US20220157094A1 - System and Method for Analyzing Vehicle Data - Google Patents
System and Method for Analyzing Vehicle Data Download PDFInfo
- Publication number
- US20220157094A1 US20220157094A1 US17/590,936 US202217590936A US2022157094A1 US 20220157094 A1 US20220157094 A1 US 20220157094A1 US 202217590936 A US202217590936 A US 202217590936A US 2022157094 A1 US2022157094 A1 US 2022157094A1
- Authority
- US
- United States
- Prior art keywords
- vehicle
- data
- driving
- vehicle data
- driving pattern
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012502 risk assessment Methods 0.000 claims abstract description 12
- 238000005259 measurement Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 description 85
- 238000004891 communication Methods 0.000 description 31
- 238000013507 mapping Methods 0.000 description 26
- 238000010801 machine learning Methods 0.000 description 19
- 238000004422 calculation algorithm Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000010191 image analysis Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009877 rendering Methods 0.000 description 2
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
- G07C5/085—Registering performance data using electronic data carriers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
- G06N3/105—Shells for specifying net layout
Definitions
- the following relates generally to analyzing vehicle data.
- Usage-based insurance is a type of vehicle insurance that may be used to set or adjust the cost of a premium paid by a user based on factors such as the driving habits of the user, the type of vehicle being used, how often the vehicle is used, or where the vehicle is being used, to name a few.
- UBI may also be referred to as “pay as you drive” or “pay how you drive” insurance.
- UBI programs typically require a device to be installed in or coupled to a vehicle or require an application to be installed in another device such as a smart phone that is meant to be located in the vehicle while the user is driving.
- Such devices or applications are often referred to as telematics devices or telematics applications and are normally connectable to a telematics system that collects driver data for several users.
- a UBI program may analyze certain variables for a UBI model. For example, speed, acceleration, and distance variables may be determined from the collected data and used in a UBI model to rate the driver. Many auto rating variables for such UBI models are not causal. Instead, many of these variables serve as a proxy to the cause of a change to the variable. Using proxy variables can increase the variance of the estimates and thus the overall premiums calculated in a UBI program.
- FIG. 1 is a schematic diagram of an example computing environment.
- FIG. 2 is a block diagram of an example configuration of a driving pattern analysis system.
- FIG. 3 is a block diagram of an example configuration of a telematics device.
- FIG. 4 is a block diagram of an example configuration of a telematics system.
- FIG. 5 is an example of a graphical output displaying driving paths in a geographic area.
- FIG. 6 is an example of a graphical output displaying speed maps in a geographic area.
- FIG. 7 is a flow diagram of an example of computer executable instructions for collecting vehicle data for a driving pattern analysis.
- FIG. 8 is a flow diagram of an example of computer executable instructions for analyzing vehicle data.
- a cause of risk in providing auto insurance can be linked to driving habits. Driving habits can be accurately portrayed using a customer's vehicle position, speed, and acceleration at each point in time. Such data points can be collected, for example, on a second-by-second basis and used to assess risk. This provides an opportunity to improve the pricing scheme used in a UBI system in order to be fairer and more accurate.
- a system and method may be provided that leverage such data to create a risk assessment process based on long term driving habits.
- Image processing and analysis techniques may be used to identify and analyze driving paths and speed maps of users in order to assess risks related to driving patterns. Deep learning may also be applied to build a model based on the paths and the data associated with these paths (e.g., frequency of use, speed at different portions, etc.).
- the assessed risks can be provided to or used by a pricing team to apply an improved pricing scheme, e.g., by ignoring traditional constraints and to view driving patterns in context rather than focusing on individual data points like total speed, number of accelerations, etc.
- a device for analyzing vehicle data includes a processor, a data interface coupled to the processor, and a memory coupled to the processor.
- the memory stores computer executable instructions that when executed by the processor cause the processor to obtain a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle.
- the computer executable instructions also cause the processor to analyze the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and provide an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
- a method of analyzing vehicle data is executed by a device having a processor and includes obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle.
- the method also includes analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
- non-transitory computer readable medium for analyzing vehicle data.
- the computer readable medium includes computer executable instructions for obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle.
- the computer readable medium further includes computer executable instructions for analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
- the set of vehicle data includes a plurality of location measurements and a corresponding plurality of speed measurements
- the device is further configured to associate the corresponding plurality of speed measurements with the at least one driving path using the corresponding plurality of location measurements; and utilize the plurality of speed measurements in identifying the at least one driving pattern.
- the map image includes at least one repeated driving path that is distinguishable by an image processing technique from at least one other driving path to be indicative of a higher frequency of use.
- the at least one path includes a vehicle trip with a plurality of portions each identifying respective vehicle speed data.
- the vehicle data can include an acceleration value.
- the device is configured to obtain the model, the model having been generated from vehicle data for a plurality of vehicles; and update the model with the at least one driving path.
- the vehicle data collected from the plurality of vehicles can include at least one similar path traveled by another vehicle.
- the device can be configured to communicate via the data interface with a telematics system connected to the vehicle for collecting the vehicle data.
- the device can communicate with a telematics device used or having been used in the vehicle to obtain the vehicle data.
- the indication of the at least one driving pattern used in the risk assessment can be used to calculate an insurance premium for a usage-based insurance program.
- the indication of the at least one driving pattern can be combined with one or more additional factors in calculating the insurance premium.
- An additional factor can include a road type associated with the at least one path, the road type being determinable from data associated with the geographic area.
- the plurality of location measurements can each include a latitude and a longitude, the set of vehicle data having been generated at least in part by a global positioning system receiver positioned in the vehicle while collecting the vehicle data.
- FIG. 1 illustrates an exemplary computing environment 10 in which a driving pattern analysis system 12 communicates with a telematics system 18 to obtain vehicle data 20 collected by the telematics system 18 from in-vehicle telematics devices 16 over a communications network 14 .
- the in-vehicle telematics devices 16 may include devices that are embedded in a vehicle 17 (e.g., in-vehicle navigation or infotainment systems), devices that are coupled to a data port in the vehicle 17 (e.g., dongles or other custom devices connected to an interface such as an on-board diagnostics (OBD) connector), or personal devices associated with a driver or other occupant of the vehicle and having a telematics application running thereon (e.g., smartphones, gaming devices, tablets, etc.).
- OBD on-board diagnostics
- the telematics devices 16 of any of these types are capable of determining data and information that is indicative of the location and speed of the vehicle 17 at various points in time. For example, in the configuration shown in FIG.
- the devices 16 are in communication with a global positioning system (GPS) having a number of GPS satellites 19 that provide location-based information to an application running on or connected to the devices 16 .
- GPS global positioning system
- other types of devices 16 such as dongles connected to an OBD port in the vehicle 17 may have access to at least speed information that is calculated by the vehicle 17 .
- the driving pattern analysis system 12 is an entity within an insurance provider system 28 .
- the driving pattern analysis system 12 may also be provided as a standalone entity, such as an independent service that can communicate with multiple insurance provider systems 28 .
- the telematics system 18 is shown in FIG. 1 as a separate entity, the telematics system 18 may also be integrated into the insurance provider system 28 or a UBI program 22 within the insurance provider system 28 .
- the driving pattern analysis system 12 in this example is separate from and coupled to at least a pricing module 24 of the UBI program 22 .
- the UBI program 22 may also have access to other data 26 within the insurance provider system 28 , such as customer data.
- the UBI program 22 , driving pattern analysis system 12 , and telematics system 18 are delineated as shown in FIG. 1 for illustrative purposes and such a configuration should not be considered limiting.
- the insurance provider system 28 can be associated with a variety of business types, such as insurance providers, financial institutions having insurance products, government entities, private lenders, etc.
- the vehicle data 20 that is collected by the telematics system 18 may include any data that the telematics devices 16 are capable of collecting.
- the telematics devices 16 may typically collect at least latitude and longitude values (collectively indicative of a location) and speed values. Other values such as acceleration can be collected if available or computed based on the location and speed values.
- the telematics system 18 and driving pattern analysis system 12 can include one or more devices such as servers capable of communicating with each other and/or the network 14 and with the insurance provider system 28 .
- the driving pattern analysis system 12 may have access to the vehicle data 20 directly or via the telematics system 18 .
- vehicle data 20 may be accessed via an Internet or other remote data connection such as an application programming interface (API).
- API application programming interface
- telematics device 16 can include, but are not limited to, a data communication device; and these may include a mobile or smart phone, a laptop computer, a tablet computer, a notebook computer, a hand-held computer, a personal digital assistant, an embedded device, a virtual reality device, an augmented reality device, third party portals, a personal computer, and any additional or alternate computing device, and may be operable to transmit and receive data across communication network 14 .
- a data communication device may include a mobile or smart phone, a laptop computer, a tablet computer, a notebook computer, a hand-held computer, a personal digital assistant, an embedded device, a virtual reality device, an augmented reality device, third party portals, a personal computer, and any additional or alternate computing device, and may be operable to transmit and receive data across communication network 14 .
- Communication network 14 may include a telephone network, cellular, and/or data communication network to connect different types of devices as will be described in greater detail below.
- the communication network 14 may include a private or public switched telephone network (PSTN), mobile network (e.g., code division multiple access (CDMA) network, global system for mobile communications (GSM) network, and/or any 3G, 4G, or 5G wireless carrier network, etc.), WiFi or other similar wireless network, and a private and/or public wide area network (e.g., the Internet). While the configuration shown in FIG. 1 illustrates the UBI program 22 and driving pattern analysis system 12 communicating with the communications network 14 via the telematics system 18 , this is done for illustrative purposes and these devices may also connect directly to communications network 14 .
- the insurance provider system 28 may have a customer relationship with the users of the telematics devices 16 and/or vehicles 17 and therefore may communicate with those users separately, which may include communications over the communications network 14 or another network or medium (not shown).
- the computing environment 10 may also include a cryptographic server (not shown) for performing cryptographic operations and providing cryptographic services (e.g., authentication (via digital signatures), data protection (via encryption), etc.) to provide a secure interaction channel and interaction session, etc.
