Natural assistant interaction

Abstract

The present disclosure designs natural assistant interactions. The invention provides systems and processes for operating a virtual assistant to provide natural assistant interactions. According to one or more examples, a method includes, at an electronic device with one or more processors and memory: receiving a first audio stream, the first audio stream including one or more utterances; determining whether the first audio stream includes a lexical trigger; generating one or more candidate textual representations of the one or more utterances; determining whether the virtual assistant is to ignore at least one of the one or more candidate textual representations. If at least one candidate textual representation is to be ignored, generating one or more candidate intents based on candidate textual representations of the one or more candidate textual representations other than the at least one candidate textual representation to be ignored.

Description

[0001] Cross-references to related applications

[0002] This application is a divisional application of Chinese national application number 201910147749.1, filed on February 27, 2019, entitled "Natural Assistant Interaction".

[0003] This patent application claims priority to U.S. Provisional Application Serial No. 62 / 648,084, filed March 26, 2018, entitled "NATURAL ASSISTANT INTERACTION," and U.S. Non-Provisional Application Serial No. 16 / 019,331, filed June 26, 2018, also entitled "NATURAL ASSISTANT INTERACTION." The contents of both patent applications are incorporated herein by reference in their entirety for all purposes. Technical Field

[0004] This involves virtual assistants in general, and more specifically, natural language interaction through virtual assistants. Background Technology

[0005] Virtual assistants (or digital assistants or intelligent automated assistants) provide a helpful human-computer interface. Such assistants allow users to interact with devices or systems using natural language in voice and / or text. For example, a user can provide voice input containing their request to a digital assistant running on an electronic device. The virtual assistant can interpret the user's intent from this voice input and act it out as a task. These tasks can then be performed by executing one or more services of the electronic device, and relevant output in response to the user's request can be returned to the user.

[0006] The virtual assistant can be activated upon receiving a trigger phrase such as "Hey Siri." Once activated, the virtual assistant can receive and process the user's voice input. For example, the user's voice input may include a leading trigger phrase to activate the virtual assistant, followed by an information request (e.g., "Hey Siri, what's the weather like today?"). However, guiding every voice input with a trigger phrase (e.g., "Hey Siri") can be inconvenient and quickly become cumbersome. It also doesn't represent a natural way of communicating. For example, when a first user is talking to a second user, the first user shouldn't typically guide every sentence with the second user's name. Therefore, requiring the user to guide every voice input with a trigger phrase is not a natural way of communicating and is inefficient. Summary of the Invention

[0007] This invention provides a system and process for providing natural language interaction through a virtual assistant.

[0008] According to one or more examples, the method includes, at an electronic device having one or more processors, memory, and a microphone: receiving a first audio stream via the microphone, the first audio stream comprising one or more utterances; and determining whether the first audio stream includes a lexical trigger. If the first audio stream is determined to include a lexical trigger, the method further includes generating one or more candidate text representations of the one or more utterances, and determining whether a virtual assistant should ignore at least one candidate text representation of the one or more candidate text representations. If the virtual assistant is determined to ignore at least one candidate text representation, the method further includes generating one or more candidate intents based on candidate text representations of the one or more candidate text representations other than the at least one candidate text representation to be ignored. The method further includes determining whether the one or more candidate intents include at least one executable intent. If the one or more candidate intents are determined to include at least one executable intent, the method further includes executing at least one executable intent and outputting the result of executing at least one executable intent.

[0009] This document discloses an example non-transitory computer-readable medium. An example non-transitory computer-readable storage medium stores one or more programs. The one or more programs include instructions that, when executed by one or more processors of an electronic device, cause the electronic device to receive a first audio stream via a microphone, the first audio stream comprising one or more utterances; determine whether the first audio stream includes a word trigger; generate one or more candidate text representations of the one or more utterances based on the determination that the first audio stream includes a word trigger; determine whether a virtual assistant should ignore at least one candidate text representation of the one or more candidate text representations; generate one or more candidate intents based on candidate text representations of the one or more candidate text representations other than the at least one candidate text representation to be ignored, based on the determination that the virtual assistant should ignore at least one candidate text representation; determine whether the one or more candidate intents include at least one executable intent; execute at least one executable intent based on the determination that the one or more candidate intents include at least one executable intent; and output the result of executing at least one executable intent.

[0010] This document discloses an example electronic device. An example electronic device includes: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing the following operations: receiving a first audio stream via a microphone, the first audio stream including one or more utterances; determining whether the first audio stream includes a lexical trigger; generating one or more candidate text representations of the one or more utterances based on the determination that the first audio stream includes a lexical trigger; determining whether a virtual assistant should ignore at least one candidate text representation of the one or more candidate text representations; generating one or more candidate intents based on candidate text representations of the one or more candidate text representations other than the at least one candidate text representation to be ignored, based on the determination that the virtual assistant should ignore at least one candidate text representation; determining whether the one or more candidate intents include at least one executable intent; executing at least one executable intent based on the determination that the one or more candidate intents include at least one executable intent; and outputting the result of executing at least one executable intent.

[0011] An exemplary electronic device includes: means for receiving a first audio stream via a microphone, the first audio stream including one or more utterances; means for determining whether the first audio stream includes word triggering; means for generating one or more candidate text representations of the one or more utterances based on the determination that the first audio stream includes word triggering; means for determining whether a virtual assistant should ignore at least one candidate text representation of the one or more candidate text representations; means for generating one or more candidate intents based on candidate text representations of the one or more candidate text representations other than the at least one candidate text representation to be ignored based on the determination that the virtual assistant should ignore at least one candidate text representation; means for determining whether the one or more candidate intents include at least one executable intent; means for executing at least one executable intent based on the determination that the one or more candidate intents include at least one executable intent; and means for outputting the result of executing at least one executable intent.

[0012] Current technologies facilitating voice-based human-computer interaction typically require the use of trigger phrases at the beginning of the user's utterance. As mentioned above, this requirement can make human-computer interaction cumbersome and render the human-computer user interface less natural and efficient. The various techniques described in this application for providing natural language interaction eliminate or reduce the need for such a requirement to guide each user's utterance with a trigger phrase. Instead, trigger words or phrases can be placed in any part of an audio stream that may include one or more user utterances. Furthermore, the techniques described in this application do not require the use of trigger phrases comprising multiple words (e.g., "Hey Siri"). A single word (e.g., "Siri") can be used to direct the audio stream, including the user's utterance, toward the virtual assistant. This makes the communication more natural.

[0013] Furthermore, the various technologies described in this application for facilitating voice-based human-computer interaction improve device operability and make the user device interface more efficient (e.g., eliminating the need to guide each user's speech with a trigger phrase). Additionally, by enabling users to use the device more quickly and efficiently, this can also reduce power consumption and extend the device's battery life. Attached Figure Description

[0014] Figure 1 Block diagrams are shown for systems and environments used to implement digital assistants, based on various examples.

[0015] Figure 2A This is a block diagram illustrating a portable multi-functional device that implements the client-side portion of a digital assistant according to various examples.

[0016] Figure 2B A block diagram illustrating exemplary components for event handling, based on various examples.

[0017] Figure 3 Portable multi-functional devices are shown that implement the client-side portion of a digital assistant according to various examples.

[0018] Figure 4 A block diagram of an exemplary multifunctional device having a display and a touch-sensitive surface, according to various examples.

[0019] Figure 5A An exemplary user interface for the menu of an application on a portable multi-functional device, based on various examples, is shown.

[0020] Figure 5B Exemplary user interfaces of multifunctional devices with touch-sensitive surfaces separate from the display are shown according to various examples.

[0021] Figure 6A The images show personal electronic devices based on various examples.

[0022] Figure 6B This is a block diagram illustrating personal electronic devices according to various examples.

[0023] Figure 7A A block diagram illustrating a digital assistant system or its server portion, based on various examples, is provided.

[0024] Figure 7B Examples are shown in Figure 7A The digital assistant functions shown.

[0025] Figure 7C A portion of the knowledge ontology is shown based on various examples.

[0026] Figure 8 A block diagram of an exemplary virtual assistant is shown for providing natural language interaction.

[0027] Figure 9 An exemplary user interface is shown for natural language interaction provided by a virtual assistant.

[0028] Figure 10 A block diagram of an exemplary virtual assistant is shown for providing natural language interaction using contextual information.

[0029] Figure 11A An exemplary user interface is shown for natural language interaction provided by a virtual assistant using contextual information associated with usage patterns.

[0030] Figure 11B An exemplary user interface is shown for natural language interaction provided by a virtual assistant using contextual information associated with sensory data.

[0031] Figures 12A to 12D An exemplary user interface is shown for natural language interaction provided by a virtual assistant using contextual information associated with the execution of a previously determined executable intent.

[0032] Figures 13A to 13B An exemplary user interface is shown for natural language interaction provided by a virtual assistant using contextual information associated with the user's speech or audio stream.

[0033] Figures 14A to 14D An exemplary user interface is shown for selecting a task from multiple tasks using contextual information.

[0034] Figures 15A to 15G The process is illustrated according to various implementation schemes for providing natural language interaction by a virtual assistant. Detailed Implementation

[0035] The accompanying drawings are referenced in the following description of the implementation scheme, in which specific examples that can be implemented are shown by way of illustration. It should be understood that other examples may be used and structural changes may be made without departing from the scope of the various examples.

[0036] Various techniques for facilitating more natural human-computer interaction are described. These techniques include reducing or eliminating the need to guide user utterances with trigger phrases and using false trigger mitigators to improve the accuracy of determining whether a user utterance is associated with a virtual assistant. These techniques also include performing candidate intent evaluation (e.g., dry running) without actual execution to determine whether a candidate intent is actionable. This determination avoids wasted processing power and user confusion, thereby improving the operational efficiency of the device.

[0037] Although the following description uses the terms "first," "second," etc., to describe various elements, these elements should not be limited by the terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the various examples described, a first input may be referred to as a second input, and similarly, a second input may be referred to as a first input. Both the first and second inputs are inputs, and in some cases, they are independent and distinct inputs.

[0038] The terminology used in the description of the various examples herein is for the purpose of describing particular examples only and is not intended to be limiting. As used in the description of the various examples and the appended claims, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context expressly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and covers any and all possible combinations of one or more of the associated listed items. It will also be understood that the term “comprising” as used in this specification specifies the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0039] Depending on the context, the term "if" can be interpreted as meaning "when..." or "in response to determination" or "in response to detection". Similarly, depending on the context, the phrases "if determination..." or "if detection [the stated condition or event]" can be interpreted as meaning "when determination..." or "in response to determination..." or "when detection [the stated condition or event]" or "in response to detection [the stated condition or event]".

[0040] 1. System and Environment

[0041] Figure 1A block diagram of system 100 according to various examples is shown. In some examples, system 100 implements a digital assistant. The terms "digital assistant," "virtual assistant," "intelligent automated assistant," or "automated digital assistant" refer to any information processing system that interprets natural language input in spoken and / or textual form to infer user intent and performs actions based on the inferred user intent. For example, to act on an inferred user intent, the system performs one or more of the following steps: identifying a task flow with steps and parameters designed to achieve the inferred user intent; inputting a specific request into the task flow based on the inferred user intent; executing the task flow by invoking programs, methods, services, APIs, etc.; and generating an output response to the user in an audible (e.g., voice) and / or visual form.

[0042] Specifically, a digital assistant can accept user requests, at least in part, in the form of natural language commands, requests, statements, narration, and / or inquiries. Typically, a user request either seeks an informational response from the digital assistant or requests the digital assistant to perform a task. A satisfactory response to a user request includes providing the requested informational response, performing the requested task, or a combination of both. For example, a user asks a digital assistant a question such as, “Where am I now?” Based on the user’s current location, the digital assistant answers, “You are near the west entrance of Central Park.” The user also requests to perform a task, such as, “Please invite my friends to my girlfriend’s birthday party next week.” In response, the digital assistant can confirm the request by saying “Okay, coming right away,” and then send the appropriate calendar invitations to each of the user’s friends listed in the user’s electronic address book on behalf of the user. During the performance of the requested task, the digital assistant sometimes interacts with the user in a sustained dialogue involving multiple exchanges of information over extended periods. Many other methods exist for interacting with a digital assistant to request information or perform various tasks. In addition to providing verbal responses and taking programmed actions, digital assistants also provide responses in other forms of video or audio, such as text, alerts, music, video, animation, etc.

[0043] like Figure 1 As shown, in some examples, the digital assistant is implemented according to a client-server model. The digital assistant includes a client-side portion 102 (hereinafter referred to as "DA client 102") executing on user device 104 and a server-side portion 106 (hereinafter referred to as "DA server 106") executing on server system 108. DA client 102 communicates with DA server 106 via one or more networks 110. DA client 102 provides client-side functionality, such as user-oriented input and output processing, and communication with DA server 106. DA server 106 provides server-side functionality for any number of DA clients 102, each residing on a corresponding user device 104.

[0044] In some examples, DA server 106 includes a client-facing I / O interface 112, one or more processing modules 114, data and models 116, and an I / O interface 118 to external services. The client-facing I / O interface 112 facilitates client-facing input and output processing of DA server 106. One or more processing modules 114 utilize data and models 116 to process voice input and determine user intent based on natural language input. Furthermore, one or more processing modules 114 perform task execution based on the inferred user intent. In some examples, DA server 106 communicates with external services 120 via one or more networks 110 to complete tasks or collect information. The I / O interface 118 to external services facilitates such communication.

[0045] User equipment 104 can be any suitable electronic device. In some examples, the user equipment is a portable multi-functional device (e.g., see below for reference). Figure 2A The described device 200), multi-functional device (for example, see below for reference) Figure 4 The device described is 400) or a personal electronic device (e.g., see below for reference). Figures 6A to 6B The device described is 600. A portable multi-function device is, for example, a mobile phone that also includes other functions such as a PDA and / or music player. Specific examples of portable multi-function devices include those from Apple Inc. (Cupertino, California). iPod and Devices. Other examples of portable multifunction devices include, but are not limited to, laptops or tablets. Additionally, in some examples, user device 104 is a non-portable multifunction device. Specifically, user device 104 is a desktop computer, game console, television, or set-top box. In some examples, user device 104 includes a touch-sensitive surface (e.g., a touchscreen display and / or touchpad). Furthermore, user device 104 optionally includes one or more other physical user interface devices, such as a physical keyboard, mouse, and / or joystick. Various examples of electronic devices such as multifunction devices are described in more detail below.

[0046] Examples of one or more communication networks 110 include local area networks (LANs) and wide area networks (WANs), such as the Internet. One or more communication networks 110 are implemented using any known network protocol, including various wired or wireless protocols such as Ethernet, Universal Serial Bus (USB), FireWire, Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, Wi-Fi, Voice over Internet Protocol (VoIP), Wi-MAX, or any other suitable communication protocol.

[0047] Server system 108 is implemented on one or more stand-alone data processing devices or a distributed computer network. In some examples, server system 108 also utilizes various virtual devices and / or services from third-party service providers (e.g., third-party cloud service providers) to provide potential computing and / or infrastructure resources for server system 108.

[0048] In some examples, user equipment 104 communicates with DA server 106 via a second user equipment 122. The second user equipment 122 is similar to or identical to user equipment 104. For example, the second user equipment 122 is similar to the one described below. Figure 2A , Figure 4 and Figures 6A to 6B The device described is 200, 400, or 600. User equipment 104 is configured to be communicatively coupled to a second user equipment 122 via a direct communication connection such as Bluetooth, NFC, BTLE, etc., or via a wired or wireless network such as a local area network (Wi-Fi). In some examples, the second user equipment 122 is configured to act as a proxy between user equipment 104 and DA server 106. For example, a DA client 102 of user equipment 104 is configured to transmit information (e.g., a user request received at user equipment 104) to DA server 106 via the second user equipment 122. DA server 106 processes the information and returns relevant data (e.g., data content in response to the user request) to user equipment 104 via the second user equipment 122.

[0049] In some examples, user equipment 104 is configured to send a shortened request for data to a second user equipment 122 to reduce the amount of information transmitted from user equipment 104. The second user equipment 122 is configured to determine supplementary information to be added to the shortened request to generate a complete request to be transmitted to DA server 106. This system architecture can advantageously allow user equipment 104 (e.g., a watch or similar compact electronic device) with limited communication capabilities and / or limited battery power (e.g., a second user equipment 122 with strong communication capabilities and / or battery power, such as a mobile phone, laptop computer, tablet computer, etc.) acting as a proxy to DA server 106 to access the services provided by DA server 106. Although Figure 1 Only two user devices, 104 and 122, are shown in this document, but it should be understood that in some examples, system 100 may include any number and type of user devices configured in this agent configuration to communicate with DA server system 106.

[0050] Although Figure 1 The digital assistant shown includes both a client-side component (e.g., DA client 102) and a server-side component (e.g., DA server 106), but in some examples, the digital assistant's functionality is implemented as a standalone application installed on the user's device. Furthermore, the functional division between the client and server components of the digital assistant can vary in different implementations. For example, in some examples, the DA client is a thin client that only provides user-facing input and output processing functions, delegating all other functions of the digital assistant to the backend server.

[0051] 2. Electronic equipment

[0052] Now let’s turn our attention to the implementation of electronic devices for the client-side portion of a digital assistant. Figure 2AThis is a block diagram illustrating a portable multi-functional device 200 with a touch-sensitive display system 212 according to some embodiments. The touch-sensitive display 212 is sometimes referred to as a “touchscreen” for convenience, and is sometimes referred to as or called a “touch-sensitive display system.” Device 200 includes a memory 202 (which optionally includes one or more computer-readable storage media), a memory controller 222, one or more processing units (CPUs) 220, a peripheral interface 218, RF circuitry 208, audio circuitry 210, a speaker 211, a microphone 213, an input / output (I / O) subsystem 206, other input control devices 216, and an external port 224. Device 200 optionally includes one or more optical sensors 264. Device 200 optionally includes one or more contact strength sensors 265 for detecting the intensity of contact on the device 200 (e.g., a touch-sensitive surface of the device 200 such as the touch-sensitive display system 212). Device 200 optionally includes one or more haptic output generators 267 for generating haptic outputs on device 200 (e.g., generating haptic outputs on a touch-sensitive surface such as the touch-sensitive display system 212 of device 200 or the touchpad 455 of device 400). These components may optionally communicate via one or more communication buses or signal lines 203.

[0053] As used in this specification and claims, the term "intensity" of contact on a tactile surface refers to the force or pressure (force per unit area) of a contact (e.g., finger contact) on a tactile surface, or to a substitute (alternative) for the force or pressure of a contact on a tactile surface. The intensity of contact has a range of values ​​that includes at least four different values ​​and more typically hundreds of different values ​​(e.g., at least 256). The intensity of contact is optionally determined (or measured) using various methods and various sensors or combinations of sensors. For example, one or more force sensors below or adjacent to the tactile surface are optionally used to measure the force at different points on the tactile surface. In some embodiments, force measurements from multiple force sensors are combined (e.g., weighted average) to determine the estimated contact force. Similarly, the pressure-sensitive tip of a stylus is optionally used to determine the pressure of the stylus on the tactile surface. Alternatively, the size and / or variation of the contact area detected on the touch-sensitive surface, the capacitance and / or variation of the touch-sensitive surface near the contact, and / or the resistance and / or variation of the touch-sensitive surface near the contact may optionally be used as substitutes for the force or pressure of the contact on the touch-sensitive surface. In some embodiments, the substitute measurement of the contact force or pressure is used directly to determine whether an intensity threshold (e.g., the intensity threshold is described in units corresponding to the substitute measurement) has been exceeded. In some embodiments, the substitute measurement of the contact force or pressure is converted into an estimated force or pressure, and the estimated force or pressure is used to determine whether an intensity threshold (e.g., the intensity threshold is a pressure threshold measured in units of pressure) has been exceeded. Using the intensity of the contact as an attribute of user input allows the user to access additional device functions that would otherwise be inaccessible to the user on smaller devices with limited physical space, such smaller devices being used (e.g., on a touch-sensitive display) to display power indications and / or receive user input (e.g., via a touch-sensitive display, touch-sensitive surface, or physical / mechanical controls, such as knobs or buttons).

