System and method for classifying vehicle trips - Patents.com

Abstract

Systems and methods according to embodiments of the present invention can acquire and use various telematics data to classify multiple trips taken by a vehicle. Multiple trip models can be generated based on telematics data captured while the vehicle is operating. Features of the various trip models, such as the timing and / or location of vehicle stops during one or more trips, can be used to classify trips as business or personal. In some embodiments, multiple machine classifiers are trained to classify features in the trip models based on past trips that have already been classified as business or personal. Multiple trip models can be combined with other driver attributes to classify a particular vehicle and / or driver as engaging in a TNC service business.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Patent Application No. 16 / 665,969, filed October 28, 2019, all of which are incorporated herein by reference. [Technical field]

[0002] Aspects of the invention relate to data processing, and more particularly, to classification of telematics data. [Background technology]

[0003] TNC service businesses (Transportation Network Companies) match passengers with vehicles through websites and mobile apps. TNC service drivers typically use their own owned or leased vehicles when driving passengers. Thus, drivers may use one vehicle for both business and personal purposes. However, due to the decentralized nature of TNC service businesses, it is difficult to assess whether a particular driver is driving for TNC service businesses or for personal use. Therefore, it is necessary to accurately determine whether a driver is traveling for business or personal use. Summary of the Invention

[0004] In light of the above technical background, the following presents a simplified summary of the disclosure in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. It is not intended to identify key or critical elements of the invention, nor is it intended to delineate the scope of the invention. The following summary merely presents some concepts of the invention in a simplified form as a prelude to the more detailed description presented later.

[0005] Systems and methods according to embodiments of the present invention can obtain and use various telematics data to classify trips taken by a vehicle. A number of trip models can be generated based on the telematics data captured while driving the vehicle. Various features of the trip models, such as the timing and / or location of vehicle stops during one or more trips, can be used to classify a trip as a business trip or a personal trip. In some embodiments, machine classifiers are trained to classify the features in the trip models based on past trips that have already been classified as business trips or personal trips. The trip models can be combined with other driver attributes to classify a particular vehicle and / or driver as being engaged in a TNC service business.

[0006] The systems and methods described herein may also include other additional elements, steps, computer-executable instructions, computer-readable data structures, and the like. In this regard, other embodiments are also disclosed and claimed herein. Details of these and other embodiments of the invention are set forth in the accompanying drawings and the description that follows. Other features and advantages of the invention will be apparent from the description, drawings, and claims. [Brief description of the drawings]

[0007] The present invention is illustrated by way of example and not by way of limitation in the accompanying figures in which like reference numbers indicate similar elements and in which: FIG.

[0008] [Figure 1] FIG. 1 illustrates an example of an operating environment in which one or more aspects described herein can be implemented. [Diagram 2] FIG. 1 illustrates an example of a computing device in accordance with one or more aspects described herein. [Diagram 3] 4 is a flowchart illustrating a process for classifying vehicle usage status according to at least one embodiment of the present invention. [Figure 4] 4 is a flow chart illustrating a process for classifying drivers in accordance with at least one embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] In the following description of various embodiments, reference is made to the accompanying drawings which form a part hereof, and in which is shown by way of illustration various embodiments of the present disclosure which may be practiced. It should be understood that other embodiments may be utilized.

[0010] Aspects described herein relate to classification of vehicle trips. Aspects described herein also relate to classification of drivers based on classified vehicle trips. Trip models can be generated based on telematics data captured while driving a vehicle. In some embodiments, the telematics data is captured using a computing device, such as a mobile device or smartphone, associated with a driver of the vehicle. Various features of the trip models, such as the timing and / or location of vehicle stops during one or more trips, can be used to classify a trip as a business trip or a personal trip. In some embodiments, machine classifiers are trained to classify features in the trip models based on past trips that have already been classified as business trips or personal trips. The trip models can be combined with other driver attributes to classify a particular vehicle and / or driver as being engaged in a TNC service business. The classification of the driver can be determined based on the time and / or location that the vehicle and / or driver typically engages in activities related to the TNC service business.