- a cryptographic server can also be configured to communicate and operate with a cryptographic infrastructure, such as a public key infrastructure (PKI), certificate authority (CA), certificate revocation service, signing authority, key server, etc.
- PKI public key infrastructure
- CA certificate authority
- certificate revocation service e.g., signing authority, key server, etc.
- the cryptographic server and cryptographic infrastructure can be used to protect the various data communications described herein, to secure communication channels therefor, authenticate parties, manage digital certificates for such parties, manage keys (e.g., public and private keys in a PKI), and perform other cryptographic operations that are required or desired for particular applications of the telematics devices 16 , vehicles 17 , telematics system 18 , UBI program 22 , driving pattern analysis system 12 , and insurance provider system 28 .
- the cryptographic server may be used to protect the data or results of the data by way of encryption for data protection, digital signatures or message digests for data integrity, and by using digital certificates to authenticate the identity of the users and devices within the computing environment 10 , to inhibit data breaches by adversaries. It can be appreciated that various cryptographic mechanisms and protocols can be chosen and implemented to suit the constraints and requirements of the particular deployment of the computing environment 10 as is known in the art.
- the driving pattern analysis system 12 may include one or more processors 30 , a communications module 32 , and a data interface module 34 for interfacing with the vehicle data 20 to receive or retrieve vehicle data 20 associated with a customer, client, or vehicle 17 for which a driving pattern analysis is being conducted.
- the data interface 34 may also be used to interface with the UBI program 22 to obtain the other data 26 , or to interface directly with the other data 26 by having the appropriate permissions or credentials issued by the insurance provider system 28 .
- Communications module 32 enables the driving pattern analysis system 12 to communicate with one or more other components of the computing environment 10 , such as telematics system 18 , UBI program 22 (e.g., pricing module 24 ), vehicles 17 , and telematics devices 16 , via a bus or other communication network, such as the communication network 14 .
- the driving pattern analysis system 12 includes at least one memory or memory device that can include a tangible and non-transitory computer-readable, medium having stored therein computer programs, sets of instructions, code, or data to be executed by processor 30 .
- FIG. 2 illustrates examples of modules, tools and engines stored in memory on the driving pattern analysis system 12 and operated by the processor 30 . R can be appreciated that any of the modules, tools, and engines shown in FIG. 2 may also be hosted on the telematics system 18 or by the UBI program 22 (or other component of the insurance provider system 28 ) as discussed above.
- the driving pattern analysis system 12 includes a driving pattern analysis engine 36 for analyzing and evaluating driving patterns of vehicles 17 using the vehicle data 20 and other data associated with a geographic area in which the vehicle 17 travels.
- the driving pattern analysis system 12 may also include a machine learning engine 38 , a classification module 40 , a training module 42 , a geolocation tool 44 , a UBI interface, module 46 , a mapping tool 48 , an insurance system interface module 50 , and a telematics system interface module 52 .
- the machine learning engine 38 is used by the driving pattern analysis engine 36 (or “analysis engine 36 ” for brevity) to generate and train models 350 (see also FIG. 8 ) to be used in evaluating vehicle data 20 and associated geolocation or mapping data, for determining driving patterns that can be used in UBI pricing.
- the analysis engine 36 may utilize or otherwise interface with the machine learning engine 38 to both classify data currently being analyzed to generate the models, and to train classifiers using data that is continually being processed and accumulated by the telematics devices 16 and telematics system 18 .
- the machine learning engine 38 may also perform operations that classify the vehicle data 20 (or information derived from the vehicle data 20 ) in accordance with corresponding classifications parameters, e.g., based on an application of one or more machine learning algorithms to the data.
- the machine learning algorithms may include, but are not limited to, a one-dimensional, convolutional neural network model (e.g., implemented using a corresponding neural network library, such as Keras®), and the one or more machine learning algorithms may be trained against, and adaptively improved using, elements of previously classified profile content identifying expected datapoints.
- the machine learning engine 38 may further process each data point to identify, and extract, a value characterizing the corresponding one of the classification parameters, e.g., based on an application of one or more additional machine learning algorithms to each of the data points.
- the additional machine learning algorithms may include, but are not limited to, an adaptive natural language processing algorithm that, among other things, predicts starting and ending indices of a candidate parameter value within each data point, extracts the candidate parameter value in accordance with the predicted indices, and computes a confidence score for the candidate parameter value that reflects a probability that the candidate parameter value accurately represents the corresponding classification parameter.
- the one or more additional machine learning algorithms may be trained against, and adaptively improved using, the locally maintained elements of previously classified data. Classification parameters may be stored and maintained using the classification module 40 , and training data may be stored and maintained using the training module 42 .
- classification data stored in the classification module 40 may identify one or more parameters, e.g., “classification” parameters, that facilitate a classification of corresponding elements or groups of recognized data points based on any of the exemplary machine learning algorithms or processes described herein.
- the one or more classification parameters may correspond to parameters that can identify expected and unexpected data points for certain types of data.
- the additional, or alternate, machine learning algorithms may include one or more adaptive, natural-language processing algorithms capable of parsing each of the classified portions of the data being examined and predicting a starting and ending index of the candidate parameter value within each of the classified portions.
- adaptive, natural-language processing algorithms include, but are not limited to, natural-language processing models that leverage machine learning processes or artificial neural network processes, such as a named entity recognition model implemented using a SpaCy® library.
- Examples of these adaptive, machine learning processes include, but are not limited to, one or more artificial, neural network models, such as a one-dimensional, convolutional neural network model, e.g., implemented using a corresponding neural network library, such as Keras®.
- the one-dimensional, convolutional neural network model may implement one or more classifier functions or processes, such a Softmax® classifier, capable of predicting an association between a data point and a single classification parameter and additionally, or alternatively, multiple classification parameters.
- machine learning engine 38 may perform operations that classify each of the discrete elements of the vehicle and/or geographic area-related data being examined as a corresponding one of the classification parameters, e.g., as obtained from classification data stored by the classification module 40 .
- the outputs of the machine learning algorithms or processes may then be used by the analysis engine 36 to generate and train models and to use such models to determine driving patterns from data and information observed or derived from the vehicle data 20 and/or related or associated geolocation or mapping data for a relevant geographic area.
- the analysis engine 36 may also use a set of rules, a weighted formula or any other statistical or mathematical function or tool to evaluate the vehicle data 20 and related geolocation/mapping data, or information derived therefrom.
- the UBI interface module 46 may be used to provide one or more outputs based on the results generated by the analysis engine 36 .
- Example outputs include indicators of driving patterns and/or graphical outputs that can be used to visualize driving paths and/or speed paths identified using image generation and image processing techniques employed by (or input to) the analysis engine 36 and used to assess driving patterns.
- the graphical output may also be displayed for a user or administrator or may be used internally by the driving pattern analysis system 12 or pricing module 24 with respect to driving patterns and pricing derived therefrom. That is, graphical outputs generated by the driving pattern analysis system 12 may be displayed to a user or may be machine-processed without a need to be displayed.
- the geolocation tool 44 may be used by the driving pattern analysis system 12 to identify geolocation data associated with location measurements taken in a geographic area. For example, the driving pattern analysis system 12 can identify a geographic area from a set of location measurements in the vehicle data 20 and use the geolocating tool 44 to identify additional entities and features within that geographic area.
- the mapping tool 48 may also be used by the driving pattern analysis system 12 to obtain or generate mapping data associated with the geographic area, including existing roadways, intersections, landmarks, and topographical features. For example, when associating location data with the geographic area, the mapping tool 48 may be used to generate a visual map on which the location measurements of a vehicle 17 and the associated geolocation data can be plotted.
- mapping tool 48 can be performed by the mapping tool 48 or by the analysis engine 36 , or both.
- the geolocation tool 44 , mapping tool 48 , and analysis engine 36 are shown as being delineated in FIG. 2 for illustrative purposes only and the associated functionality may also be integrated into the analysis engine 36 or be provided by a location-based application or service accessible to the analysis engine 36 .
- the geolocation tool 44 and/or mapping tool 48 may also be provided by one or more third party APIs that are accessed by the driving pattern analysis system 12 to integrate geolocating and mapping services into the functionality provided by the analysis engine 36 .
- the insurance system interface module 50 provides one or more interfaces to the insurance provider system 28 , e.g., to enable the driving pattern analysis system 12 to access or interface with the other data 26 stored by the insurance provider system 28 .
- the insurance system interface module 50 can also be used to access or otherwise interact or communicate with internal programs, devices, or systems of the insurance provider system 28 that can provide any suitable information that can be used in analyzing driving patterns, e.g., customer information.
- the telematics system interface module 52 is shown in FIG. 2 for illustrative purposes and the functionality thereof may be provided by the UBI interface module 46 or insurance system interface module 50 .
- the telematics system interface module 52 enables the driving pattern analysis system 12 to interface with the telematics system 18 (e.g., directly or via the UBI program 22 ) to obtain vehicle data 20 .
- the telematics device 16 may include one or more processors 60 , a communications module 62 , a data interface module, 64 , a telematics client app 66 , and a data store 70 storing device data 72 and application data 74 .
- Communications module 62 enables the telematics device 12 to communicate with one or more other components of the computing environment 10 , such as a vehicle 17 , the telematics system 18 , driving pattern analysis system 12 , and insurance provider system 28 (or one of its components), via a bus or other communication network, such as the communication network 14 . While not delineated in FIG.
- the telematics device 16 includes at least one memory or memory device that can include a tangible and non-transitory computer-readable medium having stored therein computer programs, sets of instructions, code, or data to be executed by processor 60 .
- FIG. 3 illustrates examples of modules and applications stored in memory on the telematics device 16 and operated by the processor 60 . It can be appreciated that any of the modules and applications shown in FIG. 3 may also be hosted externally by the telematics system 18 and be available to the telematics device 16 , e.g., via the communications module 62 .
- the data interface module, 64 is shown in FIG. 3 for illustrative, purposes only and the functionality thereof may also be provided by the communications module 62 , e.g., when raw location and speed data to be collected by the telematics device 16 is available via a connection to the communications network 14 .
