Travel track identification method, apparatus and device, storage medium and product

Abstract

The invention discloses a travel track identification method, device and equipment, a storage medium and a product, and relates to the technical field of data processing, and the method comprises the steps: determining a residence segment and a vehicle travel feature according to the terminal signaling data of a user; generating a target vehicle travel sequence according to the resident section and the vehicle travel characteristics; based on a target trajectory recognition model, according to the target vehicle travel sequence, performing travel trajectory recognition; through the above mode, the track record data is obtained according to the terminal signaling data of the user, then the resident section and the traffic tool travel characteristics are determined according to the modified track record data, the user track sequence of real traffic tool travel distribution is generated, and the user track sequence of the complex and irregular traffic tool travel sequence can be obtained. The target trajectory recognition model with extremely high learning ability and expansibility is adopted to recognize the travel trajectory, so that the dependence of vehicle travel trajectory recognition on data is reduced, and the accuracy of recognizing the travel trajectory can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to travel trajectory identification methods, devices, equipment, storage media and products. Background Art

[0002] At present, the common method for identifying the travel trajectory of transportation tools is to use data such as card swiping records and trajectory records, and adopt the association between the two application rules, statistics or machine learning algorithms. However, card swiping records are often difficult to obtain, and the coverage of card swiping records is not comprehensive. At the same time, card swiping records greatly limit the itinerary segments of candidate public transportation trips, and there are also influencing factors such as the complex and irregular trajectory of transportation tools. Therefore, the accuracy of identifying travel trajectories by the above methods is low.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a travel trajectory identification method, device, equipment, storage medium and product, aiming to solve the technical problem of low accuracy in identifying travel trajectories in the prior art.

[0005] To achieve the above objectives, the present application proposes a travel trajectory identification method, the method comprising:

[0006] Obtain the user's terminal signaling data;

[0007] Determine the residence segment and the travel characteristics of the vehicle according to the terminal signaling data;

[0008] Generate a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics;

[0009] The travel trajectory is identified according to the travel sequence of the target vehicle based on the target trajectory identification model.

[0010] In one embodiment, the step of determining the residence segment and the travel characteristics of the vehicle according to the terminal signaling data includes:

[0011] Obtaining the time each user has been in the base station and the time when each user entered the base station according to the terminal signaling data;

[0012] Generate trajectory record data according to the time each user spends in the base station and the time they enter the base station;

[0013] Calculating the moving speed of each track relative to the previous track and the moving speed of each track relative to the next track according to the track record data;

[0014] Modifying the track record data according to the moving speed of each track and the previous track, and the moving speed of each track and the next track;

[0015] When there is no data missing in the modified trajectory record data, the residence segment and the vehicle travel characteristics are determined according to the modified trajectory record data.

[0016] In one embodiment, the step of determining the dwell segment and the vehicle travel characteristics according to the modified trajectory record data comprises:

[0017] The target vertex sequence record data is obtained according to the transportation station data table and the bus station adjacent information table through the target dynamic programming algorithm;

[0018] Generate a mapping table between base stations and transportation sites according to the coverage range of each base station;

[0019] Divide the modified trajectory record data into travel segments to obtain trajectory record data for each travel segment;

[0020] Determine the resident segment according to the target vertex sequence record data, the mapping table between the base station and the transportation vehicle station, and the trajectory record data of each travel segment;

[0021] Determine transportation travel characteristics based on historical transportation travel data.

[0022] In one embodiment, the step of generating a target vehicle travel sequence according to the dwell segment and the vehicle travel characteristics comprises:

[0023] Determine the travel trajectory screening criteria by investigating travel literature on transportation tools;

[0024] Determine a candidate vehicle travel trajectory based on the travel trajectory screening condition according to the resident segment and the vehicle travel characteristics;

[0025] Obtaining the starting and ending points of the candidate transportation travel trajectory;

[0026] A target transportation tool travel sequence is generated according to the starting and ending points of the candidate transportation tool travel trajectory and a dynamic planning table of each site.

