Abstract: Computer systems and methods are provided for training a machine learning system to determine an authentication decision and explanation information corresponding to the authentication decision. First authentication information for a first authentication request including a first image is received. First validation information corresponding to the first image and including a first authentication decision and first explanation information is received. Data storage of a machine learning system stores the first image and the first validation information. The machine learning system updates an authentication model based on the stored first image and first validation information. Second authentication information for a second authentication request is received. The machine learning system determines second validation information, including second explanation information, based on the updated authentication model. The second explanation information is provided for display to a user device.

Abstract: Computer systems and methods are provided for determining authenticity of a document. A computer system receives first image data from a remote third party. The first image data includes a first image of a document. The computer system generates an image hash based on at least a portion of the received image data. The computer system compares the generated image hash with a stored image hash to determine whether the generated image hash meets image matching criteria. The stored image hash is associated with a first predetermined authentication decision. In accordance with a determination that the generated image hash meets the image matching criteria, the computer system transmits the first predetermined authentication decision to the remote third party.

Abstract: Systems and methods for authenticating a document are provided. The methods include receiving image data that includes a document and data from one or more sensors. The methods include determining a location of the document using the image data and the data received from the sensors. The methods further include determining electromagnetic signal parameters using the determined location of the document and emitting an electromagnetic signal at the document. The electromagnetic signal is based on the determined electromagnetic signal parameters. The methods include, while emitting the electromagnetic signal at the document, capturing a verification image of the document. The verification image includes security features that are exposed to the electromagnetic signal.

Abstract: Computer systems and methods are provided for extracting information from an image of a document. A computer system receives image data, the image data including an image of a document. The computer system determines a portion of the received image data that corresponds to a predefined document field. The computer system utilizes a neural network system to assign a label to the determined portion of the received image data. The computer system performs text recognition on the portion of the received image data and stores the recognized text in association with the assigned label.

Abstract: Computer systems and methods are provided for authenticating a user. A system receives first authentication information that includes first and second facial image data for a user. The system compares the first facial image with the second facial image to determine whether first matching criteria are met. The system, in accordance with a determination that the first matching criteria are met, generates an identity chain. The system, after generating the identity chain, receives a request to perform a transaction and receiving second authentication information that includes third facial image data for the user. The system determines whether the third facial image meets second matching criteria by comparing the third facial image with respective image data of the identity chain. The system, in accordance with a determination that the third facial image user meets the second matching criteria, transmits authorization information for the transaction.

Abstract: Computer systems and methods are provided for training a machine learning system to determine an authentication decision and explanation information corresponding to the authentication decision. First authentication information for a first authentication request including a first image is received. First validation information corresponding to the first image and including a first authentication decision and first explanation information is received. Data storage of a machine learning system stores the first image and the first validation information. The machine learning system updates an authentication model based on the stored first image and first validation information. Second authentication information for a second authentication request is received. The machine learning system determines second validation information, including second explanation information, based on the updated authentication model. The second explanation information is provided for display to a user device.

Abstract: Computer systems and methods are provided for training a machine learning system to determine an authentication decision and deleting personal data from the machine learning system in a way that cancels any results of the training based on that personal data. A deletion request is received from a user device, the deletion request designating a first image. In response, a server creates an inverse attribute for the first image, the inverse attribute contradicting an initial attribute that was associated with the first image when the first image was initially received. The server updates a machine learning system based on the first image and the inverse attribute. Subsequent to updating the machine learning model, the server deletes the first image from data storage of the machine learning system.

Abstract: Computer systems and methods are provided for determining authenticity of a document. A computer system receives first image data from a remote third party. The first image data includes a first image of a document. The computer system generates an image hash based on at least a portion of the received image data. The computer system compares the generated image hash with a stored image hash to determine whether the generated image hash meets image matching criteria. The stored image hash is associated with a first predetermined authentication decision. In accordance with a determination that the generated image hash meets the image matching criteria, the computer system transmits the first predetermined authentication decision to the remote third party.

Abstract: Computer systems and methods are provided for determining an authentication result. A computer system receives a first set of data that corresponds to a first entity. A machine learning system determines a first set of one or more values that correspond to the first set of data. The computer system receives a second set of data that corresponds to a second entity. The machine learning system determines a second set of one or more values that corresponds to the second set of data. The second set of one or more values are determined using at least a portion of the first set of one or more values.

Abstract: A computer-implemented method for automatically retrieving items for a user from an online product catalogue, the items being suitable for an upcoming calendar event, includes receiving, by a server, data from a curated list over a network, the data including curated classifications of apparel items. Trending apparel items are received by the server from selected websites for the upcoming calendar event. A deep learning module analyzes the data from the curated list and the trending apparel items to learn attributes associated with the upcoming calendar event. The server searches the online product catalogue for one or more selected apparel items which match the learned attributes. Information regarding the one or more selected apparel items is then returned to a client device of the user.