- the telematics device 16 includes a telematics client app 66 for enabling the user of the telematics device 16 to initiate and operate a UBI application in association with the insurance provider system 28 .
- the telematics client app 66 may include a display module for rendering GUIs and other visual output on a display device such as a display screen, and an input module for processing user or other inputs received at the telematics device 16 , e.g., via a touchscreen, input button, transceiver, microphone, keyboard, etc.
- the telematics device 16 may also include the same or a similar geolocation tool 44 and/or mapping tool 48 used by the driving pattern analysis system 12 .
- the geolocation tool 44 or mapping tool 48 may include a module or application that is configured to act as a GPS receiver for obtaining GPS data by communicating with one or more GPS satellites 19 . This can be done using or in conjunction with the communications module 32 or data interface module 34 of the telematics device 16 . It can be appreciated that the geolocation tool 44 and mapping tool 48 are shown in both FIGS. 2 and 3 to illustrate that such services may be available to both the client- and server-based devices for use in mapping geographic areas and identifying geolocated entities and vehicle data 20 in a map interface.
- the telematics device 16 may also include other applications not shown in FIG. 3 , such as a web browser application for accessing Internet-based content, e.g., via a mobile or traditional website.
- the data store 70 may be used to store device data 72 , such as, but not limited to, an IP address or a MAC address that uniquely identifies telematics device 16 within environment 10 .
- the data store 70 may also be used to store application data 74 , such as, but not limited to, login credentials, user preferences, cryptographic data (e.g., cryptographic keys), etc.
- the telematics system 18 may include one or more processors 80 , a communications module 82 , a data interface module 84 , a UBI interface module 86 , a telematics device interface module 88 , a driving pattern analysis system interface module 90 , and a data storage for the vehicle data 20 .
- Communications module 82 enables the telematics system 18 to communicate with one or more other components of the computing environment 10 , such as a vehicle 17 , the telematics device 16 , driving pattern analysis system 12 , and insurance provider system 28 (or one of its components), via a bus or other communication network, such as the communication network 14 , While not delineated in FIG. 4 , the telematics system 18 includes at least one memory or memory device that can include a tangible and non-transitory computer-readable medium having stored therein computer programs, sets of instructions, code, or data to be executed by processor 80 .
- FIG. 4 illustrates examples of modules and applications stored in memory on the telematics system 18 and operated by the processor 60 .
- the UBI interface module 86 may be the same or similar to the UBI interface module 46 used by the driving pattern analysis system 12 to interface with the UBI program 22 to provide access to collected vehicle data 20 for one or more users.
- the telematics device interface module 88 may be used to interface and communicate with one or more telematics devices 16 either directly or via a connection with the vehicle 17 .
- the driving pattern analysis system interface module 90 may be used to interface and communicate with the driving pattern and analysis system 12 directly. It can be appreciated that the modules 86 , 88 , and 90 are shown as being delineated in FIG. 4 for illustrative purposes only and such modules could be combined into any one or more module or application while providing the functionality illustrated herein.
- the vehicle data 20 is shown as being integrated in the telematics system 18 in FIG. 4 but may also be located externally to the telematics system 18 as shown in FIG. 1 .
- the vehicle data 20 can be stored by a third-party cloud-based storage service and accessed by entities with the appropriate permissions and credentials, entities such as the telematics system 18 , insurance provider system 28 , driving pattern analysis system 12 , etc.
- FIGS. 2 to 4 For ease of illustration and various other components would be provided and utilized by the driving pattern analysis system 12 , telematics device 16 , and telematics system 18 as is known in the art.
- any module or component exemplified herein that executes instructions may include or otherwise have access to computer readable media such as storage media, computer storage media, or data storage devices (removable and/or non-removable) such as, for example, magnetic disks, optical disks, or tape.
- Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data.
- Examples of computer storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by an application, module, or both. Any such computer storage media may be part of the telematics device 16 , telematics system 18 , insurance provider system 28 , driving pattern analysis system 12 , UBI program 22 , pricing module 24 , or accessible or connectable thereto. Any application or module herein described may be implemented using computer readable/executable instructions that may be stored or otherwise held by such computer readable media.
- the vehicle data 20 and data associated with a geographic area may be used by the driving pattern analysis system 12 to identify driving patterns and analyze those driving patterns to inform a pricing module 24 for the UBI program 22 in determining UBI-based insurance pricing.
- the vehicle data 20 includes at least location measurements and associated time stamps for each location measurement.
- the vehicle data 20 may also typically include speed measurements, however, it can be appreciated that speed and other measurements such as acceleration can be computed by the driving pattern analysis system 12 from the location measurements and the time stamps (i.e., by determining how long it takes for the vehicle 17 to travel a certain distance).
- the vehicle data 20 may be raw data such as latitude, longitude and speed measurements with associated time stamps. This vehicle data 20 is associated with the mapping and geolocation data for an associated geographic area in which the vehicle data 20 was captured to provide additional context and to permit a deeper analysis alongside other traditional variables used in UBI pricing.
- a graphical output 100 which includes a geographic map image 102 that may be generated from the mapping and geolocation data provided by the geolocation tool 44 and mapping tool 48 .
- the vehicle data 20 that is associated with a vehicle 17 and telematics device 16 may be associated with the geographic map image 102 and can be used to visualize one or more driving paths 104 .
- the raw location data may be plotted on the map image 102 and resolved or otherwise corrected to align with preexisting roadways.
- Such plotting can be performed by the geolocation tool 44 , mapping tool 48 or analysis engine 36 by implementing an image rendering or processing technique to generate visual representations of one or more paths 104 driven by the vehicle 17 .
- Each data point plotted along a path 104 has an associated location, speed, and time stamp, which enables multiple types of paths to be visualized, as discussed below.
- darkened driving paths 106 can be identified when individual driving paths 104 are repeated or otherwise include overlapping portions.
- the analysis engine 36 of the driving pattern and analysis system 12 can apply one or more image analysis techniques to the driving paths 104 to assess a driving pattern.
- the number of darkened paths 106 can be identified to determine daily or frequent routes, geolocation data can be referenced to determine a type of road or heavy traffic zone, or the number of paths or overall distance can be used to determine driving frequency, etc.
- the graphical output 120 includes a geographic map image 122 that, as above, may be generated from the mapping and geolocation data provided by the geolocation tool 44 and mapping tool 48 .
- the vehicle data 20 for a particular driving path 124 may be shown with a number of segments 126 differentiated by color or shade to indicate speed variations over the driving path 124 . That is, each driving path 124 (or driving paths 104 taken from image 100 ) can be separately analyzed to determine driving patterns such as speed and acceleration within the path 124 .
- the analysis engine 36 of the driving pattern and analysis system 12 can apply one or more image analysis techniques to the speed pattern to determine a driving pattern.
- the driving paths 104 , 124 and speed patterns can be collectively referred to as data inputs to determine a driving pattern or can be considered driving patterns themselves.
- any driving path 104 shown in FIG. 5 may be selected to initiate the graphical output 120 in FIG. 6 for that specific driving path 104 to show speed data as path 124 .
- the graphical outputs 100 , 102 generated by the analysis engine 36 may be analyzed by the analysis engine 36 itself or may be provided to the pricing module 24 as additional variable with any additional analysis outputs generated by the analysis engine 36 . That is, the driving patterns may be determined directly by the analysis engine 36 or may be indicated or identified by the analysis engine 36 for the pricing module 24 or UBI program 22 more generally for a subsequent step in a pricing calculation. As such, operations described herein may be performed by one or more of the elements of the computing environment 10 according to the principles discussed herein.
- FIG. 7 an example embodiment of computer executable instructions for collecting vehicle data 20 for a driving pattern analysis is shown.
- the example shown in FIG. 7 is based on the example configuration for the computing environment 10 in FIG. 1 in which the telematics system 18 collects vehicle data 20 from telematics devices 16 .
- the telematics device 16 collects speed measurements with associated time stamps, which are associated with a vehicle 17 and driver/user.
- the telematics device 16 collects location measurements with associated time stamps, e.g., via access to a GPS system connected to the telematics device 16 or vehicle 17 .
- the telematics device 16 in this example is configured to report a set of vehicle data 20 to the telematics system 18 at block 204 .
- the frequency of reporting vehicle data 20 at block 204 can vary based on user preferences, system preferences or constraints such as available bandwidth or data communication restrictions.
- the telematics device 16 can locally store its collected vehicle data 20 and report such data as frequently as in real-time or near-real-time, or on a less frequent basis such as intra-daily, daily or weekly.
- the set of vehicle data 20 collected by the telematics device 16 is received by the telematics system 18 at block 206 and the received vehicle data 20 is stored at block 208 .
- the vehicle data 20 that is received and stored may be associated with a user or vehicle account in the datastore used for the vehicle data 20 .
- the telematics system 18 in this example is configured to report vehicle data 20 collected from one or more telematics devices 16 to the UBI program 22 at block 210 .
- the telematics system 18 may be responsible for collecting data from a number of customers associated with the UBI program 22 for the insurance provider system 28 and may be instructed to report the vehicle data 20 to the UBI program 22 .
- the UBI program 22 may store the received vehicle data 20 with the other data 26 within the insurance provider system 28 .
- the UBI program 22 may also be provided with a permission and/or credential to access the vehicle data 20 directly from the datastore or service utilized by the telematics system 18 .
- the telematics system 18 may also provide the vehicle data 20 to the driving pattern analysis system 12 at block 212 , either by sending the data thereto, or by providing access via a credential to access the datastore or service used by the telematics system 18 or via the access provided to the UBI program 22 .
- blocks 210 and 212 may be executed using a single operation or communication between the telematics system 18 and the insurance provider system 28 .
- the telematics system 18 may be configured to send an alert to the UBI program 22 and/or driving pattern analysis system 12 when a new set or new sets of vehicle data 20 are available for processing.
- the driving pattern analysis system 12 obtains the vehicle data 20 at block 214 , either directly or via the UBI program 22 in this example.
- the vehicle data 20 thus obtained can be used to conduct a driving pattern analysis at block 216 as discussed above and described in greater detail below.
- the driving pattern analysis system 12 can provide one or more driving patterns to a risk assessment function, such as that used by the pricing module 24 of the UBI program 22 .