[0027] In one embodiment, the step of identifying the travel trajectory according to the travel sequence of the target vehicle based on the target trajectory recognition model includes:

[0028] Identifying a target vehicle travel segment according to the target vehicle travel sequence based on a target trajectory recognition model;

[0029] Acquire a base station sequence corresponding to the target vehicle travel segment;

[0030] Merge identical sites according to the base station sequence;

[0031] A target vehicle travel trajectory is generated according to the merged sites and the target vehicle travel segment based on a dynamic planning table of each site.

[0032] In one embodiment, before the step of identifying the travel trajectory according to the target vehicle travel sequence based on the target trajectory recognition model, the method further includes:

[0033] Obtaining a target path according to the starting and ending points of the candidate transportation travel trajectory and a path dynamic planning table;

[0034] Generate a simulated transportation tool sequence according to the target path and the candidate transportation tool travel trajectory through a random mode;

[0035] Generate trajectory statement data for each user based on the travel segment;

[0036] Generate positive and negative training samples according to the simulated vehicle sequence, the candidate vehicle sequence and the trajectory statement data;

[0037] The target trajectory recognition model is trained according to the positive and negative training samples based on a preset model.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a travel trajectory identification device, the travel trajectory identification device comprising:

[0039] An acquisition module is used to acquire the user's terminal signaling data;

[0040] A determination module, used to determine the resident segment and the travel characteristics of the vehicle according to the terminal signaling data;

[0041] A generating module, configured to generate a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics;

[0042] The recognition module is used to recognize the travel trajectory according to the travel sequence of the target vehicle based on the target trajectory recognition model.

[0043] In addition, to achieve the above-mentioned purpose, the present application also proposes a travel trajectory identification device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the travel trajectory identification method described above.

[0044] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the travel trajectory identification method described above are implemented.

[0045] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the travel trajectory identification method described above are implemented.

[0046] One or more technical solutions proposed in the present application have at least the following technical effects: by obtaining the user's terminal signaling data; determining the resident segment and the vehicle travel characteristics according to the terminal signaling data; generating a target vehicle travel sequence according to the resident segment and the vehicle travel characteristics; identifying the travel trajectory according to the target vehicle travel sequence based on the target trajectory recognition model; in the above manner, the trajectory record data is obtained according to the user's terminal signaling data, and then the resident segment and the vehicle travel characteristics are determined according to the modified trajectory record data, and then the user trajectory sequence of the real vehicle travel distribution, that is, the target vehicle travel sequence, is generated, and for such a complex and irregular travel sequence of vehicles, a target trajectory recognition model with strong learning ability and scalability is used to identify the travel trajectory, which reduces the dependence of the vehicle travel trajectory recognition on data, thereby effectively improving the accuracy of identifying the travel trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 A flow chart of the first embodiment of the travel trajectory identification method of the present application;

[0050] Figure 2 A schematic diagram of a flow chart of generating a simulated transportation tool sequence for the travel trajectory identification method provided in Example 1 of the present application;

[0051] Figure 3 A flow chart of the second embodiment of the travel trajectory identification method of the present application;

[0052] Figure 4 This is a schematic diagram of the module structure of the travel trajectory identification device according to an embodiment of the present application;

[0053] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the travel trajectory identification method in the embodiment of the present application.

[0054] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a travel trajectory recognition device, etc. The following takes the travel trajectory recognition device as an example to illustrate this embodiment and the following embodiments.

[0056] Based on this, the present application embodiment provides a travel trajectory identification method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the travel trajectory identification method of the present application.

[0057] In this embodiment, the travel trajectory identification method includes steps S10 to S40:

[0058] Step S10, obtaining the user's terminal signaling data.

[0059] It should be noted that the user's terminal signaling data includes but is not limited to trajectory, transportation station routes, etc. The terminal can be a mobile phone, and the transportation can be a bus, subway or shuttle bus, etc. The terminal signaling data will also record the length of time each user is at a certain base station.

[0060] Step S20, determining the residence segment and the travel characteristics of the vehicle according to the terminal signaling data.

