Abstract: The present disclosure relates generally to systems and methods for delivering personalized content to a customer. More specifically, the present disclosure relates to systems and methods for providing notifications related to the needs of a customer. A content management system may determine the needs of a customer as they relate to relevant products and/or services offered by one or more business entities, determine and prioritize actions that may fulfill these needs, and deliver personalized content to the customer based on the customer's information. Accordingly, the systems and techniques provided herein may improve the efficiency and reduce the time involved with delivering effective content to a customer.

Abstract: A method and system of providing customer-specific information and guidance to insurance policyholders during claims processing. The information is created based on outputs from a claims complexity model, customer segmentation model, and claims service level objective (SLO) model. The resulting information is tailored to the individual policyholder and their claim, and includes a summary of their claim activity, guidance regarding their next steps, and predicted wait times for each stage in their claim's processing. In some embodiments, the information is presented as messaging delivered over the policyholder's preferred communication channel(s) that can differ based on which stage of the claims process the claim is in.

Abstract: A conditions monitoring system may include a system controller. The controller may include a device processor and a non-transitory computer readable medium. The computer readable medium may include instructions executable by the device processor to perform the following steps: receiving positional data from a plurality of wearable devices of a plurality of associated wearers; making a determination of a possible dangerous environmental condition based on data received from the wearable device, including the positional data; applying one or more filters to eliminate false positive determinations of possible dangerous conditions; and providing instructions, based on the determination of a possible dangerous environmental condition, to the wearable device for the wearer to follow.

Abstract: A system and method that allow an institution's customer's anticipated data to be stored in a cache in advance of a request for that data, using predictive models based upon analyses of each specific customer's historical patterns. For example, when a customer logs on to an institution's server, a machine learning application on that server may predict the type or category of data that the customer may intend to retrieve, based upon his or her previous patterns when logging on. Typical categories of data may include, for example, account balances, status of outstanding loans, credit card data, and insurance information. By populating the cache with such anticipated data, that data may be more quickly accessed by the customer.

Abstract: A system and method for using an augmented intelligence guide system to assist users, customers, members, and other users of a service (for example, a financial service or an insurance service) in completing a task or process to improve the success rate of the accurate completion of the steps necessary to execute the task or process is described. The system includes a process detection module, an experience determination module, an assistance classification module, and a guidance engine.

Abstract: An interface modification system includes one or more processors configured to provide, to one or more client devices, a graphical representation of a web application. The graphical representation has a first layer including one or more components of the web application and a second layer configured for secondary interactions with the one or more components. The one or more processors are configured to receive, via the second layer and from the one or more client devices, feedback associated with the one or more components. Additionally, the one or more processors are configured to generate an incident record including the feedback and store the incident record in an incident database.

Abstract: A method disclosed comprises receiving sensor data indicating probable damage to the autonomous vehicle from a sensor aboard the autonomous vehicle. The method analyzing the sensor data using a decision engine to determine a confidence factor associated with the probable damage to the autonomous vehicle, and, based on the confidence factor meeting a threshold value, determining an occurrence of a condition causing damage. The method includes sending a command to a vehicle actuation manager to move the autonomous vehicle to a safe location in response to the condition and sending an alert. Systems implementing similar aspects are also disclosed.

Abstract: An autonomous vehicle includes vehicle sensors that detect driving conditions and a communication interface communicatively coupled with a driving condition database via a communication network. The driving condition database stores vehicle sensor information indicative of first driving conditions and mobile device sensor information indicative of second driving conditions. Additionally, in response to a connection rating determination logic determining that a connection rating between the communication interface and the communication network below a threshold, a controller of the autonomous vehicle gathers, processes, and stores the vehicle sensor information and the mobile device sensor information for subsequent communication to the driving condition database and operates the autonomous vehicle based on the vehicle sensor information and the mobile device sensor information.

Abstract: The present disclosure relates to monitoring data in and around a vehicle to predict anomalous, e.g., unsafe, road conditions, and using the data to suggest a corrective action to avoid the unsafe road conditions. A computing device receives information indicative of imagery, sound, or vehicle operation via sensors and/or cameras mounted in or near a vehicle. The information may be received via the vehicle itself or via a device. The computing device then determines whether there is an indication of an anomalous road condition. The computing device also receives vehicle operation data extracted from one or more vehicle sensors. The computing device then determines whether there is an indication of unsafe road conditions, and if there is, the computing device may output a notice or alert via a notification system to alert the driver.

Abstract: A system may include a vehicle system configured to monitor one or more monitor variables related to a vehicle. The system may also include a processor that may receive a selection of the one or more monitor variables to monitor and receive data from the vehicle system. The data may be limited based on the selection of the one or more monitor variables. The processor may then determine a fixed rate premium for at least two years based on the data and display a visualization that may include the fixed rate premium on a display.

Abstract: Systems and methods for using parameters with shortened resource locators to access a resource are provided. A short resource locator is associated with a full resource locator template in a resource locator association datastore. Parameters provided with the short resource locator are used to replace two or more parameter identifiers within a full resource locator template to generate a full resource locator. The full resource locator is used to access a resource.

Abstract: The embodiments disclosed herein use WiFi signals detected from nearby WiFi networks to confirm the identity of a bank's customer logging in to his or her account at the bank. Specifically, the customer's computing device may detect signals from neighboring WiFi networks. The bank may then verify that the customer's accounts are being accessed from the customer's home or office by comparing the list of neighboring WiFi networks to a previously stored list of the neighboring networks. If the lists match, it is probable that the customer's accounts are being accessed from the customer's home or office, thus reducing the possibility that a fraudulent actor is trying to access the customer's accounts.

Abstract: An applet may be downloaded or provided to a web browser when a user visits a site in order to protect data input by the user from being captured by malicious software, such as key loggers. The applet may present a user input field in the web browser and may generate a random sequence of low-level key stroke or mouse click events within the input field when the user enters information, such as a username and/or password. A listening key logger will receive a large amount of random data, whereas the applet will receive and buffer the actual user data that may be communicated to a remote site access by the user.

Abstract: A system includes a processor and a database having first data indexed therein and indicative of a plurality of online websites. The processor is configured to receive, via a search engine account, second data indicative of a search string. The processor is also configured to determine an additional online account linked with the search engine account, and locate, in the additional online account and based on the second data, third data correlated to the search string. The processor is also configured to search the database to locate a subset of the first data by identifying a correspondence between the subset of the first data and a combination of the second data and the third data. The processor is also configured to format, based on the subset of the first data, search results displayable on a display of a user device.

Abstract: Systems and methods for analyzing Robotic Process Automation (RPA) code are provided. A robotic process automation (RPA) file is received. RPA data within the RPA file is parsed and restructured for rendering in a code-review graphical user interface (GUI). A code-review GUI with the restructured RPA data is then rendered.

Abstract: A system and method for automatically detecting if a home alarm system is being used and/or actively monitored are disclosed. The system and method use data gathered from one or more sensors, including audio information from microphones. The audio information is analyzed using a machine learning system to determine if the alarm system is being regularly used and monitored. The system and method can also automatically update a policy holder's insurance policy to reflect whether or not an alarm system is being used.

Abstract: Techniques are described for cross-device presentation. During a speech interaction with a conversational user interface (CUI) executing on an input device, such as a personal assistant (PA) device or other computing device, a user may utter one or more search terms to search for an item, such as a vehicle to purchase. The search term(s) may be employed by a search engine to identify one or more items that correspond to the search term(s). The search engine can generate recommendation information that includes a description of the item(s) corresponding to the search term(s). The recommendation information can be communicated to an output device that is registered to, or otherwise associated with, the user who spoke the search term(s) to the input device. In some instances, the recommendation information can be presented through speech output on the PA device or other device.

Abstract: The present disclosure relates to detecting the use of fake voice command to activate microphones of smart devices. In one embodiment, sound characteristics associated with an audio signal from a microphone of smart device may be compared with other microphones of the smart device in order to detect fake voice commands. In another embodiment, sound characteristics associated with the audio signal from the microphone may be compared with a threshold range of stored sound characteristics in order to detect fake voice commands. In some embodiments, a controller may triangulate a position associated with a source of a sound in order to detect a fake voice command. In a further embodiment, a controller may verify that a user or associated electronic device are near a smart device to authorize a voice command.

Abstract: Implementations are disclosed to automatically evaluate, detect, or predict an event, and provide customized virtual assistance to a user based on the event. The implementations include a system capable of pulling data from a client device, detecting an event based on the pulled data, and pushing customized digital resources to the client device based on the detected event.

Abstract: A system includes a computing device comprising a memory storing instructions configured to cause a processor to receive: purchase data associated with products purchased by a user, online activity data performed by the user and other users and associated with information pertaining to the products, and vendor information comprising retail sales data, after-market sales data, and product availability associated with the products. The processor determines one or more values of the products based on the purchase data, the online activity data, and the vendor information and whether the purchased products correspond to specialty products based on the purchase data, the online activity data, and the values of the products. The processor may then send a notification to the user comprising an offer for insurance for the products in response to determining the products correspond to specialty products.