Triggering notifications associated with tasks to perform

    公开(公告)号:AU2020202534A1

    公开(公告)日:2020-05-07

    申请号:AU2020202534

    申请日:2020-04-15

    Applicant: APPLE INC

    Abstract: A method comprising: at an electronic device comprising one or more processors and memory storing one or more programs for execution by the one or more processors: receiving, from a user, natural language input that expressly specifies one or more first attributes of a task; automatically without user intervention, retrieving context data that is separate from the natural language input; deriving from the context data one or more second attributes of the task; determining, from the natural language input, one or more triggering criteria associated with the task; based on the natural language input, generating a task item for the task, the task item including the one or more first attributes, the one or more second attributes, and the one or more triggering criteria; determining whether the one or more triggering criteria are satisfied; and in response to determining that the one or more triggering criteria are satisfied, causing a notification associated with the task item to be displayed, the notification including an associated description comprising the one or more first attributes and the one or more second attributes.

    Triggering notifications associated with tasks to perform

    公开(公告)号:AU2018204265B2

    公开(公告)日:2020-03-12

    申请号:AU2018204265

    申请日:2018-06-14

    Applicant: APPLE INC

    Abstract: A task item is electronic data that represents a task to be performed, whether manually or automatically. A task item includes one or more details about its corresponding task, such as a description of the task and a location of the task. Specifically, techniques for generating task items, organizing task items, triggering notifications of task items, and consuming task items are described. In one approach, a task item is generated based on input from a user and context of the input. In another approach, different attributes of task items are used to organize the task items intelligently into multiple lists. In another approach, one or more criteria, such as location, are used to determine when to notify a user of a task item. In another approach, actions other than the generation of notification are enabled or automatically performed, actions such as emailing, calling, texting, and searching.

    User training by intelligent digital assistant

    公开(公告)号:AU2017221864A1

    公开(公告)日:2017-09-21

    申请号:AU2017221864

    申请日:2017-09-01

    Applicant: APPLE INC

    Abstract: The method includes receiving, from a user, a first speech input spoken in a first language; inferring a user intent based on at least the first speech input in the first language; based on the inferred user intent, generating one or more alternative expressions of the first speech input in the first language; and providing feedback to the user introducing the alternative expressions as a more preferred input to express the inferred user intent than the first speech input provided by the user.

    Intelligent automated assistant
    19.
    发明专利

    公开(公告)号:AU2017204217A1

    公开(公告)日:2017-07-13

    申请号:AU2017204217

    申请日:2017-06-21

    Applicant: APPLE INC

    Abstract: The intelligent automated assistant system engages with the user in an integrated, conversational manner using natural language dialog, and invokes external services when appropriate to obtain information or perform various actions. The system can be implemented using any of a number of different platforms, such as the web, email, smartphone, and the like, or any combination thereof. In one embodiment, the system is based on sets of interrelated domains and tasks, and employs additional functionally powered by external services with which the system can interact.

    Multi-command single utterance input method

    公开(公告)号:AU2015266863A1

    公开(公告)日:2016-09-29

    申请号:AU2015266863

    申请日:2015-05-28

    Applicant: APPLE INC

    Abstract: Systems and processes are disclosed for handling a multi-part voice command for a virtual assistant. Speech input can be received from a user that includes multiple actionable commands within a single utterance. A text string can be generated from the speech input using a speech transcription process. The text string can be parsed into multiple candidate substrings based on domain keywords, imperative verbs, predetermined substring lengths, or the like. For each candidate substring, a probability can be determined indicating whether the candidate substring corresponds to an actionable command. Such probabilities can be determined based on semantic coherence, similarity to user request templates, querying services to determine manageability, or the like. If the probabilities exceed a threshold, the user intent of each substring can be determined, processes associated with the user intents can be executed, and an acknowledgment can be provided to the user.

Patent Agency Ranking