[0011] These and various other systems and methods are more fully described herein. As will be appreciated by those skilled in the art upon reading the following disclosure, various aspects described herein can be embodied as a method, a computer system, or a computer program product. Thus, these aspects can take the form of an entirely hardware embodiment, an entirely software embodiment, or at least one embodiment combining software and hardware aspects. Furthermore, such aspects can take the form of a computer program product stored by one or more computer readable storage media having computer readable program code or instructions embodied in or on the storage medium. Any suitable computer readable storage medium can be utilized, including hard disks, CD-ROMs, optical storage devices, magnetic storage devices, and / or any combination thereof. Furthermore, various signals representing data or events as described herein can be communicated between a source and a destination in the form of electromagnetic waves traveling through signal conducting media, such as metal wires, optical fibers, and / or wireless transmission media (e.g., air and / or space). <Operating environment and computing devices>

[0012] 1 illustrates an operating environment 100 in accordance with at least one embodiment of the present invention. The operating environment 100 includes at least one client device 110, at least one classification server system 120, and / or at least one vehicle 130 that communicate over a network 140. Any of the devices and systems described herein may be implemented in whole or in part using one or more of the computing devices described with respect to FIG.

[0013] As described herein, client device 110 and classification server system 120 enable users to obtain telematics data from vehicles 130, create trips, and / or classify trips, vehicles, and / or drivers. Network 140 may include a local area network (LAN), a wide area network (WAN), a wireless communication network, and / or any other communication network, or combinations thereof.

[0014] The vehicle 130 may be, for example, an automobile, motorcycle, scooter, bus, recreational vehicle, boat, or other vehicle capable of collecting and analyzing sensor data or crash data. A telematics device in the vehicle 130 may be used to collect and / or receive sensor data and / or receive sensor data from the vehicle 130. The telematics device may process the data to detect a crash or non-crash event and / or transmit the sensor data or crash data to the outcome determination server system 120 or other computing devices. The telematics device may be, for example, a mobile phone, a personal digital assistant (PDA), a tablet computer, a laptop computer, a smart watch, and other devices that the driver or passenger may carry in or out of the vehicle 130. The telematics device may be integrated with the vehicle 130 and / or connected to a data bus in the vehicle 130 via a diagnostic connector such as an OBD2 connector. The telematics device may receive various data, such as acceleration, speed, position, and vehicle operation data such as braking, turning, swerving, etc., from sensors located on the telematics device itself and / or in the vehicle. For example, a telematics device with a Global Positioning System (GPS) receiver can determine the vehicle's location, speed, direction, and other basic driving data without requiring communication with vehicle sensors or external vehicle systems. However, it should be noted that any of a variety of other location determination technologies can be used, such as a location determined based on a wireless network to which the mobile device is connected, such as a Wi-Fi network or a cellular network. Sensors in the telematics device, such as a GPS and / or a compass, can sense the speed and / or direction at which the telematics device (and accordingly the vehicle 130) is traveling. An accelerometer in the telematics device can sense the acceleration of the mobile device. A gyroscope can be used to determine the orientation of the mobile device. In some aspects, the orientation can be determined at a rate of, for example, 90 Hz. The gyroscope can also be used to measure the rotational speed of the telematics device.A magnetometer may be used to measure the strength and direction of the magnetic field relative to the telematics device. Data collected by the telematics device may be stored and / or analyzed within the telematics device. A processing component of the telematics device may be used to analyze the sensor data to determine if a collision has occurred and to confirm if a collision has occurred. Additionally or alternatively, the telematics device may transmit this data via a wired or wireless communication network to one or more computing devices for storage or analysis. In various embodiments, the telematics device transmits data if it detects that a collision has occurred.

[0015] The vehicle 130 may further include a short-range communication system. The short-range communication system may be a vehicle-based data transmission system configured to transmit vehicle operation data to and receive vehicle operation data from a plurality of other nearby vehicles. In some examples, the communication system may use Dedicated Short Range Communications (DSRC) protocols and standards to perform wireless communication between vehicles. In the United States, 75 MHz of the 5.850-5.925 GHz band has been allocated for DSRC systems and applications, and other countries and jurisdictions have defined various other DSRC allocations. However, the short-range communication system need not use DSRC and may be implemented using other short-range wireless protocols in other examples, such as WLAN communication protocols (e.g., IEEE 802.11), Bluetooth (e.g., IEEE 802.15.1), or one or more of the Communication Access for Land Mobiles (CALM) wireless communication protocols and air interfaces. Vehicle-to-vehicle transmissions (V2V transmissions) between short-range communication systems can be transmitted via DSRC, Bluetooth, satellite, GSM infrared, IEEE 802.11, WiMAX, RFID, and / or any suitable wireless communication medium, standard, and protocol. In certain systems, the short-range communication system can include dedicated hardware (e.g., transceivers, antennas, etc.) installed in the vehicle 130. However, in other examples, the short-range communication system can be implemented using existing vehicle hardware components (e.g., radio and satellite equipment, navigation computer), or by software running on a telematics device in (or near) the vehicle 130. The range of V2V communication can depend on the wireless communication standard and protocol used, the transmit / receive hardware (e.g., transceivers, power, antennas), and other factors. Short-range V2V communication can range from just a few feet to many miles, and depending on the range of this V2V communication, various types of driving behaviors, vehicle operation parameters, etc. can be determined.

