Intelligent identification method, device and equipment of transportation mode and storage medium

Abstract

The invention discloses an intelligent identification method, device and equipment of a transportation mode and a storage medium. Comprising the following steps: collecting LBS position data of a user; extracting travel feature data of the user based on the LBS position data; based on the travel speed in the travel feature data and matching information of speed intervals corresponding to a plurality of to-be-identified travel modes, obtaining an identified initial travel mode; inputting the travel feature data and the initial travel mode into a preset discrimination model, and outputting an identified traffic travel mode; the discrimination model comprises a subway discrimination sub-module, a driving discrimination sub-module, a bus discrimination sub-module, a walking discrimination sub-module and a riding discrimination sub-module. According to the method, the LBS position data, the vehicle-mounted Bluetooth connection data and the travel characteristics of different traffic modes are combined to identify the travel mode of the user. The identification accuracy and efficiency can be improved, and powerful technical support can be provided for intelligent traffic management and planning on the premise of protecting user privacy.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and more specifically, to an intelligent identification method, device, equipment and storage medium for transportation travel modes. Background Art

[0002] With the acceleration of urbanization, the continuous growth of traffic flow, and the increasing demand for travel efficiency and convenience, intelligent transportation systems have become an important part of urban development. Intelligent transportation systems use advanced information technology, data communication transmission technology, electronic sensing technology, control technology, and computer technology to achieve real-time monitoring, management, and guidance of the entire traffic environment to improve the efficiency and safety of traffic operations.

[0003] In intelligent transportation systems, automatic identification of travel modes is one of the key technologies. It can not only provide accurate data support for transportation planning and management, but also provide a scientific basis for urban traffic congestion analysis, travel mode research, public transportation optimization, etc. In addition, with the popularization of the sharing economy and green travel concepts, accurate identification of travel modes is of great significance for promoting the rational allocation and utilization of transportation resources and reducing traffic congestion and environmental pollution. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for intelligently identifying a mode of transportation, so as to at least solve the technical problem in the related art that it is difficult to accurately identify a user's mode of transportation.

[0005] According to one aspect of an embodiment of the present application, a method for intelligently identifying a transportation mode is provided, comprising:

[0006] Collect user's LBS location data;

[0007] Extracting user travel characteristic data based on the LBS location data;

[0008] Based on the matching information between the travel speed in the travel characteristic data and the speed intervals corresponding to the multiple travel modes to be identified, an identified initial travel mode is obtained;

[0009] The travel feature data and the initial travel mode are input into a preset discrimination model to output the identified transportation travel mode; the discrimination model includes a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule and a cycling discrimination submodule.

[0010] In one embodiment, extracting the user's travel characteristic data based on the LBS location data includes:

[0011] Preprocessing the LBS location data by deduplication and repair;

[0012] The pre-processed LBS location data is sorted according to the time sequence, and the sorted data is spliced ​​in the time sequence to form complete travel data;

[0013] The travel time, travel speed, travel distance, travel route, and information on points of interest near the travel starting and ending points are extracted from the travel data to obtain the travel characteristic data.

[0014] In one embodiment, the travel characteristic data and the initial travel mode are input into a preset discrimination model, and the identified traffic travel mode is output, including:

[0015] Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode;

[0016] When the determination submodule is a subway determination submodule, determining whether the travel characteristic data meets a subway travel characteristic condition, wherein the subway travel characteristic condition includes that the point of interest information of the travel start and end points is a subway, and the travel time is greater than a preset first threshold;

[0017] If the subway travel characteristic condition is met, the identified transportation mode is output as subway.

[0018] In one embodiment, the travel characteristic data and the initial travel mode are input into a preset discrimination model, and the identified traffic travel mode is output, including:

[0019] Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode;

[0020] When the determination submodule is a vehicle type determination submodule, it is determined whether the travel characteristic data meets a vehicle type characteristic condition; the vehicle type characteristic condition includes a match between the vehicle Bluetooth connection data and the travel characteristic data;

[0021] If the vehicle travel characteristic condition is met, the identified transportation mode is output as a vehicle.

