there may be some uncertainty in the analysis results.

[0024] Based on the discovery of the above technical problems, the inventors have proposed the following technical solutions to solve or improve the above problems through creative work. It should be noted that the defects in the solutions in the above prior art are the results obtained by the inventors after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the embodiments of the present application for the above problems below should all be the contributions made by the inventors to the present application in the process of invention and creation, and should not be understood as technical contents known to those skilled in the art.

[0025] In view of this, an embodiment of the present invention provides a railway passenger identification method, which can use the signaling set of the target area and the signaling interaction range of each railway station in the target area, fully combine the travel behavior characteristics of railway passengers, and accurately identify each railway journey of each railway passenger in the target area within a specified time. The following is a detailed description through embodiments and the accompanying drawings.

[0026] Please refer to Figure 1 , Figure 1 A flow chart of a railway passenger identification method provided in an embodiment of the present invention. The execution subject of the method may be, but is not limited to, an electronic device with computing capabilities such as a smart phone, a personal notebook, a personal computer, a server, etc. The method includes the following steps S101 to S105: S101. Obtain a signaling set in a target area within a specified time.

[0027] In this embodiment, the target area may be a geographical area of a province, a geographical area of multiple provinces, or a national area, and the designated time may be an exact day, several days, a week, a month, etc.

[0028] Among them, the signaling set includes multiple signaling data of several users. One signaling data includes but is not limited to user code (representing the user terminal used by the user), timestamp, base station code (representing a public mobile communication base station, referred to as base station) and base station location, etc., so the signaling data can reflect the object (i.e., base station) and interaction time of the user's command interaction using the terminal device.

[0029] It should be understood that during the collection, transmission and processing of signaling data, due to some force majeure factors, redundant data, noise data, drift data, ping-pong data and other dirty data will be generated. Therefore, after initially receiving all the signaling data, it is also necessary to eliminate dirty data such as time and space conflicts and invalid data to form the required signaling set.

[0030] S102: Obtain the signaling interaction range corresponding to each railway station in the target area.

[0031] In this embodiment, the term "railway station" is a general term, which can be: an ordinary railway station serving regular-speed trains (such as trains with the prefix K, T, Z), or a high-speed railway station dedicated to high-speed railways (trains with the prefix G, D).

[0032] It should be noted that the signaling interaction range is not directly equivalent to the geographical boundary of the railway station, but is a regional range determined in combination with the base station distribution of the railway station and the geographical boundary of the railway station.

[0033] S103. Based on the signaling set and the signaling interaction range corresponding to each railway station, determine the residence information of each pending user.

[0034] In this embodiment, a pending user is a user who has performed signaling interaction within any signaling interaction range, that is, a pending user is only a suspected railway passenger. Among all pending users, there are also railway staff, pick-up and drop-off personnel, passing-by personnel, and personnel traveling by other means. Therefore, further identification is required next.

[0035] S104. Based on the residence information of each pending user, identify each candidate user who has performed signaling interaction within at least two signaling interaction ranges from all pending users, and determine the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey.

[0036] In this embodiment, the residence information of a pending user reflects the action trajectory of the user within a specified time.

[0037] It should be understood that within the specified time, a user must have performed signaling interaction within the signaling interaction ranges of at least two railway stations to be likely to be a railway passenger. Therefore, it is necessary to identify each candidate user who has performed signaling interaction within at least two signaling interaction ranges from all pending users, which can exclude pick-up and drop-off personnel and passing-by personnel passing by the railway station.

[0038] S105. Based on the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey, filter out misjudged non-railway journeys from all candidate journeys of all candidate users to obtain each railway journey of each railway passenger.

[0039] Among them, candidate users are not necessarily all railway passengers, and a candidate journey represents a travel journey between two railway stations. Therefore, each candidate journey of a candidate user is not necessarily a railway journey, and it may just happen to perform signaling interaction within the signaling interaction ranges of two railway stations within the specified time, but the actual travel mode is non-railway travel, such as road travel or air travel.

[0040] Therefore, it is also necessary to identify each railway journey of a real railway passenger based on the inter-station track sequence and travel information of each candidate user on each candidate journey, so as to facilitate the later statistics of railway passenger flow indicators such as the number of railway passengers and the number of railway passenger trips within a specified time based on all railway journeys of all railway passengers within the specified time.

[0041] The railway passenger identification method provided by the embodiments of the present invention first obtains a signaling set within a target area within a specified time, which includes multiple signaling data of several users; then obtains the signaling interaction range corresponding to each railway station within the target area; then determines the residence information of each pending user based on the signaling set and the signaling interaction range corresponding to each railway station, where the pending user is a user who conducts signaling interaction within any signaling interaction range, so that all pending users who have stayed within the signaling interaction range of the railway station can be screened out. Then, based on the residence information of each pending user, each candidate user who has conducted signaling interaction within at least two signaling interaction ranges is identified from all the pending users, so that non-railway passengers who have only stayed at one railway station, such as pick-up and drop-off personnel or railway staff, can be excluded from all the pending users. Finally, based on the inter-station track sequence and travel information of each candidate user on at least one candidate journey, each railway journey of each railway passenger is identified from all the candidate journeys of all the candidate users, and finally each railway journey of each railway passenger within the specified time is accurately identified.

[0042] Taking the target area as the national area as an example, the implementation principle of the railway passenger identification method provided by the embodiments of the present invention is introduced in detail below.

[0043] There are more than 3,600 railway stations across the country. The scale of each railway station and the economic and social development conditions of the regions where they are located are not the same, and the construction of communication infrastructure also varies greatly. Generally, micro base stations are installed inside some large-scale new railway stations built in recent years, but some early-built small-scale railway stations generally rely on macro base stations in the periphery to provide communication services.

[0044] Therefore, for the above S102, the signaling interaction range of a railway station is determined by moderately expanding the geographical boundary of the railway station, so as to be compatible with the base station installation situations of the above two types of railway stations and avoid missing railway passengers at early-built small-scale railway stations in the future. Specifically, the sub-steps of step S102 may include S1021 to S1024.

[0045] S1021. Obtain the geographical boundary information of each railway station within the target area.

[0046] In this embodiment, the geographical boundary information of the railway station may include the positions (such as longitude and latitude coordinates) of several boundary points on the boundary line of the railway station.