[0016] V2V communications may also include vehicle-to-infrastructure communications (V2I communications), e.g., communications from a vehicle to a non-vehicle receiving device such as infrastructure, or from a non-vehicle receiving device to a vehicle. The infrastructure may include one or more of a toll booth, a railroad crossing, a parking structure, a road segment, a parking lot, a building or other structure, and / or a road traffic monitoring device that may include one or more sensors for detecting environmental conditions (e.g., weather, lighting, etc.) and parking availability. Certain V2V communication systems may periodically broadcast data from the vehicle 130 to any other vehicles or other infrastructure devices that can receive the communication within the transmission capabilities of the vehicle. For example, the vehicle 130 may broadcast certain vehicle operation data periodically (e.g., every 0.1 seconds, every 0.5 seconds, every 1 second, every 5 seconds, dynamically, etc.) over a short-range communication system, regardless of whether other vehicles or receiving devices are within range. In other examples, a short-range vehicular communication system may first detect nearby vehicles and receiving devices and initialize communications with each by performing a handshake transaction before beginning transmission of vehicle operation data to the other vehicles and / or devices. Broadcasts from the infrastructure also have various ranges, and in some examples, the infrastructure may broadcast to relay stations that can further relay the information to one or more computing devices.

[0017] The type of vehicle operation data, vehicle driving data, fault data, etc. transmitted to or from the vehicle 130 and / or infrastructure may depend on the protocols and standards used for V2V or V2I communications, communication range, and other factors. In a particular example, the vehicle 130 may periodically broadcast a corresponding set of similar vehicle driving data, such as location (which may include absolute location in GPS coordinates or other coordinate system and / or relative location to another vehicle or fixed point), speed, and direction of travel. In a particular example, the nodes in a V2V (or V2I) communications system (e.g., vehicles and other receiving devices) may use internal clocks with synchronized time signals and may transmit the time of transmission within the V2V (or V2I) communications such that the receiver can calculate the distance from the transmitting node based on the difference between the time of transmission and the time of reception. The status or usage of the vehicle's controls and gauges may also be transmitted. For example, whether the vehicle 130 is accelerating, braking, or turning, and to what extent, and / or which vehicle instruments are currently being activated by the driver (e.g., headlights, turn signals, hazard lights, cruise control, four-wheel drive, traction control, etc.) Vehicle alerts, such as detection by the vehicle's internal systems that the vehicle is skidding, that an impact has occurred, that the vehicle's airbags have deployed, or that the vehicle has made an unexpected, sudden stop, can also be transmitted via V2V (or V2I) communication.

[0018] In various other examples, any data potentially collected by any vehicle sensor can be transmitted via V2V or V2I communications to other nearby vehicles or infrastructure devices that receive V2V or V2I communications from the short-range communications system. Additionally, additional vehicle driving data not from the vehicle's sensors (e.g., vehicle make / model / year information, driver insurance information, driving route information, vehicle maintenance information, driver score, etc.) can be collected and transmitted using V2V or V2I communications to nearby vehicles and other receiving devices using the short-range communications system.

[0019] Data transmitted to and from various devices in the operating environment 100 may include secure sensitive data. Therefore, it may be desirable to use secure network protocols and encryption to protect the transmission of these data and to protect the integrity of the data as it is stored on the various computing devices in the software development system. For example, a file-based aggregation scheme or a service-based aggregation scheme may be utilized to transmit data between the various computing devices. The data may be transmitted using various network communication protocols. In file transfers, secure data transmission protocols and / or encryption may be used to protect the integrity of the data, such as File Transfer Protocol (FTP), Secure File Transfer Protocol (SFTP), and / or Pretty Good Privacy (PGP) encryption. In many embodiments, one or more web services may be implemented in the various computing devices. The web services may be accessed by authorized external devices and users to support the input, retrieval, and manipulation of data between the various computing devices in the operating environment 100. Web services built to support the personalized display system may be cross-domain and / or cross-platform, and they may be built for enterprise use. Such web services can be developed according to various web services standards, such as the Web Services Interoperability (WS-I) guidelines. Data can be transmitted using Secure Sockets Layer (SSL) or Transport Layer Security (TLS) protocols to provide secure connections between computing devices. Web services can be implemented using the WS-Security standard, which provides secure SOAP messages using XML encryption. In yet other examples, the security and integration layer can include dedicated hardware for providing secure web services.For example, the secure network appliance may include built-in features such as hardware accelerated SSL and HTTPS, WS security, and / or a firewall. Such dedicated hardware may be installed and configured in the operating environment 100 in front of one or more computing devices described herein such that any external devices may communicate directly with the dedicated hardware.