[0022] In one embodiment, the travel characteristic data and the initial travel mode are input into a preset discrimination model, and the identified traffic travel mode is output, including:

[0023] Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode;

[0024] When the discrimination submodule is a public transportation discrimination submodule, it is determined whether the travel characteristic data meets the public transportation travel characteristic condition; the public transportation travel characteristic condition includes that the overlap between the travel path and the public transportation route is greater than a preset second threshold value, and the travel path is consistent with the transfer path of the public transportation route; and the travel time is within the scope of the public transportation operation time, and the point of interest information of the travel start and end points is a public transportation stop;

[0025] If the public transportation travel characteristic conditions are met, the identified transportation mode is output as public transportation.

[0026] In one embodiment, the travel characteristic data and the initial travel mode are input into a preset discrimination model, and the identified traffic travel mode is output, including:

[0027] Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode;

[0028] When the determination submodule is a walking determination submodule, determining whether the travel characteristic data meets a walking travel characteristic condition; the walking travel characteristic condition includes that the travel distance is less than a preset third threshold;

[0029] If the walking travel characteristic condition is met, the identified transportation mode is output as walking.

[0030] In one embodiment, the travel characteristic data and the initial travel mode are input into a preset discrimination model, and the identified traffic travel mode is output, including:

[0031] Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode;

[0032] When the discrimination submodule is a cycling discrimination submodule, it is determined whether the travel characteristic data meets a cycling travel characteristic condition; the cycling travel characteristic condition includes that the travel distance is less than a preset fourth threshold;

[0033] If the cycling travel characteristic condition is met, the identified transportation mode is output as cycling.

[0034] According to an embodiment of the present application, a smart identification device for a transportation mode is provided, comprising:

[0035] A collection module, used to collect the user's LBS location data;

[0036] An extraction module, used for extracting user travel characteristic data based on the LBS location data;

[0037] A first identification module, configured to obtain an identified initial travel mode based on matching information between a travel speed in the travel characteristic data and a speed interval corresponding to a plurality of travel modes to be identified;

[0038] The second identification module is used to input the travel feature data and the initial travel mode into a preset discrimination model, and output the identified transportation travel mode; the discrimination model includes a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule and a cycling discrimination submodule.

[0039] According to another aspect of the embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the intelligent identification method of the transportation mode through the computer program.

[0040] According to another aspect of the embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned intelligent identification method of the transportation mode when running.

[0041] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0042] The embodiment of the present application obtains the user's OD travel feature data based on the user's LBS location data. First, the initial transportation mode is identified by matching the travel speed with the speed range of the transportation mode. Then, based on the discriminant model, it is determined which initial transportation mode the travel feature data specifically meets the discrimination conditions, and the final identified transportation mode is output. This solution can improve the accuracy and efficiency of identification, and can also provide strong technical support for intelligent transportation management and planning under the premise of protecting user privacy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 is a flow chart of an optional intelligent identification method of a transportation mode according to an embodiment of the present application;

[0045] Figure 2 is a schematic diagram of an intelligent identification method of a transportation mode according to an embodiment of the present application;

[0046] Figure 3 is a schematic diagram of an intelligent identification device for a transportation mode according to an embodiment of the present application;

[0047] Figure 4 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0050] At the same time, it should be understood that for the sake of ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The technologies, methods and devices known to ordinary technicians in the relevant fields may not be discussed in detail, but in appropriate cases, the technologies, methods and devices should be regarded as part of the specification.

[0051] The following is combined with Figure 1 The intelligent identification method of the transportation mode of the embodiment of the present application is introduced in detail. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this respect. On the contrary, the implementation of the present application can be applied to any applicable scenario. Figure 1 As shown, the method mainly includes the following steps:

[0052] S101 collects the user's LBS location data.