[0047] Among them, step S1021 can be obtained from an external system in real time or read from the site information stored in the system. Since there will be changes such as new additions, cancellations, renovations, and expansions at railway stations, it is necessary to regularly update the geographical boundary information of each railway station in the site information. When updating, key attention should be paid to newly added / removed railway stations, railway stations with changed geographical boundaries, etc.

[0048] S1022. Obtain the longitude and latitude coordinates of each base station within the target area.

[0049] S1023. Based on the longitude and latitude coordinates of each base station, determine the signal coverage range of each base station.

[0050] Optionally, the Voronoi Diagram tool provided by ArcGIS can be called to generate the Thiessen polygon of each base station based on the longitude and latitude coordinates of each base station, so that the Thiessen polygon area of each base station can be used as the signal coverage range of the base station.

[0051] For example, taking 12 base stations as an example, please combine Figure 2 , it is necessary to first connect every two adjacent base stations to form a triangular network, and then construct the Thiessen polygon on the basis of the triangular network. Finally, the signal coverage range of each base station can be obtained. Among them, the signal coverage range of base station A is the area surrounded by the red line. It should be noted that Figure 2 The illustration is only for example, and the shape, etc. of the Thiessen polygon determined for each base station in the target area are not limited here.

[0052] S1024. Perform spatial association analysis on the signal coverage ranges of all base stations and the geographical boundary information of each railway station to determine the signaling interaction range of each railway station.

[0053] In this embodiment, for any railway station, the geographical boundary information of the railway station is superimposed on the signal coverage ranges of all base stations to filter out the signal coverage ranges of each base station that intersect with the geographical boundary of the railway station, and use this as the signaling interaction range of the railway station.

[0054] In an optional implementation manner, in step S103 above, the residence information of a to-be-determined user includes multiple residence point data, which can reflect the trajectory of the to-be-determined user within a specified time. Specifically, the sub-steps of step S103 may include S1031 to S1034.

[0055] S1031. For any signaling data in the signaling set, if the base station location of the signaling data is within any signaling interaction range, it is determined that the user corresponding to the signaling data is a to-be-identified to-be-determined user.

[0056] In this embodiment, if all the signaling data in the signaling set is classified according to the user code, a signaling subset corresponding to each user can be obtained. For any user, if the base station location in any signaling data in the signaling subset corresponding to the user is within the signaling interaction range of any railway station in the target area, it can be determined that the user is a pending user suspected of being a railway passenger. For each pending user, the residence information can be determined through the following steps S1032 to S1034.

[0057] S1032. For each pending user, based on all the signaling data of the pending user in the signaling set, at least one residence point data and at least one passing point data of the pending user are determined.

[0058] In this embodiment, the residence point data includes the location and residence period of the residence point, and the residence period can reflect the residence duration; the passing point data includes the location and passing time of the passing point.

[0059] Among them, based on the signaling subset of a pending user, all the residence point data and passing point data of the pending user within the specified time can be analyzed and determined. The specific analysis process is prior art and will not be elaborated here.

[0060] S1033. Stretch the passing time in each passing point data to convert each passing point data into residence point data.

[0061] In this embodiment, converting the passing point data into residence point data actually only converts the passing time into a residence period, regarding the passing point as a residence point.

[0062] Exemplarily, assuming the passing time is t and the preset minimum residence duration is ∆t (∆t can be 0.5s, 1s, 2s, etc.), then there can be the following three calculation methods for the residence period [t1, t2] obtained by converting the passing time t:

[0063] S1034. Among all the residence point data corresponding to the pending user, integrate the residence points whose residence points are within the signaling interaction range corresponding to the same railway station and whose residence periods are continuous into one residence point data with the railway station as the residence point, obtaining multiple residence point data of the pending user.

[0064] In this embodiment, for all the residence point data of a pending user, they can be sorted first in ascending order of the start time of the residence period, and then the residence points whose residence points are within the signaling interaction range corresponding to the same railway station and whose residence periods are continuous are integrated into one residence point data with the railway station as the residence point. The residence period of the integrated residence point data is from the minimum start time to the maximum end time of the original respective periods.

[0065] Exemplarily, assume that a user to be determined includes 11 dwelling point data (i.e., there are 11 dwelling points and their dwelling periods), and after sorting according to the dwelling period, they are dwelling points 1 to 11. Please refer to Figure 3 , assume that dwelling points 3 to 6 are within the signaling interaction range of station A, and dwelling points 7 to 10 are within the signaling interaction range of station B, then the integration situation is as follows: (1) Integrate dwelling points 3 to 6 into one dwelling point A (the position of dwelling point A is the position of station A), and its dwelling period is from the start time of dwelling point 3 to the end time of dwelling point 6; (2) Integrate dwelling points 7 to 10 into one dwelling point B (the position of dwelling point B is the position of station B), and its dwelling period is from the start time of dwelling point 7 to the end time of dwelling point 10.

[0066] From Figure 3 it can be seen that after integration, the number of dwelling points changes from 11 to 5. It should be noted that this example is only for illustration and is not limited here.

[0067] Among the dwelling information of each user to be determined obtained through the above steps S1031 to S1034, at least one of the dwelling points in the dwelling point data is a railway station, which can reflect the travel trajectory.

[0068] For the above step S104, the travel characteristics of railway passengers can be combined to screen out candidate users, and determine the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey.

[0069] And the travel characteristics of railway passengers mainly include the following four points: Characteristic 1: Point-to-point travel, that is, travel from station to station. Users will generate signaling data at the departure station, passing stations, and arrival station, and the waiting time at the departure station is generally longer than the exit time at the arrival station; Characteristic 2: During a continuous railway journey, users will not stay in other areas except stations for a long time; Characteristic 3: Users may have non-consecutive train trips in a day; Characteristic 4: There may be situations of transfer and connection during railway travel.

[0070] Based on the above travel characteristics, each user to be determined can be discriminated. Specifically, on the basis of Figure 1 , please refer to Figure 4 , the sub-steps of the above step S104 may include S1041 to S1045.

[0071] S1041 . For each pending user, sort all the residence point data of the pending user in ascending order according to the start time of the residence period to obtain a trajectory sequence of each pending user within a specified time.