[0020] It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between the computers may be used. Any of a variety of network protocols, such as TCP / IP, Ethernet, FTP, HTTP, etc., and any of a variety of wireless communication technologies, such as GSM, CDMA, WiFi, and WiMAX, are presumed to be present, and the various computing devices described herein may be configured to communicate using any of these network protocols or technologies.

[0021] 2, there is shown a computing device 200 in accordance with at least one embodiment of the present invention. The computing device 200 may include a processor 203 that controls the overall operation of the computing device 200 and its associated components including RAM 205, ROM 207, input / output devices 209, communication interface 211, and / or memory 215. A data bus may interconnect the processor 203, RAM 205, ROM 207, memory 215, I / O devices 209, and / or communication interface 211.

[0022] The input / output (I / O) devices 209 may include a microphone, a keypad, a touch panel, and / or a stylus through which a user of the computing device 200 can provide input. The I / O devices 298 may also include one or more of a speaker for providing audio output and a video display device for providing textual, audiovisual, and / or graphical output. Software may be stored within the memory 215 and may provide instructions to the processor 203 to cause the computing device 200 to perform various operations. For example, the memory 215 may store software used by the computing device 200, such as an operating system 217, application programs 219, and / or associated internal databases 221. The various hardware memory units within the memory 215 may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. The memory 215 may include one or more physical persistent memory devices and / or one or more non-persistent memory devices. The memory 215 may include, but is not limited to, random access memory (RAM) 205, read-only memory (ROM) 207, electronically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium usable to store the desired information and accessible by the processor 203.

[0023] The communications interface 211 may include one or more transceivers, digital signal processors, and / or additional circuitry and software for communicating over any network, wired or wireless, using any of the protocols described herein. The processor 203 may include a single central processing unit (CPU), which may be a single-core or multi-core (e.g., dual-core, quad-core, etc.) processor, or may include multiple CPUs. The one or more processors 203 and associated components may enable the computing device 200 to execute a sequence of computer-readable instructions to perform some or all of the processes described herein. Although not shown in FIG. 2, various elements in the memory 215 or other components of the computing device 200 may include one or more caches, such as a CPU cache used by the processor 203, a page cache used by the operating system 217, a disk cache on a hard drive, and / or a database cache used to cache content from the database 221. In embodiments that include a CPU cache, the CPU cache may be used by the one or more processors 203 to reduce memory latency and access times. The processor 203 can read data from or write data to the CPU cache rather than reading / writing from memory 215, thereby speeding up these operations. In some examples, a database cache can be created in which certain data from the database 221 is cached in a separate, smaller database in a memory separate from the database, such as in RAM 205 or on a separate computing device. For example, in a multi-tier application, a database cache on the application server can reduce data retrieval and data manipulation times by not having to communicate over a network to a back-end database server.These types of caches and the like can be included in various embodiments and can provide potential advantages in a particular implementation of a software development system, such as faster response times when sending and receiving data and reduced dependency on network conditions.

[0024] Although the various components of computing device 200 are described separately, the functionality of these various components may be combined and / or performed by a single component and / or multiple computing devices in communication without departing from the invention. <Vehicle usage classification>

[0025] 3 is a flow chart illustrating a vehicle usage classification process in accordance with at least one embodiment of the present invention. Some or all of the steps of process 300 may be performed using any and / or combination of computing devices described herein. In various embodiments, some or all of the steps described below may be combined and / or divided into sub-steps as desired.

