Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for an automated financial management system. One of the methods includes receiving data indicating a list of historic transactions of a user from a plurality of financial institutions. The method includes identifying at least one predicted unexpected expense based on providing at least some of the data to a trained machine-learning model, the trained machine-learning model trained using historic transaction data of a plurality of other users. The method includes determining a plan to account for the unexpected expense. The method also includes automatically transferring an amount based on the plan.

Abstract: Various embodiments of the present invention generally relate to identity authentication and/or recognition. Some embodiments provide a method for determining when a user may engage in a restricted activity, including engaging in an initial contact with a user via a medium for exchange, receiving a request to engage in an activity, determining an activity trust threshold required for the activity, determining an initial identity trust score for the user, and comparing the initial identity trust score with the activity trust threshold. Based on the comparison, the user is either allowed to engage in the activity, rejected from engaging in the activity, or additional identifying information is collected.

Abstract: Techniques are described for using an identity management system. One of the methods includes providing access to a decentralized identity management system to a user. The method includes storing user identity information on the decentralized identity management system. The method includes enabling one or more other users to store reputation information associated with the user identity. The method also includes using the reputation information in a transaction with the user.

Abstract: A post-disaster conditions monitoring system. The system may include plurality of aircraft drones configured to take photographic images; a conditions monitoring center having a controller including a device processor and a non-transitory computer readable medium including instructions executable by the device processor to perform the following steps: receiving images from the plurality of aircraft drones in a geographic region; determining conditions in the geographic region based on the images received from the plurality of aircraft drones; and sending information regarding the determined conditions to one or more users of the system.

Abstract: A method may include receiving an alert and a recorded data set from a first monitoring system and receiving a first set of permissions from the first monitoring system. The method may also include determining a permission associated with sharing of the recorded data set based at least in part on the first set of permissions. The method may also include determining that sharing of at least a portion of the recorded data from the first monitoring system is permitted based at least in part on the permission and sharing the at least a portion of the recorded data set.

Abstract: A system may include one or more sensors configured to acquire data associated with a driver of a vehicle and a processor. The processor may receive the data and determine whether the data is within a baseline data associated with expected behavior of the driver. The processor may then control one or more operations of the vehicle in response to the data being outside the baseline data.

Abstract: An information technology (IT) network includes configuration items (CIs) that may constantly change, where the CIs describe hardware components or software components that are configured to operate on the IT network. Machine learning techniques can be employed determine whether a CI has been changed (e.g., added, updated, or removed) in the IT network. For example, a software code or a log message associated with a CI can be analyzed to determine whether the CI is a newly added or updated within the IT network.

Abstract: A method and system of providing users with accessibility tools based on the user's behavior during their access of an application. The system identifies behavior that is potentially associated with a particular disability. In response, the system causes one or more accessibility tools configured to improve the application experience for users with the identified disability to be enabled. In addition, past in-app behavior of a user may be used to determine whether an accessibility tool should again be offered to the same user during subsequent application use.

Abstract: A computer-implemented method, includes identifying, a set of insurance policyholders that have experienced water loss and a second set of insurance policyholders that have not experienced water loss. The method also includes determining an attribute indicative of increased likelihood of future water loss using a predictive model using a percentage of the first set of insurance policyholders defining a first sample size of the first set of insurance policyholders that is smaller relative to a percentage of the second set of insurance policyholders defining the second sample size of the second set of insurance policyholders. Further, the method includes identifying at least one targeted insurance policyholder having an increased likelihood of water loss, based upon the attribute and providing a water loss mitigation strategy to the at least one targeted insurance policyholder.

Abstract: Systems and methods for mitigating damage caused by hail storms to self-driving motor-vehicles. When a self-driving motor vehicle determines or learns that a hail storm or other severe weather event may be approaching, it may seek cover under a protective structure or some other location where it might not be as exposed to the severe weather event. Depending upon the availability of suitable shelters, the self-driving motor vehicle might, for example, obtain a list of such possible shelters and apply certain factors to develop a priority list as to which shelters to seek. The self-driving motor vehicle may then drive itself to the location and remain there at least for the duration of the hail storm or other event. In some cases, the self-driving motor vehicle may evaluate the adequacy of the protective structure or other location, and may decide to seek a better protective structure or location.

Abstract: A system and method for locating electronic devices and establishing peer to peer communication with electronic devices, such as a currency exchange unit, using a beacon, is disclosed. The method may include determining a location of the currency exchange unit; generating a message indicating a location of the currency exchange unit and the availability of a variety of different currencies; and managing currency exchanges with various mobile devices.

