Abstract:
PROBLEM TO BE SOLVED: To provide mechanisms for improving interpretation and processing of commands provided to a virtual assistant.SOLUTION: A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent, to reduce the number of candidate interpretations of the user's input, and to reduce the need for the user to provide very clear input. The context includes available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. The context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.
Abstract:
PROBLEM TO BE SOLVED: To provide systems, methods and computer readable media for managing or using voicemails.SOLUTION: A method includes receiving, at a first data processing system, data representing an expiration time of a voicemail left for a user of the first data processing system and storing the data representing the expiration time for later use by the first data processing system.
Abstract:
Touch inputs such as single—finger contacts and multiple—fin— ger contacts are detected at an electronic device and translated into electronic touch communications for playback at an external electronic device.
Abstract:
A computer-implemented method for use in conjunction with a computing device with a touch screen display comprises: detecting one or more finger contacts with the touch screen display, applying one or more heuristics to the one or more finger contacts to determine a command for 5 the device, and processing the command. The one or more heuristics comprise: a heuristic for determining that the one or more finger contacts correspond to a one- dimensional vertical screen scrolling command, a heuristic for determining that the one or more finger contacts correspond to a two-dimensional screen translation command, and a heuristic for determining that the one or more finger contacts correspond to a command to transition from displaying a respective item in 0 a set of items to displaying a next item in the set of items.
Abstract:
A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user's intent and to reduce the number of candidate interpretations of the user's input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.
Abstract:
A touch input is detected on a touch-sensitive display of an electronic device and determined to be a single-finger contact or a multiple-finger contact. Based on the determination, the touch input may be translated into one or more electronic touch communications, which may 5 be used for playback at an external electronic device.
Abstract:
The method includes pairing the first device 100 with the second device 112 and establishing a trusted relationship there between, where the first device is authenticated using a device key and the exchange of a secret key. User input is received from an input/output device and the secret key is transmitted to the second device to unlock the second device in response to receiving the user input. Establishing the trusted relationship comprises using a key generated from a hardware key associated with the first device to authenticate the device key. The trusted relationship may be provided by Bluetooth and unlocking of the second device may depend on the proximity of the first device. User input from the first device may include biometrics (voice, fingerprint, etc) and the hardware key may be obtained from a secure element.
Abstract:
Among other things, techniques and systems are disclosed for implementing contextual voice commands. On a device, a data item in a first context is displayed. On the device, a physical input selecting the displayed data item in the first context is received. On the device, a voice input that relates the selected data item to an operation in a second context is received. The operation is performed on the selected data item in the second context.
Abstract:
A computer-implemented method for use in conjunction with a computing device with a touch screen display comprises: detecting one or more finger contacts with the touch screen display, applying one or more heuristics to the one or more finger contacts to determine a command for 5 the device, and processing the command. The one or more heuristics comprise: a heuristic for determining that the one or more finger contacts correspond to a one- dimensional vertical screen scrolling command, a heuristic for determining that the one or more finger contacts correspond to a two-dimensional screen translation command, and a heuristic for determining that the one or more finger contacts correspond to a command to transition from displaying a respective item in 0 a set of items to displaying a next item in the set of items.
Abstract:
uso de informações de contexto para facilitar processamento de comandos em um assistente virtual. a presente invenção refere-se a um assistente virtual usa informações de contexto para suplementar a linguagem natural ou entrada gestual de um usuário. o contexto ajuda a esclarecer a intenção do usuário e a reduzir o número de interpretações candidatas da entrada de usuário, e reduz a necessidade do usuário fornecer esclarecimento excessivo de entrada. o contexto pode incluir quaisquer informações disponíveis que são úteis ao assistente para suplementar a entrada de usuário explícita para restringir um problema de processamento de informações e/ou personalizar resultados. o contexto pode ser usado para restringir soluções durante várias fases de processamento, que incluem, por exemplo, reconhecimento de fala, processamento de linguagem natural, processamento de fluxo de tarefa, e geração de diálogo.