[0054] As used in this specification and claims, the term "haptic output" refers to a physical displacement of the device relative to a previous position of the device, a physical displacement of a component of the device (e.g., a touch-sensitive surface) relative to another component of the device (e.g., the housing), or a displacement of a component relative to the center of mass of the device, which is detected by the user using the user's tactile sense. For example, when the device or a component of the device comes into contact with a touch-sensitive surface (e.g., a finger, palm, or other part of the user's hand), the haptic output generated by the physical displacement will be interpreted by the user as a tactile sensation corresponding to a perceived change in the physical characteristics of the device or a component of the device. For example, movement of a touch-sensitive surface (e.g., a touch-sensitive display or touchpad) may optionally be interpreted by the user as a "press-click" or "release-click" on a physically actuated button. In some cases, the user will feel a tactile sensation, such as a "press-click" or "release-click," even when a physically actuated button associated with a touch-sensitive surface that has been physically pressed (e.g., displaced) by the user's movement does not move. For example, even when the smoothness of the tactile surface remains unchanged, the movement of the tactile surface can optionally be interpreted or sensed by the user as the "roughness" of the tactile surface. While such interpretations of touch by users will be limited by the individualized sensory perceptions of the user, many sensory perceptions of touch are common to most users. Therefore, when a tactile output is described as corresponding to a specific sensory perception of a user (e.g., "press click", "release click", "roughness"), unless otherwise stated, the generated tactile output corresponds to a physical displacement of the device or its components that will generate the sensory perception of a typical (or ordinary) user.

[0055] It should be understood that device 200 is merely an example of a portable multifunctional device, and device 200 may optionally have more or fewer components than shown, may optionally combine two or more components, or may optionally have different configurations or arrangements of these components. Figure 2A The various components shown are implemented in hardware, software, or a combination of both, including one or more signal processing and / or application-specific integrated circuits.

[0056] Memory 202 includes one or more computer-readable storage media. These computer-readable storage media are, for example, tangible and non-transitory. Memory 202 includes high-speed random access memory and also includes non-volatile memory, such as one or more disk storage devices, flash memory devices, or other non-volatile solid-state memory devices. Memory controller 222 controls other components of device 200 to access memory 202.

[0057] In some examples, the non-transitory computer-readable storage medium of memory 202 is used to store instructions (e.g., aspects of the processes described below) for use by or in conjunction with an instruction execution system, apparatus, or device, such as a computer-based system, a processor-integrated system, or other system from which instructions can be fetched and executed. In other examples, instructions (e.g., aspects of the processes described below) are stored on a non-transitory computer-readable storage medium (not shown) of server system 108, or partitioned between the non-transitory computer-readable storage medium of memory 202 and the non-transitory computer-readable storage medium of server system 108.

[0058] Peripheral interface 218 is used to couple the input and output peripherals of the device to CPU 220 and memory 202. The one or more processors 220 run or execute various software programs and / or instruction sets stored in memory 202 to perform various functions of device 200 and process data. In some embodiments, peripheral interface 218, CPU 220, and memory controller 222 are implemented on a single chip, such as chip 204. In some other embodiments, they are implemented on separate chips.

[0059] RF (Radio Frequency) circuit 208 receives and transmits RF signals, also known as electromagnetic signals. RF circuit 208 converts electrical signals into electromagnetic signals and vice versa, and communicates with communication networks and other communication devices via these electromagnetic signals. RF circuit 208 optionally includes well-known circuitry for performing these functions, including but not limited to antenna systems, RF transceivers, one or more amplifiers, tuners, one or more oscillators, digital signal processors, codec chipsets, Subscriber Identity Module (SIM) cards, memory, etc. RF circuit 208 optionally communicates wirelessly with networks and other devices, such as the Internet (also known as the World Wide Web (WWW)), intranets, and / or wireless networks (such as cellular phone networks, wireless local area networks (LANs), and / or metropolitan area networks (MANs)). RF circuit 208 optionally includes well-known circuitry for purposes such as detecting near-field communication (NFC) fields via near-field communication radio components. Wireless communication may optionally employ any of a variety of communication standards, protocols, and technologies, including but not limited to Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), High-Speed ​​Downlink Packet Access (HSDPA), High-Speed ​​Uplink Packet Access (HSUPA), Evolution, Pure Data (EV-DO), HSPA, HSPA+, Dual-Cell HSPA (DC-HSPDA), Long Term Evolution (LTE), Near Field Communication (NFC), Wideband Code Division Multiple Access (W-CDMA), Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Bluetooth, Bluetooth Low Energy (BTLE), and Wi-Fi (e.g., IEEE 802.11a, IEEE 802.11b, IEEE 802.11g, IEEE...). 802.11n and / or IEEE 802.11ac), Voice over Internet Protocol (VoIP), Wi-MAX, email protocols (e.g., Internet Messaging Access Protocol (IMAP) and / or Post Office Protocol (POP)), instant messaging (e.g., Extensible Messaging and Presence Protocol (XMPP), Session Initiation Protocol for Instant Messaging and Presence with Extended Utility (SIMPLE), Instant Messaging and Presence Service (IMPS)) and / or Short Message Service (SMS), or any other suitable communication protocol, including communication protocols that have not yet been developed as of the date of this document submission.

[0060] Audio circuitry 210, speaker 211, and microphone 213 provide an audio interface between the user and device 200. Audio circuitry 210 receives audio data from peripheral interface 218, converts the audio data into electrical signals, and transmits the electrical signals to speaker 211. Speaker 211 converts the electrical signals into sound waves that are audible to humans. Audio circuitry 210 also receives electrical signals converted from sound waves by microphone 213. Audio circuitry 210 converts the electrical signals into audio data and transmits the audio data to peripheral interface 218 for processing. Audio data is retrieved from and / or transmitted to memory 202 and / or RF circuitry 208 via peripheral interface 218. In some embodiments, audio circuitry 210 also includes a headset jack (e.g., ...). Figure 3 (312 in the text). The headset jack provides an interface between the audio circuitry 210 and a removable audio input / output peripheral device, such as an output-only headphone or a headset with both output (e.g., a mono or binaural headphone) and input (e.g., a microphone).

[0061] I / O subsystem 206 couples input / output peripherals on device 200, such as touchscreen 212 and other input control devices 216, to peripheral interface 218. I / O subsystem 206 optionally includes display controller 256, optical sensor controller 258, intensity sensor controller 259, haptic feedback controller 261, and one or more input controllers 260 for other input or control devices. The one or more input controllers 260 receive electrical signals from / send electrical signals to the other input control devices 216. The other input control devices 216 optionally include physical buttons (e.g., push-buttons, rocker buttons, etc.), dial pads, slide switches, joysticks, click wheels, etc. In some alternative embodiments, input controllers 260 are optionally coupled to (or not coupled to) any of the following: keyboard, infrared port, USB port, and pointing device such as mouse. The one or more buttons (e.g., Figure 3 Optionally, 308) includes a volume up / down button for volume control of speaker 211 and / or microphone 213. The one or more buttons optionally include a push-button (e.g., Figure 3 (306 in the middle).

[0062] A rapid press of the down button disengages the touchscreen 212 from its lock or initiates a process of unlocking the device using gestures on the touchscreen, as described in U.S. Patent Application No. 7,657,849, filed December 23, 2005, entitled "Unlocking a Device by Performing Gestures on an Unlock Image," the entire contents of which are incorporated herein by reference. A longer press of the down button (e.g., 306) powers the device 200 on or off. The user can customize the function of one or more buttons. The touchscreen 212 is used to implement virtual buttons or soft buttons and one or more soft keyboards.

[0063] The touch-sensitive display 212 provides input and output interfaces between the device and the user. The display controller 256 receives electrical signals from and / or sends electrical signals to the touchscreen 212. The touchscreen 212 displays visual output to the user. Visual output includes graphics, text, icons, video, and any combination thereof (collectively, "graphics"). In some embodiments, some or all of the visual output corresponds to user interface objects.

[0064] Touchscreen 212 has a touch-sensitive surface, sensor, or sensor array that accepts input from a user based on tactile and / or haptic contact. Touchscreen 212 and display controller 256 (along with any associated modules and / or instruction set in memory 202) detect contact on touchscreen 212 (and any movement or interruption of that contact) and translate the detected contact into interaction with user interface objects (e.g., one or more soft keys, icons, web pages, or images) displayed on touchscreen 212. In an exemplary embodiment, the contact point between touchscreen 212 and the user corresponds to the user's finger.

[0065] Touchscreen 212 uses LCD (Liquid Crystal Display) technology, LPD (Light Emitting Polymer Display) technology, or LED (Light Emitting Diode) technology, but other display technologies may be used in other embodiments. Touchscreen 212 and display controller 256 use any of a variety of touch sensing technologies currently known or to be developed thereafter, as well as other proximity sensor arrays or other elements for determining one or more points of contact with touchscreen 212 to detect contact and any movement or interruption thereto. These various touch sensing technologies include, but are not limited to, capacitive, resistive, infrared, and surface acoustic wave technologies. In an exemplary embodiment, projected mutual capacitance sensing technology is used, such as that from Apple Inc. (Cupertino, California). and iPod The technology used.

[0066] In some embodiments, the touchscreen 212's touch-sensitive display is similar to the multi-touchpad described in the following U.S. patents: 6,323,846 (Westerman et al.), 6,570,557 (Westerman et al.), and / or 6,677,932 (Westerman) and / or U.S. Patent Publication 2002 / 0015024A1, all of which are incorporated herein by reference in their entirety. However, the touchscreen 212 displays visual output from the device 200, while the touch-sensitive touchpad does not provide visual output.

[0067] In some embodiments, the touchscreen 212 has a touch-sensitive display as described in the following patent applications: (1) U.S. Patent Application No. 11 / 381,313, filed May 2, 2006, entitled “Multipoint Touch Surface Controller”; (2) U.S. Patent Application No. 10 / 840,862, filed May 6, 2004, entitled “Multipoint Touchscreen”; (3) U.S. Patent Application No. 10 / 903,964, filed July 30, 2004, entitled “Gestures For Touch Sensitive Input Devices”; (4) U.S. Patent Application No. 11 / 048,264, filed January 31, 2005, entitled “Gestures For Touch Sensitive Input Devices”; and (5) U.S. Patent Application No. 18, 2005, entitled “Mode-Based Graphical User Interfaces For Touch Sensitive Input”. U.S. Patent Application No. 11 / 038,590, entitled “Virtual Input Device Placement On A Touch Screen User Interface”, filed September 16, 2005; U.S. Patent Application No. 11 / 228,758, entitled “Virtual Input Device Placement On A Touch Screen User Interface”, filed September 16, 2005; U.S. Patent Application No. 11 / 228,700, entitled “Operation Of A Computer With A Touch Screen Interface”, filed September 16, 2005; U.S. Patent Application No. 11 / 228,737, entitled “Activating Virtual Keys Of A Touch-Screen Virtual Keyboard”, filed September 16, 2005; and U.S. Patent Application No. 11 / 367,749, entitled “Multi-Functional Hand-Held Device”, filed March 3, 2006. The full text of all these applications is incorporated herein by reference.

[0068] Touchscreen 212 has a video resolution of over 100 dpi, for example. In some embodiments, the touchscreen has a video resolution of approximately 160 dpi. The user interacts with touchscreen 212 using any suitable object or accessory such as a stylus, finger, etc. In some embodiments, the user interface is designed to operate primarily through finger-based touch and gestures, which may be less precise than stylus-based input due to the larger contact area of ​​a finger on the touchscreen. In some embodiments, the device translates coarse finger-based input into precise pointer / cursor positions or commands to perform the user-desired actions.

[0069] In some embodiments, in addition to the touchscreen, device 200 also includes a touchpad (not shown) for enabling or disabling specific functions. In some embodiments, the touchpad is a touch-sensitive area of ​​the device that, unlike the touchscreen, does not display visual output. The touchpad is a touch-sensitive surface separate from the touchscreen 212, or an extension of the touch-sensitive surface formed by the touchscreen.

[0070] The device 200 also includes a power system 262 for supplying power to various components. The power system 262 includes a power management system, one or more power sources (e.g., batteries, alternating current (AC)), a recharging system, a power fault detection circuit, a power converter or inverter, a power status indicator (e.g., light-emitting diodes (LEDs)), and any other components associated with the generation, management, and distribution of power in the portable device.

[0071] The device 200 also includes one or more optical sensors 264. Figure 2A An optical sensor 264 is shown coupled to an optical sensor controller 258 in the I / O subsystem 206. The optical sensor 264 includes a charge-coupled device (CCD) or complementary metal-oxide-semiconductor (CMOS) phototransistor. The optical sensor 264 receives light projected through one or more lenses from the environment and converts the light into data representing an image. In conjunction with an imaging module 243 (also called a camera module), the optical sensor 264 captures still images or video. In some embodiments, the optical sensor is located at the rear of the device 200, opposite to the touchscreen display 212 at the front of the device, such that the touchscreen display is used as a viewfinder for still image and / or video image acquisition. In some embodiments, the optical sensor is located at the front of the device, such that an image of the user is acquired for use in video conferencing while the user views other video conferencing participants on the touchscreen display. In some embodiments, the position of the optical sensor 264 can be changed by the user (e.g., by rotating the lenses and sensors within the device housing), such that a single optical sensor 264 is used in conjunction with the touchscreen display for both video conferencing and still image and / or video image acquisition.

[0072] The device 200 may optionally also include one or more contact strength sensors 265. Figure 2A A contact strength sensor 265 is shown coupled to a strength sensor controller 259 in I / O subsystem 206. The contact strength sensor 265 optionally includes one or more piezoresistive strain gauges, capacitive force sensors, electro-force sensors, piezoelectric sensors, optical force sensors, capacitive touch-sensitive surfaces, or other strength sensors (e.g., sensors for measuring the force (or pressure) of contact on a touch-sensitive surface). The contact strength sensor 265 receives contact strength information (e.g., pressure information or a substitute for pressure information) from the environment. In some embodiments, at least one contact strength sensor is arranged juxtaposed with or adjacent to a touch-sensitive surface (e.g., touch-sensitive display system 212). In some embodiments, at least one contact strength sensor is located on the rear of device 200, opposite to the touchscreen display 212 located on the front of device 200.

[0073] The device 200 also includes one or more proximity sensors 266. Figure 2A A proximity sensor 266 coupled to a peripheral device interface 218 is shown. Alternatively, the proximity sensor 266 is coupled to an input controller 260 in an I / O subsystem 206. The proximity sensor 266 performs as described in the following U.S. patent applications: No. 11 / 241,839, entitled "Proximity Detector In Handheld Device"; No. 11 / 240,788, entitled "Proximity Detector In Handheld Device"; No. 11 / 620,702, entitled "Using Ambient Light Sensor To Augment Proximity Sensor Output"; No. 11 / 586,862, entitled "Automated Response To And Sensing Of User Activity In Portable Devices"; and No. 11 / 638,251, entitled "Methods And Systems For Automatic Configuration Of Peripherals", the entire contents of which are incorporated herein by reference. In some implementations, the proximity sensor is turned off and the touchscreen 212 is disabled when the multifunction device is placed near the user's ear (e.g., when the user is making a phone call).

[0074] The device 200 may optionally also include one or more tactile output generators 267. Figure 2AA haptic output generator coupled to a haptic feedback controller 261 in I / O subsystem 206 is shown. The haptic output generator 267 optionally includes one or more electroacoustic devices such as speakers or other audio components; and / or electromechanical devices for converting energy into linear motion such as motors, solenoids, electroactive polymerizers, piezoelectric actuators, electrostatic actuators, or other haptic output generating components (e.g., components for converting electrical signals into haptic outputs on the device). A contact intensity sensor 265 receives haptic feedback generation instructions from a haptic feedback module 233 and generates a haptic output on device 200 that can be felt by a user of device 200. In some embodiments, at least one haptic output generator is juxtaposed or adjacent to a haptic surface (e.g., haptic display system 212) and optionally generates the haptic output by moving the haptic surface vertically (e.g., in / outward from the surface of device 200) or laterally (e.g., backward and forward in the same plane as the surface of device 200). In some implementations, at least one haptic output generator sensor is located on the rear of the device 200, opposite to the touch screen display 212 located on the front of the device 200.

[0075] The device 200 also includes one or more accelerometers 268. Figure 2A An accelerometer 268 is shown coupled to a peripheral device interface 218. Alternatively, the accelerometer 268 is coupled to an input controller 260 in an I / O subsystem 206. The accelerometer 268 performs as described in the following U.S. patent publications: U.S. Patent Publication 20050190059, “Acceleration-based Theft Detection System for Portable Electronic Devices” and U.S. Patent Publication 20060017692, “Methods and Apparatuses For Operating A Portable Device Based On An Accelerometer,” the entire contents of which are incorporated herein by reference. In some embodiments, information is displayed on a touchscreen display in portrait or landscape view based on analysis of data received from one or more accelerometers. Device 200 optionally includes, in addition to the accelerometer 268, a magnetometer (not shown) and a GPS (or GLONASS or other global navigation system) receiver (not shown) for acquiring information about the position and orientation (e.g., portrait or landscape) of device 200.

[0076] In some embodiments, software components stored in memory 202 include an operating system 226, a communication module (or instruction set) 228, a contact / motion module (or instruction set) 230, a graphics module (or instruction set) 232, a text input module (or instruction set) 234, a Global Positioning System (GPS) module (or instruction set) 235, a digital assistant client module 229, and an application program (or instruction set) 236. Furthermore, memory 202 stores data and models, such as user data and models 231. Additionally, in some embodiments, memory 202 ( Figure 2A ) or 470 ( Figure 4 Storage device / global internal state 257, such as Figure 2A and Figure 4 As shown in the figure. Device / global internal state 257 includes one or more of the following: active application state, which indicates which applications (if any) are currently active; display state, which indicates what applications, views or other information occupy various areas of the touch screen display 212; sensor state, including information obtained from the device's various sensors and input control devices 216; and position information about the device's position and / or orientation.

[0077] Operating system 226 (e.g., Darwin, RTXC, LINUX, UNIX, OS X, iOS, WINDOWS, or embedded operating systems such as VxWorks) includes various software components and / or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and facilitating communication between various hardware and software components.

[0078] The communication module 228 facilitates communication with other devices via one or more external ports 224 and includes various software components for processing data received by the RF circuitry 208 and / or the external ports 224. The external ports 224 (e.g., Universal Serial Bus (USB), FireWire, etc.) are adapted to be directly coupled to other devices or indirectly coupled via a network (e.g., the Internet, wireless LAN, etc.). In some embodiments, the external port is connected to… (Trademark of Apple Inc.) The same or similar and / or compatible multi-pin (e.g., 30-pin) connectors used in Apple Inc. devices.

