Transfer interlink trip mode identification method and device, storage medium and electronic equipment

Abstract

The invention provides a transit interlink trip mode identification method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring to-be-processed mobile phone signaling information of a target user by the electronic equipment; obtaining a cross-county travel result, a train travel result and an aviation travel result of the target user according to the mobile phone signaling information; and deleting a travel path corresponding to the train travel result and the aviation travel result from the cross-district and county travel results to obtain a road travel result of the target user, and finally obtaining a transit interlink travel mode of the target user according to multiple travel results. Thus, by obtaining the mobile phone signaling information of the target user, the cross-county travel result, the train travel result, the aviation travel result and the road travel result of the user are obtained, and thus the transit interlink travel mode of the target user is obtained; therefore, the technical problem that large-scale and multi-dimensional data support is lacked in existing relay interlinkage related research is effectively solved.

Description

Technical Field

[0001] This application relates to the field of big data, and more specifically, to a method, apparatus, storage medium, and electronic device for identifying connecting travel modes. Background Technology

[0003] Road transport offers high flexibility and door-to-door direct delivery, making it ideal for short-distance travel. Rail transport boasts large capacity, relatively high speed, and is less affected by weather and other natural factors, offering a relatively stable transport process. Compared to air transport, it offers high accessibility, reaching most cities in my country. Air transport maintains higher standards in speed, efficiency, and travel comfort, but its transport costs and arrival / departure costs at airports are relatively high. Water transport is significantly affected by local natural conditions and has a smaller user base, primarily concentrated in the eastern coastal areas and southern regions with developed shipping networks.

[0004] As travel distances increase, relying solely on a single mode of transportation faces multiple bottlenecks in terms of efficiency, economy, and geography. Therefore, modern transportation systems are evolving towards seamless connectivity and intelligent collaboration, enabling the combined use of multiple modes of transport to function as a highly efficient integrated network. For example, people can drive to the high-speed rail station, take the high-speed rail, and then transfer to a plane, or get off the train and take a taxi to their hotel. This type of combined travel is called a connecting journey. Simply put, a connecting journey involves using two or more different modes of transportation in a single trip. As travel distances increase and the demands for a better travel experience rise, this multi-modal travel will become increasingly common and in greater demand in the future.

[0005] Therefore, analyzing passenger connecting travel modes is crucial for optimizing transportation network layout, rationally planning hub layout, analyzing connecting transport, and researching air-rail intermodal transport. However, current research on passenger connecting transport suffers from limitations in content, small scale, and a lack of objective, multi-dimensional data support. Techniques and methods for obtaining multi-dimensional passenger connecting travel data on a large spatial scale are scarce, especially at the national level, where they are almost nonexistent. Summary of the Invention

[0006] To overcome at least one deficiency in the existing technology, this application provides a method, device, storage medium, and electronic device for identifying transit and connecting travel modes. This method can acquire the target user's mobile phone signaling information and generate cross-county travel results, train travel results, and air travel results accordingly, achieving a comprehensive analysis of cross-regional travel paths. Based on this, it removes railway and air travel results from the cross-county travel results, identifying road travel results and thus obtaining the target user's transit and connecting travel mode. This effectively solves the technical problem of the lack of large-scale, multi-dimensional data support in existing research on transit and connecting travel.

[0007] Firstly, this application provides a method for identifying connecting travel modes, the method comprising: Obtain the mobile signaling information of the target user that is yet to be processed; Based on the mobile phone signaling information, the cross-county travel results, train travel results, and air travel results of the target user are obtained; Delete the cross-county travel results corresponding to the train travel results and the air travel results from the cross-county travel results to obtain the road travel results of the target user; Based on the train travel results, the air travel results, and the road travel results, the connecting travel methods of the target user are obtained.

[0008] Secondly, this application provides a transit mode identification device, the device comprising: The signaling acquisition module is used to acquire the mobile signaling information of the target user that is yet to be processed. The travel mode identification module is used to obtain the target user's cross-county travel results, train travel results, and air travel results based on the mobile phone signaling information; The travel mode identification module is also used to delete the travel routes corresponding to the train travel results and the air travel results from the cross-county travel results to obtain the road travel results of the target user; The transit identification module is used to obtain the transit and connecting travel methods of the target user based on the train travel results, the air travel results, and the road travel results.

[0009] Thirdly, this application provides a storage medium storing a computer program that, when executed by a processor, implements the aforementioned method for identifying connecting travel modes.

[0010] Fourthly, this application provides an electronic device, which includes a processor and a memory, wherein the memory stores a computer program, and the computer program, when executed by the processor, implements the aforementioned method for identifying connecting travel modes.

[0011] Compared with the prior art, this application has the following beneficial effects: In the connecting travel mode identification method, device, storage medium, and electronic device provided in this application, the electronic device acquires the mobile phone signaling information to be processed by the target user; based on the mobile phone signaling information, it obtains the target user's cross-county results, train travel results, and air travel results; it deletes the cross-county travel routes corresponding to the train travel results and air travel results from the cross-county travel results to obtain the target user's road travel results; and based on the train travel results, air travel results, and road travel results, it obtains the target user's connecting travel mode.