[0061] It can be understood that the resident segment represents that the user's trajectory data continuously stays at a certain location, and the vehicle travel characteristics include but are not limited to the average travel speed of the vehicle, the average travel distance of the vehicle, and the average travel time of the vehicle.

[0062] Furthermore, in order to effectively improve the accuracy of determining the resident segment, step S20 includes: obtaining the duration of each user at the base station and the time of entering the base station according to the terminal signaling data; generating trajectory recording data according to the duration of each user at the base station and the time of entering the base station; calculating the moving speed of each trajectory relative to the previous trajectory and the moving speed of each trajectory relative to the next trajectory according to the trajectory recording data; modifying the trajectory recording data according to the moving speed of each trajectory relative to the previous trajectory and the moving speed of each trajectory relative to the next trajectory; when there is no data missing in the modified trajectory recording data, determining the resident segment and the travel characteristics of the vehicle according to the modified trajectory recording data.

[0063] It should be understood that the trajectory recording data includes but is not limited to the user's unique identification ID, the base station's unique identification ID, the trajectory recording start time, the trajectory recording end time, the base station longitude and the base station latitude, etc. After obtaining the user's terminal signaling data, the terminal signaling data records the length of time each (user) spends in a certain base station, and the base stations are sorted according to the time of entry, and the time of entering the next base station is recorded as the departure time of the previous base station to form the trajectory recording data.

[0064] It is understandable that after the trajectory record data is generated, it will be grouped according to users and sorted by start time from early to late, and then the trajectory record data will be modified. The modification method includes but is not limited to elimination, filling, etc. Specifically, the moving speed of each trajectory relative to the previous trajectory and the moving speed relative to the next trajectory is calculated, and the records whose speed between the i-th trajectory and the i-1-th trajectory is greater than a preset threshold are eliminated. The preset threshold can be set to 60km / h, and then it is determined whether there is data missing in the modified trajectory record data. If not, the residence segment and vehicle travel characteristics are determined based on the modified trajectory record data. If so, the most recent timestamp record is used for filling.

[0065] Furthermore, in order to effectively improve the accuracy of determining the stay segments and vehicle travel characteristics, the step of determining the stay segments and vehicle travel characteristics based on the modified trajectory record data includes: obtaining target vertex sequence record data based on the vehicle station data table and the bus station adjacent information table through a target dynamic programming algorithm; generating a mapping table between base stations and vehicle stations based on the coverage range of each base station; dividing the modified trajectory record data into travel segments to obtain trajectory record data for each travel segment; determining the stay segments based on the target vertex sequence record data, the mapping table between base stations and vehicle stations, and the trajectory record data for each travel segment; and determining vehicle travel characteristics based on historical vehicle travel data.

[0066] It can be understood that the target vertex sequence record data refers to the vertex sequence record that records the shortest path from the source vertex to all other vertices. The target dynamic programming algorithm can be the Floyd (Warren Floyd, Floyd) algorithm, wherein the transportation station data table includes but is not limited to the transportation station unique identification ID, the transportation station longitude and the transportation station dimension, etc., and the bus station adjacent information table includes but is not limited to the transportation station unique identification ID, the next stop transportation station unique identification ID and the transportation route, etc.

[0067] It should be understood that the base station coverage range can be 200-500m, and the initialization distance threshold can be set to 500m. At this time, it is cyclically determined whether the distance between each base station and the site is less than the initialization distance threshold. If so, a mapping relationship between the transportation site and the base station is generated to complete the first mapping. Considering that there are few users in the base stations in remote areas, base station construction is more important than signal coverage, and the maximum value of the base station coverage range may exceed 500m. Therefore, it is necessary to re-traverse the records of empty base stations mapped by the site, and the initialization distance threshold is the distance of the nearest base station of the site and expand 100m to update the mapping to complete the second mapping. After the mapping is completed, the user's trajectory data is divided into travel segments, and each trajectory data is circulated. If the center distance of the current travel segment is less than the initialization distance threshold, the cumulative time of the current travel segment is updated, and the center position of the current travel segment is updated. Otherwise, the update of the travel segment is terminated, and the next new travel segment is initialized with the trajectory record until the last record ends the cycle, and the travel segment with a cumulative time greater than the preset duration is identified as a resident segment, which can be 20 minutes.