[0053] Among them, LBS, or Location-Based Services, is a technology that obtains user geographic location information through mobile devices and provides corresponding services. The collection and use of LBS location data has a wide range of applications in many fields, such as navigation, traffic management, smart travel, emergency rescue, social networks, etc.

[0054] Specifically, LBS location data can be collected based on the user's mobile device. The data fields include: uuid (Universally Unique Identifier), stay location (latitude and longitude), stay duration (start time, end time), and categories of points of interest near the stay point.

[0055] After collecting the user's LBS location data, it also includes extracting the car's Bluetooth connection data. It can assist in identifying the car's travel records. The data fields include uuid, connection time, mac address, etc.

[0056] S102 extracts the user's travel characteristic data based on the LBS location data.

[0057] In one embodiment, extracting user travel characteristic data based on LBS location data includes:

[0058] The LBS location data is preprocessed by deduplication and data repair. The preprocessed LBS location data is sorted in chronological order, and the sorted data is spliced ​​in chronological order to form complete travel data; the travel time, travel speed, travel distance, travel path, and points of interest near the travel start and end points are extracted from the travel data to obtain travel feature data.

[0059] Specifically, data cleaning is performed to remove invalid records and correct obviously erroneous data. Duplicate data is removed by comparing the uuid, time and location information of the records to delete identical duplicates. Missing data processing: records with missing data are identified and filled or deleted based on the severity of the missing data.

[0060] Furthermore, spatial screening is performed: based on geographic location information, user mobility data within a specified area is screened out. Time screening: a time range is set to screen out travel data within this time period. Travel threshold setting: based on business needs, thresholds for travel duration and travel distance are set to identify valid travel records. Data splicing: splicing OD (origin-destination) travel data in chronological order to form a complete travel sequence. Data conversion: converting data into a format suitable for analysis, for example, converting a timestamp into a specific date and time.

[0061] Further, travel characteristic data is extracted based on the OD travel data. The travel time, travel speed, travel distance, travel route, and information of points of interest near the travel start and end points are extracted from the travel data to obtain the travel characteristic data.

[0062] In one embodiment, it is calculated according to the following formula:

[0063] dis=|x i -xj |+|y i -y j |

[0064] time = D start_time -O end_time

[0065] v=dis / time

[0066] Among them, x i ,y i is the latitude and longitude of the starting point O, x j ,y j is the latitude and longitude of the end point D. start_time is the starting time of the end point D, O end_time is the end time of the starting point O, dis is the OD travel distance, time is the OD travel time, and v represents the travel speed.

[0067] S103 obtains the identified initial travel mode based on the matching information between the travel speed in the travel characteristic data and the speed intervals corresponding to the multiple travel modes to be identified.

[0068] In one implementation, the reference speeds of different travel modes are first matched with the user's travel speed to perform initial screening and identification.

[0069] Specifically, a speed range is defined for each mode of travel. For example, the walking speed is usually 0-6 km / h, the bicycle speed is 6-20 km / h, the car speed may be 20-60 km / h, the bus speed is 15-40 km / h, and the subway speed is 30-80 km / h. The specific speed range can be adjusted according to the actual situation, and the embodiment of the present application does not make specific limitations.

[0070] Further, the calculated travel speed is compared with the predefined speed interval of each travel mode. According to the speed matching result, the travel mode is preliminarily identified as the travel mode corresponding to the closest speed interval.

[0071] In an exemplary scenario, the user's travel speed is 3 km / h, the matched travel mode is walking, and the identified initial travel mode is walking.

[0072] In an exemplary scenario, the user's travel speed is 20 kilometers per hour, and the matching travel modes are cycling, driving, and public transportation. The identified initial travel modes include cycling, driving, and public transportation.

[0073] S104 inputs the travel feature data and the initial travel mode into a preset discrimination model and outputs the identified transportation travel mode; the discrimination model includes a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule and a cycling discrimination submodule.

[0074] The embodiment of the present application provides a discrimination model, including a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule, and a cycling discrimination submodule. According to the input initial travel mode, the corresponding discrimination submodule is determined. The travel feature data is input into the corresponding discrimination submodule to determine whether it meets the travel characteristics of the mode, and then the final output travel mode is obtained.