[0072] Among them, the trajectory sequence of each pending user within the specified time can clearly reflect the user's spatial movement path and time distribution within the entire specified time.

[0073] S1042: If any trajectory sequence contains an off-station dwelling point, the trajectory sequence is divided into at least one trajectory sequence based on all the off-station dwelling points.

[0074] In this embodiment, the off-station dwelling point is a dwelling point where the dwelling time corresponding to the dwelling period exceeds the preset dwelling time, and the dwelling point is not a railway station. The preset dwelling time may be 1 hour or 1.5 hours.

[0075] It can be understood that if there is no trajectory point sequence in a trajectory sequence, there is no need to split it. If there is one off-station residence point in a trajectory sequence, it can be split into two new trajectory sequences. If there are two off-station residence points in a trajectory sequence, it can be split into three new trajectory sequences, and so on.

[0076] For example, assume that a trajectory sequence includes 15 dwell points (dwell points 1 to 15), see Figure 5 , where the locations of the four dwelling points 2, 6, 10, and 14 are the locations of the four railway stations A, B, C, and D, respectively, and the dwelling time of dwelling point 8 exceeds the preset dwelling time, which means it belongs to the out-of-station dwelling point. Then the two trajectory sequences after segmentation are Figure 5 The track sequence 1 and track sequence 2 are shown. It should be noted that this example is only an example and is not intended to be limiting.

[0077] S1043. From all trajectory sequences, remove non-railway trajectory sequences that include only one train station or do not include a train station, and remove trajectory sequences of non-railway passengers whose two stay points are the same train station.

[0078] In this embodiment, among all the trajectory sequences obtained through the above steps S1041 and S1042, the following three types of trajectory sequences need to be eliminated: (1) Non-railway track sequences that only include one train station: If this type is not segmented, it may be the itinerary of station pick-up and drop-off personnel, train station staff, or passers-by passing through the train station; if this type is segmented, it may be the itinerary of a railway passenger before or after a railway trip, and the itinerary may just pass through the signaling interaction range of a train station; (2) Non-railway trajectory sequence excluding railway stations: This type is usually segmented and may be the itinerary of a railway passenger before or after railway travel, and the itinerary does not pass through the signaling interaction range of any railway station; (3) Trajectory sequence of non-railway passengers with two stay points at the same railway station: This type is usually the itinerary of the staff of the train following team (conductor, steward, catering staff, cleaning staff, etc.) of a railway train.

[0079] Exemplarily, in combination with Figure 5 , if Figure 5 the stay point 10 is not the location of Station C, then trajectory sequence 2 needs to be excluded; if Station A and Station B of trajectory sequence 1 are actually the same railway station, and Station C and Station D of the trajectory sequence are also the same railway station, then the trajectory sequence belongs to the itinerary of the train following team members of the railway train and needs to be deleted. It should be noted that this example is only for illustration and is not limited here.

[0080] S1044. Take the pending user corresponding to each remaining trajectory sequence as a candidate user, and take each remaining trajectory sequence as a candidate journey to be recognized.

[0081] Therefore, through step S1043, it is possible to exclude railway station staff, pick-up and drop-off personnel, and passers-by passing through railway stations from all pending users, and it is also possible to exclude non-railway trajectory sequences corresponding to the non-railway itinerary of a railway passenger from all pending users. In this way, all pending users corresponding to the remaining trajectory sequences are candidate users who have performed signaling interactions within the signaling interaction range of at least two railway stations and are very likely to be railway passengers.

[0082] S1045. For each candidate journey of each candidate user, based on the first stay point data and the last stay point data of the stay points in the corresponding trajectory sequence that are railway stations, determine the inter-station trajectory sequence and travel information of the candidate user on this candidate journey.

[0083] In this embodiment, the inter-station trajectory sequence of a candidate user on a candidate journey only reflects the travel trajectory between two railway stations.

[0084] Optionally, the travel information may include the departure station, arrival station, travel time, travel distance, and travel speed. Therefore, for each candidate journey of each candidate user, the process of determining the inter-station trajectory sequence and travel information of the candidate user on this candidate journey based on the corresponding trajectory sequence may include the following steps S1~S6: S1. From the trajectory sequence, intercept the part from the first stay point data of the stay points that are railway stations to the last stay point data, to obtain the inter-station trajectory sequence of the candidate user on this candidate journey.

[0085] It can be understood that both the first stop point and the last stop point in the inter-station trajectory sequence of a candidate user on a candidate journey are railway stations.

[0086] S2. Respectively take the first railway station and the last railway station in the inter-station trajectory sequence as the departure station and the arrival station of this candidate journey.

[0087] In this embodiment, the inter-station trajectory sequence of each candidate journey includes multiple stop point data, and the first stop point and the last stop point therein are respectively the departure station and the arrival station of the candidate journey.

[0088] Among them, if there is still a stop point as a railway station between the departure station and the arrival station in the inter-station trajectory sequence and the residence duration of this stop point is greater than the preset transfer duration (such as 20 min or 30 min), the intermediate railway station can be recorded as the transfer station of this candidate journey.

[0089] S3. Based on the residence time periods corresponding to the departure station and the arrival station of this candidate journey, determine the travel time of this candidate journey.

[0090] Exemplarily, please combine Figure 5 with Figure 5 Take the trajectory sequence 1 in

[0091] as an example. The inter-station trajectory sequence of this candidate journey is the stop points from 2 to 6. The departure station of this candidate journey is Station A, and the arrival station is Station B. The travel time of this candidate journey is the time difference between the end moment of the residence time period of stop point 6 and the start moment of the residence time period of stop point 2. It should be noted that this example is only for illustration and is not limited here.

[0092] S4. If there are other railway stations in the inter-station trajectory sequence in addition to the departure station and the arrival station, take the sum of the distances between every two adjacent railway stations in the inter-station trajectory sequence as the travel distance.

[0093] Among them, by investigating the ratio of the actual travel distances of some trains and the straight-line distances between railway stations, the average value of the non-linear coefficient is calculated to be 1.4.

[0094] S6. Calculate the ratio of the travel distance to the travel time to obtain the travel speed.

[0095] In this embodiment, the travel speed only represents the moving speed of the user between the departure station and the arrival station of a candidate journey.