[0068] It can be understood that, referring to Table 1, Table 1 is the trajectory record data of each travel segment, specifically:

[0069] Table 1:

[0070]

[0071] First, traverse the first trajectory record, initialize the first resident segment information, traverse the second record, calculate the distance to the current resident segment information, less than the 500m threshold, and update the current resident segment information (end time and longitude and latitude). Among them, calculating the distance to the current resident segment information means: calculating the distance between the corresponding position of the longitude and latitude in the record and the longitude and latitude of the resident segment of the current record. Throughout the entire loop, the current resident segment is constantly updated, and then the resident segment that meets the conditions is retained, and the current resident segment is reinitialized. Next, traverse the second trajectory record, calculate the distance to the current resident segment information, less than the 500m threshold, and update the current resident segment information (end time and longitude and latitude). Among them, calculating the distance to the current resident segment information means: calculating the distance between the corresponding position of the longitude and latitude in the record and the longitude and latitude of the resident segment of the current record. Throughout the entire loop, the current resident segment is constantly updated, and then the resident segment that meets the conditions is retained, and the current resident segment is reinitialized.

[0072] Next, traverse the third trajectory record and calculate the distance to the current resident segment information. If the distance is greater than 500m and the time is greater than 5 minutes, store the current resident segment information in the result table, and initialize the current resident segment information with the third trajectory record. Continue to traverse the fourth trajectory record and calculate the distance to the current resident segment information. If the distance is greater than 500m and the time is less than 5 minutes, do not process the next record until the end of the loop.

[0073] Step S30: generating a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics.

[0074] It can be understood that the target vehicle travel sequence refers to the sequence of passenger trajectories of the actual vehicle travel distribution. After determining the residence segment and vehicle travel characteristics, the target vehicle travel sequence is generated according to the starting and ending points of the candidate vehicle travel trajectories and the dynamic planning table of each station. The dynamic planning table can be a Floyd table.

[0075] Step S40 , identifying the travel trajectory according to the travel sequence of the target vehicle based on the target trajectory recognition model.

[0076] It should be understood that the target trajectory recognition model refers to a model for identifying travel trajectories. After obtaining the travel sequence of the target vehicle, the target trajectory recognition model is used to identify the travel trajectory and to infer the appearance mode of the vehicle, for example, to identify that the user's travel mode is public transportation.

[0077] Furthermore, in order to effectively improve the efficiency and accuracy of training the target trajectory recognition model, before step S40, it also includes: obtaining the target path according to the starting and ending points of the candidate vehicle travel trajectory and the path dynamic planning table; generating a simulated vehicle sequence according to the target path and the candidate vehicle travel trajectory through a random mode; generating trajectory statement data for each user according to the journey segment; generating positive and negative training samples according to the simulated vehicle sequence, the candidate vehicle sequence and the trajectory statement data; and training the target trajectory recognition model according to the positive and negative training samples based on a preset model.

[0078] It can be understood that the path dynamic planning table can be a dynamic planning shortest path table. After obtaining the starting and ending points of the selected transportation tool travel trajectory, the path dynamic planning table is combined to obtain the target path, which represents the shortest path passing through the station. Then, a random mode is used to generate a simulated transportation tool sequence according to the candidate transportation tool travel trajectory. Figure 2 , Figure 2 The flowchart for generating a simulated transportation tool sequence is as follows: after determining the target path S, determine whether it is the last station. If so, randomly select the base station mapped by the station and randomly generate the arrival time, and add the above base station and arrival time to the initial simulation sequence Sˋ to generate a simulated transportation tool sequence. If not, randomly mask 15% of the stations in the simulated transportation tool sequence Sˋ and return to the initial simulation sequence Sˋ. On the one hand, the signal interaction between the user and the base station may not always exist, and on the other hand, the base station data itself is missing, so consider randomly masking the generated sequence. Replacing the set bus speed with the average speed of the candidate bus travel segment can reduce the impact of different road conditions and different times (morning and evening peaks), as well as randomly masking stations, which can reduce the impact of low base station data quality and user signals.