[0026] At step 310, telematics data may be acquired. The telematics data may be acquired from a telematics device associated with the vehicle. The telematics device may be a mobile device that may be installed in the vehicle and / or associated with one or more persons (e.g., driver, passengers, etc.) in the vehicle. The telematics data may include acceleration data, speed data, braking data, orientation data, geographic data, impact data, vehicle and / or passenger identification data, and / or any other data as desired. The acquired telematics data may also include data captured using multiple telematics devices and / or multiple telematics devices associated with multiple other vehicles and / or multiple locations proximate the vehicle. The telematics data may include a subset and / or a full set of raw sensor data captured using multiple sensors associated with the telematics device. In various embodiments, the telematics data includes a stream of raw sensor data captured using the telematics device.

[0027] In step 312, one or more trips may be determined. A trip may be determined based on locations visited by the vehicle identified in the telematics data within a particular time frame. A trip may have a start location, a start time, an end location, and an end time. A trip may further have a number of intermediate stops, each having a location, an intermediate start time, and an intermediate end time. A trip may further include additional trip locations between the locations and the stops, such that a route taken by the vehicle may be identified by the multiple trip locations. The multiple locations, multiple intermediate stops, and / or multiple additional trip locations may include multiple geographic coordinates (such as coordinates generated using a GPS receiver), multiple geographic landmarks, multiple addresses, and / or any other location identification data, as appropriate. The multiple times may include times of day, dates, and / or days of the week, as appropriate. In many embodiments, the geographic coordinates of the trip start and / or trip end can be used to identify the appropriate time zone so that the trip start / end timestamps can be converted to times that correspond to the vehicle's physical location during the trip.

[0028] In step 314, trip characteristics may be determined. The determined characteristics within a trip may include, but are not limited to, a start location of the trip, an end location of the trip, intermediate stops, the acceleration of the vehicle at a particular time, the speed of the vehicle at a particular time, points of interest (POIs) visited by the vehicle, etc. In many embodiments, the start location is determined by determining that the vehicle starts moving after being classified as not being on a trip. In some embodiments, the end location is determined by determining that the vehicle stops moving for more than an end trip threshold period. In various embodiments, an intermediate stop is identified by the vehicle being moving and stopping at a location for at least an intermediate threshold period. In some embodiments, the intermediate threshold period is shorter than the end trip threshold period. The end trip threshold period is typically longer than the intermediate threshold period. For example, the end trip threshold period may be 20 minutes, 25 minutes, 30 minutes, etc., while the intermediate threshold period may be 30 seconds, 2 minutes, 5 minutes, etc. In this manner, the end of the trip may be distinguished from an intermediate stop. It should be noted that the thresholds shown here are merely examples and any thresholds may be used as desired. In many embodiments, the POIs may be locations corresponding to residential addresses and / or businesses. The POIs may be determined using various geographic databases that map geographic coordinates to particular POIs and / or locations, where the addresses may be mapped to the POIs. In this manner, the types of locations visited during the trip may also be identified. In many embodiments, determining the characteristics of the trip includes generating a trip model. The trip model may include a set of geographic locations and metadata identifying features associated with the geographic locations. These features may include, but are not limited to, durations of stops associated with each geographic location, as described herein.

[0029] In step 316, the plurality of trips may be classified. A trip may be classified to determine whether the trip is a business trip (e.g., the vehicle is operated commercially and / or the vehicle's operator is operating the vehicle as part of a TNC service business) and / or a personal trip (e.g., the vehicle is operated for the operator's personal use). Classifying a trip may include labeling the trip as a business trip and / or a personal trip and a confidence metric indicating the probabilistic likelihood that the label correctly identifies the class of the trip. Trips may be classified based on a number of features present in the trip model. The features may be classified according to various criteria, including, but not limited to, trip duration, trip mileage, and / or the ratio of trip mileage to an ideal mileage between the start and end points of the trip, also known as the ideal mileage ratio. In some embodiments, the ideal distance traveled between the start and end points can be determined by using a mapping database that includes known routes (e.g., roadways) between multiple geographic locations to generate a recommended route between the start and end points. In various embodiments, the ideal distance traveled is the geodesic distance between the start and end locations. For example, a trip that has several short intermediate stops and follows a route that is significantly longer than the ideal route is likely to be labeled as a business trip. On the other hand, a trip that has only one intermediate stop and follows approximately the ideal distance is likely to be labeled as a personal trip. The label can be any data that identifies the output of the trip, such as a text label and / or a score. In many embodiments, the trip is scored on a scale from 0 to 1, where 0 indicates that the trip is definitely a personal trip and 1 indicates that the trip is definitely a business trip. A score threshold can be used to determine whether the trip is a personal trip or a business trip.Returning to the previous example, if the score is less than 0.5, the trip can be labeled as a personal trip, and if the score is greater than 0.5, the trip can be labeled as a business trip. In various embodiments, the score for a trip is based on the probabilistic likelihood that the label generated for the trip is correct.