[0096] The above method of screening each candidate journey for each candidate user is mainly based on the discrimination of spatial location relationships.

[0097] In actual situations, among all the candidate journeys of all candidate users, there are the following three misjudgment situations that lead to the introduction of railway journeys of non-railway passengers: Misjudgment situation 1: The distance between two railway stations is relatively close or even overlapping, and users passing by are miscounted. For example, Huadu Station and Guangzhou North Station actually have an overlapping geographical location. In this case, if a user just passes through the signaling interaction range of the two railway stations and generates a signaling interaction, then the passing journey of this user will be misjudged and counted as a candidate journey of a candidate user, and the non-railway journey (actually a passing journey) of such users needs to be excluded.

[0098] Misjudgment situation 2: With the advancement of the integrated development of comprehensive transportation, the development of transportation channels shows a trend from single to comprehensive and from plane to three-dimensional. The line coordination and cross-sectional space integration of linear infrastructure such as railways and highways are continuously deepened. Therefore, in the actual traffic line distribution, there will be a situation where the distances between railways and highways in the same traffic corridor are close, such as the Shanghai-Kunming corridor (the Shanghai-Kunming Expressway and the Shanghai-Kunming High-Speed Railway are close), the Beijing-Harbin corridor (the Beijing-Harbin Expressway and the Beijing-Harbin High-Speed Railway are close), etc. If a user traveling on the Shanghai-Kunming Expressway generates a signaling interaction within the signaling interaction range of two railway stations on the Shanghai-Kunming High-Speed Railway before and after traveling on the Shanghai-Kunming Expressway line, then it will be misjudged and counted into the category of candidate users, and the non-railway journey (actually a highway travel journey) of such highway travel users needs to be identified from all the candidate journeys of the candidate users; Misjudgment situation 3: In reality, there are situations where there are railway stations at both ends of the airport. For example, a user's air travel journey is from Nanning Wuxu International Airport (there is Wuxu Airport Station beside) to Lanzhou Zhongchuan International Airport (there is Zhongchuan Airport East Station beside), and just this user enters the signaling interaction range of the two railway stations at both ends and conducts a signaling interaction before and after, then this user's flight journey will also be misjudged and counted into the category of candidate journeys of the candidate user, and the non-railway journey (actually an air travel journey) of such air travel users needs to be identified from all the candidate journeys of the candidate users.

[0099] Therefore, the sub-steps of the above step S105 may include S1051 to S1054: S1051: From all the candidate journeys, screen out the target candidate journeys whose travel speed does not exceed the preset speed range and whose travel time is greater than the preset travel duration.

[0100] In this embodiment, the non-railway journeys pointed out in the above misjudgment case 1 usually do not conform to the speed characteristics and time characteristics of real railway trips. Therefore, it is possible to determine whether the travel speed and travel time of the candidate journey of each candidate user meet the speed characteristics and time characteristics of real railway trips, so as to exclude the non-railway journeys corresponding to the above misjudgment case 1.

[0101] Among them, the preset travel duration can be set based on the shortest travel duration between adjacent stations in the target area. For example, it can be set to 5 minutes, 10 minutes, etc., which is not limited here.

[0102] Optionally, the preset speed range can be set directly or determined by the following method: Based on the large number of historical driving speeds of various railway trains in the target area, a PDF (Probability Density Function) function is constructed. The PDF function reflects the probability distribution of the driving speed. Then, based on the PDF function, if the probability that the travel speed is in the range of 30 km / h to 350 km / h is 85%, the preset speed range can be set to 30 km / h to 350 km / h.

[0103] Among them, the probability density function is: , is the mean driving speed, is the standard deviation of the driving speed; the formula for calculating the probability density corresponding to the speed range is: ; Standardized transformation: , , .

[0104] S1052. Based on the inter-station trajectory sequence and travel information corresponding to each target candidate journey, screen out the first type of non-railway journeys misjudged due to the co-line of railway and highway from all target candidate journeys.

[0105] In this embodiment, in order to exclude the non-railway journeys corresponding to the above misjudgment case 2, it is necessary to identify whether the departure station and arrival station of each candidate journey belong to a co-line station pair. If so, it is further necessary to determine whether it belongs to the first type of non-railway journeys misjudged due to the co-line of railway and highway. And the co-line station pair means that the railway line between two railway stations is close to the highway.

[0106] Therefore, an optional implementation manner of step S1052 includes: Step a. Take the departure station and arrival station in the inter-station trajectory sequence corresponding to each target candidate journey as a station pair; Step b: Divide the inter-station trajectory sequences corresponding to all target candidate journeys with the same stations into a journey set; Step c: Based on each journey set, determine the line category of each pair of stations. The line category of a pair of stations is a collinear pair of stations or a non-collinear pair of stations; Step d: For any candidate journey corresponding to each collinear pair of stations, if the residence time of the departure station in the inter-station trajectory sequence corresponding to this candidate journey is lower than the preset waiting time threshold, it is determined that this candidate journey belongs to the first type of non-railway journey misjudged due to the co-line of railway and highway.

[0107] In this embodiment, a pair of stations represents two railway stations with a fixed driving direction. For example, the pair of stations A→B means the departure station is station A and the arrival station is station B; while the pair of stations B→A means the departure station is station B and the arrival station is station A.

[0108] Among them, since security check, ticket checking and waiting are required after entering the station, a real railway journey usually requires a certain residence time at the departure station. Therefore, after determining the line category of each pair of stations, for each candidate journey of a collinear pair of stations: if the residence time at the departure station in the inter-station trajectory sequence corresponding to this candidate journey is lower than the preset waiting time threshold (for example, 10 minutes), it is determined that this candidate journey belongs to the first type of non-railway journey misjudged due to the co-line of railway and highway; if the residence time at the departure station is not less than, then this candidate journey actually belongs to a real railway journey.

[0109] Therefore, in actual situations, the typical feature of a non-collinear pair of stations is that the residence time of the departure station in each inter-station trajectory sequence in the corresponding journey set is basically not less than the preset waiting time threshold (for example, 10 minutes). The typical feature of a collinear pair of stations is that the residence time of the departure station in each inter-station trajectory sequence in the corresponding journey set is mostly lower than the preset waiting time threshold (for example, 10 minutes), and this type belongs to a non-railway trajectory sequence, but the trajectory of a road trip journey.