[0079] It should be noted that the parameters used for randomly generating the arrival time are the distance to the previous station and the average speed of the candidate section. In addition, if it is a transfer station, a randomly generated transfer time of 0-30 minutes is added, where the distribution of transfer time conforms to a Gaussian distribution with a mean of 10 and a variance of 5. The reason for not using a fixed travel speed is the influencing factors of peak hours in the morning and evening and complex road conditions.

[0080] It should be understood that after obtaining each travel segment, the trajectory sentence data of each user is generated according to the travel segment. For example, given a set of user trajectories, the sentence data is represented as C={C 0 ,C 1 ,...C n},in, represents the trajectory statement data of a single user, s represents the number of sets after 101.4, and j represents the number of base stations in the set. It is represented as the jth base station ID of the sth set of the ith user.

[0081] It is understandable that after obtaining the trajectory statement data of each user, training generates positive and negative training samples, where the positive training sample can be a simulated transportation sequence. Because the trajectory data of users in the region for one week is accumulated, it basically covers all possible travel origins and destinations, and the amount of data can reflect the distribution of transportation travel in the city to a certain extent. Finally, the positive and negative samples are processed into a 1-minute slice base station sequence, and the number of positive samples is used as the standard, and the sampling or expansion of negative samples is 1:1.

[0082] It should be noted that the structure of the preset model is divided into an input part, a decoder part, and an output part. The input part is a word embedding, a position encoding layer, and a selection of sine and cosine function encodings; the decoding part is a plurality of decoding layers, each of which contains a plurality of multi-head self-attentions, a fully connected forward feedback network, a residual link, and a layer normalization; the classification part receives the representation input of the last decoding layer and connects to the mapping of a fully connected layer. After the softmax activation function, the output belongs to the probability of a vehicle trip. The preset model back-propagates all parameters through the cross entropy loss function to complete the iteration. In addition, the cross entropy function of the binary classification is shown in the following formula:

[0083]

[0084] Among them, y represents the true label value (the value is 0 or 1), Represents the probability that the target trajectory recognition model predicts that it belongs to category 1.

[0085] It should be noted that based on the characteristics of transformers and through the above process, a large amount of sample training data can be generated. Therefore, the preset model can continuously stack decoding modules according to the actual computing power, or refer to various sequence learning large models to expand the scale and improve recognition accuracy.

[0086] Furthermore, in order to effectively improve the accuracy of generating the travel trajectory of the target vehicle, step S40 includes: identifying the target vehicle travel segment according to the target vehicle travel sequence based on the target trajectory recognition model; obtaining the base station sequence corresponding to the target vehicle travel segment; merging the same sites according to the base station sequence; and generating the target vehicle travel trajectory according to the merged sites and the target vehicle travel segment based on the dynamic planning table of each site.

[0087] It should be understood that after the target trajectory recognition model is trained, the target trajectory recognition model is used to identify the target vehicle travel segment, and then the base station sequence corresponding to the target vehicle travel segment is determined, and after merging the same stations, the path is completed according to the dynamic planning table of each station to generate the target vehicle travel trajectory. The parameters carried by the target vehicle travel trajectory also include user ID, start time, end time, starting station and end station, etc.

[0088] This embodiment obtains the user's terminal signaling data; determines the resident segment and the vehicle travel characteristics according to the terminal signaling data; generates a target vehicle travel sequence according to the resident segment and the vehicle travel characteristics; and identifies the travel trajectory according to the target vehicle travel sequence based on a target trajectory recognition model; in the above manner, trajectory record data is obtained according to the user's terminal signaling data, and then the resident segment and the vehicle travel characteristics are determined according to the modified trajectory record data, and then the user trajectory sequence of the real vehicle travel distribution, that is, the target vehicle travel sequence, is generated, and for such a complex and irregular travel sequence of vehicles, a target trajectory recognition model with strong learning ability and scalability is used to identify the travel trajectory, which reduces the dependence of vehicle travel trajectory recognition on data, thereby effectively improving the accuracy of identifying travel trajectories.