[0012] Thus, by acquiring the target user's mobile phone signaling information and generating cross-county travel results, train travel results, and air travel results accordingly, a comprehensive analysis of cross-regional travel routes is achieved. Based on this, by removing the railway and air travel results from the cross-county travel results, the road travel results can be identified, and the connecting travel methods of the target user can be obtained. This effectively solves the technical problem of the lack of large-scale, multi-dimensional data support in existing research on connecting travel. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 A flowchart illustrating the connecting travel mode identification method provided in this application embodiment; Figure 2 This is a schematic diagram illustrating the principle of invalid district / county identification provided in an embodiment of this application. Figure 3 This is a schematic diagram of the structure of the transit and connecting travel mode identification device provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of the embodiments of this application (hereinafter referred to as "the embodiments") clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0016] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0017] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0018] In the description of this application, it should be noted that the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0019] Based on the above statement, as introduced in the background section, current research on passenger transit and connecting flights is characterized by limited content, small scale, and lack of support from objective and multidimensional data.

[0020] For example, while air travel has real-name ticketing data, rail travel has real-name ticketing data, road travel has tollbooth vehicle entry and exit data, and water transport has passenger ticket purchase data, these data have certain limitations for analyzing connecting passengers. First, these data are difficult and costly to obtain, making them almost impossible to acquire. Second, data barriers exist between different data sources, making it impossible to depict a complete travel trajectory of passengers through multi-source data. Third, it is difficult to obtain richer profiles of passengers, such as transit time, travel time, place of residence, place of origin, gender, and age.

[0021] To gain a detailed understanding of existing technologies and methods for acquiring transit passenger data, a literature review approach can be used to retrieve relevant literature on transit passengers, intermodal transport, and air-rail intermodal transport. Through summarizing and analyzing the relevant literature, current research on transit passengers mainly focuses on air-rail intermodal transport, and the research scale is primarily limited to transit between local airports and stations, with a lack of large-scale analytical studies.

[0022] There are two main technologies and methods for identifying passenger connecting travel modes: the first is the traditional questionnaire survey method; the second is to obtain connecting travel data based on mobile phone signaling data and the spatial scope of hub stations at a small spatial scale. The traditional questionnaire survey method mainly uses methods such as revealed preference (RP) and stated preference (SP) to distribute and collect questionnaires in specific areas to obtain travelers' travel information or intentions. However, traditional questionnaire surveys have small sample sizes, high costs, and low response rates, which to some extent restricts the analysis and research of passenger connecting transportation. As for the scheme of obtaining connecting travel data based on mobile phone signaling data and hub stations at a small spatial scale, it mainly focuses on local hubs, which may lead to the loss of travel information, and the data content is mainly limited to the scale of connecting passengers.

[0023] It should be noted that the defects in the solutions in the prior art are the result of practical investigation and careful study. Therefore, the discovery process of the above problems and the solutions proposed by the embodiments of this application in the following text should be regarded as contributions to this application in the process of invention and creation, and should not be understood as technical content known to those skilled in the art.

[0024] Based on the discovery of the above-mentioned technical problems, this embodiment provides a method for identifying connecting travel modes. For example... Figure 1 As shown, the method includes: S1, Obtain the mobile signaling information of the target user to be processed.

[0025] S2 obtains the target user's cross-county travel results, train travel results, and air travel results based on mobile phone signaling information.

[0026] S3, delete the travel routes corresponding to train travel results and air travel results from the cross-county travel results to obtain the road travel results of the target user; S4 obtains the transit and connecting travel results for the target user based on the results of train travel, air travel, and road travel.

[0027] In this way, by acquiring the target user's mobile phone signaling information and generating cross-county travel results, train travel results, and air travel results, a comprehensive analysis of cross-regional travel paths is achieved. Based on this, by removing the railway and air travel results from the cross-county travel results, the road travel results can be identified, and the connecting travel methods of the target user can be obtained. This effectively solves the technical problem of the lack of large-scale, multi-dimensional data support in existing research on connecting travel.

[0028] It is worth noting that the data and storage devices involved in the solution described in this application all comply with the laws and regulations of the country / region where the aforementioned data-related activities occurred, including but not limited to: authorization, generation, use, and storage. This can be understood as the storage location of the signaling records and other information used in implementing this solution complying with the laws and regulations of the country / region where the aforementioned data-related activities occurred, including but not limited to: authorization, generation, use, and storage.

[0029] It should also be understood that the electronic devices implementing this method can be general-purpose computing platforms with data processing, storage, and communication capabilities. Specifically, such electronic devices typically include computing units such as central processing units (CPUs), graphics processing units (GPUs), or field-programmable gate arrays (FPGAs) for executing algorithmic logic, along with storage modules such as memory and hard drives to load and save mobile signaling data, administrative division vector data, transportation hub vector data, and intermediate results generated at each stage. For example, this electronic device can be, but is not limited to, servers, cloud computing nodes, edge computing devices, or high-performance workstations, as long as it has sufficient computing power and data throughput capabilities to support the efficient operation of this method on a large scale.

[0030] The server can be a single server or a server cluster consisting of multiple servers. The server cluster can adopt a centralized or distributed architecture (e.g., built as a distributed system) and be deployed in an intranet environment to ensure data security during data analysis and processing and prevent information leakage. In some embodiments, the server can be local or remote relative to the user terminal.