[0110] In an alternative implementation, the line category of each pair of stations can be determined by clustering. That is, in step c, the implementation method of "based on each journey set, determine the line category of each pair of stations" includes: Step c-1: Based on the residence time of the departure station of each inter-station trajectory sequence in each journey set, determine the feature vectors of each pair of stations respectively; Step c-2: Cluster the feature vectors of all pairs of stations to obtain two clustering sets; Step c-3: If the first vector value in the feature vectors corresponding to each station pair in one of the clustering sets is greater than the set threshold, determine each station pair in this clustering set as a collinear station pair, and each station pair in the other clustering set as a non-collinear station pair.

[0111] Among them, the feature vector reflects the proportion of the number of journeys with dwell times falling within multiple time intervals from small to large. The time interval corresponding to the first vector value of the feature vector is: from 0 to the preset waiting time threshold. The set threshold can be 80%, 85%, 90%, etc.

[0112] Exemplarily, assume there are 6 time intervals: less than 10 min, 10 min - 30 min, 30 min - 1 h, 1 h - 1 h 30 min, 1 h 30 min - 2 h, and more than 2 h. If we assume a station pair A→B (the departure station is station A and the arrival station is station B), and its corresponding journey set includes 100 inter-station track sequences. If the number of journeys and the proportion of the number of journeys with dwell times at the departure station in each time interval among these 100 inter-station track sequences are as follows in the table:

[0113] Thus, the feature vector corresponding to the station pair A→B is 0.87, 0.09, 0.02, 0.02, 0, 0, which is a 6-dimensional vector. If the set threshold is 85%, and in the clustering set where the station pair A→B is located, the first vector value of the feature vector corresponding to each station pair is greater than 85%, it can be confirmed that the line category of each station pair in the clustering set where the station pair A→B is located is a collinear station pair.

[0114] It should be noted that this example is only for illustration, and the present invention does not limit the number of inter-station track sequences in the journey set, the division granularity and number of time intervals, etc.

[0115] In another alternative implementation, the line category of each station pair can be determined by means of data statistics. That is, in step c, the implementation of "determining the line category of each station pair based on each journey set" includes: Step c-A: For each station pair, count the proportion of the number of journeys with dwell times lower than the preset waiting time threshold at the departure station from the corresponding journey set; Step c-B: If the proportion of the number of journeys is greater than the set threshold, determine the station pair as a collinear station pair; Step c-C: If the proportion of the number of journeys is not greater than the set threshold, determine the station pair as a non-collinear station pair.

[0116] In practical applications, when determining the line category for each pair of stations, whether to use the clustering method or the data statistics method can depend on the scale of each journey set, and one can choose the method with less computing power consumption or faster calculation speed.

[0117] S1053. Screen out the second type of non-railway journeys misjudged due to the proximity of the airport and the railway station from all the target candidate journeys.

[0118] For the non-railway journeys corresponding to the above misjudgment case 3, to ensure flight safety, the user's mobile phone is in flight mode or shutdown mode during the flight. In fact, no signaling data will be generated during the actual flight, and no user stay point data will be counted during the flight period. And usually, there is an overlap in the location of the railway stations at both ends with the airport, that is, the railway station is located underground beneath the airport. For example, Hongqiao Railway Station is horizontally connected to Terminal 2 of Hongqiao Airport in the same building, and Zhengding Airport Station is located on the underground first floor of the terminal building of Shijiazhuang Zhengding Airport.

[0119] Therefore, in the station-to-station trajectory sequence corresponding to a target candidate journey, if there is no stay point between the departure station and the arrival station, and the departure station and the arrival station are located beneath the airport or adjacent to the airport, then the period between the end time of the stay period corresponding to the departure station and the start time of the stay period corresponding to the arrival station should actually belong to the flight period. It can be considered that this target candidate journey belongs to the second type of non-railway journey misjudged due to the proximity of the airport and the railway station and needs to be excluded.

[0120] S1054. Delete each type of non-railway journey from all the target candidate journeys to obtain each railway journey of each railway passenger.

[0121] Through the above steps S1051 - S1054, the exclusion of non-railway journeys in the above three misjudgment cases is completed, and the remaining are each railway journey of each railway passenger.

[0122] Finally, the user code of each railway passenger can be output, as well as the departure station, arrival station, transfer station, the time of entering the departure station (i.e., the start time of the stay period at the departure station), the time of leaving the departure station (i.e., the end time of the stay period at the departure station), the time of entering the arrival station (i.e., the start time of the stay period at the arrival station), the time of leaving the arrival station (i.e., the end time of the stay period at the arrival station), travel time, travel distance, and travel speed for each railway journey of each railway passenger. Overall, it can be output in the form of a detailed list of railway passengers. This is convenient for subsequent statistics of railway passenger flow indicators in the target area within a specified time, as well as related analyses such as the origin, destination, and transfer.

[0123] It should be noted that the execution order of each step in the above method embodiments is not limited by the figures shown, and the execution order of each step is subject to the actual application situation.

[0124] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: By using the signaling set of the target area and the signaling interaction range of each railway station in the target area, fully combining the travel behavior characteristics of railway passengers, and comprehensively considering various misjudgment situations, each railway journey of each railway passenger in the target area within the specified time is finally accurately identified.

[0125] To execute the corresponding steps in the above method embodiments and various possible implementation manners, an implementation manner of a railway passenger identification device is given below.

[0126] Please refer to Figure 6 , Figure 6 which shows a schematic structural diagram of the railway passenger identification device provided by the embodiments of the present invention. The railway passenger identification device 200 includes: a signaling acquisition module 210, a range determination module 220, a residence determination module 230, a first identification module 240, and a second identification module 250, where: The signaling acquisition module 210 is configured to acquire the signaling set within the target area within the specified time; the signaling set includes multiple signaling data of several users; The range determination module 220 is configured to obtain the signaling interaction range corresponding to each railway station within the target area; The residence determination module 230 is configured to determine the residence information of each pending user based on the signaling set and the signaling interaction range corresponding to each railway station; the pending user is a user who has performed signaling interaction within any signaling interaction range; The first identification module 240 is configured to identify each candidate user who has performed signaling interaction within at least two signaling interaction ranges from all pending users based on the residence information of each pending user, and determine the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey; The second identification module 250 is configured to filter out misjudged non-railway journeys from all candidate journeys of all candidate users based on the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey, so as to obtain each railway journey of each railway passenger.