- the driving pattern(s) can be indicated using various output types, including graphical outputs such as those shown in FIGS. 5 and 6 .
- the outputs may also include numerical or statistical values, scores, weights, or rankings that can show, on a relative scale, a degree of driving behavior, either positive or negative, that can be used in calculating or adjusting an insurance premium.
- FIG. 8 an example embodiment of computer executable instructions for analyzing vehicle data 20 is shown.
- the operations illustrated in FIG. 8 may be executed by the analysis engine 36 of the driving pattern analysis system 12 according to the configuration shown in FIG. 2 within the computing environment 10 shown in FIG. 1 , however, the principles may apply in other configurations.
- the analysis engine 36 obtains the set of vehicle data 20 that is to be analyzed, e.g., by obtaining a set of vehicle data 20 associated with a single vehicle 17 (or a single driver of multiple vehicles 17 ) covering a certain period of time (e.g., a week, a month, a quarter, etc.).
- the geolocation tool 44 and mapping tool 48 may be used to generate a map image 102 , 122 and location and speed measurements may be associated with the map image 102 , 122 to generate a graphical output 100 , 120 .
- This can include resolving or adjusting datapoints to fit within predetermined driving paths such as roadways to allow driving paths 104 , 124 to be rendered using one or more image processing techniques in block 304 , as discussed above. That is, the graphical output 100 , 120 visualizes the vehicle data 20 within the map image 102 , 122 such that one or more vehicle-related paths are identified. For example, a collection of successive location measurements can trace out a driving path as shown in FIG.
- the path(s) and associated geolocation/mapping data are analyzed by the analysis engine 36 to identify one or more driving patterns.
- the geolocation/mapping data may include, for example, posted road speeds, road type (e.g., city street versus freeway), elevation, time of day (e.g., sunset and sunrise conditions), geographic area (e.g., rural versus urban), traffic data, weather data, etc.
- This geolocation/mapping data can then be associated with the actual driven path(s) and the speed(s) used by the vehicle 17 along those paths to enable the analysis engine 36 and/or the pricing module 24 to generate deeper insights. For example, frequently used driving paths may be indicative of a daily commute, and road types may be indicative of highway versus city driving. Moreover, other factors such as traffic and weather can be accounted for with the time stamp information associated with the location and speed measurements.
- the path(s) identified at block 304 and the analyses conducted at block 306 can be influenced by and/or contribute to one or more models 350 that may be trained and updated by the machine learning module 38 of the driving pattern analysis system 12 using vehicle data 20 having been generated by multiple vehicles 17 .
- certain observations and inferences can be determined that can benefit subsequent analyses. For example, relatively high vehicle speeds along a certain driving path 124 can be observed as an anomaly and potentially negative driving pattern when compared to a sample set of driving paths 124 from other drivers that recorded a relatively lower speed.
- historical data from the same driver can be used, tracked, and modeled over time to determine if improvements or adjustments have been made in driving patterns and driving habits that can inform the pricing module 24 .
- an output indicative of a driving pattern may be provided by the driving pattern analysis system 12 to the pricing module 24 .
- this can include providing graphical outputs 100 , 120 for subsequent use by the pricing module 24 , variable scores for certain parameters as determined by the analysis engine 36 using the graphical outputs 100 , 120 , or a combination of such outputs. That is, the pricing module 24 and driving pattern analysis system 12 are delineated in the present example for illustrative purposes and such elements may be integral with each other and/or work in concert to assess and identify driving patterns or habits that can be used as additional variables in assessing risk related to such driving patterns.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Traffic Control Systems (AREA)
Abstract
A system and method are provided for analyzing vehicle data. The method is executed by a device having a processor and includes obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle. The method also includes analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
Description
- This application is a Continuation of U.S. patent application Ser. No. 16/542,000 filed on Aug. 15, 2019, entitled “System and Method for Analyzing Vehicle Data” and the entire contents of which is incorporated herein by reference.
- The following relates generally to analyzing vehicle data.
- Usage-based insurance (UBI) is a type of vehicle insurance that may be used to set or adjust the cost of a premium paid by a user based on factors such as the driving habits of the user, the type of vehicle being used, how often the vehicle is used, or where the vehicle is being used, to name a few. UBI may also be referred to as “pay as you drive” or “pay how you drive” insurance. UBI programs typically require a device to be installed in or coupled to a vehicle or require an application to be installed in another device such as a smart phone that is meant to be located in the vehicle while the user is driving. Such devices or applications are often referred to as telematics devices or telematics applications and are normally connectable to a telematics system that collects driver data for several users.
- With the collected data, a UBI program may analyze certain variables for a UBI model. For example, speed, acceleration, and distance variables may be determined from the collected data and used in a UBI model to rate the driver. Many auto rating variables for such UBI models are not causal. Instead, many of these variables serve as a proxy to the cause of a change to the variable. Using proxy variables can increase the variance of the estimates and thus the overall premiums calculated in a UBI program.
- Issues with auto rating variables can lead to issues in fairness in that, for example, not all young drivers are necessarily high-risk drivers. Moreover, using variables such as gender, age, territory, and marital status can lead to potential issues with discrimination. Due to these factors, some regions control or even forbid the use of such variables in determining insurance premiums.
- Embodiments will now be described with reference to the appended drawings wherein:
-
FIG. 1 is a schematic diagram of an example computing environment. -
FIG. 2 is a block diagram of an example configuration of a driving pattern analysis system. -
FIG. 3 is a block diagram of an example configuration of a telematics device. -
FIG. 4 is a block diagram of an example configuration of a telematics system. -
FIG. 5 is an example of a graphical output displaying driving paths in a geographic area. -
FIG. 6 is an example of a graphical output displaying speed maps in a geographic area. -
FIG. 7 is a flow diagram of an example of computer executable instructions for collecting vehicle data for a driving pattern analysis. -
FIG. 8 is a flow diagram of an example of computer executable instructions for analyzing vehicle data. - It will be appreciated that for simplicity and clarity of illustration, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements. In addition, numerous specific details are set forth in order to provide a thorough understanding of the example embodiments described herein. However, it will be understood by those of ordinary skill in the art that the example embodiments described herein may be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to obscure the example embodiments described herein. Also, the description is not to be considered as limiting the scope of the example embodiments described herein.
- A cause of risk in providing auto insurance can be linked to driving habits. Driving habits can be accurately portrayed using a customer's vehicle position, speed, and acceleration at each point in time. Such data points can be collected, for example, on a second-by-second basis and used to assess risk. This provides an opportunity to improve the pricing scheme used in a UBI system in order to be fairer and more accurate. A system and method may be provided that leverage such data to create a risk assessment process based on long term driving habits. Image processing and analysis techniques may be used to identify and analyze driving paths and speed maps of users in order to assess risks related to driving patterns. Deep learning may also be applied to build a model based on the paths and the data associated with these paths (e.g., frequency of use, speed at different portions, etc.). The assessed risks can be provided to or used by a pricing team to apply an improved pricing scheme, e.g., by ignoring traditional constraints and to view driving patterns in context rather than focusing on individual data points like total speed, number of accelerations, etc.
- Certain example systems and methods described herein enable vehicle data that has been collected in a telematics system to be used in determining driving patterns, e.g., for UBI pricing. In one aspect, there is provided a device for analyzing vehicle data. The device includes a processor, a data interface coupled to the processor, and a memory coupled to the processor. The memory stores computer executable instructions that when executed by the processor cause the processor to obtain a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle. The computer executable instructions also cause the processor to analyze the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and provide an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
- In another aspect, there is provided a method of analyzing vehicle data. The method is executed by a device having a processor and includes obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle. The method also includes analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
- In another aspect, there is provided non-transitory computer readable medium for analyzing vehicle data. The computer readable medium includes computer executable instructions for obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle. The computer readable medium further includes computer executable instructions for analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
- In certain example embodiments, the set of vehicle data includes a plurality of location measurements and a corresponding plurality of speed measurements, and the device is further configured to associate the corresponding plurality of speed measurements with the at least one driving path using the corresponding plurality of location measurements; and utilize the plurality of speed measurements in identifying the at least one driving pattern.
- In certain example embodiments, the map image includes at least one repeated driving path that is distinguishable by an image processing technique from at least one other driving path to be indicative of a higher frequency of use.
- In certain example embodiments, the at least one path includes a vehicle trip with a plurality of portions each identifying respective vehicle speed data. The vehicle data can include an acceleration value.
- In certain example embodiments, the device is configured to obtain the model, the model having been generated from vehicle data for a plurality of vehicles; and update the model with the at least one driving path. The vehicle data collected from the plurality of vehicles can include at least one similar path traveled by another vehicle.
- In certain example embodiments, the device can be configured to communicate via the data interface with a telematics system connected to the vehicle for collecting the vehicle data. The device can communicate with a telematics device used or having been used in the vehicle to obtain the vehicle data.
- In certain example embodiments, the indication of the at least one driving pattern used in the risk assessment can be used to calculate an insurance premium for a usage-based insurance program. The indication of the at least one driving pattern can be combined with one or more additional factors in calculating the insurance premium. An additional factor can include a road type associated with the at least one path, the road type being determinable from data associated with the geographic area.
- In certain example embodiments, the plurality of location measurements can each include a latitude and a longitude, the set of vehicle data having been generated at least in part by a global positioning system receiver positioned in the vehicle while collecting the vehicle data.