[0079] The contact / motion module 230 optionally detects contact with the touchscreen 212 (in conjunction with the display controller 256) and other touch-sensitive devices (e.g., touchpads or physical click-based rotary dials). The contact / motion module 230 includes various software components for performing various operations related to contact detection, such as determining whether contact has occurred (e.g., detecting a finger press event), determining the intensity of contact (e.g., the force or pressure of the contact, or an alternative to force or pressure), determining whether there is movement of the contact and tracking movement on the touch-sensitive surface (e.g., detecting one or more finger drag events), and determining whether the contact has stopped (e.g., detecting a finger lift event or contact disconnection). The contact / motion module 230 receives contact data from the touch-sensitive surface. Determining the movement of the contact point optionally includes determining the rate (magnitude), velocity (magnitude and direction), and / or acceleration (change in magnitude and / or direction) of the contact point, the movement of which is represented by a series of contact data. These operations are optionally applied to single-point contact (e.g., single-finger contact) or multi-point simultaneous contact (e.g., "multi-touch" / multiple-finger contact). In some implementations, the contact / motion module 230 and the display controller 256 detect contact on the touchpad.

[0080] In some implementations, the contact / motion module 230 uses a set of one or more intensity thresholds to determine whether an operation has been performed by a user (e.g., determining whether the user has “clicked” an icon). In some implementations, at least a subset of the intensity thresholds is determined based on software parameters (e.g., the intensity thresholds are not determined by the enable threshold of a specific physical actuator and can be adjusted without changing the physical hardware of device 200). For example, the mouse “click” threshold for a touchpad or touchscreen can be set to any threshold in a wide range of predefined thresholds without changing the touchpad or touchscreen display hardware. Additionally, in some implementations, the user of the device is provided with software settings for adjusting one or more intensity thresholds in a set (e.g., by adjusting the individual intensity thresholds and / or by adjusting multiple intensity thresholds at once using system-level clicks on the “intensity” parameter).

[0081] The touch / motion module 230 optionally detects the user's gesture input. Different gestures on a touch-sensitive surface have different contact patterns (e.g., different movements, timings, and / or intensities of the detected contact). Therefore, gestures are optionally detected by detecting specific contact patterns. For example, detecting a finger tap gesture includes detecting a finger press event, and then detecting a finger lift-off (lift-away) event at the same (or substantially the same) location as the finger press event (e.g., at the location of an icon). As another example, detecting a finger swipe gesture on a touch-sensitive surface includes detecting a finger press event, then detecting one or more finger drag events, and subsequently detecting a finger lift-off (lift-away) event.

[0082] The graphics module 232 includes various known software components for rendering and displaying graphics on the touchscreen 212 or other display, including components for altering the visual impact of the displayed graphics (e.g., brightness, transparency, saturation, contrast, or other visual characteristics). As used herein, the term "graphics" includes any object that can be displayed to a user, and non-limitingly includes text, web pages, icons (such as user interface objects including soft keys), digital images, videos, animations, etc.

[0083] In some implementations, the graphics module 232 stores data representing the graphics to be used. Each graphic is optionally assigned a corresponding code. The graphics module 232 receives one or more codes from an application or the like to specify the graphic to be displayed, and, if necessary, also receives coordinate data and other graphic attribute data, and then generates screen image data for output to the display controller 256.

[0084] The haptic feedback module 233 includes various software components for generating instructions that are used by the haptic output generator 267 to produce haptic output at one or more locations on the device 200 in response to user interaction with the device 200.

[0085] In some examples, the text input module 234, which is a component of the graphics module 232, provides a soft keyboard for entering text in various applications (e.g., contacts 237, email 240, IM 241, browser 247, and any other application that requires text input).

[0086] GPS module 235 determines the location of the device and provides that information for use in various applications (e.g., to phone 238 for use in location-based dialing; to camera 243 as image / video metadata; and to applications that provide location-based services, such as weather desktop apps, local yellow pages desktop apps, and map / navigation desktop apps).

[0087] The digital assistant client module 229 includes various client-side digital assistant commands to provide client-side functionality for the digital assistant. For example, the digital assistant client module 229 can accept audio input (e.g., voice input), text input, touch input, and / or gesture input through various user interfaces of the portable multifunction device 200 (e.g., microphone 213, accelerometer 268, touch-sensitive display system 212, optical sensor 229, other input control devices 216, etc.). The digital assistant client module 229 can also provide audio output (e.g., voice output), visual output, and / or haptic output through various output interfaces of the portable multifunction device 200 (e.g., speaker 211, touch-sensitive display system 212, haptic output generator 267, etc.). For example, output can be provided as voice, sound, alarms, text messages, menus, graphics, video, animation, vibration, and / or combinations of both or more of these. During operation, the digital assistant client module 229 communicates with the DA server 106 using RF circuitry 208.

[0088] User data and models 231 include various data associated with the user (e.g., user-specific vocabulary data, user preference data, user-specified name pronunciations, data from the user's electronic address book, to-do lists, shopping lists, etc.) to provide client-side functionality for the digital assistant. Furthermore, user data and models 231 include various models (e.g., speech recognition models, statistical language models, natural language processing models, knowledge ontology, task flow models, service models, etc.) for processing user input and determining user intent.

[0089] In some examples, the digital assistant client module 229 utilizes various sensors, subsystems, and peripherals of the portable multifunction device 200 to collect additional information from the surrounding environment of the portable multifunction device 200 to establish a context associated with the user, the current user interaction, and / or the current user input. In some examples, the digital assistant client module 229 provides the contextual information, or a subset thereof, along with the user input to the DA server 106 to help infer the user's intent. In some examples, the digital assistant also uses the contextual information to determine how to prepare output and deliver it to the user. This contextual information is referred to as contextual data.

[0090] In some examples, the contextual information accompanying user input includes sensor information such as lighting, ambient noise, ambient temperature, and images or videos of the surrounding environment. In some examples, the contextual information may also include the physical state of the device, such as device orientation, device location, device temperature, power level, speed, acceleration, motion mode, and cellular signal strength. In some examples, information related to the software state of the DA server 106, such as the operation of the portable multifunction device 200, installed programs, past and current network activity, background services, error logs, and resource usage, is provided to the DA server 106 as contextual information associated with the user input.

[0091] In some examples, the digital assistant client module 229 selectively provides information (e.g., user data 231) stored on the portable multifunction device 200 in response to a request from the DA server 106. In some examples, the digital assistant client module 229 also elicits additional input from the user via natural language dialogue or other user interfaces when requested by the DA server 106. The digital assistant client module 229 transmits this additional input to the DA server 106 to assist the DA server 106 in intent inference and / or fulfilling the user intent expressed in the user request.

[0092] The following is for reference. Figures 7A-7C A more detailed description of the digital assistant follows. It should be understood that the digital assistant client module 229 may include any number of sub-modules of the digital assistant module 726 described below.

[0093] Application 236 includes the following modules (or instruction sets) or subsets or supersets thereof:

[0094] • Contacts module 237 (sometimes called address book or contact list);

[0095] • Telephone module 238;

[0096] • Video conferencing module 239;

[0097] • Email client module 240;

[0098] • Instant Messaging (IM) module 241;

[0099] Fitness support module 242;

[0100] • Camera module 243 for still images and / or video images;

[0101] • Image management module 244;

[0102] • Video player module;

[0103] Music player module;

[0104] • Browser module 247;

[0105] • Calendar module 248;

[0106] • Desktop mini-program module 249, which in some examples includes one or more of the following: weather desktop mini-program 249-1, stock desktop mini-program 249-2, calculator desktop mini-program 249-3, alarm clock desktop mini-program 249-4, dictionary desktop mini-program 249-5 and other desktop mini-programs acquired by the user and desktop mini-programs created by the user 249-6.

[0107] • Desktop app creator module 250 for creating user-created desktop apps 249-6;

[0108] • Search module 251;

[0109] • Video and music player module 252, which combines a video player module and a music player module;

[0110] Notepad module 253;

[0111] • Map module 254; and / or

[0112] • Online video module 255.

[0113] Examples of other applications 236 stored in memory 202 include other word processing applications, other image editing applications, drawing applications, rendering applications, Java-enabled applications, encryption, digital rights management, sound recognition, and sound copying.

[0114] In conjunction with touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, and text input module 234, contact module 237 manages the address book or contact list (e.g., in the application internal state 292 of contact module 237 stored in memory 202 or memory 470), including: adding one or more names to the address book; deleting names from the address book; associating phone numbers, email addresses, physical addresses, or other information with names; associating images with names; categorizing and classifying names; providing phone numbers or email addresses to initiate and / or facilitate communication via telephone 238, video conferencing module 239, email 240, or IM 241; and so on.

[0115] Combining RF circuitry 208, audio circuitry 210, speaker 211, microphone 213, touchscreen 212, display controller 256, contact / motion module 230, graphics module 232, and text input module 234, telephone module 238 is used to input character sequences corresponding to telephone numbers, access one or more telephone numbers in contact module 237, modify already entered telephone numbers, dial corresponding telephone numbers, initiate conversations, and disconnect or hang up when a conversation is completed. As described above, wireless communication uses any of a variety of communication standards, protocols, and technologies.

[0116] Combining RF circuitry 208, audio circuitry 210, speaker 211, microphone 213, touchscreen 212, display controller 256, optical sensor 264, optical sensor controller 258, contact / motion module 230, graphics module 232, text input module 234, contact module 237, and telephone module 238, video conferencing module 239 includes executable instructions to initiate, conduct, and terminate video conferences between the user and one or more other participants based on user instructions.

[0117] Incorporating RF circuitry 208, touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, and text input module 234, email client module 240 includes executable instructions for creating, sending, receiving, and managing emails in response to user commands. Combined with image management module 244, email client module 240 makes it very easy to create and send emails containing still images or video images captured by camera module 243.

[0118] In conjunction with RF circuitry 208, touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, and text input module 234, instant messaging module 241 includes executable instructions for: inputting a character sequence corresponding to an instant message, modifying previously input characters, transmitting a corresponding instant message (e.g., using Short Message Service (SMS) or Multimedia Messaging Service (MMS) protocols for telephone-based instant messaging or using XMPP, SIMPLE, or IMPS for internet-based instant messaging), receiving an instant message, and viewing received instant messages. In some embodiments, the transmitted and / or received instant messages include graphics, photographs, audio files, video files, and / or other attachments such as those supported in MMS and / or Enhanced Messaging Services (EMS). As used herein, "instant message" refers to both telephone-based messages (e.g., messages sent using SMS or MMS) and internet-based messages (e.g., messages sent using XMPP, SIMPLE, or IMPS).

[0119] Incorporating RF circuitry 208, touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, text input module 234, GPS module 235, map module 254, and music player module, fitness support module 242 includes executable instructions for: creating fitness activities (e.g., with time, distance, and / or calorie burning goals); communicating with fitness sensors (exercise equipment); receiving fitness sensor data; calibrating sensors used to monitor fitness; selecting and playing music for fitness; and displaying, storing, and transmitting fitness data.

[0120] In conjunction with the touchscreen 212, display controller 256, optical sensor 264, optical sensor controller 258, contact / motion module 230, graphics module 232, and image management module 244, the camera module 243 includes executable instructions for: capturing still images or videos (including video streams) and storing them in memory 202, modifying the characteristics of still images or videos, or deleting still images or videos from memory 202.

[0121] Incorporating touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, text input module 234, and camera module 243, image management module 244 includes executable instructions to arrange, modify (e.g., edit), or otherwise manipulate, label, delete, present (e.g., in a digital slideshow or album), and store still and / or video images.

[0122] Combining RF circuitry 208, touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, and text input module 234, browser module 247 includes executable instructions for browsing the Internet according to user instructions, including searching, linking to, receiving, and displaying web pages or portions thereof, as well as attachments and other files linked to web pages.

[0123] Combining RF circuitry 208, touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, text input module 234, email client module 240, and browser module 247, calendar module 248 includes executable instructions to create, display, modify, and store calendars and associated data (e.g., calendar entries, to-dos, etc.) according to user instructions.

[0124] In conjunction with RF circuitry 208, touchscreen 212, display controller 256, contact / motion module 230, graphics module 232, text input module 234, and browser module 247, the desktop applet module 249 is a micro-application that can be downloaded and used by a user (e.g., weather desktop applet 249-1, stock market desktop applet 249-2, calculator desktop applet 249-3, alarm clock desktop applet 249-4, and dictionary desktop applet 249-5) or a user-created micro-application (e.g., user-created desktop applet 249-6). In some embodiments, the desktop applet includes HTML (Hypertext Markup Language) files, CSS (Cascading Style Sheets) files, and JavaScript files. In some embodiments, the desktop applet includes XML (Extensible Markup Language) files and JavaScript files (e.g., Yahoo! desktop applet).

[0125] Combining RF circuit 208, touch screen 212, display controller 256, contact / motion module 230, graphics module 232, text input module 234, and browser module 247, the desktop applet creator module 250 is used by the user to create desktop applets (e.g., to turn a user-specified part of a webpage into a desktop applet).

[0126] In conjunction with the touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, and text input module 234, the search module 251 includes executable instructions to search the memory 202 for text, music, sound, images, videos, and / or other files that match one or more search criteria (e.g., one or more user-specified search terms) according to user instructions.

[0127] Combining touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, audio circuitry 210, speaker 211, RF circuitry 208, and browser module 247, the video and music player module 252 includes executable instructions allowing users to download and play back recorded music and other sound files stored in one or more file formats, such as MP3 or AAC files, as well as executable instructions for displaying, presenting, or otherwise playing back video (e.g., on touchscreen 212 or on an external display connected via external port 224). In some embodiments, device 200 optionally includes the functionality of an MP3 player such as an iPod (a trademark of Apple Inc.).

[0128] Combining the touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, and text input module 234, the notepad module 253 includes executable instructions for creating and managing notes, to-do items, etc., according to user instructions.

[0129] Combining RF circuit 208, touch screen 212, display controller 256, contact / motion module 230, graphics module 232, text input module 234, GPS module 235, and browser module 247, map module 254 is used to receive, display, modify, and store maps and data associated with the maps (e.g., driving directions, data related to shops and other points of interest at or near a specific location, and other location-based data) according to user instructions.

[0130] Incorporating touchscreen 212, display controller 256, touch / motion module 230, graphics module 232, audio circuitry 210, speaker 211, RF circuitry 208, text input module 234, email client module 240, and browser module 247, the online video module 255 includes instructions allowing users to access, browse, receive (e.g., via streaming and / or downloading), play back (e.g., on the touchscreen or on a connected external display via external port 224), send emails with links to specific online videos, and otherwise manage online videos in one or more file formats (such as H.264). In some embodiments, instant messaging module 241 is used instead of email client module 240 to send links to specific online videos. Further descriptions of the online video application can be found in U.S. Provisional Patent Application No. 60 / 936,562, filed June 20, 2007, entitled “Portable Multifunction Device, Method, and Graphical User Interface for Playing Online Videos,” and U.S. Patent Application No. 11 / 968,067, filed December 31, 2007, entitled “Portable Multifunction Device, Method, and Graphical User Interface for Playing Online Videos,” the contents of which are incorporated herein by reference in their entirety.

[0131] Each of the modules and applications described above corresponds to an executable set of instructions for performing one or more of the functions described above and the methods described in this patent application (e.g., computer-implemented methods and other information processing methods as described herein). These modules (e.g., instruction sets) need not be implemented as standalone software programs, processes, or modules, and therefore various subsets of these modules can be combined or otherwise rearranged in various embodiments. For example, a video player module can be combined with a music player module into a single module (e.g., Figure 2A(e.g., video and music player module 252). In some embodiments, memory 202 stores a subset of the aforementioned modules and data structures. Additionally, memory 202 stores other modules and data structures not described above.

[0132] In some implementations, device 200 is a device on which the operation of a predefined set of functions is performed solely via a touchscreen and / or touchpad. By using a touchscreen and / or touchpad as the primary input control device for the operation of device 200, the number of physical input control devices (such as push-buttons, dials, etc.) on device 200 is reduced.

[0133] A predefined set of functions, uniquely performed via a touchscreen and / or touchpad, optionally includes navigation between user interfaces. In some implementations, the touchpad, when touched by a user, navigates device 200 from any user interface displayed on device 200 to the main menu, home menu, or root menu. In such implementations, a touchpad is used to implement a "menu button." In some other implementations, the menu button is a physical push-button or other physical input control device, rather than a touchpad.

[0134] Figure 2B This is a block diagram illustrating exemplary components for event processing according to some embodiments. In some embodiments, memory 202 ( Figure 2A ) or memory 470 ( Figure 4 This includes an event classifier 270 (e.g., in operating system 226) and a corresponding application 236-1 (e.g., any one of the aforementioned applications 237 to 251, 255, 480 to 490).

[0135] Event classifier 270 receives event information and determines the application 236-1 to which the event information should be delivered and the application view 291 of application 236-1. Event classifier 270 includes event monitor 271 and event dispatcher module 274. In some embodiments, application 236-1 includes application internal state 292, which indicates one or more current application views displayed on touch-sensitive display 212 when the application is active or executing. In some embodiments, device / global internal state 257 is used by event classifier 270 to determine which application(s) is currently active, and application internal state 292 is used by event classifier 270 to determine the application view 291 to which the event information should be delivered.

[0136] In some implementations, the application internal state 292 includes additional information such as one or more of the following: recovery information to be used when the application 236-1 resumes execution, user interface state information indicating that information is being displayed or ready to be displayed by the application 236-1, a state queue for enabling the user to return to the previous state or view of the application 236-1, and a repeat / undo queue for the user's previous actions.

[0137] Event monitor 271 receives event information from peripheral device interface 218. The event information includes information about sub-events (e.g., user touches on touch-sensitive display 212 as part of a multi-touch gesture). Peripheral device interface 218 transmits information it receives from I / O subsystem 206 or sensors such as proximity sensor 266, accelerometer 268, and / or microphone 213 (via audio circuitry 210). The information received by peripheral device interface 218 from I / O subsystem 206 includes information from touch-sensitive display 212 or touch-sensitive surfaces.

[0138] In some implementations, event monitor 271 sends requests to peripheral device interface 218 at predetermined intervals. In response, peripheral device interface 218 transmits event information. In other implementations, peripheral device interface 218 transmits event information only when a significant event occurs (e.g., receiving input above a predetermined noise threshold and / or receiving input for a predetermined duration).

[0139] In some implementations, the event classifier 270 also includes a hit view determination module 272 and / or an activity event recognizer determination module 273.

[0140] When the touch-sensitive display 212 displays more than one view, the hit view determination module 272 provides a software process for determining where a sub-event has occurred within one or more views. A view consists of controls and other elements that the user can see on the display.

[0141] Another aspect of the user interface associated with an application is a set of views, sometimes referred to herein as application views or user interface windows, in which information is displayed and touch-based gestures occur. The application view (of the corresponding application) in which a touch is detected corresponds to a procedural level within the application's procedural hierarchy or view hierarchy. For example, the lowest-level view in which a touch is detected is called the hit view, and the set of events considered as correct input is determined at least in part based on the hit view of the initial touch that initiates the touch-based gesture.