Abstract: A computer-implemented method for automated product recommendations personalized to a user browsing a webpage of an e-commerce website or web application via a computer device. Image data of one or more product items displayed on the webpage is captured responsive to user input, and then sent to a server over a network. A software module that executes on the server analyzes the image data and segments it into one or more of attributes, constituent items, or objects of the one or more product items. The software module also receives media content feeds that contain images representative of style preferences of the user. The software module selects one or more specific items from a product catalogue of the e-commerce website or web application based, in part, on a visual similarity to the images representative of the style preferences of the user.

Abstract: In one embodiment, a conference bridge receives a call initiated by a first caller endpoint. The conference bridge identifies a conference to which the call requests entry and determines whether the conference bridge has available resources to process the call. The conference bridge enables the call to join the conference via a second conference bridge associated with a second caller endpoint participating in the conference according to whether the conference bridge has available resources to process the call.

Abstract: A system and method for computer originated audio file transmission includes a server having a communications module operable to communicate with a terminal unit. The server may also include a storage module operable to store at least one file. A processor may be provided to separate the file into a plurality of packets. In accordance with one embodiment of the present invention, the communications module is operable to send an initial burst of packets to the terminal unit, wherein the initial burst of packets includes at least two of the plurality of packets. In accordance with another embodiment of the present invention, the communications module is further operable to send additional packets of the plurality of packets at a predetermined rate, until each of the plurality of packets has been sent to the terminal unit.

Abstract: A unified messaging system for an enterprise includes a messaging module operable to store a message sent by a first user to a second user in a first media type, and to deliver the message to the second user in either the first type or a second media type. A natural language speech parsing (NLSP) module coupled with the messaging module is operable to detect an actionable item contained within the message, the messaging module dynamically modifying a response menu to include an option corresponding to the actionable item, and then presenting the modified response menu to the second user concurrent with or following delivery of the message. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract: A method for automatically identifying wireless signal quality of a region includes receiving signal quality information associated with wireless signals received by each of a plurality of mobile endpoints and receiving location information identifying locations of each of the plurality of mobile endpoints. The method also includes, based on the received signal quality information and the received location information, identifying a first region of an area, the first region having a first signal quality.

Abstract: A system for navigating includes an interface operable to receive position information of a first modality. The position information of the first modality is associated with a navigation unit. The interface is further operable to receive position information of a second modality. The position information of the second modality is associated with the navigation unit. The system also includes a processor coupled to the interface and operable to identify a destination. The system is further operable to navigate to the destination based on the position information of the first and second modalities by switching between the first modality and the second modality.

Abstract: A method and apparatus to process an incoming message is described. The method may comprise, at a recipient system, receiving an incoming message from a message communicator and automatically analyzing message content to identify a keyword included in the message content. Thereafter, a predefined action associated with the keyword may be identified and the action may be performed. In an example embodiment, the predefined action may be a priority with the message, alerting an intended recipient of the message, routing the message to the intended recipient, paging the intended recipient, emailing the message to the intended recipient, sending an SMS message to the intended recipient, or the like. In an example embodiment, a user/owner of a mailbox may search a message database to identify incoming messages which includes the search term in the message content.

Abstract: In a wide-area communication system, users or numbers in the system to be alerted are ranked so to improve the efficiency of the alert calls. Rankings are based on various factors, including whether two or more users are on the same active call, whether a user is on an active call, how recently a user ended a call, and whether a user recently missed a call. Within rankings, there may be multiple callers or numbers. These users may further be ranked, such as by determining which caller is expected to end a call first based on the current elapsed time of the call and the average call duration for that user or number.

Abstract: In one embodiment, techniques for alerting a user of unchecked messages correlated to a contact before communicating with the contact are provided. The check for unchecked messages may be performed across a plurality of communication modalities. If one or more unchecked messages are found, then the user is alerted that there may be unchecked messages. The user may then have the option to check the unchecked messages before contacting the contact.

Abstract: A method and apparatus to provide speaker selection in a multi-party conference call is described. The method may comprise processing a speaker queue for at least one new speaker and monitoring when a number of active speakers is less than a predetermined number of active speakers. When less than the predetermined number, the method automatically, without human intervention, adds a new speaker from the speaker queue. A request for a new speaker may be received via a communication channel independent of a voice communication channel of the multi-party conference call. The request may be received from the conference endpoint via a voice communication channel of the multi-party conference call. In an example embodiment, new speakers in the speaker queue may be prioritized based a class of service associated with each new speaker. Priority may be given to a new speaker with a higher associated class of service.