[0030] The trips may also be classified based on grouping of trips made within a particular time frame. The time frame may be any time frame, such as 5 minutes, 10 minutes, and / or 15 minutes. A group of trips may be classified based on total trip duration, total distance traveled, total ideal distance traveled ratio, minimum trip length in the group, maximum trip length in the group, average trip length in the group, minimum trip distance in the group, maximum trip distance in the group, average trip distance in the group, minimum ideal distance traveled ratio for the group, maximum ideal distance traveled ratio for the group, and / or average ideal distance traveled ratio for the group. The total trip duration of a group of trips may be determined based on an earliest start time and a latest end time of the trips in the group. The total ideal distance traveled ratio may be determined based on a total distance traveled for each trip in the group and an ideal trip between an earliest start point and a latest end point in the group. The classification of the trips may be based on multiple groupings, and each trip may be included in multiple groups.

[0031] In some embodiments, the trip labels and / or probabilistic likelihoods can be calculated using one or more machine classifiers. A variety of machine classifiers can be used, including, but not limited to, decision trees, k-nearest neighbors, support vector machines (SVMs), neural networks (NNs), recurrent neural networks (RNNs), convolutional neural networks (CNNs), and / or probabilistic neural networks (PNNs). RNNs can further include, but are not limited to, fully recurrent networks, Hopfield networks, Boltzmann machines, self-organizing maps, learning vector quantization, simple recurrent networks, echo state networks, long short-term memory networks, bidirectional RNNs, hierarchical RNNs, probabilistic neural networks, and / or gene-scale RNNs. In many embodiments, a combination of machine classifiers can be used, with more specific machine classifiers where possible and general machine classifiers where not, to further improve the accuracy of the predictions. The machine classifier can be trained based on historical trip data as well as multiple ground truth labels indicating whether each trip is a business trip and / or a personal trip. Various additional data, such as telematics data, can also be included in training the machine classifier. In some embodiments, training the machine classifier includes automatically updating one or more weights for neurons in one or more layers of a machine learning model utilized by the machine classifier to generate a probabilistic likelihood that a particular trip is associated with a particular label. In many embodiments, the machine classifier can be retrained using classified trips. In this manner, the performance of the machine classifier can be continually improved based on newly acquired telematics data.

[0032] In step 318, the driver may be classified. The classified trips may be used to determine whether the vehicle and / or driver is associated with a service offering of the TNC service enterprise. The classification results may also indicate the times and / or days of the week during which the vehicle and / or driver engages in driving associated with business trips and / or personal trips. Various processes for classifying drivers based on classified trips are described in more detail with respect to FIG. 4.

[0033] 4 is a flow chart illustrating a driver classification process in accordance with at least one embodiment of the present invention. Some or all of the steps of process 400 may be performed using any and / or combination of the computing devices described herein. In various embodiments, some or all of the steps described below may be combined and / or divided into sub-steps as desired.

[0034] At step 410, categorized trip data may be obtained. As described herein, the categorized trip data may include a set of trips, a number of labels indicating whether a particular trip is a business trip and / or a personal trip, and / or a probabilistic likelihood that a label associated with a trip is correct.

[0035] In step 414, the driver may be classified. Classifying the driver may determine whether the driver drives primarily for business trips or for personal trips. The classification of the driver may be based on the number of trips of a particular type taken by the driver. The classification of the driver may be based on the overall characteristics of the trips taken by the driver and / or the types of trips taken by the driver on a particular day and / or time. For example, a driver may regularly drive for a TNC service business on Friday and Saturday nights and drive for personal reasons at other times.

[0036] Classification of drivers may be useful in various situations, such as determining when a vehicle should be insured as a commercial vehicle rather than a personal vehicle. In some embodiments, a vehicle may be issued multiple insurance policies depending on the time of day the vehicle is driven. In this manner, a vehicle may be insured as a commercial vehicle when it is typically used for business trips, and as a personal vehicle when it is used for personal trips. Similarly, drivers may be classified as engaged in a business trip or a personal trip, independent of the vehicle they are driving. In this manner, drivers who use various vehicles to provide commercial services for the TNC service business may be tracked and appropriately insured. For example, drivers who rent vehicles to engage in business trips on certain days (rather than owning a single vehicle) may be identified. This information may be used, for example, to adjust the variable rental rates for the driver and / or to offer appropriate insurance that covers both personal and professional driving.