[0142] The hit view determination module 272 receives information related to sub-events of touch-based gestures. When an application has multiple views organized in a hierarchical structure, the hit view determination module 272 identifies the hit view as the lowest-level view in the hierarchical structure from which the sub-events should be processed. In most cases, the hit view is the lowest-level view in which the initiating sub-event (e.g., the first sub-event in a sequence of sub-events forming an event or potential event) occurs. Once the hit view is identified by the hit view determination module 272, the hit view typically receives all sub-events related to the same touch or input source to which it was identified as the hit view.

[0143] The activity event recognizer determination module 273 determines which views(s) within the view hierarchy should receive a specific sub-event sequence. In some embodiments, the activity event recognizer determination module 273 determines that only the hit view should receive the specific sub-event sequence. In other embodiments, the activity event recognizer determination module 273 determines that all views including the physical location of the sub-event are actively participating views, and therefore determines that all actively participating views should receive the specific sub-event sequence. In other embodiments, even if the touch sub-event is entirely confined to the area associated with a particular view, the higher-level view in the hierarchy should still remain an actively participating view.

[0144] Event assigner module 274 assigns event information to event identifiers (e.g., event identifier 280). In embodiments that include active event identifier determination module 273, event assigner module 274 delivers event information to the event identifier determined by active event identifier determination module 273. In some embodiments, event assigner module 274 stores event information in an event queue, which is retrieved by the corresponding event receiver 282.

[0145] In some embodiments, operating system 226 includes event classifier 270. Alternatively, application 236-1 includes event classifier 270. In yet another embodiment, event classifier 270 is a standalone module or part of another module (such as contact / motion module 230) stored in memory 202.

[0146] In some embodiments, application 236-1 includes a plurality of event handlers 290 and one or more application views 291, each of which includes instructions for handling touch events occurring within a corresponding view of the application's user interface. Each application view 291 of application 236-1 includes one or more event recognizers 280. Typically, a corresponding application view 291 includes a plurality of event recognizers 280. In other embodiments, one or more event recognizers among the event recognizers 280 are part of a separate module, such as a user interface toolkit (not shown) or a higher-level object from which application 236-1 inherits methods and other properties. In some embodiments, the corresponding event handler 290 includes one or more of the following: a data updater 276, an object updater 277, a GUI updater 278, and / or event data 279 received from an event classifier 270. The event handler 290 utilizes or invokes the data updater 276, the object updater 277, or the GUI updater 278 to update the application's internal state 292. Alternatively, one or more application views in application view 291 include one or more corresponding event handlers 290. Additionally, in some embodiments, one or more of data updater 276, object updater 277, and GUI updater 278 are included in the corresponding application view 291.

[0147] The corresponding event recognizer 280 receives event information (e.g., event data 279) from the event classifier 270 and identifies events from the event information. The event recognizer 280 includes an event receiver 282 and an event comparator 284. In some embodiments, the event recognizer 280 also includes at least one subset of metadata 283 and event delivery instructions 288 (which includes sub-event delivery instructions).

[0148] Event receiver 282 receives event information from event classifier 270. The event information includes information about sub-events such as touch or touch movement. Depending on the sub-event, the event information also includes additional information, such as the location of the sub-event. When the sub-event involves touch movement, the event information also includes the rate and direction of the sub-event. In some embodiments, the event includes the device rotating from one orientation to another (e.g., from a portrait orientation to a lateral orientation, or vice versa), and the event information includes corresponding information about the device's current orientation (also referred to as device pose).

[0149] Event comparator 284 compares event information with predefined event or sub-event definitions and, based on the comparison, determines the event or sub-event, or determines or updates the state of the event or sub-event. In some embodiments, event comparator 284 includes event definition 286. Event definition 286 contains definitions of events (e.g., predefined sequences of sub-events), such as event 1 (287-1), event 2 (287-2), and other events. In some embodiments, sub-events in event (287) include, for example, touch start, touch end, touch move, touch cancel, and multi-touch. In one example, event 1 (287-1) is defined as a double-click on a displayed object. For example, a double-click includes a first touch (touch start) of a predetermined duration on the displayed object, a first lift-off of a predetermined duration (touch end), a second touch (touch start) of a predetermined duration on the displayed object, and a second lift-off of a predetermined duration (touch end). In another example, event 2 (287-2) is defined as a drag on a displayed object. For example, dragging includes a touch (or contact) on the displayed object for a predetermined duration, movement of the touch on the touch-sensitive display 212, and lifting off the touch (end of touch). In some embodiments, the event also includes information for use by one or more associated event handlers 290.

[0150] In some implementations, event definition 287 includes event definitions for corresponding user interface objects. In some implementations, event comparator 284 performs a hit test to determine which user interface object is associated with the sub-event. For example, in an application view displaying three user interface objects on touch-sensitive display 212, when a touch is detected on touch-sensitive display 212, event comparator 284 performs a hit test to determine which of the three user interface objects is associated with the touch (sub-event). If each displayed object is associated with a corresponding event handler 290, the event comparator uses the result of the hit test to determine which event handler 290 should be enabled. For example, event comparator 284 selects the event handler associated with the sub-event and the object that triggered the hit test.

[0151] In some implementations, the definition of the corresponding event (287) also includes a delay action that delays the delivery of event information until it has been determined whether the sub-event sequence actually corresponds to or does not correspond to the event type of the event recognizer.

[0152] When the corresponding event recognizer 280 determines that the sub-event sequence does not match any event in event definition 286, the corresponding event recognizer 280 enters an event impossible, event failed, or event ended state, after which subsequent sub-events based on touch gestures are ignored. In this case, other event recognizers (if any) that remain active in the hit view continue to track and process the ongoing sub-events based on touch gestures.

[0153] In some embodiments, the corresponding event recognizer 280 includes metadata 283 having configurable attributes, flags, and / or lists instructing how the event delivery system should perform sub-event delivery to actively participating event recognizers. In some embodiments, the metadata 283 includes configurable attributes, flags, and / or lists instructing how or how likely event recognizers can interact with each other. In some embodiments, the metadata 283 includes configurable attributes, flags, and / or lists instructing whether sub-events are delivered to different levels in a view or programmatic hierarchy.

[0154] In some implementations, when one or more specific sub-events of an event are identified, the corresponding event recognizer 280 enables the event handler 290 associated with the event. In some implementations, the corresponding event recognizer 280 delivers event information associated with the event to the event handler 290. Enabling the event handler 290 is different from sending (and delaying) the sub-events to the corresponding hit view. In some implementations, the event recognizer 280 throws a tag associated with the identified event, and the event handler 290 associated with that tag retrieves the tag and executes a predefined procedure.

[0155] In some implementations, event delivery instruction 288 includes a sub-event delivery instruction that delivers event information about a sub-event without enabling an event handler. Instead, the sub-event delivery instruction delivers the event information to an event handler associated with the sub-event sequence or to a view with active participation. The event handler associated with the sub-event sequence or the view with active participation receives the event information and performs a predetermined procedure.

[0156] In some implementations, data updater 276 creates and updates data used in application 236-1. For example, data updater 276 updates phone numbers used in contact module 237 or video files used in storage video player module. In some implementations, object updater 277 creates and updates objects used in application 236-1. For example, object updater 277 creates new user interface objects or updates the location of user interface objects. GUI updater 278 updates the GUI. For example, GUI updater 278 prepares display information and sends the display information to graphics module 232 for display on touch-sensitive display.

[0157] In some implementations, event handler 290 includes, or has access to, a data updater 276, an object updater 277, and a GUI updater 278. In some implementations, data updater 276, object updater 277, and GUI updater 278 are included in a single module of the corresponding application 236-1 or application view 291. In other implementations, they are included in two or more software modules.

[0158] It should be understood that the above discussion regarding event handling for user touch on a touch-sensitive display also applies to other forms of user input used to operate the multifunction device 200 using an input device, and not all user input is initiated on the touchscreen. Examples include mouse movements and mouse button presses optionally cooperating with single or multiple keyboard presses or holds; touch movements on the touchpad, such as taps, drags, scrolling, etc.; stylus input; device movement; verbal commands; detected eye movements; biometric input; and / or any combination thereof optionally used as input corresponding to sub-events of events defined to be identified.

[0159] Figure 3A portable multifunction device 200 with a touchscreen 212 is shown according to some embodiments. The touchscreen optionally displays one or more graphics within a user interface (UI) 300. In this embodiment and other embodiments described below, a user can select one or more graphics by gesturing over the graphics, for example, using one or more fingers 302 (not drawn to scale in the figure) or one or more styluses 303 (not drawn to scale in the figure). In some embodiments, selection of one or more graphics occurs when the user breaks contact with one or more graphics. In some embodiments, gestures optionally include one or more taps, one or more swipes (from left to right, from right to left, up and / or down), and / or scrolling (from right to left, from left to right, up and / or down) of a finger already in contact with the device 200. In some specific embodiments or in some cases, unintentional contact with a graphic does not select the graphic. For example, a swipe gesture over an application icon optionally does not select the corresponding application when the gesture corresponding to selection is a tap.

[0160] Device 200 also includes one or more physical buttons, such as a "home" or menu button 304. As previously described, menu button 304 is used to navigate to any application 236 of a set of applications running on device 200. Alternatively, in some embodiments, the menu button is implemented as a soft key, which is displayed in a GUI on touchscreen 212.

[0161] In some embodiments, device 200 includes a touchscreen 212, a menu button 304, a push-button 306 for powering on / off and locking the device, one or more volume control buttons 308, a SIM card slot 310, a headset jack 312, and a docking / charging external port 224. The push-button 306 is optionally used to power on / off the device by pressing the button and holding it in the pressed state for a predefined time interval; to lock the device by pressing the button and releasing it before the predefined time interval has elapsed; and / or to unlock the device or initiate an unlocking process. In another embodiment, device 200 also accepts voice input via microphone 213 for enabling or disabling certain functions. Device 200 also optionally includes: one or more contact strength sensors 265 for detecting the intensity of contact on the touchscreen 212; and / or one or more haptic output generators 267 for generating haptic output for the user of device 200.

[0162] Figure 4This is a block diagram of an exemplary multifunctional device with a display and a touch-sensitive surface according to some embodiments. Device 400 need not be portable. In some embodiments, device 400 is a laptop computer, desktop computer, tablet computer, multimedia player device, navigation device, educational device (such as a children's learning toy), gaming system, or control device (e.g., a home controller or industrial controller). Device 400 typically includes one or more processing units (CPUs) 410, one or more network or other communication interfaces 460, memory 470, and one or more communication buses 420 for interconnecting these components. The communication bus 420 optionally includes circuitry (sometimes referred to as a chipset) that interconnects system components and controls communication between system components. Device 400 includes an input / output (I / O) interface 430 with a display 440, which is typically a touchscreen display. The I / O interface 430 also optionally includes a keyboard and / or mouse (or other pointing device) 450 and a touchpad 455, and a haptic output generator 457 for generating haptic output on device 400 (e.g., similar to the reference above). Figure 2A The one or more tactile output generators 267 and sensors 459 (e.g., optical sensors, accelerometers, proximity sensors, touch sensors, and / or similar to those mentioned above) are described. Figure 2A The contact strength sensor of the one or more contact strength sensors 265. Memory 470 includes: high-speed random access memory, such as DRAM, SRAM, DDR RAM, or other random access solid-state memory devices; and optionally includes non-volatile memory, such as one or more disk storage devices, optical disk storage devices, flash memory devices, or other non-volatile solid-state storage devices. Memory 470 optionally includes one or more storage devices located remotely from CPU 410. In some embodiments, memory 470 stores data with portable multifunction device 200 (…). Figure 2A The memory 470 stores programs, modules, and data structures similar to those in the memory 202 of the portable multifunction device 200, or subsets thereof. Additionally, the memory 470 optionally stores additional programs, modules, and data structures not present in the memory 202 of the portable multifunction device 200. For example, the memory 470 of the device 400 optionally stores a drawing module 480, a rendering module 482, a word processing module 484, a website creation module 486, a disk editing module 488, and / or a spreadsheet module 490, while the portable multifunction device 200 ( Figure 2A The memory 202 optionally does not store these modules.

[0163] Figure 4Each of the aforementioned elements is stored in one or more of the previously mentioned memory devices in some examples. Each of the aforementioned modules corresponds to an instruction set for performing the functions described above. The aforementioned modules or programs (e.g., instruction sets) need not be implemented as standalone software programs, processes, or modules; therefore, various subsets of these modules are combined or otherwise rearranged in various embodiments. In some embodiments, memory 470 stores a subset of the aforementioned modules and data structures. Furthermore, memory 470 stores additional modules and data structures not described above.

[0164] Now let’s turn our attention to implementations of user interfaces that can be implemented, for example, on a portable multi-functional device 200.

[0165] Figure 5A An exemplary user interface for an application menu on a portable multifunction device 200 according to some embodiments is shown. A similar user interface is implemented on device 400. In some embodiments, user interface 500 includes the following elements or a subset or superset thereof:

[0166] Signal strength indicator 502 for wireless communications (such as cellular signals and Wi-Fi signals);

[0167] Time 504;

[0168] Bluetooth indicator 505;

[0169] • Battery status indicator 506;

[0170] • Tray tray 508, which features icons for commonly used applications, such as:

[0171] ○ The icon 516 of the telephone module 238 is labeled "telephone", and the icon may optionally include an indicator 514 for the number of missed calls or voicemails;

[0172] ○ Email client module 240 icon 518, labeled "Mail", which optionally includes an indicator 510 for the number of unread emails;

[0173] ○ The icon 520 of browser module 247 is labeled "Browser"; and

[0174] The icon 522 of the video and music player module 252 (also known as the iPod (a trademark of Apple Inc.) module 252) is labeled "iPod"; and

[0175] • Icons of other applications, such as:

[0176] Icon 524 of IM module 241 is marked as "Message";

[0177] ○ Icon 526 of calendar module 248 is labeled "Calendar";

[0178] ○ The icon 528 of the image management module 244 is labeled "Photo".

[0179] ○ The icon 530 of camera module 243 is labeled "camera";

[0180] ○ The icon 532 of the online video module 255 is labeled "Online Video";

[0181] ○ The icon 534 of the stock market desktop mini-program 249-2 is labeled "stock market";

[0182] ○ Icon 536 of map module 254 is labeled "map";

[0183] ○The icon 538 of the Weather desktop mini-program 249-1 is marked as "Weather";

[0184] The icon 540 of the alarm clock desktop mini-program 249-4 is labeled as "clock";

[0185] ○ The icon 542 of the fitness support module 242 is labeled "fitness support";

[0186] ○ The icon 544 of the Notepad module 253 is labeled "Notepad"; and

[0187] ○ An icon 546 used to set applications or modules, labeled "Settings", provides access to settings for device 200 and its various applications 236.

[0188] It should be pointed out that, Figure 5A The icon labels shown are merely exemplary. For example, the icon 522 of the video and music player module 252 is optionally labeled "Music" or "Music Player". Other labels are optionally used for various application icons. In some embodiments, the label of a particular application icon includes the name of the application corresponding to that particular application icon. In some embodiments, the label of a particular application icon is different from the name of the application corresponding to that particular application icon.

[0189] Figure 5B A touch-sensitive surface 551 (e.g., separate from the display 550 (e.g., touchscreen display 212)) is shown. Figure 4 Devices (e.g., tablets or touchpads 455) Figure 4An exemplary user interface on device 400. Device 400 may also optionally include: one or more contact intensity sensors (e.g., one or more of sensors 457) for detecting the intensity of contact on the touch-sensitive surface 551; and / or one or more haptic output generators 459 for generating haptic output for the user of device 400.

[0190] While some examples of input on a reference touchscreen display 212 (which combines a touch-sensitive surface and a display) are given in the following examples, in some implementations, the device detects input on a touch-sensitive surface separate from the display, such as... Figure 5B As shown in the diagram. In some embodiments, the touch-sensitive surface (e.g., Figure 5B 551) has a spindle (e.g., on the display (e.g., 550) that is aligned with the main axis on the display (e.g., Figure 5B The spindle corresponding to 553 in the figure (e.g., Figure 5B (552 in the example). According to these embodiments, the device detects the position corresponding to the corresponding position on the display (e.g., in the example). Figure 5B In the middle, 560 corresponds to 568 and 562 corresponds to 570) the contact with the touch-sensitive surface 551 at the location (e.g., Figure 5B (560 and 562 in the example). Thus, on touch-sensitive surfaces (e.g., Figure 5B 551 in the middle) and the display of a multi-functional device (e.g., Figure 5B When 550 is separated from 560, user input detected by the device on the touch-sensitive surface (e.g., touches on 560 and 562 and their movement) is used by the device to manipulate the user interface on the display. It should be understood that similar methods may optionally be used for other user interfaces described herein.

[0191] Additionally, while the examples below are primarily given with reference to finger input (e.g., finger touch, single-finger tap, finger swipe), it should be understood that in some implementations, one or more of these finger inputs may be replaced by input from another input device (e.g., mouse-based input or stylus input). For example, a swipe gesture may optionally be replaced by a mouse click (e.g., instead of a touch), followed by movement of the cursor along the swipe path (e.g., instead of movement of the touch). Similarly, a tap gesture may optionally be replaced by a mouse click while the cursor is over the location of the tap gesture (e.g., instead of detection of touch, followed by cessation of touch detection). Likewise, when multiple user inputs are detected simultaneously, it should be understood that multiple computer mice may optionally be used simultaneously, or mouse and finger touch may optionally be used simultaneously.

[0192] Figure 6AAn exemplary personal electronic device 600 is illustrated. Device 600 includes a body 602. In some embodiments, device 600 includes components relative to devices 200 and 400 (e.g., Figures 2A-4 Some or all of the features described herein. In some embodiments, device 600 has a touch-sensitive display screen 604, hereinafter referred to as touchscreen 604. As an alternative to or complement to touchscreen 604, device 600 has a display and a touch-sensitive surface. Similar to devices 200 and 400, in some embodiments, touchscreen 604 (or touch-sensitive surface) has one or more intensity sensors for detecting the intensity of an applied contact (e.g., a touch). The one or more intensity sensors of touchscreen 604 (or touch-sensitive surface) provide output data representing the intensity of the touch. The user interface of device 600 responds to touches based on the touch intensity, meaning that touches of different intensities may invoke different user interface operations on device 600.

[0193] Techniques for detecting and processing touch intensity can be found, for example, in the relevant applications: International Patent Application No. PCT / US2013 / 040061, filed May 8, 2013, entitled “Device, Method, and Graphical User Interface for Displaying User Interface Objects Corresponding to an Application”, and International Patent Application No. PCT / US2013 / 069483, filed November 11, 2013, entitled “Device, Method, and Graphical User Interface for Transitioning Between Touch Input to Display Output Relationships”, each of which is incorporated herein by reference in its entirety.

[0194] In some embodiments, device 600 has one or more input mechanisms 606 and 608. Input mechanisms 606 and 608 (if included) are physical in form. Examples of physical input mechanisms include push-buttons and rotatable mechanisms. In some embodiments, device 600 has one or more attachment mechanisms. Such attachment mechanisms (if included) allow device 600 to be attached to items such as hats, glasses, earrings, necklaces, shirts, jackets, bracelets, watch straps, bangles, trousers, belts, shoes, wallets, backpacks, etc. These attachment mechanisms allow a user to wear device 600.