[0031] To make the solution provided in this embodiment clearer, a server is used as the electronic device for implementing the method below, and in conjunction with... Figure 1 Each step of the method is described in detail. However, it should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. Furthermore, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowchart, or remove one or more operations from the flowchart. Figure 1 As shown, the method includes: S1, Obtain the mobile signaling information of the target user to be processed.

[0032] This can be understood as follows: the above steps can collect raw signaling records reflecting user movement behavior from the communication network side. These records typically include user equipment identifiers (such as encrypted user IDs), base station connection times, location area codes (LACs), cell IDs, and geographic coordinates. In practical applications, mobile signaling data may be affected by communication disturbances or base station handover logic during collection, transmission, and processing, resulting in various types of abnormal data. Therefore, preprocessing of the raw data is necessary to improve the accuracy of subsequent analysis.

[0033] In practice, the server first sorts the acquired mobile signaling information according to timestamps to facilitate subsequent trajectory reconstruction based on time series. Duplicate data, either identical or occurring repeatedly within a very short timeframe, can be directly deleted to avoid redundant calculations. For drift data—anomalies caused by a user signal accidentally connecting to a distant base station and then quickly switching back—the server can identify them by setting speed and time interval thresholds.

[0034] If the instantaneous speed calculated based on the spatial distance and time difference between two adjacent signaling points far exceeds the normal speed range for land traffic, then the point is identified as a drift point and removed. For ping-pong handover data, which is continuous oscillating signaling records caused by frequent switching between two or more adjacent base stations, such repeated handover behavior can be identified within a set time window. The first and last valid connection points are retained, while invalid records of repeated jumps in between are deleted, thereby restoring the user's true camping state.

[0035] In this way, by preprocessing the original signaling records and deleting obviously problematic or interference-inducing records, the mobile signaling information to be processed is obtained, ensuring that the subsequent cross-county travel results, train travel results, and air travel results are true and reliable.

[0036] Based on the mobile signaling information to be processed obtained from the above steps, continue to refer to... Figure 1 Next, we will explain step S2 in the diagram: S2 obtains the target user's cross-county travel results, train travel results, and air travel results based on mobile phone signaling information.

[0037] Research has found that related technologies generally face problems in identifying travel outcomes, such as fragmented travel trajectories and difficulty in distinguishing between valid travel and transit behaviors, resulting in the inability to accurately construct reliable and meaningful travel data. Therefore, this embodiment includes multiple signaling records in the mobile phone signaling information and provides the following optional implementation methods for step S2: S2-1 spatially matches multiple signaling records with administrative region data within a preset range to obtain the signaling records of the target user in multiple districts and counties they pass through.

[0038] S2-2, based on the signaling records of each district and county through which the target user resides, obtain the residence information of the target user in the corresponding district and county through which the target user resides.

[0039] This embodiment can be understood as follows: by spatially matching multiple signaling records with administrative region data within a preset range, and extracting the user's residence information in each district and county they pass through based on the matching results, the embodiment identifies the districts and counties where the user has actually resided for an extended period of time. The preset range can be the entire country or a portion of the country.

[0040] Specifically, the server first uses multiple mobile signaling records of the target user as input data. Each record contains a timestamp and spatial location information. It performs spatial correlation calculations with the national county-level administrative division vector data, and uses a point-to-surface spatial matching algorithm to determine the county-level administrative division to which each signaling point belongs. Then, it adds a corresponding county-level administrative division code field to each signaling record.

[0041] During this process, the server can filter out target users who have generated signaling records in two or more different districts / counties to ensure that the analysis targets are users traveling across districts / counties. Then, according to the district / county scale, the server merges the signaling records of the same user that are consecutive in time within the same district / county to identify the user's valid stay segments in that district / county. In specific implementation, the server can determine the time nodes when a user enters and leaves a certain district / county based on the time sequence of the signaling, and then calculate the user's start stay time, end stay time, and stay duration in that district / county; and obtain the first stay location, the last stay location, and the location with the longest stay time in that stay segment.

[0042] In this way, the discrete signaling records are categorized according to the spatial dimension of districts and counties, providing complete stop information for the subsequent construction of cross-district and county travel results. Therefore, the stop information here should be understood as multi-dimensional information including the start and end times of the stay, the duration of the stay, and key locations (e.g., the first stop location, the last stop location, and the location with the longest stay).

[0043] Based on the residency information obtained from the above steps, step S2 further includes: S2-3: Based on the target user's stay information in each district and county they pass through, obtain cross-district and county travel results.

[0044] It should be understood that mobile signaling data contains a large number of records with extremely short dwell times, which may simply be due to signal connection or base station switching when a user passes through a certain district or county, and do not represent actual travel behavior. Including such areas in travel path analysis would introduce false dwell nodes, leading to incorrect judgments about the user's travel origin and travel distance.

[0045] Therefore, as an optional implementation of steps S2-3, the server can determine invalid districts and counties whose stay duration is lower than the duration threshold based on the stay information of the target user in each district and county it passes through; delete the invalid districts and counties from multiple districts and counties it passes through to obtain multiple remaining valid districts and counties; and obtain the cross-district and county travel results based on the stay information of each valid district and county.