[0075] In one embodiment, the travel characteristic data is input into the discrimination submodule corresponding to the initial travel mode; when the discrimination submodule is a subway discrimination submodule, it is determined whether the travel characteristic data meets the subway travel characteristic condition, and the subway travel characteristic condition includes that the interest point information of the travel start and end points is the subway, and the travel time is greater than a preset first threshold; if the subway travel characteristic condition is met, the identified transportation travel mode is output as the subway. The specific threshold can be set according to the actual implementation scenario.

[0076] For example, if the identified initial travel mode includes subway travel, the travel feature data is input into the subway identification submodule. If the start and end point POI categories of the travel data are both subways and the travel time is greater than 2 minutes, the transportation travel mode is determined to be subway.

[0077] In one embodiment, the travel characteristic data is input into a discrimination submodule corresponding to the initial travel mode; when the discrimination submodule is a vehicle type discrimination submodule, it is determined whether the travel characteristic data meets the vehicle type characteristic conditions; the vehicle type characteristic conditions include matching the vehicle Bluetooth connection data with the travel characteristic data; if the vehicle type characteristic conditions are met, the identified transportation travel mode is output as a vehicle.

[0078] In one embodiment, the identified initial travel mode includes a vehicle, and the vehicle identification submodule is used to identify the travel mode. When the vehicle Bluetooth connection data is collected, and the time of the data corresponds to the travel time, and the address of the data corresponds to the travel area, the travel mode is determined to be a vehicle.

[0079] In one embodiment, the travel characteristic data is input into the discrimination submodule corresponding to the initial travel mode; when the discrimination submodule is a bus discrimination submodule, it is determined whether the travel characteristic data meets the bus travel characteristic condition; the bus travel characteristic condition includes that the overlap between the travel path and the bus route is greater than the preset second threshold. And the travel path is consistent with the bus line transfer path; and the travel time is within the bus operating time range, and the point of interest information of the travel start and end points is a bus stop; if the bus travel characteristic condition is met, the output identified transportation travel mode is bus. Among them, the value of the specific threshold can be set according to the actual situation, and the embodiment of this application does not limit it.

[0080] In one embodiment, the travel characteristic data is input into a discrimination submodule corresponding to the initial travel mode; when the discrimination submodule is a walking discrimination submodule, it is determined whether the travel characteristic data meets the walking travel characteristic conditions; the walking travel characteristic conditions include a travel distance less than a preset third threshold; if the walking travel characteristic conditions are met, the identified transportation travel mode is output as walking.

[0081] For example, the upper limit of walking distance is 2.5 km. When the travel distance is less than or equal to 2.5 km, the travel mode is determined to be walking.

[0082] In one embodiment, the travel characteristic data is input into a discrimination submodule corresponding to the initial travel mode; when the discrimination submodule is a cycling discrimination submodule, it is determined whether the travel characteristic data meets the cycling travel characteristic conditions; the cycling travel characteristic conditions include a travel distance less than a preset fourth threshold; if the cycling travel characteristic conditions are met, the identified transportation travel mode is output as cycling.

[0083] For example, the upper limit of cycling distance is 6 km. When the travel distance is less than or equal to 6 km, the travel mode is determined to be cycling.

[0084] Optionally, receive travel mode feedback information from the user, train a discrimination model based on the travel mode feedback information from the user, adjust model parameters, and improve the accuracy and robustness of model recognition.

[0085] Optionally, it also includes vehicle records that are not connected to the in-vehicle Bluetooth. If the vehicle speed overlaps with the bus speed, it is identified by the following method: if the travel path has a high degree of overlap with the bus path and meets the bus line transfer path, it is a bus trip; the rest of the unidentified records are most likely vehicle records that are not connected to the in-vehicle Bluetooth.