-
FIG. 1 illustrates anexemplary computing environment 10 in which a drivingpattern analysis system 12 communicates with atelematics system 18 to obtainvehicle data 20 collected by thetelematics system 18 from in-vehicle telematics devices 16 over acommunications network 14. The in-vehicle telematics devices 16 may include devices that are embedded in a vehicle 17 (e.g., in-vehicle navigation or infotainment systems), devices that are coupled to a data port in the vehicle 17 (e.g., dongles or other custom devices connected to an interface such as an on-board diagnostics (OBD) connector), or personal devices associated with a driver or other occupant of the vehicle and having a telematics application running thereon (e.g., smartphones, gaming devices, tablets, etc.). Thetelematics devices 16 of any of these types, are capable of determining data and information that is indicative of the location and speed of thevehicle 17 at various points in time. For example, in the configuration shown inFIG. 1 , thedevices 16 are in communication with a global positioning system (GPS) having a number ofGPS satellites 19 that provide location-based information to an application running on or connected to thedevices 16. However, it can be appreciated that other types ofdevices 16 such as dongles connected to an OBD port in thevehicle 17 may have access to at least speed information that is calculated by thevehicle 17. - In the example configuration shown in
FIG. 1 , the drivingpattern analysis system 12 is an entity within aninsurance provider system 28. However, it can be appreciated that the drivingpattern analysis system 12 may also be provided as a standalone entity, such as an independent service that can communicate with multipleinsurance provider systems 28. Similarly, while thetelematics system 18 is shown inFIG. 1 as a separate entity, thetelematics system 18 may also be integrated into theinsurance provider system 28 or aUBI program 22 within theinsurance provider system 28. The drivingpattern analysis system 12 in this example is separate from and coupled to at least apricing module 24 of theUBI program 22. TheUBI program 22 may also have access toother data 26 within theinsurance provider system 28, such as customer data. TheUBI program 22, drivingpattern analysis system 12, andtelematics system 18 are delineated as shown inFIG. 1 for illustrative purposes and such a configuration should not be considered limiting. - Details of the
insurance provider system 28 are omitted for ease of illustration and it will be appreciated that theinsurance provider system 28 can be associated with a variety of business types, such as insurance providers, financial institutions having insurance products, government entities, private lenders, etc. - The
vehicle data 20 that is collected by thetelematics system 18 may include any data that thetelematics devices 16 are capable of collecting. For example, thetelematics devices 16 may typically collect at least latitude and longitude values (collectively indicative of a location) and speed values. Other values such as acceleration can be collected if available or computed based on the location and speed values. - The
telematics system 18 and drivingpattern analysis system 12 can include one or more devices such as servers capable of communicating with each other and/or thenetwork 14 and with theinsurance provider system 28. - The driving
pattern analysis system 12 may have access to thevehicle data 20 directly or via thetelematics system 18.Such vehicle data 20 may be accessed via an Internet or other remote data connection such as an application programming interface (API). - In certain aspects,
telematics device 16,telematics system 18, drivingpattern analysis system 12, andUBI program 22 can include, but are not limited to, a data communication device; and these may include a mobile or smart phone, a laptop computer, a tablet computer, a notebook computer, a hand-held computer, a personal digital assistant, an embedded device, a virtual reality device, an augmented reality device, third party portals, a personal computer, and any additional or alternate computing device, and may be operable to transmit and receive data acrosscommunication network 14. -
Communication network 14 may include a telephone network, cellular, and/or data communication network to connect different types of devices as will be described in greater detail below. For example, thecommunication network 14 may include a private or public switched telephone network (PSTN), mobile network (e.g., code division multiple access (CDMA) network, global system for mobile communications (GSM) network, and/or any 3G, 4G, or 5G wireless carrier network, etc.), WiFi or other similar wireless network, and a private and/or public wide area network (e.g., the Internet). While the configuration shown inFIG. 1 illustrates theUBI program 22 and drivingpattern analysis system 12 communicating with thecommunications network 14 via thetelematics system 18, this is done for illustrative purposes and these devices may also connect directly tocommunications network 14. For example, as shown in dashed lines inFIG. 1 , theinsurance provider system 28 may have a customer relationship with the users of thetelematics devices 16 and/orvehicles 17 and therefore may communicate with those users separately, which may include communications over thecommunications network 14 or another network or medium (not shown). - The
computing environment 10 may also include a cryptographic server (not shown) for performing cryptographic operations and providing cryptographic services (e.g., authentication (via digital signatures), data protection (via encryption), etc.) to provide a secure interaction channel and interaction session, etc. Such a cryptographic server can also be configured to communicate and operate with a cryptographic infrastructure, such as a public key infrastructure (PKI), certificate authority (CA), certificate revocation service, signing authority, key server, etc. The cryptographic server and cryptographic infrastructure can be used to protect the various data communications described herein, to secure communication channels therefor, authenticate parties, manage digital certificates for such parties, manage keys (e.g., public and private keys in a PKI), and perform other cryptographic operations that are required or desired for particular applications of thetelematics devices 16,vehicles 17,telematics system 18,UBI program 22, drivingpattern analysis system 12, andinsurance provider system 28. The cryptographic server may be used to protect the data or results of the data by way of encryption for data protection, digital signatures or message digests for data integrity, and by using digital certificates to authenticate the identity of the users and devices within thecomputing environment 10, to inhibit data breaches by adversaries. It can be appreciated that various cryptographic mechanisms and protocols can be chosen and implemented to suit the constraints and requirements of the particular deployment of thecomputing environment 10 as is known in the art. - In
FIG. 2 , an example configuration of the drivingpattern analysis system 12 is shown. In certain embodiments, the drivingpattern analysis system 12 may include one ormore processors 30, acommunications module 32, and adata interface module 34 for interfacing with thevehicle data 20 to receive or retrievevehicle data 20 associated with a customer, client, orvehicle 17 for which a driving pattern analysis is being conducted. The data interface 34 may also be used to interface with theUBI program 22 to obtain theother data 26, or to interface directly with theother data 26 by having the appropriate permissions or credentials issued by theinsurance provider system 28.Communications module 32 enables the drivingpattern analysis system 12 to communicate with one or more other components of thecomputing environment 10, such astelematics system 18, UBI program 22 (e.g., pricing module 24),vehicles 17, andtelematics devices 16, via a bus or other communication network, such as thecommunication network 14. While not delineated inFIG. 2 , the drivingpattern analysis system 12 includes at least one memory or memory device that can include a tangible and non-transitory computer-readable, medium having stored therein computer programs, sets of instructions, code, or data to be executed byprocessor 30.FIG. 2 illustrates examples of modules, tools and engines stored in memory on the drivingpattern analysis system 12 and operated by theprocessor 30. R can be appreciated that any of the modules, tools, and engines shown inFIG. 2 may also be hosted on thetelematics system 18 or by the UBI program 22 (or other component of the insurance provider system 28) as discussed above. - In the example embodiment shown in
FIG. 2 , the drivingpattern analysis system 12 includes a drivingpattern analysis engine 36 for analyzing and evaluating driving patterns ofvehicles 17 using thevehicle data 20 and other data associated with a geographic area in which thevehicle 17 travels. The drivingpattern analysis system 12 may also include amachine learning engine 38, aclassification module 40, atraining module 42, ageolocation tool 44, a UBI interface,module 46, amapping tool 48, an insurancesystem interface module 50, and a telematicssystem interface module 52. - The
machine learning engine 38 is used by the driving pattern analysis engine 36 (or “analysis engine 36” for brevity) to generate and train models 350 (see alsoFIG. 8 ) to be used in evaluatingvehicle data 20 and associated geolocation or mapping data, for determining driving patterns that can be used in UBI pricing. Theanalysis engine 36 may utilize or otherwise interface with themachine learning engine 38 to both classify data currently being analyzed to generate the models, and to train classifiers using data that is continually being processed and accumulated by thetelematics devices 16 andtelematics system 18. - The
machine learning engine 38 may also perform operations that classify the vehicle data 20 (or information derived from the vehicle data 20) in accordance with corresponding classifications parameters, e.g., based on an application of one or more machine learning algorithms to the data. The machine learning algorithms may include, but are not limited to, a one-dimensional, convolutional neural network model (e.g., implemented using a corresponding neural network library, such as Keras®), and the one or more machine learning algorithms may be trained against, and adaptively improved using, elements of previously classified profile content identifying expected datapoints. Subsequent to classifying the data, themachine learning engine 38 may further process each data point to identify, and extract, a value characterizing the corresponding one of the classification parameters, e.g., based on an application of one or more additional machine learning algorithms to each of the data points. By way of the example, the additional machine learning algorithms may include, but are not limited to, an adaptive natural language processing algorithm that, among other things, predicts starting and ending indices of a candidate parameter value within each data point, extracts the candidate parameter value in accordance with the predicted indices, and computes a confidence score for the candidate parameter value that reflects a probability that the candidate parameter value accurately represents the corresponding classification parameter. As described herein, the one or more additional machine learning algorithms may be trained against, and adaptively improved using, the locally maintained elements of previously classified data. Classification parameters may be stored and maintained using theclassification module 40, and training data may be stored and maintained using thetraining module 42. - In some instances, classification data stored in the
classification module 40 may identify one or more parameters, e.g., “classification” parameters, that facilitate a classification of corresponding elements or groups of recognized data points based on any of the exemplary machine learning algorithms or processes described herein. The one or more classification parameters may correspond to parameters that can identify expected and unexpected data points for certain types of data. - In some instances, the additional, or alternate, machine learning algorithms may include one or more adaptive, natural-language processing algorithms capable of parsing each of the classified portions of the data being examined and predicting a starting and ending index of the candidate parameter value within each of the classified portions. Examples of the adaptive, natural-language processing algorithms include, but are not limited to, natural-language processing models that leverage machine learning processes or artificial neural network processes, such as a named entity recognition model implemented using a SpaCy® library.
- Examples of these adaptive, machine learning processes include, but are not limited to, one or more artificial, neural network models, such as a one-dimensional, convolutional neural network model, e.g., implemented using a corresponding neural network library, such as Keras®. In some instances, the one-dimensional, convolutional neural network model may implement one or more classifier functions or processes, such a Softmax® classifier, capable of predicting an association between a data point and a single classification parameter and additionally, or alternatively, multiple classification parameters.