[0046] This embodiment can be understood as follows: by filtering out district / county stay records that meet the minimum stay duration requirements, and constructing structured cross-district / county travel results based on the valid stay districts / counties, the actual cross-district / county travel paths of the target user can be identified.

[0047] In practical applications, after obtaining the target user's stay information in each district and county they pass through, the server first determines whether the district or county constitutes a valid travel node based on the stay duration. For districts and counties with a stay duration below a preset threshold, it can be considered that the user only made a brief stop or passed through during the journey and did not form an actual travel purpose, so they are identified as invalid districts and counties and are removed.

[0048] During this process, the server removes invalid districts from the multiple transit districts, retaining only the remaining valid districts with sufficiently long stays as the basis for constructing cross-district travel results. It should be noted that the duration threshold here can be flexibly set according to the actual application scenario. For example, 30 minutes can be used as the criterion for distinguishing transit behavior from actual travel: if a user's continuous stay within the same district is less than 30 minutes, it is considered an invalid district with only a short stay and is not included in the cross-district travel statistics; otherwise, it is considered a valid district.

[0049] For example, such as Figure 2 As shown, a target user starts from district / county A, passes through district / county B, and finally arrives at district / county C. The server obtains the user's signaling records in districts / counties A, B, and C through spatial matching and calculates the duration of the user's stay in each district / county. Assume the user stays continuously in district / county A for 2 hours, in district / county B for only 15 minutes (e.g., due to highway transit or brief signal access), and in district / county C for 6 hours. In this case, the server identifies district / county B as an invalid district / county with a stay duration below the threshold and removes it from the list of transit districts / counties, retaining districts / counties A and C as valid travel nodes.

[0050] Furthermore, the server sorts the stay information of each valid district / county in ascending order according to the start time of stay, and constructs a complete travel record from the travel segments between two adjacent valid districts / counties. Each record includes fields such as the administrative division code of the departure district / county and the arrival district / county, the start and end times of stay, and the first and last locations of stay, ultimately forming a cross-district / county travel result that reflects the user's complete cross-district / county travel path.

[0051] Thus, by introducing a validity filtering mechanism in the time dimension, this method effectively eliminates false travel paths caused by instantaneous signal drift and brief stops along the way, improving the accuracy and practicality of the identification results. Therefore, the cross-district / county travel results here should be understood as structured data after sorting the stay information of multiple valid districts / counties in chronological order.

[0052] The study also found that when using mobile signaling data to identify railway travel, related technologies generally face the problem of a mismatch between the actual service area of ​​the train station and its original geographical boundaries. Specifically, the original area of ​​the train station only covers core facilities such as the station building and platforms, and it is difficult to cover the actual activity range of users during their journey to and from the station, such as surrounding roads, parking lots, and subway connection areas. Due to the uneven distribution of base stations, users may connect to peripheral base stations far from the station while entering and exiting the train station, causing their signaling points to not fall within the area where the train station is located and thus be missed. Therefore, directly using the original area for spatial matching may result in incomplete identification of railway travel samples, thereby affecting the accuracy of travel mode judgment.

[0053] In view of this, this embodiment also provides the following optional implementation methods for step S2: S2-4, Obtain railway station area data within the preset range.

[0054] Among them, the railway station area data records the areas where multiple railway stations are located.

[0055] S2-5 performs spatial matching of multiple signaling records with multiple train stations to obtain all signaling records generated by the target user at at least one train station.

[0056] S2-6: Based on all signaling records generated by the target user at at least one train station, obtain the target user's train travel results.

[0057] This embodiment can be understood as follows: the server performs a series of spatial matching, temporal aggregation and behavioral pattern recognition on multiple signaling records to identify the train travel result.

[0058] In practical applications, the server first acquires railway station area data within a preset range. This data, recorded in the form of a digital map, shows the spatial boundaries of all passenger railway stations nationwide, with each station corresponding to an identifiable geographical area. Then, it spatially matches multiple signaling records of the target user with this data. Any multiple signaling records that appear consecutively within the same railway station boundary are identified by the server as behavioral data generated by the user during their stay at that railway station. This allows the server to aggregate all signaling records generated by the user at at least one railway station.

[0059] Next, the server aggregates consecutive signaling at the same train station into a dwell time period, and determines the user's arrival time and departure time at the station based on this period; then, it combines this with the actual travel patterns of railway passengers to identify the train travel result.

[0060] For example, a real train journey usually has two clearly defined stations: the starting station and the destination station, and the journey is point-to-point. Therefore, in a continuous train journey, users generally do not stay for a long time at stations they do not pass through. The same user may have multiple independent train journeys in one day. Some journeys involve transfers, that is, arriving at different stations one after another but with close connections between them. And there is often a long waiting time at the departure station.

[0061] Based on the above rules, the server eliminates interference from short stops, passing through, pick-up and drop-off, and finally outputs a structured train travel result, which includes information such as the user's encrypted ID, departure station name, arrival time at departure station, departure time from departure station, arrival station name, arrival time at arrival station, departure time from arrival station, travel time, travel distance, and travel speed.