[0127] Optionally, the range determination module 220 may specifically be configured to: acquire the geographical boundary information of each railway station within the target area; acquire the longitude and latitude coordinates of each base station within the target area; determine the signal coverage range of each base station based on the longitude and latitude coordinates of each base station; perform spatial association analysis on the signal coverage ranges of all base stations and the geographical boundary information of each railway station to determine the signaling interaction range of each railway station.

[0128] Optionally, the signaling set includes multiple signaling data of several users, and the signaling data includes the base station location; the residence information includes multiple residence point data, and at least one of the residence points in at least one residence point data is a railway station. The residence determination module 230 can specifically be used for: For any signaling data in the signaling set, if the base station location of the signaling data is within any signaling interaction range, it is determined that the user corresponding to the signaling data is a to-be-identified user to be determined; for each to-be-determined user, based on all the signaling data of the to-be-determined user in the signaling set, at least one residence point data and at least one passing point data of the to-be-determined user are determined; the residence point data includes the location and residence period of the residence point; the passing point data includes the location and passing time of the passing point; stretch the passing time in each passing point data to convert each passing point data into residence point data; among all the residence point data corresponding to the to-be-determined user, integrate each residence point whose residence point is within the signaling interaction range corresponding to the same railway station and whose residence periods are continuous into a residence point data with the residence point being the railway station, to obtain multiple residence point data of the to-be-determined user.

[0129] Optionally, the residence information includes multiple residence point data, the residence point data includes the location and residence period of the residence point, and at least one of the residence points in each residence information is a railway station. The first identification module 240 can specifically be used for: For each to-be-determined user, sort all the residence point data of the to-be-determined user in ascending order of the start time of the residence period to obtain the trajectory sequence of each to-be-determined user within the specified time; if any trajectory sequence includes off-station residence points, based on all the off-station residence points, divide the trajectory sequence into at least one trajectory sequence; the off-station residence point is a residence point whose corresponding residence duration exceeds the preset residence duration; from all the trajectory sequences, eliminate the non-railway trajectory sequences that include only one railway station or do not include a railway station, and eliminate the trajectory sequences of non-railway passengers with two residence points being the same railway station; use the to-be-determined user corresponding to each remaining trajectory sequence as a candidate user, and use each remaining trajectory sequence as a candidate journey to be identified; for each candidate journey of each candidate user, based on the first residence point data and the last residence point data whose residence points are railway stations in the corresponding trajectory sequence, determine the inter-station trajectory sequence and travel information of the candidate user on this candidate journey.

[0130] Optionally, the travel information includes the departure station, arrival station, travel time, travel distance, and travel speed. In the process of the first identification module 240 being used to "determine the inter-station trajectory sequence and travel information of the candidate user on this candidate journey based on the first residence point data and the last residence point data whose residence points are railway stations in the corresponding trajectory sequence", it can specifically be used for: From the trajectory sequence, intercept the part from the first residence point data with the residence point being the railway station to the last residence point data, obtaining the inter-station trajectory sequence of the candidate user on this candidate journey segment; use the first railway station and the last railway station in the inter-station trajectory sequence as the departure station and the arrival station of this candidate journey segment respectively; determine the travel time of this candidate journey segment based on the residence periods corresponding to the departure station and the arrival station of this candidate journey segment; if the inter-station trajectory sequence includes railway stations other than the departure station and the arrival station, use the sum of the distances between every two adjacent railway stations in the inter-station trajectory sequence as the travel distance; if the inter-station trajectory sequence only includes these two railway stations, namely the departure station and the arrival station, use the product of the straight-line distance between the departure station and the arrival station and a preset non-straight-line coefficient as the travel distance; calculate the ratio of the travel distance to the travel time to obtain the travel speed.

[0131] Optionally, the inter-station trajectory sequence includes multiple residence point data. The residence point data includes the position and residence period of the residence point. The residence period reflects the residence duration. The first residence point and the last residence point in the inter-station trajectory sequence are the departure station and the arrival station of a candidate journey segment respectively; the travel information includes the departure station, the arrival station, the travel time, the travel distance, and the travel speed. The second recognition module 250 can specifically be used for: From all candidate journeys, screen out the target candidate journeys whose travel speed does not exceed the preset speed range and whose travel time is greater than the preset travel duration; based on the inter-station trajectory sequence and travel information corresponding to each target candidate journey, screen out the first type of non-railway journeys misjudged due to the co-linearity of railway and highway from all target candidate journeys; screen out the second type of non-railway journeys misjudged due to the proximity of the airport to the railway station from all target candidate journeys; in the inter-station trajectory sequence of the second type of non-railway journeys, there is no residence point between the departure station and the residence station, and the departure station and the arrival station are located below the airport or adjacent to the airport; delete each type of non-railway journey from all target candidate journeys to obtain each railway journey of each railway passenger.

[0132] Optionally, in the process of the second recognition module 250 being used for "based on the inter-station trajectory sequence and travel information corresponding to each target candidate journey, screen out the first type of non-railway journeys misjudged due to the co-linearity of railway and highway from all target candidate journeys", it can specifically be used for: Take the departure station and the arrival station in the inter-station trajectory sequence corresponding to each target candidate journey as a pair of stations; divide the inter-station trajectory sequences corresponding to all target candidate journeys with the same pair of stations into a journey set; based on each journey set, determine the line category of each pair of stations, and the line category is a collinear pair of stations or a non-collinear pair of stations; for any candidate journey corresponding to each collinear pair of stations, if the residence time of the departure station in the inter-station trajectory sequence corresponding to this candidate journey is lower than the preset waiting time threshold, it is determined that this candidate journey belongs to the first type of non-railway journey misjudged due to the co-line of railway and highway.