- Based on the output of the one or more machine learning algorithms or processes, such as the one-dimensional, convolutional neural network model described herein,
machine learning engine 38 may perform operations that classify each of the discrete elements of the vehicle and/or geographic area-related data being examined as a corresponding one of the classification parameters, e.g., as obtained from classification data stored by theclassification module 40. - The outputs of the machine learning algorithms or processes may then be used by the
analysis engine 36 to generate and train models and to use such models to determine driving patterns from data and information observed or derived from thevehicle data 20 and/or related or associated geolocation or mapping data for a relevant geographic area. Theanalysis engine 36 may also use a set of rules, a weighted formula or any other statistical or mathematical function or tool to evaluate thevehicle data 20 and related geolocation/mapping data, or information derived therefrom. - Referring again to
FIG. 2 , theUBI interface module 46 may be used to provide one or more outputs based on the results generated by theanalysis engine 36. Example outputs include indicators of driving patterns and/or graphical outputs that can be used to visualize driving paths and/or speed paths identified using image generation and image processing techniques employed by (or input to) theanalysis engine 36 and used to assess driving patterns. The graphical output may also be displayed for a user or administrator or may be used internally by the drivingpattern analysis system 12 orpricing module 24 with respect to driving patterns and pricing derived therefrom. That is, graphical outputs generated by the drivingpattern analysis system 12 may be displayed to a user or may be machine-processed without a need to be displayed. - The
geolocation tool 44 may be used by the drivingpattern analysis system 12 to identify geolocation data associated with location measurements taken in a geographic area. For example, the drivingpattern analysis system 12 can identify a geographic area from a set of location measurements in thevehicle data 20 and use thegeolocating tool 44 to identify additional entities and features within that geographic area. Themapping tool 48 may also be used by the drivingpattern analysis system 12 to obtain or generate mapping data associated with the geographic area, including existing roadways, intersections, landmarks, and topographical features. For example, when associating location data with the geographic area, themapping tool 48 may be used to generate a visual map on which the location measurements of avehicle 17 and the associated geolocation data can be plotted. This image or map generation operation can be performed by themapping tool 48 or by theanalysis engine 36, or both. It can be appreciated that thegeolocation tool 44,mapping tool 48, andanalysis engine 36 are shown as being delineated inFIG. 2 for illustrative purposes only and the associated functionality may also be integrated into theanalysis engine 36 or be provided by a location-based application or service accessible to theanalysis engine 36. Thegeolocation tool 44 and/ormapping tool 48 may also be provided by one or more third party APIs that are accessed by the drivingpattern analysis system 12 to integrate geolocating and mapping services into the functionality provided by theanalysis engine 36. - The insurance
system interface module 50 provides one or more interfaces to theinsurance provider system 28, e.g., to enable the drivingpattern analysis system 12 to access or interface with theother data 26 stored by theinsurance provider system 28. The insurancesystem interface module 50 can also be used to access or otherwise interact or communicate with internal programs, devices, or systems of theinsurance provider system 28 that can provide any suitable information that can be used in analyzing driving patterns, e.g., customer information. - The telematics
system interface module 52 is shown inFIG. 2 for illustrative purposes and the functionality thereof may be provided by theUBI interface module 46 or insurancesystem interface module 50. The telematicssystem interface module 52 enables the drivingpattern analysis system 12 to interface with the telematics system 18 (e.g., directly or via the UBI program 22) to obtainvehicle data 20. - In
FIG. 3 , an example configuration of thetelematics device 16 is shown. In certain embodiments, thetelematics device 16 may include one ormore processors 60, acommunications module 62, a data interface module, 64, atelematics client app 66, and adata store 70storing device data 72 andapplication data 74.Communications module 62 enables thetelematics device 12 to communicate with one or more other components of thecomputing environment 10, such as avehicle 17, thetelematics system 18, drivingpattern analysis system 12, and insurance provider system 28 (or one of its components), via a bus or other communication network, such as thecommunication network 14. While not delineated inFIG. 3 , thetelematics device 16 includes at least one memory or memory device that can include a tangible and non-transitory computer-readable medium having stored therein computer programs, sets of instructions, code, or data to be executed byprocessor 60.FIG. 3 illustrates examples of modules and applications stored in memory on thetelematics device 16 and operated by theprocessor 60. It can be appreciated that any of the modules and applications shown inFIG. 3 may also be hosted externally by thetelematics system 18 and be available to thetelematics device 16, e.g., via thecommunications module 62. R can be appreciated that the data interface module, 64 is shown inFIG. 3 for illustrative, purposes only and the functionality thereof may also be provided by thecommunications module 62, e.g., when raw location and speed data to be collected by thetelematics device 16 is available via a connection to thecommunications network 14. - In the example embodiment shown in
FIG. 3 , thetelematics device 16 includes atelematics client app 66 for enabling the user of thetelematics device 16 to initiate and operate a UBI application in association with theinsurance provider system 28. Thetelematics client app 66 may include a display module for rendering GUIs and other visual output on a display device such as a display screen, and an input module for processing user or other inputs received at thetelematics device 16, e.g., via a touchscreen, input button, transceiver, microphone, keyboard, etc. Thetelematics device 16 may also include the same or asimilar geolocation tool 44 and/ormapping tool 48 used by the drivingpattern analysis system 12. When used by thetelematics device 16, thegeolocation tool 44 ormapping tool 48 may include a module or application that is configured to act as a GPS receiver for obtaining GPS data by communicating with one ormore GPS satellites 19. This can be done using or in conjunction with thecommunications module 32 ordata interface module 34 of thetelematics device 16. It can be appreciated that thegeolocation tool 44 andmapping tool 48 are shown in bothFIGS. 2 and 3 to illustrate that such services may be available to both the client- and server-based devices for use in mapping geographic areas and identifying geolocated entities andvehicle data 20 in a map interface. - The
telematics device 16 may also include other applications not shown inFIG. 3 , such as a web browser application for accessing Internet-based content, e.g., via a mobile or traditional website. Thedata store 70 may be used to storedevice data 72, such as, but not limited to, an IP address or a MAC address that uniquely identifiestelematics device 16 withinenvironment 10. Thedata store 70 may also be used to storeapplication data 74, such as, but not limited to, login credentials, user preferences, cryptographic data (e.g., cryptographic keys), etc. - In
FIG. 4 , an example configuration of thetelematics system 18 is shown. In certain embodiments, thetelematics system 18 may include one ormore processors 80, acommunications module 82, adata interface module 84, aUBI interface module 86, a telematicsdevice interface module 88, a driving pattern analysissystem interface module 90, and a data storage for thevehicle data 20.Communications module 82 enables thetelematics system 18 to communicate with one or more other components of thecomputing environment 10, such as avehicle 17, thetelematics device 16, drivingpattern analysis system 12, and insurance provider system 28 (or one of its components), via a bus or other communication network, such as thecommunication network 14, While not delineated inFIG. 4 , thetelematics system 18 includes at least one memory or memory device that can include a tangible and non-transitory computer-readable medium having stored therein computer programs, sets of instructions, code, or data to be executed byprocessor 80.FIG. 4 illustrates examples of modules and applications stored in memory on thetelematics system 18 and operated by theprocessor 60. - The
UBI interface module 86 may be the same or similar to theUBI interface module 46 used by the drivingpattern analysis system 12 to interface with theUBI program 22 to provide access to collectedvehicle data 20 for one or more users. The telematicsdevice interface module 88 may be used to interface and communicate with one ormore telematics devices 16 either directly or via a connection with thevehicle 17. The driving pattern analysissystem interface module 90 may be used to interface and communicate with the driving pattern andanalysis system 12 directly. It can be appreciated that themodules FIG. 4 for illustrative purposes only and such modules could be combined into any one or more module or application while providing the functionality illustrated herein. Thevehicle data 20 is shown as being integrated in thetelematics system 18 inFIG. 4 but may also be located externally to thetelematics system 18 as shown inFIG. 1 . For example, thevehicle data 20 can be stored by a third-party cloud-based storage service and accessed by entities with the appropriate permissions and credentials, entities such as thetelematics system 18,insurance provider system 28, drivingpattern analysis system 12, etc. - It will be appreciated that only certain modules, applications, tools and engines are shown in
FIGS. 2 to 4 for ease of illustration and various other components would be provided and utilized by the drivingpattern analysis system 12,telematics device 16, andtelematics system 18 as is known in the art. - It will be appreciated that any module or component exemplified herein that executes instructions may include or otherwise have access to computer readable media such as storage media, computer storage media, or data storage devices (removable and/or non-removable) such as, for example, magnetic disks, optical disks, or tape. Computer storage media may include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer readable instructions, data structures, program modules, or other data. Examples of computer storage media include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by an application, module, or both. Any such computer storage media may be part of the
telematics device 16,telematics system 18,insurance provider system 28, drivingpattern analysis system 12,UBI program 22,pricing module 24, or accessible or connectable thereto. Any application or module herein described may be implemented using computer readable/executable instructions that may be stored or otherwise held by such computer readable media. - As indicated above, the
vehicle data 20 and data associated with a geographic area (e.g., geolocation/mapping data) may be used by the drivingpattern analysis system 12 to identify driving patterns and analyze those driving patterns to inform apricing module 24 for theUBI program 22 in determining UBI-based insurance pricing. In this example embodiment, thevehicle data 20 includes at least location measurements and associated time stamps for each location measurement. Thevehicle data 20 may also typically include speed measurements, however, it can be appreciated that speed and other measurements such as acceleration can be computed by the drivingpattern analysis system 12 from the location measurements and the time stamps (i.e., by determining how long it takes for thevehicle 17 to travel a certain distance). Thevehicle data 20 may be raw data such as latitude, longitude and speed measurements with associated time stamps. Thisvehicle data 20 is associated with the mapping and geolocation data for an associated geographic area in which thevehicle data 20 was captured to provide additional context and to permit a deeper analysis alongside other traditional variables used in UBI pricing. - Referring to