[0195] Figure 6B An exemplary personal electronic device 600 is illustrated. In some embodiments, device 600 includes, relative to... Figure 2A , Figure 2B and Figure 4 Some or all of the components described herein. Device 600 has a bus 612 that operatively couples I / O portion 614 to one or more computer processors 616 and memory 618. I / O portion 614 is connected to display 604, which may have touch-sensitive component 622 and optionally also has touch intensity-sensitive component 624. Furthermore, I / O portion 614 is connected to communication unit 630 for receiving application and operating system data using Wi-Fi, Bluetooth, near field communication (NFC), cellular and / or other wireless communication technologies. Device 600 includes input mechanisms 606 and / or 608. For example, input mechanism 606 is a rotatable input device or a pressable input device, and a rotatable input device. In some examples, input mechanism 608 is a button.

[0196] In some examples, the input mechanism 608 is a microphone. The personal electronic device 600 includes, for example, various sensors such as a GPS sensor 632, an accelerometer 634, an orientation sensor 640 (e.g., a compass), a gyroscope 636, a motion sensor 638, and / or combinations thereof, all of which are operatively connected to the I / O section 614.

[0197] The memory 618 of the personal electronic device 600 is a non-transitory computer-readable storage medium for storing computer-executable instructions, which, when executed by one or more computer processors 616, cause the computer processors to perform, for example, the techniques and processes described above. These computer-executable instructions are also stored and / or transferred, for example, within any non-transitory computer-readable storage medium, for use by or in conjunction with an instruction execution system, apparatus, or device, such as a computer-based system, a processor-integrated system, or other system capable of retrieving and executing instructions from and from an instruction execution system, apparatus, or device. The personal electronic device 600 is not limited to... Figure 6BIt can be the components and configurations, or it can include other components or additional components in a variety of configurations.

[0198] As used herein, the term "power indication" refers, for example, in devices 200, 400, and / or 600 (… Figure 2A , Figure 4 and Figures 6A-6B A graphical user interface object displayed on a screen. For example, images (e.g., icons), buttons, and text (e.g., hyperlinks) each constitute a display representation.

[0199] As used herein, the term "focus selector" refers to an input element used to indicate the current portion of a user interface with which a user is interacting. In some specific implementations that include a cursor or other positional marker, the cursor acts as a "focus selector," such that when the cursor is over a particular user interface element (e.g., a button, window, slider, or other user interface element), the cursor is positioned on a touch-sensitive surface (e.g., a...). Figure 4 The touchpad 455 or Figure 5B When an input (e.g., a press input) is detected on the touch-sensitive surface 551 of the display, the specific user interface element is adjusted according to the detected input. This applies to touchscreen displays (e.g., those capable of direct interaction with user interface elements on a touchscreen display) that enable direct interaction with user interface elements on the touchscreen display. Figure 2A The touch-sensitive display system 212 or Figure 5A In some embodiments of the touchscreen 212, a touch detected on the touchscreen acts as a "focus selector" such that when input (e.g., a press input by touch) is detected at the location of a particular user interface element (e.g., a button, window, slider, or other user interface element) on the touchscreen display, that particular user interface element is adjusted according to the detected input. In some embodiments, focus moves from one area of ​​the user interface to another without corresponding movement of the cursor or movement of a touch on the touchscreen display (e.g., moving focus from one button to another using tab keys or arrow keys); in these embodiments, the focus selector moves according to the movement of focus between different areas of the user interface. Regardless of the specific form the focus selector takes, the focus selector is typically a user-controlled user interface element (or a touch on the touchscreen display) that delivers the user-expected interaction with the user interface (e.g., by indicating to the device the element of the user interface that the user expects to interact with). For example, when a press input is detected on a touch-sensitive surface (e.g., a touchpad or touchscreen), the position of the focus selector (e.g., a cursor, touch, or selection box) above the corresponding button will indicate to the user that they expect the corresponding button to be enabled (rather than other user interface elements shown on the device's display).

[0200] As used in the specification and claims, the term "characteristic intensity" of a contact refers to a characteristic of the contact based on one or more intensities of the contact. In some embodiments, the characteristic intensity is based on multiple intensity samples. The characteristic intensity is optionally based on a predefined number of intensity samples or a set of intensity samples collected over a predetermined time period (e.g., 0.05 seconds, 0.1 seconds, 0.2 seconds, 0.5 seconds, 1 second, 2 seconds, 5 seconds, 10 seconds) relative to a predefined event (e.g., after contact is detected, before contact is detected to be lifted, before or after contact begins to move, before contact ends, before or after contact intensity is detected to increase and / or before or after contact intensity decreases). The characteristic intensity of the contact is optionally based on one or more of the following: the maximum value of the contact intensity, the mean value of the contact intensity, the average value of the contact intensity, the value at the top 10% of the contact intensity, the half maximum value of the contact intensity, the 90% maximum value of the contact intensity, etc. In some embodiments, the duration of the contact is used when determining the characteristic intensity (e.g., when the characteristic intensity is the average value of the contact intensity over time). In some implementations, the feature intensity is compared to a set of one or more intensity thresholds to determine whether a user has performed an action. For example, the set of one or more intensity thresholds may include a first intensity threshold and a second intensity threshold. In this example, contact with a feature intensity not exceeding the first threshold results in a first action, contact with a feature intensity exceeding the first intensity threshold but not exceeding the second intensity threshold results in a second action, and contact with a feature intensity exceeding the second threshold results in a third action. In some implementations, a comparison between the feature intensity and one or more thresholds is used to determine whether to perform one or more actions (e.g., whether to perform the corresponding action or abort performing the corresponding action), rather than to determine whether to perform the first or second action.

[0201] In some implementations, a portion of the gesture is identified to determine the characteristic intensity. For example, a touch-sensitive surface receives a series of swipes that transition from a starting position to an ending position, where the intensity of the contact increases. In this example, the characteristic intensity of the contact at the ending position is based only on a portion of the series of swipes, not the entire swipe (e.g., only the portion of the swipe at the ending position). In some implementations, a smoothing algorithm is applied to the intensity of the swipe gesture before determining the characteristic intensity of the contact. For example, the smoothing algorithm optionally includes one or more of the following: unweighted moving average smoothing algorithm, triangular smoothing algorithm, median filter smoothing algorithm, and / or exponential smoothing algorithm. In some cases, these smoothing algorithms eliminate narrow spikes or dips in the intensity of the swipe contact to achieve the purpose of determining the characteristic intensity.

[0202] The strength of a contact on a touch-sensitive surface is characterized relative to one or more strength thresholds, such as a contact detection strength threshold, a light press strength threshold, a deep press strength threshold, and / or one or more other strength thresholds. In some embodiments, the light press strength threshold corresponds to an intensity at which the device performs an operation typically associated with clicking a button on a physical mouse or touchpad. In some embodiments, the deep press strength threshold corresponds to an intensity at which the device performs an operation different from the operation typically associated with clicking a button on a physical mouse or touchpad. In some embodiments, when a contact with a characteristic strength lower than the light press strength threshold (e.g., and higher than the nominal contact detection strength threshold, where contacts lower than the nominal contact detection strength threshold are no longer detected) is detected, the device will move the focus selector based on the movement of the contact on the touch-sensitive surface without performing the operation associated with the light press strength threshold or the deep press strength threshold. Generally, unless otherwise stated, these strength thresholds are consistent across different groups of user interface figures.

[0203] An increase in contact intensity from below a light press intensity threshold to an intensity between the light press intensity threshold and the deep press intensity threshold is sometimes referred to as a "light press" input. An increase in contact intensity from below a deep press intensity threshold to an intensity above the deep press intensity threshold is sometimes referred to as a "deep press" input. An increase in contact intensity from below a contact detection intensity threshold to an intensity between the contact detection intensity threshold and the light press intensity threshold is sometimes referred to as detecting a contact on the touch surface. A decrease in contact intensity from above a contact detection intensity threshold to an intensity below the contact detection intensity threshold is sometimes referred to as detecting a contact being lifted off the touch surface. In some embodiments, the contact detection intensity threshold is zero. In some embodiments, the contact detection intensity threshold is greater than zero.

[0204] In some embodiments described herein, one or more operations are performed in response to detecting a gesture including a corresponding press input or in response to detecting a corresponding press input performed using a corresponding contact (or multiple contacts), wherein the corresponding press input is detected at least in part based on detecting that the intensity of the contact (or multiple contacts) increases to above a press input intensity threshold. In some embodiments, the corresponding operation is performed in response to detecting that the intensity of the corresponding contact increases to above a press input intensity threshold (e.g., a "downward stroke" of the corresponding press input). In some embodiments, the press input includes the intensity of the corresponding contact increasing to above a press input intensity threshold and the intensity of the contact subsequently decreasing to below the press input intensity threshold, and the corresponding operation is performed in response to detecting that the intensity of the corresponding contact subsequently decreases to below the press input threshold (e.g., an "upward stroke" of the corresponding press input).

[0205] In some implementations, the device employs intensity hysteresis to avoid unintended inputs sometimes referred to as "jitter," wherein the device defines or selects a hysteresis intensity threshold that has a predefined relationship with a press input intensity threshold (e.g., the hysteresis intensity threshold is X intensity units lower than the press input intensity threshold, or the hysteresis intensity threshold is 75%, 90%, or some reasonable percentage of the press input intensity threshold). Therefore, in some implementations, a press input includes an increase in the intensity of the corresponding contact above the press input intensity threshold and a subsequent decrease in the intensity of that contact below the hysteresis intensity threshold corresponding to the press input intensity threshold, and a corresponding operation is performed in response to detecting that the intensity of the corresponding contact subsequently decreases below the hysteresis intensity threshold (e.g., an "upstroke" of the corresponding press input). Similarly, in some implementations, a press input is detected only when the device detects that the contact intensity increases from an intensity equal to or below the hysteresis intensity threshold to an intensity equal to or above the press input intensity threshold and optionally the contact intensity subsequently decreases to an intensity equal to or below the hysteresis intensity threshold, and a corresponding operation is performed in response to detecting a press input (e.g., an increase or decrease in contact intensity depending on the environment).

[0206] For ease of explanation, optionally, the description of an operation triggered in response to a press input associated with a press input strength threshold or in response to a gesture including a press input is provided in response to detecting any of the following conditions: the contact strength increases to above the press input strength threshold, the contact strength increases from below a hysteresis strength threshold to above the press input strength threshold, the contact strength decreases to below the press input strength threshold, and / or the contact strength decreases to below the hysteresis strength threshold corresponding to the press input strength threshold. Additionally, in the example where the operation is described as being performed in response to detecting a decrease in contact strength below the press input strength threshold, the operation is optionally performed in response to detecting a decrease in contact strength below a hysteresis strength threshold corresponding to and less than the press input strength threshold.

[0207] 3. Digital Assistant System

[0208] Figure 7A A block diagram of a digital assistant system 700 according to various examples is shown. In some examples, the digital assistant system 700 is implemented on a standalone computer system. In some examples, the digital assistant system 700 is distributed across multiple computers. In some examples, some of the modules and functions of the digital assistant are divided into server and client parts, wherein the client part resides on one or more user devices (e.g., device 104, device 122, device 200, device 400, or device 600) and communicates with the server part (e.g., server system 108) via one or more networks, for example, as... Figure 1 As shown in the image. In some examples, the digital assistant system 700 is... Figure 1 The specific implementation of the server system 108 (and / or DA server 106) shown is illustrated. It should be noted that the digital assistant system 700 is merely an example of a digital assistant system, and the digital assistant system 700 may have more or fewer components than shown, combine two or more components, or have different configurations or layouts of components. Figure 7A The various components shown are implemented in hardware, software instructions for execution by one or more processors, firmware (including one or more signal processing integrated circuits and / or application-specific integrated circuits), or a combination thereof.

[0209] The digital assistant system 700 includes a memory 702, an input / output (I / O) interface 706, a network communication interface 708, and one or more processors 704. These components can communicate with each other via one or more communication buses or signal lines 710.

[0210] In some examples, memory 702 includes non-transitory computer-readable media, such as high-speed random access memory and / or non-volatile computer-readable storage media (e.g., one or more disk storage devices, flash memory devices or other non-volatile solid-state memory devices).

[0211] In some examples, I / O interface 706 couples input / output devices 716 of digital assistant system 700, such as a display, keyboard, touchscreen, and microphone, to user interface module 722. I / O interface 706, in conjunction with user interface module 722, receives user input (e.g., voice input, keyboard input, touch input, etc.) and processes that input accordingly. In some examples, for instance, when the digital assistant is implemented on a standalone user device, digital assistant system 700 includes a user interface module 722. Figure 2A , Figure 4 , Figures 6A to 6B The components and I / O communication interfaces described by devices 200, 400, or 600 are respectively. In some examples, digital assistant system 700 represents the server portion of a digital assistant implementation and can interact with the user through a client-side portion located on a user device (e.g., device 104, device 200, device 400, or device 600).

[0212] In some examples, the network communication interface 708 includes one or more wired communication ports 712 and / or wireless transmission and reception circuitry 714. The one or more wired communication ports receive and transmit communication signals via one or more wired interfaces such as Ethernet, Universal Serial Bus (USB), FireWire, etc. The wireless circuitry 714 receives RF signals and / or optical signals from the communication network and other communication devices, and transmits RF signals and / or optical signals to the communication network and other communication devices. Wireless communication uses any of a variety of communication standards, protocols, and technologies, such as GSM, EDGE, CDMA, TDMA, Bluetooth, Wi-Fi, VoIP, Wi-MAX, or any other suitable communication protocol. The network communication interface 708 enables the digital assistant system 700 to communicate with other devices via networks such as the Internet, intranets, and / or wireless networks such as cellular telephone networks, wireless local area networks (LANs), and / or metropolitan area networks (MANs).

[0213] In some examples, memory 702 or its computer-readable storage medium stores programs, modules, instructions, and data structures, including all or a subset of the following: operating system 718, communication module 720, user interface module 722, one or more application programs 724, and digital assistant module 726. Specifically, memory 702 or its computer-readable storage medium stores instructions for performing the aforementioned processes. One or more processors 704 execute these programs, modules, and instructions, and read data from or write data to data structures.

[0214] Operating systems 718 (e.g., Darwin, RTXC, LINUX, UNIX, iOS, OS X, WINDOWS, or embedded operating systems such as VxWorks) include various software components and / or drivers for controlling and managing general system tasks (e.g., memory management, storage device control, power management, etc.) and facilitating communication between various hardware, firmware, and software components.

[0215] The communication module 720 facilitates communication between the digital assistant system 700 and other devices via a network communication interface 708. For example, the communication module 720 communicates with electronic devices such as those in… Figure 2A , Figure 4 , Figures 6A to 6B The RF circuit 208 of the devices 200, 400, and 600 shown communicates. The communication module 720 also includes various components for processing data received by the wireless circuit 714 and / or the wired communication port 712.

[0216] The user interface module 722 receives commands and / or input from the user (e.g., from a keyboard, touchscreen, pointing device, controller, and / or microphone) via the I / O interface 706 and generates user interface objects on the display. The user interface module 722 also prepares output (e.g., voice, sound, animation, text, icons, vibration, haptic feedback, lighting, etc.) and transmits it to the user via the I / O interface 706 (e.g., through a display, audio channel, speaker, touchpad, etc.).

[0217] Application 724 includes programs and / or modules configured to be executed by one or more processors 704. For example, if the digital assistant system is implemented on a standalone user device, application 724 includes user applications such as games, calendar applications, navigation applications, or email applications. If the digital assistant system 700 is implemented on a server, application 724 includes, for example, resource management applications, diagnostic applications, or scheduling applications.

[0218] The memory 702 also stores the digital assistant module 726 (or the server portion of the digital assistant). In some examples, the digital assistant module 726 includes the following submodules or subsets or supersets: input / output processing module 728, speech-to-text (STT) processing module 730, natural language processing module 732, dialogue flow processing module 734, task flow processing module 736, service processing module 738, and speech synthesis module 740. Each of these modules has access to one or more, or subsets or supersets of, the following systems or data and models of the digital assistant module 726: knowledge ontology 760, vocabulary index 744, user data 748, task flow model 754, service model 756, and ASR system 758.

[0219] In some examples, using the processing modules, data, and models implemented in the digital assistant module 726, the digital assistant may perform at least some of the following: converting voice input into text; recognizing user intent expressed in natural language input received from the user; proactively eliciting and obtaining the information needed to fully infer the user intent (e.g., by deambiguity of words, names, intents, etc.); determining a task flow to satisfy the inferred intent; and executing the task flow to satisfy the inferred intent.

[0220] In some examples, such as Figure 7B As shown, the I / O processing module 728 can... Figure 7A The I / O device 716 in the middle interacts with the user or through Figure 7AThe network communication interface 708 interacts with user equipment (e.g., device 104, device 200, device 400, or device 600) to receive user input (e.g., voice input) and provide a response to the user input (e.g., as voice output). The I / O processing module 728 optionally obtains contextual information associated with the user input from the user equipment along with or shortly after receiving the user input. The contextual information includes user-specific data, vocabulary, and / or preferences related to the user input. In some examples, the contextual information also includes the software and hardware state of the user equipment at the time the user request is received and / or information related to the user's surrounding environment at the time the user request is received. In some examples, the I / O processing module 728 also sends follow-up questions related to the user request to the user and receives answers from the user. When a user request is received by the I / O processing module 728 and the user request includes voice input, the I / O processing module 728 forwards the voice input to the STT processing module 730 (or speech recognizer) for speech-to-text conversion.

[0221] STT processing module 730 includes one or more ASR systems 758. The one or more ASR systems 758 can process speech input received through I / O processing module 728 to produce recognition results. Each ASR system 758 may include a front-end speech preprocessor. The front-end speech preprocessor extracts representative features from the speech input. For example, the front-end speech preprocessor performs a Fourier transform on the speech input to extract spectral features characterizing the speech input as a sequence of representative multidimensional vectors. Additionally, each ASR system 758 includes one or more speech recognition models (e.g., acoustic models and / or language models) and implements one or more speech recognition engines. Examples of speech recognition models include Hidden Markov Models, Gaussian Mixture Models, Deep Neural Network Models, n-gram language models, and other statistical models. Examples of speech recognition engines include engines based on Dynamic Time Warping (VT) and engines based on Weighted Finite State Transformers (WFST). One or more speech recognition models and one or more speech recognition engines are used to process the representative features extracted by the front-end speech preprocessor to produce intermediate recognition results (e.g., phonemes, phoneme strings, and sub-words) and ultimately produce text recognition results (e.g., words, word strings, or symbol sequences). In some examples, the speech input is processed at least in part by a third-party service or on the user's device (e.g., device 104, device 200, device 400, or device 600) to produce the recognition results. Once the STT processing module 730 produces a recognition result containing a text string (e.g., words, or sequences of words or symbols), the recognition result is passed to the natural language processing module 732 for intent inference. In some examples, the STT processing module 730 produces multiple candidate text representations of the speech input. Each candidate text representation is a sequence of words or symbols corresponding to the speech input. In some examples, each candidate text representation is associated with a speech recognition confidence score. Based on the speech recognition confidence score, the STT processing module 730 sorts the candidate text representations and provides the n best (e.g., the n highest-ranked) candidate text representations to the natural language processing module 732 for intent inference, where n is a predetermined integer greater than zero. For example, in one example, only the highest-ranked (n=1) candidate text representation is delivered to the natural language processing module 732 for intent inference. Alternatively, the five highest-ranked (n=5) candidate text representations are passed to the natural language processing module 732 for intent inference.

[0222] Further details regarding speech-to-text processing are described in U.S. Utility Model Patent Application Serial No. 13 / 236,942, entitled "Consolidating Speech Recognition Results," filed on September 20, 2011, the entire disclosure of which is incorporated herein by reference.