[0133] Optionally, in the process of the second recognition module 250 for "determining the line category of each pair of stations based on each journey set", it can specifically be used for: Based on the residence duration of the departure station of each inter-station trajectory sequence in each journey set, respectively determine the feature vectors of each pair of stations; the feature vector reflects the proportion of the number of journeys in which the residence duration falls within multiple duration intervals from small to large; cluster the feature vectors of all pairs of stations to obtain two clustering sets; if the first vector value in the feature vector corresponding to each pair of stations in one of the clustering sets is greater than the set threshold, determine that each pair of stations in this clustering set is a collinear pair of stations, and each pair of stations in the other clustering set is a non-collinear pair of stations; or, it can specifically also be used for: For each pair of stations, count the proportion of the number of journeys with a residence duration lower than the preset duration threshold at the departure station from the corresponding journey set; if the proportion of the number of journeys is greater than the set threshold, determine that the pair of stations is a collinear pair of stations; if the proportion of the number of journeys is not greater than the set threshold, determine that the pair of stations is a non-collinear pair of stations.

[0134] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described railway passenger identification device 200 can refer to the corresponding process in the foregoing method embodiments, and will not be elaborated here.

[0135] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device 300 includes a processor 310, a memory 320, and a bus 330, and the processor 310 is connected to the memory 320 through the bus 330.

[0136] The memory 320 can be used to store software programs or firmware. For example, store the software program or firmware corresponding to the above-described railway passenger identification device 200. The processor 310 executes various functional applications and data processing by running the software program stored in the memory 320 to implement the railway passenger identification method provided by the embodiments of the present invention.

[0137] Among them, the memory 320 can be, but is not limited to: RAM (Random Access Memory), ROM (Read Only Memory), FLASH (Flash Memory), PROM (Programmable Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electric Erasable Programmable Read-Only Memory), etc.

[0138] The processor 310 can be an integrated circuit chip with signal processing capabilities and can be used to execute software programs. For example, it can execute the software program corresponding to the above-mentioned railway passenger identification device 200. The processor 310 can be a general-purpose processor, including: CPU (Central Processing Unit), NP (Network Processor), SoC (System on Chip), etc.; it can also be: DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0139] It can be understood that Figure 7 The structure shown is only schematic, and the electronic device 300 can also include more or fewer components than those shown Figure 7 in the figure, or have a different configuration from that shown Figure 7 in the figure. Figure 7 Each component shown in the figure can be implemented using hardware, software, or a combination thereof.

[0140] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the railway passenger identification method disclosed in the above embodiment. The computer-readable storage medium can be, but is not limited to: USB flash drive, mobile hard disk, ROM, RAM, PROM, EPROM, EEPROM, FLASH magnetic disk, or optical disc, etc., various media that can store program codes.

[0141] In summary, the embodiments of the present invention provide a method, apparatus, electronic device and computer-readable storage medium for identifying railway passengers. First, a signaling set within a target area within a specified time is obtained, which includes multiple signaling data of several users; then, the signaling interaction range corresponding to each railway station within the target area is obtained; next, based on the signaling set and the signaling interaction ranges corresponding to each railway station, the residence information of each pending user is determined, where the pending user is a user who conducts signaling interaction within any signaling interaction range, so that all pending users who have stayed within the signaling interaction range of the railway station can be screened out. Then, based on the residence information of each pending user, each candidate user who has conducted signaling interaction within at least two signaling interaction ranges is identified from all the pending users, so that non-railway passengers who have only stayed at one railway station, such as pick-up and drop-off personnel or railway staff, can be excluded from all the pending users. Finally, based on the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey, each railway journey of each railway passenger is identified from all the candidate journeys of all the candidate users, and finally each railway journey of each railway passenger within the specified time is accurately identified.

[0142] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for identifying railway passengers, characterized in that, Including: Obtain a signaling set within a target area within a specified time; Obtain the signaling interaction range corresponding to each railway station within the target area; Based on the signaling set and the signaling interaction ranges corresponding to each railway station, determine the residence information of each pending user; The pending user is a user who has performed signaling interaction within any of the signaling interaction ranges; Based on the residence information of each pending user, identify each candidate user who has performed signaling interaction within at least two signaling interaction ranges from all the pending users, and determine the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey; Based on the inter-station trajectory sequences and travel information of each candidate user on at least one candidate journey, filter out misjudged non-railway journeys from all the candidate journeys of all the candidate users to obtain each railway journey of each railway passenger.

2. The railway passenger identification method according to claim 1, wherein The step of obtaining the signaling interaction range corresponding to each railway station within the target area includes: Obtain the geographical boundary information of each railway station within the target area; Obtain the longitude and latitude coordinates of each base station within the target area; Based on the longitude and latitude coordinates of each base station, determine the signal coverage range of each base station; Perform spatial association analysis on the signal coverage ranges of all the base stations and the geographical boundary information of each railway station to determine the signaling interaction range of each railway station.

3. The railway passenger identification method according to claim 1, characterized in that The signaling set includes multiple signaling data of several users, and the signaling data includes the base station location; the residence information includes multiple residence point data, and at least one of the residence points in at least one residence point data is the railway station; the step of determining the residence information of each pending user based on the signaling set and the signaling interaction ranges corresponding to each railway station includes: For any signaling data in the signaling set, if the base station location of the signaling data is within any of the signaling interaction ranges, determine that the user corresponding to the signaling data is a pending user to be identified; For each pending user, based on all the signaling data of the pending user in the signaling set, determine at least one residence point data and at least one passing point data of the pending user; the residence point data includes the location and residence period of the residence point; the passing point data includes the location and passing time of the passing point; Perform stretching processing on the passing times in each passing point data to convert each passing point data into residence point data; Integrate each residence point in all the residence point data corresponding to the pending user, where the residence point is within the signaling interaction range corresponding to the same railway station and the residence periods are continuous, into one residence point data with the residence point being the railway station to obtain multiple residence point data of the pending user.

