Abstract: A method of determining an injury segment includes training a machine learning model, receiving a loss report, analyzing the loss report using the trained model to determine a severity of an injury, determining, based on the severity of the injury, an injury segment, and storing, via a processor, an indication of the injury segment. A computer system includes a processor configured to train a machine learning model, receive a loss report, analyze the loss report using the trained model to determine the severity of an injury, determine an injury segment, and store an indication of the injury segment. A non-transitory computer readable medium containing program instructions that when executed cause a computer to train a machine learning model, receive a loss report, analyze the loss report using the trained model to determine the severity of an injury, determine an injury segment, and store an indication of the injury segment.

Abstract: A computer-implemented method for presenting relevant information to a customer service representative of a business may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream, determining one or more keywords from the text stream; comparing the one or more keywords with a history of keywords that have previously been searched; and/or searching a database for information related to the one or more keywords that have not been previously searched. As a result of the keyword search, information about topics that the customer is interested in, may be located and displayed on a customer service representative display to facilitate the customer service representative timely relaying the information found by the keyword search to enhance the customer experience. Exemplary keywords may relate to insurance and financial services, such as “auto,” “home,” “life,” “insurance,” or “vehicle loan.

Abstract: Provided herein is an engagement and care support platform (“ECSP”) computer system including at least one processor in communication with at least one memory device for facilitating senior user engagement. The processor is programmed to: (i) register a user through an application, (ii) register a caregiver associated with the user through the application, (iii) generate a senior profile based upon user personal and scheduling data, (iv) build a daily interactive user interface that reflects the senior profile, (v) display the daily interactive user interface at a first client device associated with the user, (vi) cause the first client device to initiate a daily interaction prompt to the user, (vii) determine whether any user interaction was received in response to the daily interaction prompt, and (viii) transmit a daily update message to a second client device associated with the caregiver, including an indication of whether any user interaction was received.

Abstract: A system for movement-based device control is presented. The system may include a target device and a control device. The control device may be configured to determine an indication of the target device. The control device may also be configured to detect at least one movement associated with the control device. The movement(s) may correspond to at least one control command associated with the target device. The control device may additionally be configured to generate a control signal indicative of the control command(s) associated with the target device based on the movement(s) associated with the control device. The control device may also be configured to transmit the control signal indicative of the control command(s) associated with the target device to the target device based on the indication of the target device so that the target device is controlled according to the control command(s).

Abstract: Methods and systems for monitoring use, determining risk, and pricing insurance policies for a vehicle having autonomous or semi-autonomous operation features are provided. According to certain aspects, a computer-implemented method for generating or updating usage-based insurance policies for autonomous or semi-autonomous vehicles may be provided. A request to generate an insurance quote may be received via wireless communication, and with the customer's permission, risk levels associated with intended usage by the customer of an autonomous or semi-autonomous vehicle may be determined. An insurance policy may be adjusted based upon the risk levels and the intended vehicle usage. The insurance policy may then be presented on the customer's mobile device for review and approval. In some aspects, the vehicle may be rented, and the intended vehicle usage is measured in distance or duration of vehicle operation. Insurance discounts may be provided to risk averse vehicle owners based upon low risk levels.

Abstract: A data pipeline tool provides a machine-learning design interface that a user can utilize (e.g., via an electronic device such as a personal computer, tablet, or smart phone) to design or configure data pipelines or workflows defining the manner in which ML models are developed, trained, tested, validated, or deployed. Once deployed, a designed ML model may generate predictive results based on input data fed to the ML model. The tool may present the predictive results via a GUI, and may enable a user to mark-up or otherwise interact with those predictive results. The tool may enable the user to share the results (which may include a mark-up or annotation provided by a user).

Abstract: Techniques for generating an insurance claim include receiving pupil data from an electronic device. The pupil data indicates a gaze direction of a user. Environment information is received from the electronic device, including point cloud data representing an environment in which the electronic device is currently disposed and a plurality of objects located within the environment. The techniques include determining an identity of an object of the plurality of objects based at least in part on the gaze direction and the environment information. The techniques include receiving, from the electronic device and via the network, information indicative of an input provided by the user, the input corresponding to the object, and comprising at least one of a first user utterance or a hand gesture. The techniques include generating an insurance claim based at least in part on the information and on the identity of the object.

Abstract: A computer-implemented method of using telematics data at a destination device is provided. The destination device may be a mobile device associated with a driver, or a smart vehicle controller of a destination vehicle. The telematics data is generated by an originating mobile device (i) having a Telematics Application (or “App”), and (ii) associated with a second driver/vehicle, the telematics data including acceleration, braking, speed, heading, and location data associated with an originating vehicle. The telematics data may be broadcast from the originating mobile device to the destination device that (a) analyzes the telematics data received, (b) determines that an abnormal travel condition exists, and (c) automatically take corrective action that alleviates a negative impact of the abnormal travel condition on the destination vehicle to facilitate safer travel.

Abstract: Methods and systems for determining fault for an accident involving a vehicle having one or more autonomous and/or semi-autonomous operation features are provided. According to certain aspects, performance data indicative of the performance of the features may be used to determine fault for a vehicle accident, such as a collision, by allocating fault for the accident between a vehicle operator, the autonomous operation features, or a third party. The allocation of fault may be used to determine an adjustment to an insurance policy and/or adjust coverage levels for an insurance policy. The allocation of fault may further be used to adjust risk levels or profiles associated with the autonomous or semi-autonomous operation features, which may be applied to other vehicles having the same or similar features.