[0223] In some examples, the STT processing module 730 includes a vocabulary of recognizable words and / or accesses that vocabulary via the speech-to-letter conversion module 731. Each vocabulary word is associated with one or more candidate pronunciations of a word represented in the speech recognition alphabet. Specifically, the vocabulary of recognizable words includes words associated with multiple candidate pronunciations. For example, the vocabulary includes words associated with... and The candidate pronunciations are associated with the word "tomato". Additionally, vocabulary words are associated with custom candidate pronunciations based on previous speech input from the user. These custom candidate pronunciations are stored in the STT processing module 730 and associated with a specific user via a user profile on the device. In some examples, candidate pronunciations are determined based on the spelling of the word and one or more linguistic and / or phonetic rules. In some examples, candidate pronunciations are generated manually, for example, based on known standard pronunciations.

[0224] In some examples, candidate pronunciations are ranked based on their prevalence. For example, candidate speech... The sorting is higher than This is because the former is a more commonly used pronunciation (e.g., among all users, for users in a specific geographic region, or for any other suitable subset of users). In some examples, candidate pronunciations are ranked based on whether they are custom candidate pronunciations associated with a user. For example, custom candidate pronunciations rank higher than standard candidate pronunciations. This can be used to identify proper nouns with unique pronunciations that deviate from the canonical pronunciation. In some examples, candidate pronunciations are associated with one or more phonological features, such as geographic origin, country, or ethnicity. For example, candidate pronunciations... Associated with the United States, and candidate pronunciation The candidate pronunciations are associated with the United Kingdom. Furthermore, the ranking of candidate pronunciations is based on one or more characteristics of the user (e.g., geographic origin, country, ethnicity, etc.) stored in the user profile on the device. For example, it can be determined from the user profile that the user is associated with the United States. Based on the user's association with the United States, candidate pronunciations... (US-related) Comparable candidate pronunciations (Related to the UK) Ranked higher. In some examples, one of the sorted candidate pronunciations can be selected as the predicted pronunciation (e.g., the most likely pronunciation).

[0225] Upon receiving voice input, the STT processing module 730 is used (e.g., using a sound model) to determine the phonemes corresponding to the voice input, and then attempts (e.g., using a language model) to determine the words that match those phonemes. For example, if the STT processing module 730 first identifies a sequence of phonemes corresponding to a portion of the voice input... It can then determine, based on vocabulary index 744, that the sequence corresponds to the word "tomato".

[0226] In some examples, the STT processing module 730 uses fuzzy matching techniques to determine words in a utterance. Therefore, for example, the STT processing module 730 determines phoneme sequences. This corresponds to the word "tomato," even if the specific phoneme sequence is not a candidate phoneme sequence for that word.

[0227] The digital assistant's natural language processing module 732 ("Natural Language Processor") acquires n best candidate text representations ("word sequences" or "symbol sequences") generated by the STT processing module 730 and attempts to associate each candidate text representation with one or more "executable intents" recognized by the digital assistant. In some embodiments, as described in more detail below, the STT processing module 730 attempts to associate each candidate text representation with one or more "candidate intents" using a false trigger mitigator (FTM). The FTM provides candidate intents to a candidate intent evaluator (CIE), which evaluates whether a candidate intent includes one or more "executable intents." An "executable intent" (or "user intent") represents a task that can be performed by the digital assistant and may have an associated task flow implemented in the task flow model 754. An associated task flow is a series of programmed actions and steps taken by the digital assistant to perform a task. The capabilities of the digital assistant depend on the number and type of task flows that have been implemented and stored in the task flow model 754, or in other words, on the number and type of "executable intents" recognized by the digital assistant. However, the effectiveness of a digital assistant also depends on its ability to infer the correct "one or more actionable intents" from user requests expressed in natural language.

[0228] In some examples, in addition to the sequence of words or symbols obtained from the STT processing module 730, the natural language processing module 732 also receives (e.g., from the I / O processing module 728) contextual information associated with the user request. The natural language processing module 732 optionally uses the contextual information to clarify, supplement, and / or further define the information contained in the candidate text representation received from the STT processing module 730. Contextual information includes, for example, user preferences, the hardware and / or software state of the user's device, sensor information collected before, during, or shortly after the user request, previous interactions (e.g., conversations) between the digital assistant and the user, and so on. As described herein, in some examples, the contextual information is dynamic and varies with the time, location, content, and other factors of the conversation.

[0229] In some examples, natural language processing is based on, for example, a knowledge ontology 760. Knowledge ontology 760 is a hierarchical structure containing many nodes, each node representing an "executable intent" or an "attribute" associated with one or more of the "executable intent" or other "attributes." As mentioned above, an "executable intent" represents a task that a digital assistant can perform; that is, the task is "executable" or can be done. An "attribute" represents a parameter associated with a sub-aspect of an executable intent or another attribute. The connections between executable intent nodes and attribute nodes in knowledge ontology 760 define how the parameters represented by the attribute nodes are subordinate to the task represented by the executable intent nodes.

[0230] In some examples, the knowledge ontology 760 consists of executable intent nodes and attribute nodes. Within the knowledge ontology 760, each executable intent node is directly connected to or connected to one or more attribute nodes via one or more intermediate attribute nodes. Similarly, each attribute node is directly connected to or connected to one or more executable intent nodes via one or more intermediate attribute nodes. For example, as... Figure 7C As shown, knowledge ontology 760 includes a "Restaurant Reservation" node (i.e., an executable intent node). The attribute nodes "Restaurant", "Date / Time" (for reservations) and "Party Attendees" are all directly connected to the executable intent node (i.e., the "Restaurant Reservation" node).

[0231] Furthermore, the attribute nodes "Cuisine," "Price Range," "Phone Number," and "Location" are child nodes of the attribute node "Restaurant," and all are connected to the "Restaurant Reservation" node (i.e., the executable intent node) through the intermediate attribute node "Restaurant." For example, ... Figure 7C As shown, knowledge ontology 760 also includes a "Set Reminder" node (i.e., another executable intent node). The attribute nodes "Date / Time" (for setting reminders) and "Topic" (for reminders) are both connected to the "Set Reminder" node. Since the attribute "Date / Time" is related to both the task of making a restaurant reservation and the task of setting a reminder, the attribute node "Date / Time" is connected to both the "Restaurant Reservation" node and the "Set Reminder" node in knowledge ontology 760.

[0232] An executable intent node, along with the conceptual nodes it connects to, is described as a "domain." In this discussion, each domain is associated with a corresponding executable intent and involves a set of nodes (and the relationships between these nodes) associated with a particular executable intent. For example, Figure 7CThe knowledge ontology 760 shown includes examples of a restaurant reservation domain 762 and a reminder domain 764 within the knowledge ontology 760. The restaurant reservation domain includes an actionable intent node “Restaurant Reservation”, attribute nodes “Restaurant”, “Date / Time”, and “Participant Size”, and sub-attribute nodes “Cuisine”, “Price Range”, “Phone Number”, and “Location”. The reminder domain 764 includes an actionable intent node “Set Reminder” and attribute nodes “Topic” and “Date / Time”. In some examples, the knowledge ontology 760 consists of multiple domains. Each domain shares one or more attribute nodes with one or more other domains. For example, in addition to the restaurant reservation domain 762 and the reminder domain 764, the “Date / Time” attribute node is associated with many different domains (e.g., itinerary domain, travel booking domain, movie ticket domain, etc.).

[0233] although Figure 7C Two exemplary fields within knowledge ontology 760 are shown, but other fields include, for example, "Find a movie," "Initiate a phone call," "Find directions," "Schedule a meeting," "Send a message," and "Provide answers to questions," "Reading lists," "Provide navigation instructions," "Provide instructions for a task," etc. The "Send a message" field is associated with the "Send a message" executable intent node and also includes attribute nodes such as "One or more recipients," "Message type," and "Message body." The attribute node "Recipients" is further defined, for example, by sub-attribute nodes such as "Recipient name" and "Message address."

[0234] In some examples, knowledge ontology 760 includes all domains (and thus executable intents) that a digital assistant can understand and act upon. In some examples, knowledge ontology 760 is modified, such as by adding or removing entire domains or nodes, or by modifying the relationships between nodes within knowledge ontology 760.

[0235] In some examples, nodes associated with multiple related executable intents are clustered under a “superdomain” in knowledge ontology 760. For example, the “Travel” superdomain includes clusters of travel-related attribute nodes and executable intent nodes. Travel-related executable intent nodes include “flight booking,” “hotel booking,” “car rental,” “get route,” “find point of interest,” and so on. Executable intent nodes under the same superdomain (e.g., the “Travel” superdomain) have multiple shared attribute nodes. For example, executable intent nodes for “flight booking,” “hotel booking,” “car rental,” “route planning,” and “find point of interest” share one or more of the attribute nodes “starting location,” “destination,” “departure date / time,” “arrival date / time,” and “party size.”

[0236] In some examples, each node in the knowledge ontology 760 is associated with a set of words and / or phrases related to the attribute or executable intent represented by the node. The corresponding set of words and / or phrases associated with each node is called the "vocabulary" associated with the node. The corresponding set of words and / or phrases associated with each node are stored in the vocabulary index 744 associated with the attribute or executable intent represented by the node. For example, returning... Figure 7B The vocabulary associated with nodes of the "restaurant" attribute includes words such as "food," "drinks," "cuisine," "hunger," "eat," "pizza," "fast food," and "meals." Similarly, the vocabulary associated with nodes of the "initiate a phone call" action includes words and phrases such as "call," "make a phone call," "dial," "talk to," "call this number," and "make a phone call." The vocabulary index 744 optionally includes words and phrases from different languages.

[0237] Natural Language Processing (NLP) module 732 receives candidate text representations (e.g., one or more text strings or one or more sequences of symbols) from STT processing module 730 and, for each candidate representation, determines which nodes the words in the candidate text representation relate to. In some examples, if a word or phrase in a candidate text representation is found to be associated with one or more nodes in knowledge ontology 760 (via vocabulary index 744), the word or phrase "triggers" or "enables" those nodes. Based on the number and / or relative importance of the enabled nodes, NLP module 732 selects one of the executable intents as the task the user intends the digital assistant to perform. In some examples, the domain with the most "triggered" nodes is selected. In some examples, the domain with the highest confidence (e.g., based on the relative importance of its individual triggered nodes) is selected. In some examples, the domain is selected based on a combination of the number and importance of the triggered nodes. In some examples, additional factors, such as whether the digital assistant has previously correctly interpreted similar requests from the user, are also considered in the node selection process.

[0238] User data 748 includes user-specific information such as user-specific vocabulary, user preferences, user address, user's default and second languages, user's contact list, and other short- or long-term information for each user. In some examples, the natural language processing module 732 uses user-specific information to supplement information contained in the user input to further refine the user's intent. For example, in response to a user request "Invite my friends to my birthday party," the natural language processing module 732 can access user data 748 to determine who the "friends" are and when and where the "birthday party" should be held, without requiring the user to explicitly provide such information in their request.

[0239] It should be recognized that, in some examples, the natural language processing module 732 is implemented using one or more machine learning agencies (e.g., neural networks). Specifically, the one or more machine learning agencies are configured to receive candidate text representations and contextual information associated with the candidate text representations. Based on the candidate text representations and the associated contextual information, the one or more machine learning agencies are configured to determine an intent confidence score based on a set of candidate executable intents. The natural language processing module 732 can select one or more candidate executable intents from the set of candidate executable intents based on the determined intent confidence score. In some examples, a knowledge ontology (e.g., knowledge ontology 760) is also utilized to select one or more candidate executable intents from the set of candidate executable intents.

[0240] Further details regarding the symbol string-based search of knowledge ontology are described in U.S. Utility Model Patent Application Serial No. 12 / 341,743, entitled “Method and Apparatus for Searching Using An Active Ontology,” filed on December 22, 2008, the entire disclosure of which is incorporated herein by reference.

[0241] In some examples, once the natural language processing module 732 identifies an executable intent (or domain) based on a user request, it generates a structured query to represent the identified executable intent. In some examples, the structured query includes parameters for one or more nodes within the domain of the executable intent, and at least some of these parameters are populated with specific information and requirements specified in the user request. For example, a user says, “Reserve a table at a sushi restaurant for 7 pm.” In this case, the natural language processing module 732 is able to correctly identify the executable intent as “restaurant reservation” based on the user input. According to the knowledge ontology, the structured query for the “restaurant reservation” domain includes parameters such as {cuisine}, {time}, {date}, {number of people}, etc. In some examples, based on voice input and text derived from the voice input using the STT processing module 730, the natural language processing module 732 generates a partially structured query for the restaurant reservation domain, where the partially structured query includes the parameters {cuisine = “sushi”} and {time = “7 pm”}. However, in this example, the user's utterance contains insufficient information to complete a structured query associated with the domain. Therefore, based on the currently available information, no other necessary parameters, such as {number of people in the same group} and {date}, are specified in the structured query. In some examples, the natural language processing module 732 uses the received context information to populate some parameters of the structured query. For example, in some examples, if requesting "nearby" sushi restaurants, the natural language processing module 732 uses GPS coordinates from the user's device to populate the {location} parameter in the structured query.

[0242] In some examples, the Natural Language Processing (NLP) module 732 identifies multiple candidate executable intents for each candidate text representation received from the STT processing module 730. Additionally, in some examples, a corresponding structured query (partially or entirely) is generated for each identified candidate executable intent. The NLP module 732 determines an intent confidence score for each candidate executable intent and ranks the candidate executable intents based on the intent confidence scores. In some examples, the NLP module 732 transmits one or more of the generated structured queries (including any completed parameters) to the task flow processing module 736 (“task flow processor”). In some examples, one or more structured queries for the m best (e.g., the m highest-ranked) candidate executable intents are provided to the task flow processing module 736, where m is a predetermined integer greater than zero. In some examples, one or more structured queries for the m best candidate executable intents, along with their corresponding candidate text representations, are provided to the task flow processing module 736.

[0243] Further details regarding the inference of user intent based on multiple candidate executable intents determined from multiple candidate text representations of speech input are described in U.S. Utility Model Patent Application No. 14 / 298,725, filed June 6, 2014, entitled “System and Method for Inferring User Intent From Speech Inputs,” the entire disclosure of which is incorporated herein by reference.

[0244] Task flow processing module 736 is configured to receive one or more structured queries from natural language processing module 732, complete the structured queries (if necessary), and perform the actions required to "complete" the user's final request. In some examples, the various processes necessary to complete these tasks are provided in task flow model 754. In some examples, task flow model 754 includes: processes for obtaining additional information from the user; and task flows for performing actions associated with the executable intent.

[0245] As described above, in order to complete a structured query, the task flow processing module 736 needs to initiate additional dialogue with the user to obtain additional information and / or clarify potentially ambiguous statements. When such interaction is necessary, the task flow processing module 736 invokes the dialogue flow processing module 734 to participate in the dialogue with the user. In some examples, the dialogue flow processor module 734 determines how (and / or when) to request additional information from the user and receives and processes the user's response. The I / O processing module 728 presents questions to the user and receives answers from the user. In some examples, the dialogue processing module 734 presents dialogue output to the user via audio and / or video output and receives input from the user via verbal or physical (e.g., click) responses. Continuing with the above example, when the task flow processing module 736 invokes the dialogue flow processing module 734 to determine the "party size" and "date" information for a structured query associated with the domain "restaurant reservation," the dialogue flow processing module 734 generates questions such as "How many people in one group?" and "Which day to book?" and presents them to the user. Once a response is received from the user, the dialogue flow processing module 734 either fills the structured query with the missing information or passes the information to the task flow processing module 736 to complete the missing information based on the structured query.

[0246] Once the task flow processing module 736 has completed a structured query for the executable intent, it begins executing the final task associated with the executable intent. Therefore, the task flow processing module 736 executes steps and instructions in the task flow model based on the specific parameters contained in the structured query. For example, a task flow model for the executable intent "restaurant reservation" includes steps and instructions for contacting the restaurant and actually requesting a reservation for a specific number of people at a specific party at a specific time. For example, using a structured query such as: restaurant reservation, {restaurant = ABC Cafe, date = 3 / 12 / 2012, time = 7pm, number of people = 5}, the task flow processing module 736 can perform the following steps: (1) log in to ABC Cafe's server or such (1) The restaurant reservation system; (2) Enter the date, time and number of people to the party on the website; (3) Submit the form; and (4) Create a calendar entry for the reservation in the user's calendar.

[0247] In some examples, task flow processing module 736, with the assistance of service processing module 738 (“service processing module”), completes the task requested in the user input or provides the informational answer requested in the user input. For example, service processing module 738, on behalf of task flow processing module 736, initiates a phone call, sets a calendar entry, invokes a map search, invokes or interacts with other user applications installed on the user's device, and invokes or interacts with third-party services (e.g., restaurant reservation portals, social networking sites, bank portals, etc.). In some examples, the protocols and application programming interfaces (APIs) required for each service are specified through the corresponding service model in service model 756. Service processing module 738 accesses the appropriate service model for a service and, based on the service model, generates a request for that service according to the protocols and APIs required by that service.

[0248] For example, if a restaurant has enabled an online reservation service, it submits a service model that specifies the necessary parameters for making a reservation and the values ​​of those parameters to be sent to the online reservation service's API. When requested by the task flow processing module 736, the service processing module 738 can use the web address stored in the service model to establish a network connection with the online reservation service and send the necessary reservation parameters (e.g., time, date, number of people traveling with the customer) to the online reservation interface according to the format of the online reservation service's API.

[0249] In some examples, the natural language processing module 732, the dialogue processing module 734, and the task flow processing module 736 are used together and repeatedly to infer and define the user's intent, obtain information to further clarify and refine the user's intent, and ultimately generate a response (i.e., output to the user or to complete the task) to satisfy the user's intent. The generated response is a dialogue response to the voice input that at least partially satisfies the user's intent. Additionally, in some examples, the generated response is output as voice output. In these examples, the generated response is sent to the speech synthesis module 740 (e.g., a speech synthesizer), where the generated response can be processed to synthesize the dialogue response into speech. In other examples, the generated response is data content related to satisfying the user's request in the voice input.

[0250] In an example where the task flow processing module 736 receives multiple structured queries from the natural language processing module 732, the task flow processing module 736 first processes a first structured query of the received structured queries to attempt to complete the first structured query and / or execute one or more tasks or actions represented by the first structured query. In some examples, the first structured query corresponds to the highest-ranking executable intent. In other examples, the first structured query is selected from received structured queries based on a combination of the corresponding speech recognition confidence score and the corresponding intent confidence score. In some examples, if the task flow processing module 736 encounters an error during the processing of the first structured query (e.g., due to the inability to determine necessary parameters), the task flow processing module 736 may continue to select and process a second structured query of the received structured queries that corresponds to a lower-ranking executable intent. For example, the second structured query may be selected based on the speech recognition confidence score of the corresponding candidate text representation, the intent confidence score of the corresponding candidate executable intent, missing necessary parameters in the first structured query, or any combination thereof.