[0037] One or more aspects discussed herein may be embodied in computer usable or readable data and / or computer executable instructions, such as one or more program modules executed by one or more computers or other devices, as described herein. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types when executed by a processor in a computer or other device. Modules may be written in source code programming languages ​​that are compiled for later execution, or may be written in scripting languages ​​such as, but not limited to, HTML and XML. Computer executable instructions may be stored on computer readable media, such as hard disks, optical disks, removable storage media, solid state memory, RAM, etc. In various embodiments, the functionality of the program modules may be combined or distributed as desired, as will be appreciated by those skilled in the art. Furthermore, the functionality may be embodied in whole or in part in firmware or hardware equivalents, such as integrated circuits, field programmable gate arrays (FPGAs), etc. Certain data structures may be used to more effectively implement one or more aspects discussed herein, and such data structures are contemplated within the scope of the computer-executable instructions and computer-usable data described herein. Various aspects discussed herein may be embodied as methods, computing devices, systems, and / or computer program products.

[0038] While the present invention has been described with respect to certain specific aspects, it will be apparent to those skilled in the art that various other modifications and variations are possible. In particular, any of the various operations described above can be performed in alternative sequences and / or in parallel (on different computing devices) to achieve similar results in a manner more suited to the requirements of a particular application. It is therefore to be understood that the present invention can be practiced otherwise than as specifically described without departing from the scope and spirit of the invention. Thus, the present embodiments are to be understood in all respects as illustrative and not restrictive. The scope of the present invention should therefore be defined not by the exemplified embodiments, but by the appended claims and their equivalents.

Claims

1. acquiring, by a classification server system, telematics data including a plurality of geographic locations and a plurality of times indicating when the vehicle was at each geographic location; determining, by the classification server system, a plurality of trips based on the telematics data; determining, by the classification server system, a plurality of characteristics for each trip included in the plurality of trips; and classifying, by the classification server system, each trip included in the plurality of trips based on the plurality of features for the each trip, comprising: In determining the plurality of trips, Each trip included in the plurality of trips includes a start location, a start time when the vehicle was at the start location, an end location, and an end time when the vehicle was at the end location; the start location and the end location are indicated at the plurality of geographic locations; In classifying each trip, a classified trip including the plurality of features, a label indicating whether the trip is a business trip or a personal trip, and a confidence metric indicating the probabilistic likelihood that the label correctly identifies the class of the trip; The method, wherein the business trip is a trip during which the vehicle is operated on business and the personal trip is a trip during which the vehicle is operated for personal use.

2. The method of claim 1 , wherein the telematics data is obtained from a mobile device associated with an operator of the vehicle.

3. The telematics data further includes a driver identifier for identifying a driver of the vehicle; 10. The method of claim 1, further comprising classifying, by the classification server system, the driver as a commercial driver or a private driver based on the classified trips.

4. 2. The method of claim 1, wherein the plurality of features for a trip includes at least one intermediate stop at a point of interest (POI) visited by the vehicle.

5. determining, by the classification server system, the end location of a trip included in the plurality of trips based on an end threshold time; determining, by the classification server system, the at least one intermediate stop based on an intermediate threshold time; In determining the at least one intermediate stop, The method of claim 4 , wherein the intermediate threshold time is less than the end threshold time.

6. A trip included in the plurality of trips, calculating, by the classification server system, a total trip duration based on the start time and the end time; calculating, by the classification server system, a trip mileage based on the distance between each geographic location in the trip; calculating, by the classification server system, a ratio of the trip distance to an ideal distance between the start location and the end location of the trip; generating, by the classification server system, the label based on the total trip duration, the trip distance, and the ratio of the trip distance to the ideal distance between the start location and the end location; 2. The method of claim 1, further comprising: classifying by:

7. classifying each trip using a machine classifier; 2. The method of claim 1, further comprising: retraining, by the classification server system, the machine classifier based on the classified trips.