[0086] If the speed of driving and walking overlap, they are identified by the following method: if there is a connection to the car's Bluetooth during the travel time, it is driving; if it is more than 2.5km, it is driving; if it is less than 2.5km, there is walking and driving without connecting to the car's Bluetooth, and within 1km, it is directly judged as walking.

[0087] If the speed of driving and cycling overlap, they are identified by the following method: if there is a connection to the car's Bluetooth during the travel time, it is a driving mode; more than 6km is basically driving; below 6km, there is cycling and driving without connecting to the car's Bluetooth, below 1km is directly judged as cycling, and the speed change within the path interval of 1-6km can be calculated. If it exceeds the upper limit of cycling speed, it is driving.

[0088] If the bus and walking speeds overlap, they are identified using the following method: if the travel path has a high degree of overlap with the bus path and meets the bus line transfer path, it is a bus trip; distances above 2.5km are basically bus trips; distances below 2.5km are set as walking.

[0089] If the speed of buses and bicycles overlap, they are identified by the following method: if the travel path has a high degree of overlap with the bus path and meets the bus line transfer path, it is a bus trip; more than 6km is basically a bus trip; less than 6km is set as cycling.

[0090] If the speeds of cars, buses, and pedestrians overlap, they are identified using the following methods: if there is a connection to the car's Bluetooth during the travel time, it is a car trip; if the travel path has a high degree of overlap with the bus path and meets the bus line transfer path, it is a bus trip; if it is over 2.5km, it is a car trip without connecting to the car's Bluetooth; if it is under 2.5km, there is walking and driving without connecting to the car's Bluetooth, and within 1km it is directly judged as walking.

[0091] If the speeds of cars, buses, and bicycles overlap, they are identified using the following methods: if there is a connection to the car's Bluetooth during the travel time, it is a car trip; if the travel path has a high degree of overlap with the bus path and meets the bus line transfer path, it is a bus trip; if it is above 6km, it is a car trip without connecting to the car's Bluetooth; if it is below 6km, there is a combination of cycling and driving without connecting to the car's Bluetooth, and if it is below 1km, it is directly judged as cycling.

[0092] Optionally, multimodal data can be introduced for discrimination. This includes obtaining weather conditions. If the weather conditions are bad, such as rain, snow, etc., the probability of taking a car or subway is high. Travel habit data can also be introduced, including obtaining the user's travel mode identified within a preset time period, and the corresponding time period, and constructing a user travel habit table. The travel habit table includes user ID, time period, and the number of travel modes used in each time period. For example, user A takes the subway to work from Monday to Friday. Through the user travel habit table, the user's travel information can be obtained, the public's travel mode selection situation can be analyzed, and data support can be provided for urban rail transit operations and vehicle management.

[0093] Optionally, when the user's travel speed corresponds to the speed of multiple modes and it is difficult to distinguish based on the above conditions, the weighted probability coefficient of each travel mode can be calculated based on the multimodal data. Introduce the weather coefficient and the user habit coefficient. For example, the travel mode score = speed compliance * 90% + discrimination condition compliance * 90% + weather compliance * 50% + user habit compliance * 50%. That is, the weighted probability coefficient of the travel mode is obtained by adding the speed weight factor, the discrimination condition weight factor, the weather weight factor, and the user habit weight factor. For example, if the speed of riding and driving overlap, there are riding and driving behaviors without connecting to the car Bluetooth below 6km. At this time, the speed factors are the same, but it is detected that the user likes riding in the past travel, then it is concluded that it is riding according to the weighted probability coefficient.

[0094] In order to facilitate understanding of the method provided in the embodiment of the present application, Figure 2 Further description. Figure 2 As shown, the method of the present application includes collecting data, collecting user LBS location data, including collecting anonymous personnel ID, longitude and latitude, residence time and other information. Collecting vehicle Bluetooth data, including collecting anonymous personnel ID, vehicle Bluetooth data, connection time, MAC address data and so on.

[0095] Furthermore, data processing includes data cleaning, filtering the user's spatial movement process in the specified area, and setting thresholds for travel duration and travel distance.