[0251] Speech synthesis module 740 is configured to synthesize speech output for presentation to a user. Speech synthesis module 740 synthesizes speech output based on text provided by a digital assistant. For example, the generated dialogue response is in the form of a text string. Speech synthesis module 740 converts the text string into audible speech output. Speech synthesis module 740 uses any appropriate speech synthesis techniques to generate speech output from text, including but not limited to: concatenation synthesis, unit selection synthesis, diphone synthesis, domain-specific synthesis, formant synthesis, articulation synthesis, Hidden Markov Model (HMM) based synthesis, and sine wave synthesis. In some examples, speech synthesis module 740 is configured to synthesize individual words based on phoneme strings corresponding to those words. For example, phoneme strings are associated with words in the generated dialogue response. Phoneme strings are stored in metadata associated with the words. Speech synthesis module 740 is configured to directly process the phoneme strings in the metadata to synthesize words in speech form.

[0252] In some examples, instead of using a speech synthesis module 740 (or other alternatives), speech synthesis is performed on a remote device (e.g., server system 108), and the synthesized speech is sent to a user device for output to the user. For example, this could occur in some implementations where the output of a digital assistant is generated at the server system. And since server systems typically have greater processing power or more resources than user devices, it is possible to obtain speech output of a higher quality than what should be achieved through client-side synthesis.

[0253] Further details regarding digital assistants can be found in U.S. Utility Model Patent Application No. 12 / 987,982, entitled “Intelligent Automated Assistant”, filed January 10, 2011, and U.S. Utility Model Patent Application No. 13 / 251,088, entitled “Generating and Processing Task Items That Represent Tasks to Perform”, filed September 30, 2011, the entire disclosure of which is incorporated herein by reference.

[0254] 4. Exemplary architecture and functionality of virtual assistants

[0255] Figure 8 A block diagram of a virtual assistant 800 for providing natural language interaction is shown. In some examples, the digital assistant 800 (e.g., digital assistant system 700) may be implemented by a user device according to various embodiments. In some embodiments, the virtual assistant 800 may be implemented by a user device, a server (e.g., server 108), or a combination thereof. The user device may utilize, for example, Figure 1 , Figures 2A to 2B , Figure 4 , Figure 9 , Figures 11A to 11B , Figures 12A to 12D , Figures 13A to 13B and Figures 14A to 14D The devices shown are 104, 200, 400, 900, 1120, 1220, 1320, or 1420. In some implementations, such as Figure 8 As shown, the virtual assistant 800 includes the following sub-modules, subsets, or supersets: an input module 810, a natural language engine 820, a false trigger mitigator (FTM) 840, a candidate intent estimator (CIE) 860, and a task execution module 880. In some implementations, the virtual assistant 800 may utilize... Figure 7B The digital assistant system 700 shown is implemented using a digital assistant module 726. For example, a virtual assistant 800 may include one or more modules, models, applications, vocabularies, and user data similar to digital assistant module 726. (See reference...) Figure 7B and Figure 8 As an example, input module 810 may be a submodule or variant of, for example, input / output processing module 728. Natural language engine 820 may include one or more of, for example, STT processing module 730, speech-to-alphabet conversion module 731, vocabulary 744, user data 748, and / or natural language processing module 760. Virtual assistant 800 may also include modules, models, applications, vocabulary, and user data not included in digital assistant module 726. For example, as... Figure 8The false trigger mitigator 840 shown may not be included in the digital assistant module 726.

[0256] refer to Figure 8 In some embodiments, the input module 810 receives one or more audio streams 802. The audio streams may include one or more utterances. In some embodiments, the utterances in the audio streams may include words, phrases comprising multiple words, and / or one or more sentences. Figure 9 In the example shown, audio stream 912 may include one or more user utterances, which are sentences (such as "It's too dark outside. Turn on the light, Siri.").

[0257] Refer again Figure 8 The input module 810 may be enabled or kept active (e.g., for a pre-configured time period) to receive one or more audio streams 802. For example, the voice activity detector 814 of the input module 810 may detect the presence of human speech (e.g., based on the amplitude and / or spectrum of the input signal received at the voice activity detector 814). In some embodiments, the input module 810 may include a buffer 812 (e.g., a ring buffer) configured to store one or more received audio streams (e.g., storing 10 seconds of audio stream).

[0258] In some implementations, using the received audio stream stored in buffer 812, voice activity detector 814 can determine whether the audio stream includes a word trigger. A word trigger can include a single word or multiple words. For example, a word trigger could be “Hey Siri,” “Hey Assistant,” “Siri,” “Assistant,” etc. In some implementations, at least a portion of virtual assistant 800 (e.g., NLE 820) is enabled when a word trigger is received via input module 810 (e.g., voice activity detector 814). In some implementations, at least a portion of virtual assistant 800 (e.g., input module 810, NLE 820, FTM 840) can remain active or remain active for a pre-configured time period. For example, input module 810 can remain active for 30 seconds to receive audio stream 802. In implementations where at least a portion of virtual assistant 800 remains active for at least each configured time period, a word trigger may not enable a portion of virtual assistant 800. Instead, a word trigger may indicate that at least a portion of the audio stream is directed to the virtual assistant.

[0259] use Figure 9In the example shown above, the phrase “Turn on the light, Siri” includes a single-word lexical trigger “Siri” that instructs the phrase to point to the virtual assistant operating on device 900. In some implementations, the lexical trigger may be positioned at the beginning of the phrase in the audio stream (e.g., “Siri, what is the stock price?”). In some implementations, the lexical trigger may be positioned anywhere other than the beginning of the phrase (e.g., “Turn on the light, Siri”). Allowing the lexical trigger to be positioned anywhere other than the beginning of the phrase enables a more natural human-computer interaction between the user and the virtual assistant, rather than requiring the user to guide the phrase to the virtual assistant with each lexical trigger. This enhances the user experience, reduces power consumption, and improves system efficiency.

[0260] Refer again Figure 8 As described above, the input module 810 receives one or more audio streams 802. The virtual assistant 800 (e.g., using a VAD 814 of the input module 810) can determine the start / end point and / or duration of a particular audio stream from the one or more audio streams 802. Based on this determination, the virtual assistant 800 can determine whether a word trigger is included within the particular audio stream.

[0261] As an example, in order to detect the start point of a specific audio stream, the virtual assistant 800 uses a microphone (not in...) Figure 8 (As shown in the diagram) Detection of no voice activity prior to receiving a specific audio stream (e.g., detecting silence or pause between adjacent utterances). The virtual assistant 800 can also determine whether the time of no voice activity prior to receiving a specific audio stream exceeds a first threshold time period (e.g., 3 seconds). If the time of no voice activity exceeds the first threshold time period, the virtual assistant 800 determines the start point of the specific audio stream. For example, if the first threshold time period is 3 seconds and if the virtual assistant 800 determines that there was 5 seconds of silence prior to receiving the first audio stream, or if the input module 810 has not received any audio input in the past 5 seconds, then the virtual assistant 800 determines that the time of no voice activity exceeds the first threshold time period. Therefore, the start point of the specific audio stream can be determined.

[0262] In some implementations, in order to detect the end of a specific audio stream, the virtual assistant 800 may use a microphone (not in...) Figure 8(As shown in the diagram) Detection indicates that no voice activity is detected after receiving one or more utterances of a specific audio stream (e.g., detecting silence or pause between adjacent utterances). The virtual assistant 800 can also determine whether the time without voice activity after receiving the specific audio stream exceeds a second threshold time period (e.g., 3 seconds). If the time without voice activity exceeds the second threshold time period, the virtual assistant 800 determines the end point of the first audio stream. For example, if the second threshold time period is 3 seconds and if the virtual assistant 800 determines that there is 5 seconds of silence after receiving the specific audio stream, or that the input module 810 does not receive any other audio input in the next 5 seconds, then the virtual assistant 800 can determine that the time without voice activity exceeds the second threshold time period. Therefore, the end point of the specific audio stream can be determined.

[0263] As Figure 9 As illustrated in the example, a specific audio stream 912 may include a first utterance (e.g., “It’s too dark outside.”) and a second utterance (e.g., “Turn on the light, Siri.”). A virtual assistant operating on device 900 (e.g., virtual assistant 800) can determine that: no audio input was received for at least 3 seconds before receiving the first utterance of audio stream 912; and no audio input was received for at least 3 seconds after receiving the second utterance of audio stream 912. The virtual assistant can also determine that there is only a short period of missing voice activity between the first and second utterances (e.g., a short pause of 0.5 seconds). Therefore, the virtual assistant can determine the start / end point and / or duration of audio stream 912.

[0264] In some implementation schemes, reference Figure 8 The end point of an audio stream can be determined based on a pre-configured duration for which the input module 810 is configured to receive the audio stream. For example, if one or more user utterances in the audio stream are directed at a virtual assistant (e.g., to obtain information or instruct the virtual assistant to perform a task), the user utterances typically cannot last longer than 30 seconds. Therefore, the pre-configured duration can be set to, for example, 30 seconds. Thus, any user utterance received within 30 seconds after the start point of a particular audio stream can be identified as an utterance from the same audio stream. Therefore, to determine the end point of a particular audio stream, in some embodiments, the virtual assistant 800 (e.g., using the input module 810) can detect the start point of the audio stream, obtain a pre-configured duration of the audio stream (e.g., 30 seconds), and determine the end point of the audio stream (e.g., the end point is 30 seconds after the start point) based on the pre-configured duration and the start point.

[0265] refer to Figure 8In some implementations, the end point of the audio stream can be determined based on the capacity of buffer 812. Buffer 812 can store one or more received audio streams as an audio file. The storage capacity of audio file buffer 812 depends on the capacity of buffer 812 (e.g., in the megabyte range). As an example of determining the end point of the audio stream based on the capacity of buffer 812, virtual assistant 800 (e.g., using input module 810) can determine the size of an audio file representing a received audio stream including one or more utterances and compare the size of the audio file with the capacity of buffer 812. In some implementations, if the size of the audio file reaches the capacity of buffer 812 (e.g., substantially equal to the capacity of buffer 812), virtual assistant 800 can determine that the utterances included in the audio file represent the entire audio stream. Based on this determination, virtual assistant 800 can determine the end point of the audio stream.

[0266] In some implementations, the virtual assistant 800 may also estimate the probability that a specific absence of audio stream before or after receiving a specific audio stream corresponds to the start or end point of that specific audio stream, respectively. As mentioned above, the virtual assistant 800 may detect the absence of voice activity before or after receiving voice input. In some examples, the virtual assistant 800's automatic speech recognition system (e.g., Figure 7A The system 758 shown processes voice input and generates a recognition result. Based on this recognition result (e.g., the text of the voice input) and one or more language models (e.g., the model used by the ASR system 758 as described above), the virtual assistant 800 estimates the probability that a specific absence of voice activity corresponds to the start or end point of a particular audio stream. In the above example of audio stream 912 (e.g., “It’s dark outside. Turn on the light, Siri.”), based on the recognition result of the ASR system and one or more language models, the virtual assistant 800 can estimate the probability that a absence of voice activity after receiving audio stream 912 (e.g., 3 seconds of silence) corresponds to the end point of audio stream 912. Based on this estimated probability, the virtual assistant 800 can increase or improve the confidence level (e.g., based on a comparison of the estimated probability with a threshold) to detect the end point of audio stream 912.

[0267] Upon detecting the end and start points of a specific audio stream, the virtual assistant 800 can determine the duration of the specific audio stream. In some implementations, based on the duration of the specific audio stream, the virtual assistant 800 can determine whether a word trigger is included in the specific audio stream. In some implementations, the virtual assistant 800 does not determine the duration of the specific audio stream, but can use the detected end and start points of the specific audio stream to determine whether a word trigger is included in the specific audio stream.

[0268] As mentioned above, Figure 9 An audio stream 912 comprising one or more phrases is shown (e.g., “It’s too dark outside. Turn on the light, Siri.”) and the virtual assistant 800 determines that a word trigger (e.g., “Siri”) is included in the audio stream 912. Figure 9 As shown, one or more utterances in audio stream 912 may include at least one utterance that is not directed at virtual assistant 800. For example, the first utterance “It’s too dark outside” could be a comment, rather than a utterance directed at the virtual assistant operating on device 900 (e.g., virtual assistant 800). Therefore, the virtual assistant may not perform a task or take action based on such utterances. As described in detail below, by using various techniques, the virtual assistant can determine that a utterance is not directed at it, and therefore such utterances should be ignored. Such utterances may include, for example, comments from users, utterances from one user to another, etc. The ability of the virtual assistant to determine whether a utterance is directed at it improves the operational efficiency of the device because the virtual assistant can ignore any utterance that is not directed at it, while eliminating or reducing the requirement to guide each utterance directed at the virtual assistant with a trigger word or phrase.

[0269] refer to Figure 8 In some implementations, based on a specific audio stream of one or more determined audio streams 802 including word triggers (e.g., “Siri”), the input module 810 generates one or more speech results 816. The speech results 816 may include audio representations (e.g., speech representations) of one or more utterances included in the specific audio stream. The input module 810 also provides the speech results 816 to a natural language engine 820, which may include one or more modules, such as a speech-to-text (STT) processing module 730 and / or a natural language processing module 732. Figure 7B (as shown in the image) or its variants. Based on the speech result 816, the natural language engine 820 can generate candidate text representations 822 representing one or more utterances in a specific audio stream. As mentioned above, each candidate text representation can be a word or token corresponding to a utterance in a specific audio stream. Figure 9 As an example, the audio stream 912 shown can be used by the natural language engine of a virtual assistant operating on device 900 to perform speech-to-text conversion on each utterance of the audio stream 912 and generate candidate text representations including a first candidate text representation (e.g., “It’s too dark outside.”) and a second candidate text representation (e.g., “Turn on the light, Siri.”).

[0270] In some implementations, the natural language engine 820 may also determine a confidence level corresponding to one or more candidate text representations 822. For example, as described above, each candidate text representation may be associated with a speech recognition confidence score. Furthermore, the natural language engine 820 may rank the candidate text representations 822 (e.g., using the STT processing module 730) and provide n best (e.g., n highest-ranked) candidate text representations for candidate intent generation or derivation.

[0271] As described above, the natural language engine 820 may include one or more of the following: STT processing module 730, speech-to-alphabet conversion module 731, vocabulary 744, user data 748, and / or natural language processing module 760. In some embodiments, using the natural language processing module 760, the natural language engine 820 may also interpret candidate text representations to derive pre-relief intentions and optionally confidence levels associated with the pre-relief intentions. For example, the natural language engine 820 may optionally rank the confidence levels associated with the pre-relief intentions and provide n optimal pre-relief intentions for candidate intention generation or derivation.

[0272] refer to Figure 8 The false trigger mitigator (FTM) 840 of the virtual assistant 800 can determine whether the virtual assistant 800 should ignore at least one candidate text representation of one or more candidate text representations 822 (or sorted candidate text representations). The FTM 840 can use, for example... Figure 7B The digital assistant module 726 shown is implemented as a submodule or variant thereof. For example, FTM 840 may include natural language processing 732 or a variant thereof to derive one or more candidate intents 842. In some embodiments, FTM 840 may include a decision tree, such as a simple decision tree or a boosting decision tree. As described above, in some embodiments, at least one utterance of one or more utterances in a particular audio stream may not be directed to the virtual assistant 800 and may therefore be ignored by the virtual assistant 800.

[0273] Figure 9 An example is shown for determining whether to ignore at least one candidate text representation. For example... Figure 9As shown and as described above, based on the utterance of user 910, the natural language engine (e.g., NLE 820) of the virtual assistant operating on device 900 can generate, for example, two candidate text representations, such as “It’s too dark outside.” and “Turn on the light, Siri.” In some implementations, the virtual assistant’s FTM (e.g., FTM 840) determines for each of the two candidate text representations whether the candidate text representation includes a lexical trigger. For example, the FTM determines that the first candidate text representation (e.g., “It’s too dark outside.”) does not include a lexical trigger, but the second candidate text representation (e.g., “Turn on the light, Siri.”) includes a lexical trigger (e.g., “Siri”).

[0274] refer to Figure 8 In some implementations, if the FTM 840 determines that a candidate text representation includes a lexical trigger, then the FTM 840 determines that the corresponding user utterance points to the virtual assistant 800, and therefore this particular candidate text representation should not be ignored. Therefore, this particular candidate text representation should be further processed, as described in more detail below. Figure 9 In the example shown, the FTM of the virtual assistant operating on device 900 determines that the second candidate text representation (e.g., “Turn on the lights, Siri.”) should not be ignored because it includes the lexical trigger “Siri” of the single word.

[0275] refer to Figure 8 In some implementations, if FTM 840 determines that a candidate text representation does not include lexical triggers, then FTM 840 can estimate the probability that the utterance corresponding to a particular candidate text representation does not refer to the virtual assistant 800. Figure 9 As illustrated in the example above, the FTM of the virtual assistant operating on device 900 determines that the first candidate text representation (e.g., “It’s too dark outside.”) does not include a lexical trigger. Furthermore, using a decision tree, the virtual assistant’s FTM can estimate the probability that the utterance corresponding to the first candidate text representation does not refer to the virtual assistant. For example, the FTM can determine that the pre-relief intent corresponding to the first candidate text representation (e.g., “It’s too dark outside.”) is not, or may not, be associated with a domain or candidate intent identified by the virtual assistant. Therefore, the FTM can estimate the probability that the utterance corresponding to the first candidate text representation (e.g., “It’s too dark outside.”) does not refer to the virtual assistant and determine whether the estimated probability meets a threshold condition. If it does, the FTM determines that the utterance does not refer to the virtual assistant. Therefore, for the purpose of generating candidate intents, the first candidate text representation (e.g., “It’s too dark outside.”) can be ignored. In some embodiments, determining whether to ignore a candidate text representation may also be based on contextual information, such as the use of pattern and / or sensory data, as described in more detail below.

[0276] Refer again Figure 8 In some implementations, FTM 840 can determine for each of the candidate text representations 822 whether a particular candidate text representation should be ignored. If at least one of the candidate text representations 822 is to be ignored, FTM 840 can generate one or more candidate intents 842 based on the candidate text representations that are not to be ignored. For example, FTM 840 can derive candidate intents 842 based on pre-mitigation intents of the candidate text representations that are not to be ignored. Figure 9 In the example shown above, the FTM of a virtual assistant operating on device 900 determines to ignore a first candidate text representation (e.g., “It’s too dark outside.”) while not ignoring a second candidate text representation (e.g., “Turn on the lights, Siri.”). Therefore, in some implementations, the virtual assistant’s FTM may attempt to interpret the pre-relief intent of the second candidate text representation by associating it with one of the recognition domains in an ontology (e.g., ontology 760), thereby deriving the candidate intent. For example, the FTM may select the pre-relief intent corresponding to the second candidate text representation (e.g., turn on the lights in the user’s living room) as the candidate intent while filtering out pre-relief intents corresponding to the first candidate text representation.

[0277] refer to Figure 8 In some implementations, FTM 840 can acquire a confidence level corresponding to each of one or more candidate intents 842. As described above, NLE 820 can generate a confidence level for each pre-relief intent. For example, a particular candidate text representation can be associated with multiple identified domains, thus multiple pre-relief intents can be derived from the same candidate text representation. NLE 820 and / or FTM 840 can determine a confidence score (e.g., based on its relative importance to various triggering nodes in the ontology) to select the domain with the highest confidence value, and thus determine the corresponding candidate intent.