FIG. 5 , agraphical output 100 is shown which includes ageographic map image 102 that may be generated from the mapping and geolocation data provided by thegeolocation tool 44 andmapping tool 48. Thevehicle data 20 that is associated with avehicle 17 andtelematics device 16 may be associated with thegeographic map image 102 and can be used to visualize one ormore driving paths 104. For example, the raw location data may be plotted on themap image 102 and resolved or otherwise corrected to align with preexisting roadways. Such plotting can be performed by thegeolocation tool 44,mapping tool 48 oranalysis engine 36 by implementing an image rendering or processing technique to generate visual representations of one ormore paths 104 driven by thevehicle 17. Each data point plotted along apath 104 has an associated location, speed, and time stamp, which enables multiple types of paths to be visualized, as discussed below. - As shown in
FIG. 5 , darkened drivingpaths 106 can be identified whenindividual driving paths 104 are repeated or otherwise include overlapping portions. By tracing out drivingpaths 104 as shown inFIG. 5 , theanalysis engine 36 of the driving pattern andanalysis system 12 can apply one or more image analysis techniques to the drivingpaths 104 to assess a driving pattern. For example, the number ofdarkened paths 106 can be identified to determine daily or frequent routes, geolocation data can be referenced to determine a type of road or heavy traffic zone, or the number of paths or overall distance can be used to determine driving frequency, etc. - Turning now to
FIG. 6 , agraphical output 120 is shown for another type of image analysis. In this example, thegraphical output 120 includes ageographic map image 122 that, as above, may be generated from the mapping and geolocation data provided by thegeolocation tool 44 andmapping tool 48. Thevehicle data 20 for aparticular driving path 124 may be shown with a number ofsegments 126 differentiated by color or shade to indicate speed variations over the drivingpath 124. That is, each driving path 124 (or drivingpaths 104 taken from image 100) can be separately analyzed to determine driving patterns such as speed and acceleration within thepath 124. By plotting thepaths 124 as shown inFIG. 6 , theanalysis engine 36 of the driving pattern andanalysis system 12 can apply one or more image analysis techniques to the speed pattern to determine a driving pattern. As such, it can be appreciated that the drivingpaths - It can also be appreciated that the graphical outputs shown in
FIGS. 5 and 6 may be linked such that any drivingpath 104 shown inFIG. 5 may be selected to initiate thegraphical output 120 inFIG. 6 for thatspecific driving path 104 to show speed data aspath 124. - The
graphical outputs analysis engine 36 may be analyzed by theanalysis engine 36 itself or may be provided to thepricing module 24 as additional variable with any additional analysis outputs generated by theanalysis engine 36. That is, the driving patterns may be determined directly by theanalysis engine 36 or may be indicated or identified by theanalysis engine 36 for thepricing module 24 orUBI program 22 more generally for a subsequent step in a pricing calculation. As such, operations described herein may be performed by one or more of the elements of thecomputing environment 10 according to the principles discussed herein. - Referring to
FIG. 7 , an example embodiment of computer executable instructions for collectingvehicle data 20 for a driving pattern analysis is shown. The example shown inFIG. 7 is based on the example configuration for thecomputing environment 10 inFIG. 1 in which thetelematics system 18 collectsvehicle data 20 fromtelematics devices 16. Atblock 200, thetelematics device 16 collects speed measurements with associated time stamps, which are associated with avehicle 17 and driver/user. Atblock 202, thetelematics device 16 collects location measurements with associated time stamps, e.g., via access to a GPS system connected to thetelematics device 16 orvehicle 17. Thetelematics device 16 in this example is configured to report a set ofvehicle data 20 to thetelematics system 18 atblock 204. It can be appreciated that the frequency of reportingvehicle data 20 atblock 204 can vary based on user preferences, system preferences or constraints such as available bandwidth or data communication restrictions. For example, thetelematics device 16 can locally store its collectedvehicle data 20 and report such data as frequently as in real-time or near-real-time, or on a less frequent basis such as intra-daily, daily or weekly. - The set of
vehicle data 20 collected by thetelematics device 16 is received by thetelematics system 18 atblock 206 and the receivedvehicle data 20 is stored atblock 208. Thevehicle data 20 that is received and stored may be associated with a user or vehicle account in the datastore used for thevehicle data 20. Thetelematics system 18 in this example is configured to reportvehicle data 20 collected from one ormore telematics devices 16 to theUBI program 22 atblock 210. For example, thetelematics system 18 may be responsible for collecting data from a number of customers associated with theUBI program 22 for theinsurance provider system 28 and may be instructed to report thevehicle data 20 to theUBI program 22. TheUBI program 22 may store the receivedvehicle data 20 with theother data 26 within theinsurance provider system 28. TheUBI program 22 may also be provided with a permission and/or credential to access thevehicle data 20 directly from the datastore or service utilized by thetelematics system 18. - In this example embodiment, the
telematics system 18 may also provide thevehicle data 20 to the drivingpattern analysis system 12 atblock 212, either by sending the data thereto, or by providing access via a credential to access the datastore or service used by thetelematics system 18 or via the access provided to theUBI program 22. As such, it can be appreciated that blocks 210 and 212 may be executed using a single operation or communication between thetelematics system 18 and theinsurance provider system 28. For example, thetelematics system 18 may be configured to send an alert to theUBI program 22 and/or drivingpattern analysis system 12 when a new set or new sets ofvehicle data 20 are available for processing. - The driving
pattern analysis system 12 obtains thevehicle data 20 atblock 214, either directly or via theUBI program 22 in this example. Thevehicle data 20 thus obtained can be used to conduct a driving pattern analysis atblock 216 as discussed above and described in greater detail below. Based on the analysis or analyses conducted atblock 216, the drivingpattern analysis system 12 can provide one or more driving patterns to a risk assessment function, such as that used by thepricing module 24 of theUBI program 22. As indicated above, the driving pattern(s) can be indicated using various output types, including graphical outputs such as those shown inFIGS. 5 and 6 . The outputs may also include numerical or statistical values, scores, weights, or rankings that can show, on a relative scale, a degree of driving behavior, either positive or negative, that can be used in calculating or adjusting an insurance premium. - Referring to
FIG. 8 , an example embodiment of computer executable instructions for analyzingvehicle data 20 is shown. The operations illustrated inFIG. 8 may be executed by theanalysis engine 36 of the drivingpattern analysis system 12 according to the configuration shown inFIG. 2 within thecomputing environment 10 shown inFIG. 1 , however, the principles may apply in other configurations. - At
block 300, theanalysis engine 36 obtains the set ofvehicle data 20 that is to be analyzed, e.g., by obtaining a set ofvehicle data 20 associated with a single vehicle 17 (or a single driver of multiple vehicles 17) covering a certain period of time (e.g., a week, a month, a quarter, etc.). - At
block 302 thegeolocation tool 44 andmapping tool 48 may be used to generate amap image map image graphical output paths block 304, as discussed above. That is, thegraphical output vehicle data 20 within themap image FIG. 5 , and a collection of speed measurements within a driving path can be used to highlight variations in speed along that path as shown inFIG. 6 . In this way, significant amounts of raw data generated by thetelematics system 18 can be efficiently and conveniently assembled and graphically visualized to allow image-based techniques to assess driving patterns and/or driving habits. - At
block 306 the path(s) and associated geolocation/mapping data are analyzed by theanalysis engine 36 to identify one or more driving patterns. The geolocation/mapping data may include, for example, posted road speeds, road type (e.g., city street versus freeway), elevation, time of day (e.g., sunset and sunrise conditions), geographic area (e.g., rural versus urban), traffic data, weather data, etc. This geolocation/mapping data can then be associated with the actual driven path(s) and the speed(s) used by thevehicle 17 along those paths to enable theanalysis engine 36 and/or thepricing module 24 to generate deeper insights. For example, frequently used driving paths may be indicative of a daily commute, and road types may be indicative of highway versus city driving. Moreover, other factors such as traffic and weather can be accounted for with the time stamp information associated with the location and speed measurements. - The path(s) identified at
block 304 and the analyses conducted atblock 306 can be influenced by and/or contribute to one ormore models 350 that may be trained and updated by themachine learning module 38 of the drivingpattern analysis system 12 usingvehicle data 20 having been generated bymultiple vehicles 17. By analyzing driving patterns for a multitude of vehicles, certain observations and inferences can be determined that can benefit subsequent analyses. For example, relatively high vehicle speeds along acertain driving path 124 can be observed as an anomaly and potentially negative driving pattern when compared to a sample set of drivingpaths 124 from other drivers that recorded a relatively lower speed. Similarly, historical data from the same driver can be used, tracked, and modeled over time to determine if improvements or adjustments have been made in driving patterns and driving habits that can inform thepricing module 24. - At
block 308, an output indicative of a driving pattern may be provided by the drivingpattern analysis system 12 to thepricing module 24. As discussed above, this can include providinggraphical outputs pricing module 24, variable scores for certain parameters as determined by theanalysis engine 36 using thegraphical outputs pricing module 24 and drivingpattern analysis system 12 are delineated in the present example for illustrative purposes and such elements may be integral with each other and/or work in concert to assess and identify driving patterns or habits that can be used as additional variables in assessing risk related to such driving patterns. - It will be appreciated that the examples and corresponding diagrams used herein are for illustrative purposes only. Different configurations and terminology can be used without departing from the principles expressed herein. For instance, components and modules can be added, deleted, modified, or arranged with differing connections without departing from these principles.
- The steps or operations in the flow charts and diagrams described herein are just for example. There may be many variations to these steps or operations without departing from the principles discussed above. For instance, the steps may be performed in a differing order, or steps may be added, deleted, or modified.
- Although the above principles have been described with reference to certain specific examples, various modifications thereof will be apparent to those skilled in the art as outlined in the appended claims.
Claims (20)
1. A device for analyzing vehicle data, the device comprising:
a processor;
a data interface coupled to the processor; and
a memory coupled to the processor, the memory storing computer executable instructions that when executed by the processor cause the processor to:
obtain a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle;
analyze the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and
provide an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
2. The device of claim 1 , wherein the set of vehicle data comprises a plurality of location measurements and a corresponding plurality of speed measurements, and the computer executable instructions further cause the processor to:
associate the corresponding plurality of speed measurements with the at least one driving path using the corresponding plurality of location measurements; and
utilize the plurality of speed measurements in identifying the at least one driving pattern.
3. The device of claim 1 , wherein the map image comprises at least one repeated driving path that is distinguishable by an image processing technique from at least one other driving path to be indicative of a higher frequency of use.
4. The device of claim 1 , wherein the at least one path comprises a vehicle trip with a plurality of portions each identifying respective vehicle speed data.