[0096] Furthermore, the travel mode is identified. Identification is performed based on the judgment conditions. The judgment condition for subway identification is to determine whether the starting and ending points of the trip are both subway POIs. The walking identification condition is to determine whether it is walking based on the travel distance and speed. The upper limit of the walking distance is reversely verified through Amap data and paper data. The vehicle identification condition is to connect through Bluetooth, determine the shortest path through grid division and Dijkstra algorithm, and match the actual speed with the calculated speed. Bus identification adds screening conditions, including the bus operating time and the starting and ending points are within 20m of the bus stop. Cycling identification includes determining the shortest path through grid division and Dijkstra algorithm, and matching the actual speed with the calculated speed.

[0097] This application combines LBS location data and vehicle Bluetooth connection data to propose a new method for intelligent identification of transportation modes. This method can not only improve the accuracy and efficiency of identification, but also provide strong technical support for intelligent transportation management and planning under the premise of protecting user privacy.

[0098] According to another aspect of the embodiment of the present application, there is also provided a device for intelligently identifying a mode of transportation for implementing the above-mentioned method for intelligently identifying a mode of transportation. Figure 3 As shown, the device comprises:

[0099] The collection module 301 is used to collect the LBS location data of the user;

[0100] An extraction module 302 is used to extract the user's travel characteristic data based on the LBS location data;

[0101] A first identification module 303, configured to obtain an identified initial travel mode based on matching information between a travel speed in the travel characteristic data and a speed interval corresponding to a plurality of travel modes to be identified;

[0102] The second identification module 304 is used to input the travel feature data and the initial travel mode into a preset discrimination model and output the identified transportation travel mode; the discrimination model includes a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule and a cycling discrimination submodule.

[0103] It should be noted that the intelligent identification device for transportation modes provided in the above embodiments only uses the division of the above functional modules as an example when executing the intelligent identification method for transportation modes. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent identification device for transportation modes provided in the above embodiments and the intelligent identification method for transportation modes are of the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0104] According to another aspect of the embodiments of the present application, an electronic device corresponding to the intelligent identification method of transportation mode provided in the above embodiments is also provided to execute the above intelligent identification method of transportation mode.

[0105] Please refer to Figure 4 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 4 As shown, the electronic device includes: a processor 400, a memory 401, a bus 402 and a communication interface 403, and the processor 400, the communication interface 403 and the memory 401 are connected via the bus 402; the memory 401 stores a computer program that can be run on the processor 400, and when the processor 400 runs the computer program, it executes the intelligent identification method of the transportation mode provided in any of the aforementioned embodiments of the present application.

[0106] The memory 401 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 403 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0107] The bus 402 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 401 is used to store programs, and the processor 400 executes the program after receiving the execution instruction. The intelligent identification method of the transportation mode disclosed in any implementation of the embodiment of the present application may be applied to the processor 400, or implemented by the processor 400.

[0108] The processor 400 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 400. The above processor 400 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 401, and the processor 400 reads the information in the memory 401 and completes the steps of the above method in combination with its hardware.

[0109] The electronic device provided in the embodiment of the present application and the intelligent identification method of transportation mode provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0110] According to another aspect of the embodiments of the present application, a computer-readable storage medium corresponding to the intelligent identification method for transportation modes provided in the aforementioned embodiments is also provided, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the intelligent identification method for transportation modes provided in any of the aforementioned embodiments.

[0111] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0112] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the intelligent identification method of transportation modes provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0113] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for intelligently identifying a mode of transportation, characterized in that: include: Collect user's LBS location data; Extracting user travel characteristic data based on the LBS location data; Based on the matching information of the travel speed in the travel characteristic data and the speed intervals corresponding to the multiple travel modes to be identified, an identified initial travel mode is obtained; The travel feature data and the initial travel mode are input into a preset discrimination model to output the identified transportation travel mode; the discrimination model includes a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule and a cycling discrimination submodule.