[0062] Furthermore, considering the varying sizes, surrounding road networks, and socio-economic development conditions of different train stations, relying solely on the original area is insufficient to fully reflect the signaling distribution characteristics generated during passenger entry and exit. Therefore, in this embodiment, the server can further expand the original area of ​​the train station outwards to construct an extended area that better reflects the actual area of ​​the train station. This extended area serves as the location of the train station, thereby improving the accuracy of identifying railway travel modes based on mobile signaling data. In this way, the extended area of ​​the train station overcomes the limitations of traditional static boundary delineation methods in spatial matching, enabling a more complete capture of the target user's actual behavioral trajectory while passing through the train station, thus improving the quality of generated train travel results.

[0063] Based on the extended areas of multiple railway stations obtained in the above embodiments, step S2 further includes: S2-6 spatially matches multiple signaling records with the extended areas of multiple train stations to obtain the signaling records of the target user at at least one train station they pass through.

[0064] S2-7: Based on the signaling records of the target user at at least one train station along the route, obtain the target user's train travel results.

[0065] Specifically, after obtaining the expanded area outside the train station, the server performs spatial association calculations on multiple signaling records of the target user, that is, it determines whether each signaling point falls within the expanded area of ​​any train station. If a signaling record is located within a certain expanded area, it is considered to be valid data generated at the corresponding train station, thereby obtaining the target user's signaling records at at least one train station.

[0066] During this process, the server further aggregates and processes signaling data that is spatially and temporally continuous within the same station, identifying the time points when users enter and leave the station, and extracting their station stay trajectory. For example, railway travel typically exhibits a point-to-point, station-to-station path pattern; during a complete railway trip, users generally do not stay for extended periods at stations they do not pass through; there may be transfers along the way; waiting times at departure stations are relatively long; and multiple discontinuous railway trips may occur within the same day.

[0067] Therefore, in practice, the server utilizes the aforementioned behavioral patterns to identify each independent railway journey, ultimately generating train travel results containing information such as the user's encrypted ID, departure station name, arrival time at the departure station, departure time from the departure station, arrival station name, arrival time at the arrival station, departure time from the arrival station, travel time, travel distance, and travel speed. In other words, the train travel results here reflect the user's actual railway travel route and key time points.

[0068] The study also found that when using mobile signaling data to identify air travel, there are problems such as the wide range of airports and the complex distribution of base stations, making it easy to misidentify non-passengers in the vicinity as air travelers if spatial matching is used alone.

[0069] In view of this, this embodiment also provides the following optional implementation methods for step S2: S2-8 spatially matches multiple signaling records with airport data within a preset range to obtain the signaling records of the target user at at least one airport, where the airport data records the areas where multiple airports are located; S2-9: Based on the signaling records of each airport, obtain the target user's stay information at the corresponding airport; S2-10: Based on multiple signaling records, the communication interruption period of the target user is obtained; S2-11 obtains air travel results based on the target user's stay information at each airport and the period of communication interruption.

[0070] This embodiment can be understood as follows: by integrating spatial matching and communication interruption features, an air travel result that can accurately identify air travel behavior is constructed.

[0071] In practical applications, the server can first spatially associate multiple signaling records of the target user with airport data within a preset range. The airport data records the vector boundaries of the areas where multiple airports are located. Therefore, by performing point-to-surface matching operations, it can be determined whether each signaling record falls within any airport area, thereby obtaining the user's signaling records at at least one airport.

[0072] During this process, the server further aggregates and processes signaling data that is continuous in time within the same airport spatial area, identifies the time nodes when users enter and leave the airport, and calculates the start and end times, duration, and key location information of their stay at the airport, forming the target user's stay information at the corresponding airport. Simultaneously, the server also detects periods of prolonged periods without signaling reports, i.e., communication interruption periods, based on the discontinuous time characteristics of multiple signaling records. This phenomenon typically occurs during flight, when the user's phone is switched off or in airplane mode, preventing the phone from connecting to the base station and resulting in a signaling gap.

[0073] In practice, the server analyzes airport location information and communication interruption periods to determine the transit route via aircraft. For example, if a user leaves an airport and immediately enters a prolonged communication interruption period (e.g., more than 30 minutes) without any signaling activity, and then signaling records reappear at another distant airport, it can be inferred that the user has completed air travel from the departure airport to the arrival airport. Based on the travel characteristics of air passengers—airport-to-airport, no signal in the air, and high travel speed—this path is determined to be a valid air trip.

[0074] Ultimately, the server generates a detailed table containing information such as the user's encrypted ID, departure airport name, arrival time at departure airport, departure time from departure airport, arrival airport name, arrival time at arrival airport, departure and arrival times at arrival airports, flight time, flight distance, and flight speed, which serves as the target user's air travel result.

[0075] Thus, potential air travelers are first identified by their geographical location at the airport, and then air travelers are identified by introducing the key identification factor of signaling interruption.

[0076] Based on the cross-county travel results, train travel results, and air travel results obtained from the above embodiments, we will continue to analyze... Figure 1 Step S3 will be explained below: S3 removes the travel routes corresponding to train and air travel results from the cross-county travel results to obtain the road travel results for the target user.