[0089] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , step S30 includes steps S301 to S304:

[0090] Step S301, determining travel trajectory screening conditions by investigating travel documents on transportation tools.

[0091] It should be noted that the transportation travel document refers to the document related to transportation travel written by professionals, and the transportation travel document can be public transportation travel document. The travel trajectory screening condition refers to the condition for screening the travel segment where the possibility of transportation vehicles appearing is relatively small, and the screening condition can be an average travel speed of 5-30km / h, an average travel distance of 1-15km, and an average travel time of 10-50min.

[0092] Step S302 : determining a candidate vehicle travel trajectory based on the travel trajectory screening condition according to the resident segment and the vehicle travel characteristics.

[0093] It can be understood that after the travel segments are screened using the travel trajectory screening conditions, a candidate vehicle travel trajectory is determined according to the resident segment and the vehicle travel characteristics, wherein the candidate vehicle travel trajectory includes multiple candidate vehicle travel segments.

[0094] Step S303, obtaining the starting and ending points of the candidate transportation travel trajectory.

[0095] Step S304: generating a target transportation travel sequence according to the starting and ending points of the candidate transportation travel trajectories and a dynamic planning table of each station.

[0096] It can be understood that after obtaining the starting and ending points of the candidate transportation travel trajectories, for each candidate transportation travel trajectory, the longitude and latitude of the starting and ending points are used to match the nearest transportation station to determine the starting transportation station, and then the dynamic planning table of each station is queried to filter out the travel segments with existing paths and update them to transportation travel segments. If there are multiple travel segments with existing paths, all possible routes can be retained when generating the transportation travel sequence, and then the target transportation travel sequence can be generated.

[0097] This embodiment determines travel trajectory screening conditions by investigating travel literature on vehicles; determines candidate vehicle travel trajectories based on the travel trajectory screening conditions according to the residence segments and the travel characteristics of the vehicles; obtains the starting and ending points of the candidate vehicle travel trajectories; generates a target vehicle travel sequence according to the starting and ending points of the candidate vehicle travel trajectories and the dynamic planning table of each station; through the above method, after determining the travel trajectory screening conditions, the travel segments are screened, and after obtaining the starting and ending points of the candidate vehicle travel trajectories, the target vehicle travel sequence is generated in combination with the dynamic planning table of each station, thereby effectively improving the accuracy of generating the target vehicle travel sequence.

[0098] This application also provides a travel trajectory identification device, please refer to Figure 4 , the travel trajectory identification device comprises:

[0099] The acquisition module 10 is used to acquire the terminal signaling data of the user.

[0100] The determination module 20 is used to determine the residence segment and the travel characteristics of the vehicle according to the terminal signaling data.

[0101] The generating module 30 is used to generate a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics.

[0102] The recognition module 40 is used to recognize the travel trajectory according to the travel sequence of the target vehicle based on the target trajectory recognition model.

[0103] This embodiment obtains the user's terminal signaling data; determines the resident segment and the vehicle travel characteristics according to the terminal signaling data; generates a target vehicle travel sequence according to the resident segment and the vehicle travel characteristics; and identifies the travel trajectory according to the target vehicle travel sequence based on a target trajectory recognition model; in the above manner, trajectory record data is obtained according to the user's terminal signaling data, and then the resident segment and the vehicle travel characteristics are determined according to the modified trajectory record data, and then the user trajectory sequence of the real vehicle travel distribution, that is, the target vehicle travel sequence, is generated, and for such a complex and irregular travel sequence of vehicles, a target trajectory recognition model with strong learning ability and scalability is used to identify the travel trajectory, which reduces the dependence of vehicle travel trajectory recognition on data, thereby effectively improving the accuracy of identifying travel trajectories.

[0104] The travel trajectory identification device provided by the present application adopts the travel trajectory identification method in the above embodiment, which can solve the technical problem of low accuracy in identifying travel trajectories in the prior art. Compared with the prior art, the beneficial effects of the travel trajectory identification device provided by the present application are the same as the beneficial effects of the travel trajectory identification method provided by the above embodiment, and other technical features in the travel trajectory identification device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0105] In one embodiment, the determination module 20 is further used to obtain the time each user spends in the base station and the time of entering the base station according to the terminal signaling data; generate trajectory recording data according to the time each user spends in the base station and the time of entering the base station; calculate the moving speed of each trajectory compared with the previous trajectory, and the moving speed of each trajectory compared with the next trajectory according to the trajectory recording data; modify the trajectory recording data according to the moving speed of each trajectory compared with the previous trajectory, and the moving speed of each trajectory compared with the next trajectory; when there is no data missing in the modified trajectory recording data, determine the resident segment and vehicle travel characteristics according to the modified trajectory recording data.

[0106] In one embodiment, the determination module 20 is also used to obtain target vertex sequence record data according to the transportation site data table and the bus site adjacent information table through a target dynamic programming algorithm; generate a mapping table between base stations and transportation sites according to the coverage range of each base station; divide the modified trajectory record data into travel segments to obtain trajectory record data for each travel segment; determine the resident segment according to the target vertex sequence record data, the mapping table between base stations and transportation sites, and the trajectory record data for each travel segment; and determine the travel characteristics of the vehicle according to the historical vehicle travel data.

[0107] In one embodiment, the generation module 30 is also used to determine travel trajectory screening conditions by investigating travel literature on vehicles; determine candidate travel trajectories based on the travel trajectory screening conditions according to the residence segment and the travel characteristics of the vehicle; obtain the starting and ending points of the candidate travel trajectories; and generate a target vehicle travel sequence based on the starting and ending points of the candidate travel trajectories and a dynamic planning table of each station.

[0108] In one embodiment, the recognition module 40 is also used to obtain a target path based on the starting and ending points of the candidate vehicle travel trajectory and a path dynamic planning table; generate a simulated vehicle sequence based on the target path and the candidate vehicle travel trajectory through a random mode; generate trajectory statement data for each user based on the journey segment; generate positive and negative training samples based on the simulated vehicle sequence, the candidate vehicle sequence and the trajectory statement data; and train a target trajectory recognition model based on the positive and negative training samples based on a preset model.

[0109] In one embodiment, the identification module 40 is also used to identify the target vehicle travel segment according to the target vehicle travel sequence based on the target trajectory identification model; obtain the base station sequence corresponding to the target vehicle travel segment; merge the same sites according to the base station sequence; and generate the target vehicle travel trajectory according to the merged sites and the target vehicle travel segment based on the dynamic planning table of each site.

[0110] The present application provides a travel trajectory identification device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the travel trajectory identification method in the above-mentioned embodiment 1.

[0111] Reference below Figure 5 , which shows a schematic diagram of the structure of a travel trajectory identification device suitable for implementing the embodiment of the present application. The travel trajectory identification device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The travel trajectory identification device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0112] like Figure 5 As shown, the travel trajectory recognition device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the travel trajectory recognition device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the travel trajectory identification device to communicate with other devices wirelessly or wired to exchange data. Although the figure shows a travel trajectory identification device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0113] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0114] The travel trajectory recognition device provided by the present application adopts the travel trajectory recognition method in the above embodiment, which can solve the technical problem of low accuracy in identifying travel trajectories in the prior art. Compared with the prior art, the beneficial effects of the travel trajectory recognition device provided by the present application are the same as the beneficial effects of the travel trajectory recognition method provided by the above embodiment, and other technical features in the travel trajectory recognition device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0115] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0116] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0117] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the travel trajectory identification method in the above-mentioned embodiment.

[0118] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0119] The computer-readable storage medium may be included in the travel trajectory recognition device; or may exist independently without being assembled into the travel trajectory recognition device.

[0120] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0123] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned travel trajectory recognition method, and can solve the technical problem of low accuracy in identifying travel trajectories in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the travel trajectory recognition method provided in the above-mentioned embodiment, and will not be repeated here.

[0124] The present application also provides a computer program product, including a computer program, which implements the steps of the travel trajectory identification method as described above when executed by a processor.

[0125] The computer program product provided by the present application can solve the technical problem of low accuracy in identifying travel trajectories in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the travel trajectory identification method provided by the above embodiment, which will not be described in detail here.

[0126] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A travel trajectory identification method, characterized in that: The method comprises: Obtain the user's terminal signaling data; Determine the residence segment and the travel characteristics of the vehicle according to the terminal signaling data; Generate a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics; The travel trajectory is identified according to the travel sequence of the target vehicle based on the target trajectory identification model.

2. The method according to claim 1, characterized in that The step of determining the resident segment and the travel characteristics of the vehicle according to the terminal signaling data comprises: Obtaining the time each user has been in the base station and the time when each user entered the base station according to the terminal signaling data; Generate trajectory record data according to the time each user spends in the base station and the time they enter the base station; Calculating the moving speed of each track relative to the previous track and the moving speed of each track relative to the next track according to the track record data; Modifying the track record data according to the moving speed of each track and the previous track, and the moving speed of each track and the next track; When there is no data missing in the modified trajectory record data, the residence segment and the vehicle travel characteristics are determined according to the modified trajectory record data.

3. The method according to claim 2, characterized in that The step of determining the residence segment and the vehicle travel characteristics according to the modified trajectory record data comprises: The target vertex sequence record data is obtained according to the transportation station data table and the bus station adjacent information table through the target dynamic programming algorithm; Generate a mapping table between base stations and transportation sites according to the coverage range of each base station; Divide the modified trajectory record data into travel segments to obtain trajectory record data for each travel segment; Determine the resident segment according to the target vertex sequence record data, the mapping table between the base station and the transportation vehicle station, and the trajectory record data of each travel segment; Determine transportation travel characteristics based on historical transportation travel data.

4. The method according to claim 1, characterized in that The step of generating a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics comprises: Determine the travel trajectory screening criteria by investigating travel literature on transportation tools; Determine a candidate vehicle travel trajectory based on the travel trajectory screening condition according to the resident segment and the vehicle travel characteristics; Obtaining the starting and ending points of the candidate transportation travel trajectory; A target transportation tool travel sequence is generated according to the starting and ending points of the candidate transportation tool travel trajectory and a dynamic planning table of each site.

5. The method according to claim 1, characterized in that The step of identifying the travel trajectory according to the target vehicle travel sequence based on the target trajectory recognition model includes: Identifying a target vehicle travel segment according to the target vehicle travel sequence based on a target trajectory recognition model; Acquire a base station sequence corresponding to the target vehicle travel segment; Merge identical sites according to the base station sequence; A target vehicle travel trajectory is generated according to the merged sites and the target vehicle travel segment based on a dynamic planning table of each site.

6. The method according to any one of claims 1 to 5, characterized in that Before the step of identifying the travel trajectory according to the travel sequence of the target vehicle based on the target trajectory recognition model, the method further includes: Obtaining a target path according to the starting and ending points of the candidate transportation travel trajectory and a path dynamic planning table; Generate a simulated transportation tool sequence according to the target path and the candidate transportation tool travel trajectory through a random mode; Generate trajectory statement data for each user based on the travel segment; Generate positive and negative training samples according to the simulated vehicle sequence, the candidate vehicle sequence and the trajectory statement data; The target trajectory recognition model is trained according to the positive and negative training samples based on a preset model.

7. A travel trajectory identification device, characterized in that: The device comprises: An acquisition module is used to acquire the user's terminal signaling data; A determination module, used to determine the resident segment and the travel characteristics of the vehicle according to the terminal signaling data; A generating module, configured to generate a target vehicle travel sequence according to the residence segment and the vehicle travel characteristics; The recognition module is used to recognize the travel trajectory according to the travel sequence of the target vehicle based on the target trajectory recognition model.

8. A travel trajectory identification device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the travel trajectory identification method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the travel trajectory identification method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the travel trajectory identification method according to any one of claims 1 to 6 are implemented.

Images