4. The railway passenger identification method according to claim 1, characterized in that The residence information includes multiple residence point data, the residence point data includes the location and residence period of the residence point, and at least one of the residence points in each residence information is the railway station; The step of identifying, from all the to-be-determined users, each candidate user who has performed signaling interactions within at least two signaling interaction ranges based on the residence information of each of the to-be-determined users, and determining the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey includes: For each of the to-be-determined users, sort all the residence point data of the to-be-determined user in ascending order of the start time of the residence period, to obtain the trajectory sequence of each to-be-determined user within the specified time; If any of the trajectory sequences contains off-station residence points, based on all the off-station residence points, divide the trajectory sequence into at least one trajectory sequence; the off-station residence points are residence points whose residence duration corresponding to the residence period exceeds a preset residence duration; From all the trajectory sequences, eliminate non-railway trajectory sequences that include only one railway station or do not include a railway station, and eliminate the trajectory sequences of non-railway passengers with two residence points being the same railway station; Take the to-be-determined user corresponding to each remaining trajectory sequence as the candidate user, and take each remaining trajectory sequence as a candidate journey to be identified; For each candidate journey of each candidate user, based on the first residence point data and the last residence point data in the trajectory sequence where the residence point is the railway station, determine the inter-station trajectory sequence and travel information of the candidate user on this candidate journey.

5. The railway passenger identification method according to claim 4, characterized in that, The travel information includes the departure station, the arrival station, the travel time, the travel distance, and the travel speed; The step of determining the inter-station trajectory sequence and travel information of the candidate user on this candidate journey based on the first residence point data and the last residence point data in the trajectory sequence where the residence point is the railway station includes: From the trajectory sequence, intercept the part from the first residence point data where the residence point is the railway station to the last residence point data, to obtain the inter-station trajectory sequence of the candidate user on this candidate journey; Take the first railway station and the last railway station in the inter-station trajectory sequence as the departure station and the arrival station of this candidate journey respectively; Based on the residence periods corresponding to the departure station and the arrival station of this candidate journey, determine the travel time of this candidate journey; If the inter-station trajectory sequence includes other railway stations in addition to the departure station and the arrival station, take the sum of the distances between every two adjacent railway stations in the inter-station trajectory sequence as the travel distance; If the inter-station trajectory sequence includes only the two railway stations of the departure station and the arrival station, take the product of the straight-line distance between the departure station and the arrival station and a preset non-straight-line coefficient as the travel distance; Calculate the ratio of the travel distance to the travel time to obtain the travel speed.

6. The railway passenger identification method according to claim 1, wherein The inter-station trajectory sequence includes a plurality of residence point data. The residence point data includes the position and residence period of the residence point. The residence period reflects the residence duration. The first residence point and the last residence point in the inter-station trajectory sequence are the departure station and the arrival station of a candidate journey respectively. The travel information includes the departure station, the arrival station, the travel time, the travel distance, and the travel speed. The step of filtering misjudged non-railway journeys from all candidate journeys of all candidate users based on the inter-station trajectory sequences and travel information of each candidate user on at least one candidate journey to obtain each railway journey of each railway passenger includes: From all candidate journeys, screen out target candidate journeys whose travel speed does not exceed a preset speed range and whose travel time is greater than a preset travel duration. Based on the inter-station trajectory sequences and travel information corresponding to each target candidate journey, screen out the first type of non-railway journeys misjudged due to the co-linearity of railway and highway from all target candidate journeys. Screen out the second type of non-railway journeys misjudged due to the proximity of the airport to the railway station from all target candidate journeys. In the inter-station trajectory sequence of the second type of non-railway journey, there is no residence point between the departure station and the residence station, and the departure station and the arrival station are located below the airport or adjacent to the airport. Delete each type of non-railway journey from all target candidate journeys to obtain each railway journey of each railway passenger.

7. The railway passenger identification method according to claim 6, wherein The step of screening out the first type of non-railway journeys misjudged due to the co-linearity of railway and highway from all target candidate journeys based on the inter-station trajectory sequences and travel information corresponding to each target candidate journey includes: Take the departure station and the arrival station in the inter-station trajectory sequence corresponding to each target candidate journey as a pair of stations. Divide the inter-station trajectory sequences corresponding to all target candidate journeys with the same pair of stations into a journey set. Based on each journey set, determine the line category of each pair of stations. The line category is a co-line pair of stations or a non-co-line pair of stations. For any candidate journey corresponding to each co-line pair of stations, if the residence time of the departure station in the inter-station trajectory sequence corresponding to this candidate journey is lower than a preset waiting time threshold, it is determined that this candidate journey belongs to the first type of non-railway journey misjudged due to the co-linearity of railway and highway.

8. The railway passenger identification method according to claim 7, characterized in that, The step of determining the line category of each pair of stations based on each journey set includes: Based on the residence duration of the departure station in each inter-station trajectory sequence in each journey set, respectively determine the feature vectors of each pair of stations. The feature vector reflects the proportion of the number of journeys in which the residence duration falls within multiple duration intervals from small to large. Cluster the feature vectors of all pairs of stations to obtain two cluster sets. If the first vector value in the feature vector corresponding to each pair of stations in one of the cluster sets is greater than a set threshold, determine that each pair of stations in this cluster set is a co-line pair of stations, and each pair of stations in the other cluster set is a non-co-line pair of stations.

9. The railway passenger identification method according to claim 7, characterized in that, The step of determining the line category of each station pair based on each of the journey sets includes: For each station pair, count the proportion of the number of journeys with a residence duration at the departure station lower than a preset duration threshold in the corresponding journey set; If the proportion of the number of journeys is greater than a set threshold, determine that the station pair is the collinear station pair; If the proportion of the number of journeys is not greater than the set threshold, determine that the station pair is a non-collinear station pair.

10. A railway passenger identification device, characterized in that, Including: A signaling acquisition module, configured to acquire a signaling set within a target area within a specified time; the signaling set includes a plurality of signaling data of a number of users; A range determination module, configured to obtain the signaling interaction range corresponding to each railway station within the target area; A residence determination module, configured to determine the residence information of each pending user based on the signaling set and the signaling interaction ranges corresponding to each railway station; The pending user is a user who has performed signaling interaction within any of the signaling interaction ranges; A first identification module, configured to identify, based on the residence information of each of the pending users, each candidate user who has performed signaling interaction within at least two signaling interaction ranges from all the pending users, and determine the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey; A second identification module, configured to filter misjudged non-railway journeys from all the candidate journeys of all the candidate users based on the inter-station trajectory sequence and travel information of each candidate user on at least one candidate journey, so as to obtain each railway journey of each railway passenger.

11. An electronic device, characterized in that, Including: A memory and a processor, the memory stores a software program, and when the electronic device runs, the processor executes the software program to implement the railway passenger identification method according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the railway passenger identification method according to any one of claims 1-9.

Images