[0077] The research revealed that cross-county travel results constructed based on administrative divisions may simultaneously include results from multiple modes of transportation, such as road, rail, and air. Failure to differentiate between these modes can lead to misjudgments of users' actual travel behavior. Therefore, accurately removing independently identified rail and air journeys from mixed travel paths and extracting purely road travel results is crucial for identifying the connecting travel modes of target users.

[0078] Therefore, this embodiment provides the following optional implementation methods for step S3: S3-1, obtain the longest time intersection between cross-county travel results, train travel results, and air travel results; S3-2, remove the travel routes corresponding to the longest intersection from the cross-county travel results to obtain the highway travel results.

[0079] This embodiment can be understood as follows: by using an elimination method, the travel path with the longest time overlap with rail and air travel is removed from the mixed travel paths, thereby identifying the pure road travel path.

[0080] Specifically, cross-county travel results are cross-county travel records constructed based on administrative boundaries and user dwell time behavior. This includes all travel segments that meet the criteria across county-level administrative divisions, regardless of whether the mode of transport is road, rail, or air. Since road travel lacks the clear characteristics of train or air travel and its origins and destinations are widely distributed, making direct and independent identification difficult, the server employs an indirect extraction strategy. This involves first identifying rail and air travel results with obvious identifying features, then removing them from the cross-county travel results; the remaining portion is considered road travel results.

[0081] In practical applications, the server first performs correlation analysis between the generated train and air travel results and the cross-county travel results. To achieve accurate matching without compromising privacy, each result is based on the user's encrypted ID, and a unique identifier is added to each user's daily travel to distinguish multiple trips within the same day. Subsequently, the server performs Cartesian product correlation between the cross-county travel results and the train and air travel results respectively to establish candidate matching combinations.

[0082] During this process, the server calculates the time intersection of departure and arrival times for each pair of matching records and determines the duration of this intersection. For example, if the time range of a certain district / county travel record overlaps significantly with that of a certain railway travel record, it indicates that the cross-district movement is likely actually a railway trip rather than a road trip. To determine the optimal match, the server groups records according to the user's encrypted ID and the unique ID of the railway or air trip, filters out the record pairs with the longest time intersection, and removes these paths confirmed as railway or air trips from the cross-district / county travel results.

[0083] Thus, this embodiment aligns and deduplicates cross-county travel results by using the principle of maximum overlap in the time dimension. The final retained cross-county travel routes not covered by rail and air travel constitute the road travel results of the target user.

[0084] Based on the train travel results, air travel results, and road travel results obtained from the above embodiments, please refer to... Figure 1 Next, we will continue with... Figure 1 Step S4 will be explained below: S4 determines the connecting travel methods of the target user based on train travel results, air travel results, and road travel results.

[0085] It should be noted that train travel results, air travel results, and road travel results record multiple independent travel events that occurred to the target user at different times and locations. A user may use airplanes, trains, or roads multiple times a day, but these trips may not belong to the same itinerary; therefore, they cannot be simply superimposed to determine connecting travel behavior. Without distinguishing between time and spatial scope, it is easy to misjudge the user's connecting travel methods. In view of this, this embodiment provides the following optional implementation of step S4: S4-1 combines train travel results, air travel results, and road travel results into a complete travel result.

[0086] It should be understood that train travel results, air travel results, and road travel results are inherently discrete and unrelated. For example, a user might stop in County A in the morning, take a high-speed train to County B, and then drive from County B to County C in the afternoon. Previously, these might have been identified as one train trip and one road trip, but it hasn't yet been determined whether these two segments belong to the same trip. Therefore, the server first integrates these three independently identified travel events—train travel results, air travel results, and road travel results—into a unified, comprehensive travel result that includes all modes of transportation.

[0087] Based on the above explanation of the complete travel results, step S4 also includes: S4-2: Based on the length of time the target user stays in each administrative region, the destination of each trip of the target user is obtained.

[0088] The server determines the destination of each trip based on the length of time the target user stays within each administrative region. It should be understood that after completing a cross-regional trip, users usually stay at the destination or somewhere along the way for a considerable period of time for actual activities such as rest, work, and transfer preparation. Based on this travel pattern, the server considers a situation where the target user stays continuously in a certain region for more than 4 hours (this threshold is only an example and can be adjusted as needed) as the destination of this trip.

[0089] S4-3 divides the complete trip result into independent trip units by using the destination of each trip of the target user.

[0090] Using the endpoint determination results, the server further divides all travel segments in the complete travel result into several independent travel units with clearly defined start and end points, according to their chronological order and using each identified endpoint as a dividing point. For example, if the server finds that the target user stays in County D for more than 4 hours, it will classify all previous travel segments that were not assigned to other endpoints (including railway, air, or road records that occurred before County D and are temporally consecutive) into this travel unit with County D as the endpoint; if a subsequent stay in County E for more than 4 hours occurs again, it will be used as the new endpoint to construct the next travel unit.

[0091] S4-4. If a travel unit contains at least two modes of transportation, then the travel unit is determined to be a connecting travel unit.

[0092] Based on the travel units obtained in the above embodiments, the server retrieves the types of travel modes contained in each of the divided independent travel units. If the unit contains records from both train travel results and air travel results, or records from both road travel results and any one of them, then the server determines that the travel unit contains at least two travel modes. At this time, the server confirms that the travel unit belongs to a connecting trip.

[0093] Based on the same inventive concept as the transit mode identification method provided in this embodiment, this embodiment also provides a transit mode identification device. This device includes at least one software functional module that can be stored in a memory or embedded in an electronic device. The processor in the electronic device executes the executable module stored in the memory. For example, the software functional modules and computer programs included in the device. Please refer to... Figure 3 Functionally, the device may include: Signaling acquisition module 11 is used to acquire mobile phone signaling information to be processed by the target user; The travel identification module 12 is used to obtain the cross-county travel results, train travel results, and air travel results of the target user based on mobile phone signaling information; The travel identification module 12 is also used to delete the travel routes corresponding to train travel results and air travel results from the cross-county travel results to obtain the road travel results of the target user; The transit identification module 13 is used to determine the transit and connecting travel methods of the target user based on the results of train travel, air travel, and road travel.

[0094] In this embodiment, the signaling acquisition module 11 is used to implement Figure 1 In step S1, the travel identification module 12 is used to implement... Figure 1 Steps S2 and S3 in the process, the transit identification module is used to implement Figure 1 Step S4 in the above; therefore, for a detailed description of each of the above modules, please refer to the specific implementation of the corresponding steps.

[0095] Since it shares the same inventive concept as the transit mode identification method provided in this embodiment, the transit mode identification device can also implement other steps or sub-steps of the method through the above-mentioned modules.

[0096] Optionally, the mobile phone signaling information includes multiple signaling records, and the travel identification module 12 is also specifically used for: Multiple signaling records are spatially matched with administrative region data within a preset range to obtain the signaling records of the target user in multiple districts and counties they pass through; Based on the signaling records of each district and county through which the target user passes, the user’s residence information in the corresponding district and county through which the target user passes is obtained. Based on the target user's stay information in each district and county they pass through, cross-district and county travel results are obtained.

[0097] Optionally, the travel recognition module 12 is also specifically used for: Based on the target user's stay information in each district and county they pass through, invalid districts and counties with a stay duration lower than the duration threshold are identified; The invalid districts and counties are removed from the multiple transit districts and counties to obtain the remaining multiple valid districts and counties; Based on the residency information of each valid district / county, the results of cross-district / county travel are obtained.

[0098] Optionally, the mobile phone signaling information includes multiple signaling records, and the travel identification module 12 is also specifically used for: Obtain railway station area data within a preset range, where the railway station area data records the locations of multiple railway stations; Multiple signaling records are spatially matched with multiple train stations to obtain all signaling records generated by the target user at at least one train station; Based on all signaling records generated by the target user at at least one train station, the train travel results of the target user are obtained.

[0099] Optionally, the mobile phone signaling information includes multiple signaling records, and the travel identification module 12 is also specifically used for: Multiple signaling records are spatially matched with airport data within a preset range to obtain the signaling records of the target user at at least one airport. The airport data records the areas where multiple airports are located. Based on the signaling records of each airport, the target user's stay information at the corresponding airport is obtained; Based on multiple signaling records, the communication interruption period of the target user was obtained; Based on the target user's stay information at each airport and the period of communication interruption, air travel results are obtained.

[0100] Optionally, the travel recognition module 12 is also used for: Obtain the longest time intersection between cross-county travel results, train travel results, and air travel results; By removing the travel routes that intersect with the longest travel time from the cross-county travel results, the highway travel results are obtained.

[0101] Optionally, the transit identification module 13 is also specifically used for: Combine train travel results, air travel results, and road travel results into a complete travel result; Based on the length of time the target user stays in each administrative region, the destination of each trip of the target user is obtained; By utilizing the destination of each trip taken by the target user, the complete trip outcome is divided into independent trip units; If a travel unit contains at least two modes of transportation, it is determined to be a connecting travel unit.

[0102] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0103] It should also be understood that if the above embodiments are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0104] Therefore, this embodiment also provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, which, when executed by a processor, implements the transit and connecting travel mode identification method provided in this embodiment. The storage medium can be any medium capable of storing program code, such as a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0105] This embodiment also provides an electronic device for implementing a transit mode identification device. For example... Figure 4 As shown, the electronic device includes a processor 22 and a memory 21. The memory 21 stores a computer program, and the processor reads and executes the computer program corresponding to the above-described embodiments in the memory 21 to implement the transit and connecting travel mode identification method provided in this embodiment.

[0106] See also Figure 4 The electronic device also includes a communication unit 23. The memory 21, processor 22 and communication unit 23 are electrically connected to each other directly or indirectly through system bus 24 to realize data transmission or interaction.

[0107] The memory 21 can be an information recording device based on any electronic, magnetic, optical, or other physical principles, used to record execution instructions, data, etc. In some embodiments, the memory 21 can be, but is not limited to, volatile memory, non-volatile memory, memory drive, etc.

[0108] In some embodiments, the volatile memory may be random access memory (RAM); in some embodiments, the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, etc.; in some embodiments, the storage drive may be a disk drive, solid-state drive, any type of storage disk (such as optical disc, DVD, etc.), or similar storage media, or a combination thereof.