Abstract: A computer device and method for processing data to detect modifications to insured property. Received is specification data regarding modifications to be made to insured property in connection with an insurance claim. Also received is data from one or more sensor devices associated with the insured property indicative of a status regarding modifications made to the insured property. Analysis is performed on the received specification and data to determine whether one or more predefined conditions for the insurance claim is satisfied regarding the modifications to be made to the insured property.

Abstract: A system and method for monitoring driving conditions and reacting to the driving conditions is disclosed. The system includes a risk monitoring system that can detect adverse road conditions. The method includes performing rerouting when hazardous road conditions are detected. The vehicle may be routed along a different route that lacks the hazardous road condition. The method also includes providing feedback to the driver when adverse driver behavior, such as a drowsy driver, is detected.

Abstract: A system and a method for diagnosing a problem with a motor vehicle using sound. Ambient noise information for the motor vehicle is determined. Current sound information is received, and whether there is a variation in sound between the current sound information and the ambient noise information is determined. The ambient noise information is subtracted from the current sound information if the variation has been identified, to identify a sound anomaly. A sound anomaly signal is extracted and compared with predetermined anomaly signal information stored in a database. The predetermined anomaly signal information is associated with diagnostic information.

Abstract: Techniques are described for communicating between two organizations without exchanging sensitive private information. One of the methods includes generating a token representative of private data. The method includes identifying at least one entity associated with the private data. The method includes associating the token with at least one entity. The method also includes providing information identifying at least one entity and the token to a machine learning system.

Abstract: The embodiments provide a system and method for interpreting predictions from machine learning systems using natural language. The system includes a prediction module and an explanation module. The prediction module includes a machine learning model to make predictions for quantities such as recommended coverage amounts for insurance policies. The explanation module includes an impact analyzer that calculates impact values, which represent the degree of influence that each attribute has on predicted values. The explanation module also includes a natural language processing system for transforming generating natural language explanations indicating how the user attributes have influenced the predicted value.

Abstract: The present disclosure relates to a system, method, and mobile computing device apparatus for detecting the physical presence of a bank customer at a bank branch, and delivering an enhanced customer service experience by anticipating the bank customer's needs. Detection of the bank customer through visual data such as facial recognition, or electronic data such as medium range electronic communication networks to the customer's mobile computing device, allow a bank to retrieve relevant customer profile and customer transaction history data and use that data to deliver communications to the customer even before the customer speaks to a bank teller.

Abstract: Methods and systems described herein can provide a computing device configured to display on a display screen of the computing device a first window listing a set of entries and a second window that can add entries directly into the set of entries and that can search for entries having selected features. The second window can dynamically display one or more keywords related to an entry as the entry is being created. The keywords can be determined as the entry is created and can be associated with the entry as the entry is added to the set of entries. The second window can receive a search request with the keywords and in response, cause the entries associated with the keywords to be displayed in the first window.

Abstract: An electric outlet fire detection and prevention system may comprise a temperature sensor and an electromagnetic interference (EMI) sensor. A processor within the system may monitor the measurements of the temperature and EMI sensors to determine that a fire has developed in an electric outlet box. The processor may then actuate a triggering mechanism in a cartridge containing fire extinguishing material such that the fire extinguishing material is dispersed in the outlet box. The fire extinguishing material may extinguish a developing fire and prevent the fire from spreading further. The processor may also be coupled with a server, which is configured to analyze measurements of the temperature and the EMI sensors and generate a building profile. When the server determines that any measurements deviate from the building profile, the server may instruct the processor to actuate the triggering mechanism and/or notify an electronic device associated with the building.

Abstract: A computer system includes a memory with instructions to receive telematics data regarding a vehicle, analyze the telematics data to determine a low fuel condition based on the fuel of the vehicle violating a predetermined threshold, and determine a location of the vehicle based on at least one of the telematics data. The instructions, in response to determining the low fuel condition, further identify one or more fuel dispensing stations in proximity to the location of the vehicle, provide information related to the one or more fuel dispensing stations to a mobile application displayed to a driver of the vehicle, and determine a scope of fueling permissions associated with the vehicle at the one of the one or more fuel dispensing stations. The instructions also automatically initiate a fueling session at the one of the one or more fuel dispensing stations contingent upon the scope of fueling permission.