Abstract: Systems and methods are disclosed with respect to using a blockchain for managing the subrogation claim process related to a vehicle accident, in particular, utilizing historical data related to a vehicle or vehicle collisions as part of the subrogation process. An exemplary embodiment may include receiving historical sensor data, such as image, audio, telematics, and/or autonomous vehicle data, associated with a past vehicle collision; inputting the historical sensor data into a machine learning program to determine data relevant to a past vehicle collision; receiving current sensor data associated with a current vehicle collision; inputting the current sensor data into the machine learning program to determine data relevant to the current vehicle collision; and determining a percentage of fault of the vehicle collision for one or more autonomous vehicles, autonomous vehicle systems, and/or drivers based upon, at least in part, analysis of the historical sensor data and the current sensor data.

Abstract: Provided herein is an engagement and care support platform (“ECSP”) computer system including at least one processor in communication with at least one memory device for facilitating senior user engagement. The processor is programmed to: (i) register a user through an application, (ii) register a caregiver associated with the user through the application, (iii) generate a senior profile based upon user personal and scheduling data, (iv) build a daily interactive user interface that reflects the senior profile, (v) display the daily interactive user interface at a first client device associated with the user, (vi) cause the first client device to initiate a daily interaction prompt to the user, (vii) determine whether any user interaction was received in response to the daily interaction prompt, and (viii) transmit a daily update message to a second client device associated with the caregiver, including an indication of whether any user interaction was received.

Abstract: Methods and systems for automatically mitigating risks of insurance-related events to a property are provided. According to certain aspects, a smart home controller or insurance provider remote processor may analyze data received from a plurality of smart devices disposed on, within, or proximate to a property, as well as data received from an insurance provider. If it is determined that an actual or potential risk of property damage exists, the smart home controller or insurance provider remote processor may automatically issue commands to one or more smart devices to take actions that mitigate the risk. The smart home controller may also transmit information about the actual or potential risks and any mitigative actions to an insurance provider. The insurance provider remote processor may interpret the transmitted data to perform insurance activities, such as providing a discount and/or adjusting an insurance premium or policy associated with the property.

Abstract: A system and method for automatically screening applicants for disability insurance in real-time, and if the results are favorable, automatically communicating acceptances and issuing policies via wireless communication. An applicant's BMI is calculated, and the applicant is rejected if the BMI is too high or low. The applicant's prescription drug history is obtained, and the applicant is rejected if the history shows use of a drug associated with a serious medical condition. The acceptance or rejection and a premium for the insurance product may be set based upon the real-time screening results and communicated to the applicant. Additionally, an occupation class assigned to the applicant may be confirmed, a motor vehicle report for the applicant may be obtained, and an insurance information report for the applicant may be obtained. If the applicant is rejected, they may be allowed to apply for the insurance product using an alternate non-real-time process.

Abstract: In one aspect, a system for allocating fault in a collision involving a vehicle is provided. The system may include (1) a sensor coupled to the vehicle and configured to collect contextual data related to the collision, (2) a non-transitory memory configured to store the contextual data, and (3) a processor coupled to the non-transitory memory and configured to (a) gain access to the contextual data, and (b) compute and assign a fault percentage to a driver of the vehicle based upon the contextual data.

Abstract: The following relates generally to diagnosing problems with websites. In some embodiments, a webpage interaction processor receives a list of potential user experience problems. The webpage interaction processor then extracts click data from the website, and processes the extracted click data into grams. Subsequently, an analytics engine is trained based on the processed click data. The trained analytics engine may then diagnose the problem of the website with a potential user experience problem from the received list of potential user experience problems. In some embodiments, the process is entirely automated.

Abstract: Systems and methods may incorporate machine learning techniques to evaluate the extent of damage caused to vehicles involved in an accident. The system will receive photos of a vehicle involved in an accident and retrieve data from a number of different sources and use the data to calculate the cost of repair for the vehicle. Data sources can include information of vehicles involved in similar accidents, information of similar vehicles involved in accidents, virtual reality models of vehicles obtained from a database provided by the manufacturer, etc. The system will continuously update machine learning algorithms by comparing calculated damage to actual repair costs and further update the appropriate databases.

Abstract: The present disclosure is directed to systems and methods for analyzing digital images to determine alphanumeric strings depicted in the digital images. An electronic device may generate a set of filtered images using a received digital image. The electronic device may also perform an optical character recognition (OCR) technique on the set of filtered images, and may filter out any of the set of filtered images according to a set of rules. The electronic device may further identify a set of common elements representative of the alphanumeric string depicted in the digital image, and determine a machine-encoded alphanumeric string based on the set of common elements.

Abstract: Example methods, apparatus, and articles of manufacture to capture and compress telematics data are disclosed herein. An example computer-implemented method, executed by a processor, to represent telematics data includes identifying, with the processor, a physical intersection of roads, identifying, with the processor, virtual lines crossing the roads, assigning, with the processor, ordinals to the virtual lines, representing, with the processor, a physical traversal through the physical intersection captured in first telematics data by a pair of the ordinals, and storing the pair of the ordinals in second compressed telematics data.

Abstract: Methods, systems, apparatus, and non-transitory computer readable media are described for detecting system outages using application event logs. Various aspects may include obtaining several prior application event logs where the status of the system is known at the time the application event logs were recorded. Additionally, various aspects may include determining characteristics of prior application event logs which were recorded during a system outage, and/or determining characteristics of prior application event logs which were recorded while the system was available. When current application event logs are obtained where the status of the system is unknown at the time the current application event logs are recorded, various aspects include comparing the current application event logs to the prior application event logs to determine that a system outage has occurred based upon the comparison.

Abstract: The present disclosure is directed to apparatuses, systems and methods for automatically classifying digital images of occupants inside a vehicle. More particularly, the present disclosure is directed to apparatuses, systems and methods for automatically classifying digital images of occupants inside a vehicle by comparing current image data to previously classified image data.