8. One or more processors; A computing device comprising: The instructions, when executed by the one or more processors, cause the computing device to: acquiring telematics data including a plurality of geographic locations and a plurality of times indicating when a vehicle was at each geographic location; determining a plurality of trips based on the telematics data; determining a plurality of characteristics for each trip in the plurality of trips; classifying each trip based on the plurality of features for each trip included in the plurality of trips; In determining the plurality of trips, Each trip included in the plurality of trips includes a start location, a start time when the vehicle was at the start location, an end location, and an end time when the vehicle was at the end location; the start location and the end location are indicated at the plurality of geographic locations; In classifying each trip, a classified trip including the plurality of features, a label indicating whether the trip is a business trip or a personal trip, and a confidence metric indicating the probabilistic likelihood that the label correctly identifies the class of the trip; A computing device, comprising: a computing device configured to: record and store information about a vehicle on a network; a computing device configured to store and store information about the vehicle on a network;

9. The instructions, when executed by the one or more processors, cause the computing device to:

10. The computing device of claim 8, further configured to obtain the telematics data from a mobile device associated with an operator of the vehicle.

10. The telematics data further includes a driver identifier for identifying a driver of the vehicle; The instructions, when executed by the one or more processors, cause the computing device to:

10. The computing device of claim 8, further configured to classify the driver as a commercial driver or a personal driver based on the classified trips.

11. 10. The computing device of claim 8, wherein the plurality of features for a trip includes at least one intermediate stop at a point of interest (POI) visited by the vehicle.

12. The instructions, when executed by the one or more processors, cause the computing device to: determining the end location of a trip included in the plurality of trips based on an end threshold time; determining the at least one intermediate stop based on an intermediate threshold time; In determining the at least one intermediate stop, The computing device of claim 11 , wherein the intermediate threshold time is less than the end threshold time.

13. The instructions, when executed by the one or more processors, cause the computing device to: A trip included in the plurality of trips, calculating a total trip duration based on the start time and the end time; calculating a trip mileage based on a distance between each geographic location in the trip; calculating a ratio of the trip distance to an ideal distance between the start location and the end location of the trip; generating the label based on the total trip duration, the trip distance, and the ratio of the trip distance to the ideal distance between the start location and the end location; 10. The computing device of claim 8, further configured to classify by:

14. The instructions, when executed by the one or more processors, cause the computing device to: classifying each trip using a machine classifier; 10. The computing device of claim 8, further comprising: retraining the machine classifier based on the classified trips.

15. A non-transitory machine-readable medium storing a plurality of instructions that, when executed by one or more processors, cause the one or more processors to: acquiring telematics data including a plurality of geographic locations and a plurality of times indicating when the vehicle was at each geographic location; determining a plurality of trips based on the telematics data; determining a plurality of characteristics for each trip in the plurality of trips; classifying each trip based on the plurality of features for each trip included in the plurality of trips; In the step of determining a plurality of trips, Each trip included in the plurality of trips includes a start location, a start time when the vehicle was at the start location, an end location, and an end time when the vehicle was at the end location; the start location and the end location are indicated at the plurality of geographic locations; In the step of classifying each trip, a classified trip including the plurality of features, a label indicating whether the trip is a business trip or a personal trip, and a confidence metric indicating the probabilistic likelihood that the label correctly identifies the class of the trip; The non-transitory machine-readable medium, wherein the business trip is a trip during which the vehicle is operated for business purposes and the personal trip is a trip during which the vehicle is operated for personal use.

16. The instructions, when executed by the one or more processors, cause the one or more processors to:

20. The non-transitory machine-readable medium of claim 15, further comprising obtaining the telematics data from a mobile device associated with an operator of the vehicle.

17. The instructions, when executed by the one or more processors, cause the one or more processors to: classifying the vehicle driver as a professional driver or a personal driver based on the classified trips; 20. The non-transitory machine-readable medium of claim 15, wherein the driver is indicated in the telematics data.

18. 16. The non-transitory machine-readable medium of claim 15, wherein the plurality of features for a trip includes at least one intermediate stop at a point of interest (POI) visited by the vehicle.

19. The instructions, when executed by the one or more processors, cause the one or more processors to: determining the end location of a trip included in the plurality of trips based on an end threshold time; determining the at least one intermediate stop based on an intermediate threshold time; In the step of determining at least one intermediate stop, 20. The non-transitory machine-readable medium of claim 18, wherein the intermediate threshold time is less than the end threshold time.

20. The instructions, when executed by the one or more processors, cause the one or more processors to: A trip included in the plurality of trips, calculating a total trip duration based on the start time and the end time; calculating a trip mileage based on a distance between each geographic location in the trip; calculating a ratio of the trip distance to an ideal distance between the start location and the end location of the trip; generating the label based on the total trip duration, the trip distance, and the ratio of the trip distance to the ideal distance between the start location and the end location; 20. The non-transitory machine-readable medium of claim 15, further comprising the step of: classifying by:

Images