5. The device of claim 4 , wherein the vehicle data comprises an acceleration value.
6. The device of claim 1 , wherein the computer executable instructions further cause the processor to:
obtain the model, the model having been generated from vehicle data for a plurality of vehicles; and
update the model with the at least one driving path.
7. The device of claim 6 , wherein the vehicle data collected from the plurality of vehicles comprises at least one similar path traveled by another vehicle.
8. The device of claim 1 , wherein the computer executable instructions further cause the processor to:
communicate via the data interface with a telematics system connected to the vehicle for collecting the vehicle data.
9. The device of claim 8 , wherein the device communicates with a telematics device used or having been used in the vehicle to obtain the vehicle data.
10. The device of claim 1 , wherein the indication of the at least one driving pattern used in the risk assessment is used to calculate an insurance premium for a usage-based insurance program.
11. The device of claim 10 , wherein the indication of the at least one driving pattern is combined with one or more additional factors in calculating the insurance premium.
12. The device of claim 11 , wherein an additional factor comprises a road type associated with the at least one path, the road type being determinable from data associated with the geographic area.
13. The device of claim 2 , wherein the plurality of location measurements each comprise a latitude and a longitude, the set of vehicle data having been generated at least in part by a global positioning system receiver positioned in the vehicle while collecting the vehicle data.
14. A method of analyzing vehicle data, the method executed by a device having a processor, and comprising:
obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle;
analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and
providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
15. The method of claim 14 , wherein the set of vehicle data comprises a plurality of location measurements and a corresponding plurality of speed measurements, and further comprising:
associating the corresponding plurality of speed measurements with the at least one driving path using the corresponding plurality of location measurements; and
utilizing the plurality of speed measurements in identifying the at least one driving pattern.
16. The method of claim 14 , wherein the map image comprises at least one repeated driving path that is distinguishable by an image processing technique from at least one other driving path to be indicative of a higher frequency of use.
17. The method of claim 14 , wherein the at least one path comprises a vehicle trip with a plurality of portions each identifying respective vehicle speed data.
18. The method of claim 14 , further comprising:
communicating via the data interface with a telematics system connected to the vehicle for collecting the vehicle data.
19. The method of claim 14 , wherein the indication of the at least one driving pattern used in the risk assessment is used to calculate an insurance premium for a usage-based insurance program.
20. A non-transitory computer readable medium for analyzing vehicle data, the computer readable medium comprising computer executable instructions for:
obtaining a geographic map image of a geographic area, the map image plotting a set of vehicle data indicative of at least one driving path traveled by the vehicle;
analyzing the at least one driving path in the map image and a model generated from data associated with the geographic area, to identify at least one driving pattern within the geographic area; and
providing an indication of the at least one driving pattern to contribute to a risk assessment associated with a driver of the vehicle.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/590,936 US20220157094A1 (en) | 2019-08-15 | 2022-02-02 | System and Method for Analyzing Vehicle Data |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/542,000 US11276257B2 (en) | 2019-08-15 | 2019-08-15 | System and method for analyzing vehicle data |
US17/590,936 US20220157094A1 (en) | 2019-08-15 | 2022-02-02 | System and Method for Analyzing Vehicle Data |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/542,000 Continuation US11276257B2 (en) | 2019-08-15 | 2019-08-15 | System and method for analyzing vehicle data |
Publications (1)
Publication Number | Publication Date |
---|---|
US20220157094A1 true US20220157094A1 (en) | 2022-05-19 |
Family
ID=74567383
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/542,000 Active 2040-10-02 US11276257B2 (en) | 2019-08-15 | 2019-08-15 | System and method for analyzing vehicle data |
US17/590,936 Pending US20220157094A1 (en) | 2019-08-15 | 2022-02-02 | System and Method for Analyzing Vehicle Data |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/542,000 Active 2040-10-02 US11276257B2 (en) | 2019-08-15 | 2019-08-15 | System and method for analyzing vehicle data |
Country Status (1)
Country | Link |
---|---|
US (2) | US11276257B2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US12002305B1 (en) * | 2019-08-28 | 2024-06-04 | State Farm Mutual Automobile Insurance Company | Systems and methods for generating improved vehicle usage analytics based upon vehicle sensor and telematics data |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4066511A1 (en) * | 2020-01-16 | 2022-10-05 | Huawei Technologies Co., Ltd. | Representation of media data |
US20230116055A1 (en) * | 2020-03-03 | 2023-04-13 | BlueOwl, LLC | Systems and methods for creating personalized public transit guides |
US11790458B1 (en) | 2020-04-23 | 2023-10-17 | State Farm Mutual Automobile Insurance Company | Systems and methods for modeling telematics, positioning, and environmental data |
FI20206314A1 (en) * | 2020-12-16 | 2022-06-17 | Nokia Technologies Oy | Estimating delay spread and doppler spread |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10163274B1 (en) * | 2012-12-19 | 2018-12-25 | Allstate Insurance Company | Driving trip and pattern analysis |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2925145A1 (en) | 2003-07-07 | 2005-01-13 | Insurance Services Office, Inc. | Traffic information system |
US8600604B2 (en) | 2004-01-29 | 2013-12-03 | Intelligent Mechatronic Systems Inc. | Data integrity verification device |
US8996234B1 (en) | 2011-10-11 | 2015-03-31 | Lytx, Inc. | Driver performance determination based on geolocation |
US9786009B2 (en) | 2011-11-29 | 2017-10-10 | Hartford Fire Insurance Company | System and method for administering a telematics-enabled test drive dealer program |
US8768734B2 (en) * | 2012-05-10 | 2014-07-01 | Hartford Fire Insurance Company | System and method for computing and sorting trip similarities using geo-spatial information |
US8799032B2 (en) | 2012-05-22 | 2014-08-05 | Hartford Fire Insurance Company | System and method to predict an insurance policy benefit associated with telematics data |
US9141582B1 (en) * | 2012-12-19 | 2015-09-22 | Allstate Insurance Company | Driving trip and pattern analysis |
US20140195272A1 (en) | 2013-01-07 | 2014-07-10 | Hassan Sadiq | Systems and methods of gamification for a driving performance product |
US9754428B2 (en) | 2013-09-16 | 2017-09-05 | Fleetmatics Ireland Limited | Interactive timeline interface and data visualization |
US9189897B1 (en) | 2014-07-28 | 2015-11-17 | Here Global B.V. | Personalized driving ranking and alerting |
CN104599347B (en) | 2014-12-26 | 2016-11-02 | 广州通易科技有限公司 | A kind of method representing driving behavior on map |
US9361599B1 (en) | 2015-01-28 | 2016-06-07 | Allstate Insurance Company | Risk unit based policies |
US10269075B2 (en) | 2016-02-02 | 2019-04-23 | Allstate Insurance Company | Subjective route risk mapping and mitigation |
JP6962316B2 (en) | 2016-03-29 | 2021-11-05 | ソニーグループ株式会社 | Information processing equipment, information processing methods, programs, and systems |
US11295218B2 (en) * | 2016-10-17 | 2022-04-05 | Allstate Solutions Private Limited | Partitioning sensor based data to generate driving pattern map |
-
2019
- 2019-08-15 US US16/542,000 patent/US11276257B2/en active Active
-
2022
- 2022-02-02 US US17/590,936 patent/US20220157094A1/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10163274B1 (en) * | 2012-12-19 | 2018-12-25 | Allstate Insurance Company | Driving trip and pattern analysis |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US12002305B1 (en) * | 2019-08-28 | 2024-06-04 | State Farm Mutual Automobile Insurance Company | Systems and methods for generating improved vehicle usage analytics based upon vehicle sensor and telematics data |
Also Published As
Publication number | Publication date |
---|---|
US11276257B2 (en) | 2022-03-15 |
US20210049840A1 (en) | 2021-02-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11276257B2 (en) | System and method for analyzing vehicle data | |
US20200134735A1 (en) | Enhancement using analytics based on vehicle kinematic data | |
US9797740B2 (en) | Method of determining trajectories through one or more junctions of a transportation network | |
US20140108058A1 (en) | Method and System to Determine Auto Insurance Risk | |
US20110184784A1 (en) | Tracking Carbon Footprints | |
CN112380448B (en) | Vehicle data processing method and device, computer equipment and storage medium | |
Fekih et al. | A data-driven approach for origin–destination matrix construction from cellular network signalling data: a case study of Lyon region (France) | |
US8880323B2 (en) | Combining road and vehicle traffic information | |
US20170124660A1 (en) | Telematics Based Systems and Methods for Determining and Representing Driving Behavior | |
CN112633395B (en) | Abnormal data detection method, device, computer equipment and storage medium | |
US9301099B2 (en) | Method of analyzing points of interest with probe data | |
WO2014028377A2 (en) | Apparatus and method for detecting driving performance data | |
Qin et al. | EXIMIUS: A measurement framework for explicit and implicit urban traffic sensing | |
US20240089325A1 (en) | Using contextual information for vehicle trip loss risk assessment scoring | |
US20210048309A1 (en) | System and method of creating custom dynamic neighborhoods for individual drivers | |
US20240096211A1 (en) | Processing apparatus and method for generating route navigation data | |
Correa et al. | Urban path travel time estimation using GPS trajectories from high-sampling-rate ridesourcing services | |
CN113256405A (en) | Method, device, equipment and storage medium for predicting cheating user concentrated area | |
US20180180431A1 (en) | Determining Commute Tolerance Areas | |
Pesé et al. | Spy: Car steering reveals your trip route! | |
CN117041885A (en) | User residence analysis method based on signaling data | |
CA3052159A1 (en) | System and method for analyzing vehicle data | |
US20190327450A1 (en) | Public safety camera identification and monitoring system and method | |
US9098386B1 (en) | System, method, and computer program for determining a subjective distance between two locations | |
Ricord et al. | Investigation of equity biases in transportation data: a literature review synthesis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: THE TORONTO-DOMINION BANK, CANADA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MOGHTADAI, MEHRAN;QUIJANO XACUR, OSCAR ALBERTO;SIGNING DATES FROM 20220105 TO 20220117;REEL/FRAME:058858/0638 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |