Abstract: Techniques are described for performing multi-factor authentication of a user during a service session, based at least partly on a code conveyed using an audio file. A code is generated that corresponds to the user and/or their user device. A playback device that is registered to the user can be used to output a playback of an audio file that encodes the code. The playback of the audio file is conveyed through the service session by the user device and received by a backend server, which analyzes the playback of the audio file to extract the code. The user can be authenticated based at least partly on verifying the code that is extracted from the playback of the audio file, by comparing the extracted code to the code that was generated and sent to the playback device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a digital conversation is described. One of the methods includes guiding a user through a directed conversation having a plurality of flows, each flow including at least one statement to be made by a digital advisor. The method includes receiving user input as part of the directed conversation. The method includes selecting one of the flows based on the received user input. The method also includes storing at least some of the information provided by the user in a data store.

Abstract: A computer system and method having a user interface including a touch-sensitive display screen. The system and method enables entry of a password which includes displaying a first array of a plurality of images on the touch-sensitive display prompting a user to select with a finger one of the plurality of images displayed. Subsequently at least another array of a plurality of images successive to the first array is displayed on the touch sensitive display prompting a user to select with a finger one of the plurality of images displayed in the another array of images. A computer processor then determines if a user selected a predetermined image from the first array of the plurality of images and a predetermined image from each at least another array of plurality of images displayed after the first array. If determined, the user is permitted access to an application executable on the computer system.

Abstract: A system and method for alerting a driver of a motor vehicle or a person walking along a road or hiking on a trail of potentially dangerous hazards in their path. Hazards may be deep water, ice, oil slicks or other hazards. In the case of a motor vehicle, the system uses cameras mounted on or within the vehicle to detect potential hazards and then analyzes the images combined with the known topography of the location to evaluate the ability of the vehicle to safely traverse the hazard. In the case of a person walking or hiking, the person may use the camera on a personal mobile device to capture images of the hazard and to combine the images with the known topography at the location to evaluate the danger presented by the hazard.

Abstract: A security object management system may include a management module including a device processor and a non-transitory computer readable medium including instructions stored thereon, and executable by the processor, for performing the following steps: accessing a database having stored therein data regarding a plurality of security objects, wherein the data includes ownership data regarding the assignment of rights associated with the security objects; and receiving user input to change the reassignment of rights of at least one of the security objects from one user to another user of the system.

Abstract: A plumbing system may include a first conduit that supplies a fluid to a destination device. The plumbing system may also include a second conduit concentric to the first conduit. The second conduit includes an indicator material that changes one or more properties of the fluid supplied to the destination device when the fluid contacts the indicator material via an opening present in the first conduit.

Abstract: An image processing system or electronic device may implement processing circuitry. The processing circuitry may receive an image, such as financial document image. The processing circuitry may determine a character count for the financial document image or particular portions of the financial document image without recognizing any particular character in the financial document image. In that regard, the processing circuitry may determine a top left score for pixels in the financial document, the top left score indicating or representing a likelihood that a particular pixel corresponds to a top left corner of a text character. The processing circuitry may also determine top right score for image pixels. Then, the processing circuitry may identify one or more text chunks using the top left and top rights scores for pixels in the financial document image. The processing circuitry may determine a character count for the identified text chunks.

Abstract: A system and method for automatically detecting if a vehicle safety system is being used by a driver is disclosed. The system and method use data gathered from one or more sensors in the vehicle. The data is analyzed to determine if the safety system is being used or disabled. The system can send reminders to a driver to use the safety system. The system and method can also automatically update a policy holder's insurance policy to reflect whether or not a safety system is being used.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data from previous service sessions between service representative(s) and individual(s). Training data may include, for previous service session(s), a session record (e.g., audio record) of the session and a set of survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that is a combination of a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network.

Abstract: A system and method for providing an interactive voice response dialogue by using a cloud computing system coupled to a mobile computing device. The cloud computing system may receive a request from a mobile computing device to initiate communication with an interactive voice response system having a tree structure including audio files in the cloud computing system. An interactive voice response dialogue may be conducted using the cloud computing system when the mobile computing device does not have the capacity to receive the one or more files. When the mobile computing device does have the capacity to receive the one or more files, one or more files may be transmitted from the cloud computing system to the mobile computing device, so that he mobile computing device may conduct the interactive voice response dialogue.

Abstract: A system and method for providing an audible explanation of documents upon request is disclosed. The system and method use an intelligent voice assistant that can receive audible requests for document explanations. The intelligent voice assistant can retrieve document summary information and provide an audible response explaining key points of the document.

Abstract: The technology described includes an adaptive probability matrix that creates a notification schedule. The schedule can be used to send reminders to users to press a physical, connected device/button, that when pressed or clicked, causes money to be transferred according to a set of rules (i.e., a “one-click” transfer of funds).

Abstract: Embodiments described herein disclose methods and systems for using more than one Recurrent Neural Network (RNN) to analyze a user input and to predict a request being made by the user as the user is inputting the request. In an embodiment, a first RNN and a second RNN can simultaneously or near simultaneously process the user requested information by separating and analyzing the characters and words in the user's request. A third RNN can process the output vectors generated by the first and second RNNs to identify one or more solutions that predict the user's request.

Abstract: Methods and systems described in this disclosure receive, from a device, information associated with an activity for input into an enterprise integrated calendar, including a start date of the activity, a completion date of the activity, and a resource expected to be impacted by the activity from the start date to the completion date. Based on the start and completions dates and the resource impacted, a change impact score for the activity can be determined. A saturation score (or a series of saturation scores) for the resource can be generated from the start date to the completion date based on the change impact score for the activity and change impact scores of other activities. Such scores can provide information about whether the activity should remain on the enterprise calendar or be moved to a different date where the saturation scores do not exceed certain saturation levels.

Abstract: The present disclosure relates generally to a system that includes a storage component that stores data and a processor. The processor may install an application using a portion of the storage component, partition the portion of the storage component from a remaining portion of the storage component, and execute the application via the portion of the storage component.

Abstract: Techniques are described for generating metric(s) that predict survey score(s) for a service session. Model(s) may be trained, through supervised or unsupervised machine learning, using training data such as communications from previous service sessions between service representative(s) and individual(s), and survey scores provided by the serviced individual to rate the session on one or more criteria (e.g., survey questions). The model(s) may be trained to output, based on an input session record, metric(s) that each correspond to a survey score that would have been provided by the individual had they completed the survey. The model may be a concatenated model that combines a language model output from a language classifier recurrent neural network, and an acoustic model output from an acoustic feature layer convolutional neural network. Individuals can be clustered according to the metric(s) and/or other factors, and the cluster(s) can be employed for routing incoming service requests.

Abstract: Illustrated herein are systems and methods of transferring physical currency into electronic credit that becomes electronically available. One method includes remotely and quickly depositing non-negotiable instruments, such as cash, by communicating information, such as an image of the currency, about the instrument to a depositor. An exemplary system includes computing devices and a capture module with a retrieval engine, a transmission engine, an inspection engine, and a conferral engine. The capture module receives information about a non-negotiable instrument, and an inspection engine analyzes the information to confirm if the unit of currency is authentic.

Abstract: Embodiments described herein disclose technology for verifying authorization of an application download. The system can receive from a device associated with a user, a request to download an application. In response to a first instance of the application being downloaded on the device, the system can assign a unique identifier to the first instance of the application. After the application is downloaded and prior to granting the person requesting the application download access to the first instance of the application, the system can request via the first instance of the application identification information and particular authentication information to verify that the person requesting the application download is authorized to do so. In response to verifying that the person requesting the application download is authorized, the unique identifier can be associated with the account, user and/or device to result in a verified download of the first instance of the application.

Abstract: Methods and systems are provided for making a pre-payment. In some embodiments, a user is provided with a mobile wallet; information populating at least one payment instrument to the mobile wallet is received; information that the mobile wallet is usable with respect to the vehicle is received; information that the mobile wallet has been presented by the vehicle to a payment location is received; an authorized pre-payment corresponding to items or an amount associated with the payment location is received; a token is received from the user at the payment location; and the pre-payment is settled using the payment instrument.