[0109] The communication unit 23 is used to send and receive data over a network. In some embodiments, the network may include a wired network, a wireless network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, or a near field communication (NFC) network, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and / or network switching nodes, through which one or more components of the service request processing system can connect to the network to exchange data and / or information.

[0110] The processor 22 may be an integrated circuit chip with signal processing capabilities, and may include one or more processing cores (e.g., a single-core processor or a multi-core processor). By way of example only, the processor described above may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction-set Processor (ASIP), a Graphics Processing Unit (GPU), a Physics Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computing (RISC) computer, or a microprocessor, or any combination thereof.

[0111] Understandable. Figure 4 The structure shown is for illustrative purposes only. Electronic devices may also have more advanced features. Figure 4 Showing more or fewer components, or having with Figure 4 The different configurations shown. Figure 4 The components shown can be implemented using hardware, software, or a combination thereof.

[0112] It should be understood that the apparatus and methods disclosed in the above embodiments can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0113] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for identifying connecting travel modes, characterized in that, The method includes: Obtain the mobile signaling information of the target user that is yet to be processed; Based on the mobile phone signaling information, the cross-county travel results, train travel results, and air travel results of the target user are obtained; The travel routes corresponding to the train travel results and air travel results are deleted from the cross-county travel results to obtain the road travel results of the target user; Based on the train travel results, the air travel results, and the road travel results, the connecting travel methods of the target user are obtained.

2. The method for identifying transit and connecting travel modes according to claim 1, characterized in that, The mobile phone signaling information includes multiple signaling records. Based on the mobile phone signaling information, the cross-county travel results of the target user are obtained, including: Spatially match the multiple signaling records with administrative region data within a preset range to obtain the signaling records of the target user in multiple districts and counties they pass through; Based on the signaling records of each of the counties and districts through which the target user passes, the residence information of the target user in the corresponding counties and districts through which the target user passes is obtained; The cross-county travel results are obtained based on the stay information of the target user in each district and county they pass through.

3. The method for identifying transit and connecting travel modes according to claim 2, characterized in that, Based on the target user's stay information in each district and county they pass through, the cross-district and county travel results are obtained, including: Based on the target user's stay information in each district and county they pass through, invalid districts and counties with a stay duration lower than the duration threshold are identified; The invalid districts and counties are removed from the multiple transit districts and counties to obtain the remaining multiple valid districts and counties; The cross-county travel results are obtained based on the residency information of each of the valid districts and counties.

4. The method for identifying transit and connecting travel modes according to claim 1, characterized in that, The mobile phone signaling information includes multiple signaling records. Based on the mobile phone signaling information, the train travel result of the target user is obtained, including: Obtain railway station area data within a preset range, wherein the railway station area data records the locations of multiple railway stations; The multiple signaling records are spatially matched with the multiple railway stations to obtain all signaling records generated by the target user at at least one railway station; Based on all signaling records generated by the target user at at least one train station, the train travel results of the target user are obtained.

5. The method for identifying transit and connecting travel modes according to claim 1, characterized in that, The mobile phone signaling information includes multiple signaling records. Based on the mobile phone signaling information, the target user's air travel results are obtained, including: The multiple signaling records are spatially matched with airport data within a preset range to obtain that the target user has generated signaling records at at least one airport, wherein the airport data records the areas where multiple airports are located; Based on the signaling records of each airport, the stay information of the target user at the corresponding airport is obtained; Based on the multiple signaling records, the communication interruption period of the target user is obtained; The air travel results are obtained based on the target user's stay information at each airport and the communication interruption period.

6. The method for identifying transit and connecting travel modes according to claim 1, characterized in that, The travel routes corresponding to the train travel results and air travel results are deleted from the cross-county travel results to obtain the target user's road travel results, including: Obtain the longest time intersection between the cross-county travel results and the train and air travel results; The travel path corresponding to the longest intersection time is deleted from the cross-county travel results to obtain the highway travel results.

7. The method for identifying transit and connecting travel modes according to claim 1, characterized in that, Based on the train travel results, the air travel results, and the road travel results, the connecting travel methods of the target user are obtained, including: The train travel results, the air travel results, and the road travel results will be combined into a complete travel result. Based on the length of stay of the target user in each administrative region, the destination of each trip of the target user is obtained; By utilizing the destination of each trip of the target user, the complete trip result is divided into independent trip units; If the travel unit contains at least two modes of transportation, then the travel unit is determined to be a connecting travel unit.

8. A device for identifying connecting travel modes, characterized in that, The device includes: The signaling acquisition module is used to acquire the mobile signaling information of the target user that is yet to be processed. The travel identification module is used to obtain the cross-county travel results, train travel results, and air travel results of the target user based on the mobile phone signaling information; The travel identification module is also used to delete the travel routes corresponding to the train travel results and air travel results from the cross-county travel results to obtain the road travel results of the target user; The transit identification module is used to obtain the transit and connecting travel methods of the target user based on the train travel results, the air travel results, and the road travel results.

9. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the transit and connecting travel mode identification method according to any one of claims 1-7.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing a computer program that, when executed by the processor, implements the transit and connecting travel mode identification method according to any one of claims 1-7.

Images