2. The method according to claim 1, characterized in that: Extracting user travel characteristic data based on the LBS location data includes: Preprocessing the LBS location data by deduplication and repair; The pre-processed LBS location data is sorted according to the time sequence, and the sorted data is spliced ​​in the time sequence to form complete travel data; The travel time, travel speed, travel distance, travel route, and information on points of interest near the travel starting and ending points are extracted from the travel data to obtain the travel characteristic data.

3. The method according to claim 2, characterized in that Inputting the travel characteristic data and the initial travel mode into a preset discrimination model and outputting the identified traffic travel mode includes: Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode; When the determination submodule is a subway determination submodule, it is determined whether the travel characteristic data meets the subway travel characteristic condition, wherein the subway travel characteristic condition includes that the point of interest information of the travel start and end points is a subway, and the travel time is greater than a preset first threshold; If the subway travel characteristic condition is met, the identified transportation mode is output as subway.

4. The method according to claim 2, characterized in that: Inputting the travel characteristic data and the initial travel mode into a preset discrimination model and outputting the identified traffic travel mode includes: Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode; When the determination submodule is a vehicle type determination submodule, it is determined whether the travel characteristic data meets a vehicle type characteristic condition; the vehicle type characteristic condition includes a match between the vehicle Bluetooth connection data and the travel characteristic data; If the vehicle travel characteristic condition is met, the identified transportation mode is output as a vehicle.

5. The method according to claim 2, characterized in that: Inputting the travel characteristic data and the initial travel mode into a preset discrimination model and outputting the identified traffic travel mode includes: Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode; When the discrimination submodule is a public transportation discrimination submodule, it is determined whether the travel characteristic data meets the public transportation travel characteristic condition; the public transportation travel characteristic condition includes that the overlap between the travel path and the public transportation route is greater than a preset second threshold value, and the travel path is consistent with the transfer path of the public transportation route; and the travel time is within the scope of the public transportation operation time, and the point of interest information of the travel start and end points is a public transportation stop; If the public transportation travel characteristic conditions are met, the identified transportation mode is output as public transportation.

6. The method according to claim 2, characterized in that Inputting the travel characteristic data and the initial travel mode into a preset discrimination model and outputting the identified traffic travel mode includes: Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode; When the determination submodule is a walking determination submodule, determining whether the travel characteristic data meets a walking travel characteristic condition; the walking travel characteristic condition includes that the travel distance is less than a preset third threshold; If the walking travel characteristic condition is met, the identified transportation mode is output as walking.

7. The method according to claim 2, characterized in that: Inputting the travel characteristic data and the initial travel mode into a preset discrimination model and outputting the identified traffic travel mode includes: Inputting the travel characteristic data into a discrimination submodule corresponding to the initial travel mode; When the discrimination submodule is a cycling discrimination submodule, it is determined whether the travel characteristic data meets a cycling travel characteristic condition; the cycling travel characteristic condition includes that the travel distance is less than a preset fourth threshold; If the cycling travel characteristic condition is met, the identified transportation mode is output as cycling.

8. An intelligent identification device for transportation mode, characterized in that: include: A collection module, used to collect the user's LBS location data; An extraction module, used for extracting user travel characteristic data based on the LBS location data; A first identification module, configured to obtain an identified initial travel mode based on matching information between a travel speed in the travel characteristic data and a speed interval corresponding to a plurality of travel modes to be identified; The second identification module is used to input the travel feature data and the initial travel mode into a preset discrimination model, and output the identified transportation travel mode; the discrimination model includes a subway discrimination submodule, a vehicle discrimination submodule, a bus discrimination submodule, a walking discrimination submodule and a cycling discrimination submodule.

9. An electronic device, characterized in that: It comprises a processor and a memory storing program instructions, wherein the processor is configured to execute a method for intelligently identifying a transportation mode as claimed in any one of claims 1 to 7 when executing the program instructions.

10. A computer-readable medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement a method for intelligently identifying a transportation mode as described in any one of claims 1 to 7.

Images