[0278] refer to Figure 8 In some implementations, the virtual assistant 800 includes a candidate intent evaluator (CIE) 860. CIE 860 can determine whether one or more candidate intents 842 include at least one executable intent. For example, CIE 860 can determine whether a task is executable for each candidate intent 842. In some implementations, CIE 860 can make such a determination without actually performing the task (e.g., performing a dry run). As an example, CIE 860 may include one or more submodules of the digital assistant module 726 or variations thereof, such as... Figure 7B The task flow processing module 736 and dialogue processing module 734 are shown. The CIE 860 can use these submodules or variations thereof to determine whether a candidate intent 842 is an executable intent, without providing the result to the speech synthesis module 740 or outputting the result.

[0279] As Figure 8 As another example shown, CIE 860 may include a task flow processing module 862 and a dialogue processing module 864 for determining whether a candidate intent 842 is an executable intent. Figure 8 The task flow processing module 862 and dialogue processing module 864 shown can be as follows: Figure 7B The illustrated task flow processing module 736 and dialogue processing module 734 are copies, differing in that task flow processing module 862 and dialogue processing module 864 may not provide their processing results to the speech synthesis module or otherwise output the results to the user. Therefore, CIE 860 can determine whether candidate intent 842 is an executable intent, and can make such a determination even if the virtual assistant 8000 does not actually perform the task. Thus, if the task cannot be performed or can only be partially performed, CIE 860 can make such a determination without causing the virtual assistant 8000 to actually perform the task, but should instead attempt to obtain more information for actually performing the task (e.g., obtaining contextual information or initiating a dialogue with the user to obtain more information). Determining whether a candidate intent is an executable intent without actually performing the task improves operational efficiency and enhances the human-computer interface. For example, this determination saves power and avoids outputting partially performed tasks or confusing the user.

[0280] Continued Figure 9 As illustrated above, based on candidate text representations (e.g., “Turn on the lights, Siri.”), the FTM of a virtual assistant operating on device 900 generates candidate intents to turn on the lights in the user’s living room. The virtual assistant’s CIE (e.g., CIE 860) determines whether a task can be performed for the candidate intent. In some implementations, the CIE may use a task flow processing module (e.g., task flow processing module 862) and / or a dialogue processing module (e.g., dialogue processing module 864) to perform this determination. For example, the task flow processing module may attempt to perform the task of turning on the lights in the user’s living room based on a structured query generated using the corresponding candidate intent. In some examples, the task flow processing module may determine that such a task cannot be performed because it cannot find a home automation device to control the lights in the living room. In some examples, the task flow processing module may determine that a home automation device to control the lights is available, and therefore the corresponding task can be performed.

[0281] refer to Figure 8 In some implementations, if CIE 860 determines that a task corresponding to candidate intent 842 can be performed, then it determines that a particular candidate intent 842 is an executable intent. CIE 860 may repeat this determination for each candidate intent 842 and generate an executable intent 868. For example... Figure 8As shown, CIE 860 provides each executable intent 868 to task execution module 880, which executes one or more tasks based on the executable intent 868. Task execution module 880 may include one or more submodules of digital assistant module 726 or variations thereof, such as... Figure 7B The task flow processing module 736 and dialogue processing module 734 are shown. Unlike CIE 860, which does not actually execute tasks, task execution module 880 receives a structured query (or multiple structured queries) based on executable intent 868, completes the structured query, and, if necessary, executes the tasks required to "complete" the user's final request. (Continued) Figure 9 In the example shown, upon receiving an executable intent to turn on a light in a user's living room, the task execution module of a virtual assistant operating on device 900 can turn on the light and optionally output the result of the execution intent (e.g., providing audio and / or visual output 942, such as "Your light is on.").

[0282] Refer again Figure 8 In some implementations, CIE 860 may determine whether a task can be performed based on an estimate of the confidence level associated with the task. For example, CIE 860 may estimate the confidence level associated with the task and determine whether the confidence level associated with the task meets a threshold confidence level. If CIE 860 determines that the confidence level associated with the task meets the threshold confidence level, then CIE 860 determines that the task can be performed.

[0283] Figure 10 A block diagram of an exemplary virtual assistant 1000 is shown for providing natural language interaction using execution results and contextual information. In some examples, the digital assistant 1000 (e.g., digital assistant system 700) may be implemented by a user device according to various embodiments. In some embodiments, the virtual assistant 1000 may be implemented by a user device, a server (e.g., server 108), or a combination thereof. The user device may utilize, for example, Figure 1 , Figures 2A to 2B , Figure 4 , Figure 9 , Figures 11A to 11B , Figures 12A to 12D , Figures 13A to 13B and Figures 14A to 14DThe devices shown are 104, 200, 400, 900, 1120, 1220, 1320, or 1420. Similar to Virtual Assistant 800, Virtual Assistant 1000 includes an input module 810, a natural language engine 816, an FTM 840, a CIE 860, and a task execution module 880. These modules or components of Virtual Assistant 1000 are similar to those described above with respect to Virtual Assistant 800 and therefore will not be described again. In some embodiments, one or more of the various modules, models, applications, vocabularies, and user data of Virtual Assistant 1000 may receive additional information, such as previous execution results and / or contextual information, to help detect speech activity, determine candidate text representations, determine candidate intents, determine executable intents, and / or execute executable intents.

[0284] refer to Figure 10 and Figure 11A For example, a virtual assistant (e.g., virtual assistant 1000) operating on device 1120 receives an audio stream 1112 from user 1110 via an input module (e.g., input module 810). The audio stream 1112 includes one or more user utterances, such as “What’s the weather like today, Siri? Do you know what the stock price is?” The virtual assistant uses the utterances included in the audio stream 1112 to generate a speech result. Based on the speech result, the virtual assistant generates one or more candidate text representations (e.g., candidate text representation 1022) via a natural language engine (e.g., natural language engine 820).

[0285] Next, for each candidate text representation, the virtual assistant determines, via an FTM (e.g., FTM840), whether to ignore that particular candidate text representation. As described above, in some implementations, the virtual assistant may determine, for example, whether a particular candidate text representation includes a word trigger. Figure 11A The example shown indicates that the candidate text representations for audio stream 1112 include a first candidate text representation (e.g., “How’s the weather today, Siri?”) and a second candidate text representation (e.g., “Do you know what the stock price is?”). The virtual assistant determines that the first candidate text representation includes a lexical trigger (e.g., “Siri”) and therefore should not be ignored, as the corresponding utterance refers to the virtual assistant operating on device 1120. Regarding the second candidate text representation, the virtual assistant determines that it does not include a lexical trigger. Based on this determination, the virtual assistant estimates the probability that the utterance corresponding to the second candidate text representation does not refer to virtual assistant 1000.

[0286] refer to Figure 10 and Figure 11AIn some implementations, to estimate the probability that the utterance corresponding to the second candidate text representation does not refer to the virtual assistant, the virtual assistant acquires contextual information (e.g., execution result and contextual information 1044). The contextual information may be associated with the usage patterns of the virtual assistant operating on device 1120. The usage patterns of the virtual assistant may indicate patterns in which user 1110 uses the virtual assistant and / or performs specific activities using device 1120, such as... Figure 11A As shown. For example, user 1110 might frequently ask the same questions about the weather and stock prices around 6 a.m. Therefore, a usage pattern can be generated based on the user's activity (e.g., asking the same question to the virtual assistant) around 6 a.m. Contextual information may include this usage pattern obtained from device 1120 and time 1122 (e.g., indicating the current time is around 6 a.m.). Based on the contextual information associated with the usage pattern, the virtual assistant can estimate, via FTM (e.g., FTM 840), the likelihood that the utterance corresponding to the second candidate text representation does not refer to the virtual assistant. For example, based on the contextual information indicating that the user frequently asks the virtual assistant about stock prices around 6 a.m. and the current time being around 6 a.m., the virtual assistant can estimate that the likelihood that the utterance “Do you know what the stock price is?” does not refer to virtual assistant 1000 is low (e.g., does not meet a threshold). Therefore, the virtual assistant determines not to ignore the second candidate text representation based on this estimated likelihood.

[0287] In some implementations, contextual information can also be used to determine whether a candidate intent is an executable intent. (Continued) Figure 11A In the example shown above, a virtual assistant operating on device 1120 generates one or more candidate intents based on determining that neither a first candidate text representation (e.g., “What’s the weather like today, Siri?”) nor a second candidate text representation (e.g., “Do you know what the stock price is?”) should be ignored. For example, the virtual assistant generates a first candidate intent to get today’s weather information and a second candidate intent to get stock price information. For each candidate intent, the virtual assistant determines whether the task can be performed using a CIE (e.g., CIE 860). As mentioned above, the CIE can make this determination using, for example, a task flow processing module and / or a dialogue processing module, without actually performing the task.

[0288] In some implementations, regarding the first candidate intent to obtain weather information, the virtual assistant determines that additional location information may be needed to perform the task of obtaining weather information. However, this location information is not presented in or provided by the first candidate text representation. Therefore, in some implementations, the virtual assistant may acquire contextual information associated with sensory data from one or more sensors communicatively coupled to device 1120 and determine whether the task can be performed based on the contextual information. For example, location data may be acquired as contextual information indicating the current location of device 1120. Using this contextual information, the virtual assistant determines that the first candidate intent to obtain weather information is an executable intent because weather information for the current location of device 1120 can be obtained from an internal or external data source (e.g., from a weather information website).

[0289] refer to Figure 11A Regarding the second candidate intent to obtain stock price information, the virtual assistant determines that additional information about the stock name may be needed to perform the task of obtaining the stock price. However, this stock name information is neither presented in nor provided by the second candidate text representation. Therefore, in some embodiments, the virtual assistant may obtain contextual information associated with the usage patterns of the virtual assistant and / or device 1120. The usage patterns of the virtual assistant and / or device 1120 may indicate patterns of specific activities performed by user 1110 using virtual assistant 1000 and / or using user device 1120, such as... Figure 11A As shown. For example, user 1110 might frequently ask questions about the S&P 500 index around 6:00 AM. Therefore, a usage pattern can be generated based on the user's activity around 6:00 AM (e.g., asking the virtual assistant the same question about the S&P 500 index). Contextual information may include this usage pattern provided by device 1120 and time 1122 (e.g., indicating the current time is around 6:00 AM). Using this contextual information, the virtual assistant determines that a second candidate intent to obtain stock prices is an executable intent because information about the S&P 500 index can be obtained.

[0290] Figure 11B An exemplary user interface is shown for use with contextual information associated with sensory data by a virtual assistant (e.g., Figure 10 The virtual assistant 1000 shown provides natural language interaction. For example... Figure 10 and Figure 11BAs shown, for example, a virtual assistant operating on device 1120 receives one or more audio streams from users 1110 and 1130. The audio streams may include, for example, utterances 1132, 1134, and 1136 from user 1130. One or more utterances from user 1110 may be directed to the virtual assistant or user 1130. For example, utterance 1132 from user 1110 may include “Siri, what is today’s S&P 500 index?”. Similar to those described above, the virtual assistant determines that the first candidate text representation of utterance 1132 includes a lexical trigger (e.g., “Siri”) and therefore should not be ignored. Based on this determination, the virtual assistant generates a first candidate intent and determines that the first candidate intent to obtain the S&P 500 index is executable. Therefore, the virtual assistant performs the task of obtaining the S&P 500 index and outputs result 1138 (e.g., audio and / or visual output indicating “today’s S&P 500 index is 12000”).

[0291] like Figure 11B As shown, upon hearing the S&P 500 index output by the virtual assistant 1000, user 1130 can provide the utterance 1134, “Have you heard that AAPL went up a lot today?”, asking user 1110. The virtual assistant operating on device 1120 can generate a second candidate text representation corresponding to utterance 1134 and determine whether to ignore the second candidate text representation. For example, the virtual assistant can determine that the second candidate text representation does not include a word trigger and thus estimate the probability that utterance 1134 is not directed at the virtual assistant. In some embodiments, to estimate this probability, the virtual assistant can acquire sensory data from one or more sensors communicatively coupled to device 1120 and estimate the probability that utterance 1134 is not directed at the virtual assistant based on the acquired sensory data. For example, device 1120 may include an optical sensor 264 (e.g., a camera) that detects user 1110’s eye gaze toward device 1120 at any given time. Optical sensor 264 can detect, for example, that user 1130 is not looking at device 1120 when the virtual assistant operating on device 1120 receives utterance 1134. Therefore, the virtual assistant estimates a high probability that the utterance 1134, estimated using sensory data provided by optical sensor 264, is not directed at the virtual assistant (e.g., compared to a threshold). Consequently, FTM 840 determines to ignore the second candidate text representation.

[0292] Continued Figure 11BIn the example shown, upon hearing utterance 1134, user 1110 can provide utterance 1136, “Really? What’s the price of AAPL today?” The virtual assistant can generate a third candidate text representation corresponding to utterance 1136 and determine whether to ignore the third candidate text representation. Similar to those described above, the virtual assistant can determine that the third candidate text representation does not include a word trigger. Based on such a determination, the virtual assistant can estimate the probability that utterance 1136 does not refer to the virtual assistant operating on device 1120. In some embodiments, to estimate this probability, the virtual assistant acquires sensory data and estimates the probability that utterance 1136 does not refer to virtual assistant 1000 based on the acquired sensory data. For example, optical sensor 264 can detect, for example, that user 1110 is looking at device 1120 when the virtual assistant receives utterance 1136. Therefore, the virtual assistant uses the sensory data provided by optical sensor 264 to estimate that the probability that utterance 1136 does not refer to virtual assistant 1000 is low (e.g., compared to a probability threshold). Therefore, the virtual assistant determines not to ignore the third candidate text representation. Therefore, the virtual assistant can generate candidate intents based on the third candidate text representation and determine whether the candidate intents are executable. Thus, the virtual assistant performs the task of obtaining the stock price of AAPL and outputs result 1140 (e.g., audio and / or visual output indicating "AAPL closed at $200 today").

[0293] Figures 12A to 12D An exemplary user interface is shown for natural language interaction provided by a virtual assistant operating on device 1220 using contextual information associated with the execution of a previously determined executable intent. Figure 10 and Figure 12A As shown, user 1210 provides a first audio stream 1212 (e.g., “Siri, play some music”), which is received by a virtual assistant operating on device 1220. Similar to those described above, the virtual assistant determines that the first audio stream 1212 includes a word trigger (e.g., “Siri”), generates candidate text representations of the first audio stream 1212 (e.g., “Siri, play some music.”), determines candidate text representations of the first audio stream 1212 not to be ignored (because it includes a word trigger), generates candidate intents, determines that the candidate intents are executable intents (e.g., the task of playing music can be performed), executes the executable intents, and outputs the execution result (e.g., outputting an audio and / or visual message 1224, such as “Here are some music you might like.”). Figure 12A As shown, the virtual assistant 1000 can receive and process the first audio stream 1212 at time 1222A (e.g., 9 a.m.).

[0294] like Figure 12BAs shown, when a virtual assistant operating on device 1220 is performing a task of playing music, it can receive a second audio stream 1214 from user 1210 at time 1222B (e.g., 9:05 AM). In some embodiments, the virtual assistant generates candidate text representations of the second audio stream 1214. Based on the candidate text representations of the second audio stream 1214, the virtual assistant can determine whether the second audio stream 1214 (e.g., "stop") is part of the same audio session as the first audio stream 1212 (e.g., "play some music").

[0295] In some implementations, to determine whether the second audio stream 1214 is part of the same audio session that includes the first audio stream 1212, a virtual assistant operating on device 1220 may acquire contextual information associated with performing a previously determined executable intent. For example, the virtual assistant detects that playing music is a result of performing a previously determined executable intent when the second audio stream 1214 is received. Therefore, the virtual assistant determines that the second audio stream 1214 is, or may be, part of the same audio session that includes the first audio stream 1212. In some implementations, this determination may also take into account the relationship between the first audio stream 1212 and the second audio stream 1214 (e.g., semantic relationship, topic relationship). Implementations that take into account relationships are described in further detail below.

[0296] refer to Figure 12B Since the second audio stream 1214 is determined to be part of the same audio session including the first audio stream 1212, the virtual assistant generates a second candidate intent based on the candidate text representation of the second audio stream 1214. The virtual assistant also determines whether the second candidate intent includes an executable intent. In some embodiments, this determination may be based on contextual information associated with a task previously performed or currently being performed by the virtual assistant. For example, the contextual information may be associated with a previous task of playing music. Figure 12B As shown, the second candidate intent can therefore be determined to be to stop playing the currently playing music. Therefore, the virtual assistant can determine, based on this second candidate intent, that a task can be performed (e.g., stop playing music), and thus the second candidate intent is executable. Therefore, the virtual assistant executes the executable intent to stop playing music. In some embodiments, the virtual assistant optionally provides audio and / or visual output 1226 indicating the execution result (e.g., "OK").

[0297] Figure 12C and Figure 12DA similar scenario is illustrated, where a virtual assistant operating on device 1220 receives a first audio stream 1242 including a statement such as “Siri, play some music.” Similar to those described above, the virtual assistant determines an executable intent to play music, executes the executable intent, and optionally outputs an audio / visual message 1222 (e.g., “Here are some songs you might like.”). While the music is still playing, the virtual assistant receives a second audio stream 1244 including a statement such as “Skip this song.” The virtual assistant detects that playing music is a result of executing the previously determined executable intent when the second audio stream 1244 is received. Therefore, the virtual assistant can determine that the second audio stream 1244 is or may be part of the same audio session that includes the first audio stream 1242. Therefore, the virtual assistant generates a second candidate intent based on the candidate text representation of the second audio stream 1244. The virtual assistant also determines whether the second candidate intent includes an executable intent. For example, as... Figure 12D As shown, the second candidate intent can be determined to be to skip the currently playing audio track 1 and start playing the next audio track. Therefore, the virtual assistant can determine that the task can be executed based on this second candidate intent, and thus the second candidate intent is executable. Therefore, the virtual assistant executes this executable intent to stop playing audio track 1 and start playing audio track 2.

[0298] Figures 13A to 13B An exemplary user interface is shown for natural language interaction provided by a virtual assistant using contextual information associated with the user's utterance or audio stream. As described above, contextual information can be provided to one or more modules or components of the virtual assistant (e.g., Figure 10 The virtual assistant 1000 shown includes the FTM 840 and CIE 860. In some implementations, contextual information may be provided to the CIE (e.g., CIE 860) to determine whether a candidate intent is an executable intent. Such contextual information may include, for example, one or more relationships between candidate text representations of user utterances in an audio stream.

[0299] As Figure 13AIn the example shown, a virtual assistant (e.g., virtual assistant 1000) operating on device 1320 receives audio stream 1312. Audio stream 1312 may include a first utterance (e.g., “Did you know that the Warriors played really well in the last game?”) and a second utterance (e.g., “When is the next game, Siri?”). Based on audio stream 1312, candidate text representations can be generated to represent the utterances included in audio stream 1312. The virtual assistant may determine (e.g., using FTM840) that the candidate text representation of the first utterance (e.g., “Did you know that the Warriors played really well in the last game?”) does not include a word trigger, and the first utterance may not be directed at the virtual assistant. Therefore, the virtual assistant may determine candidate text representations of the first utterance to ignore in order to generate candidate intents. In some implementations, although the candidate text representation of the first utterance is ignored in order to generate candidate intents, the candidate text representation may be retained for determining relationships between multiple candidate text representations.

[0300] Continued Figure 13A In the example shown, the virtual assistant can determine (e.g., using an FTM 840) that the candidate text representation of the second utterance (e.g., “When is the next game, Siri?”) includes a lexical trigger, and therefore the second utterance may point to the virtual assistant. Therefore, the candidate text representation of the second utterance should not be ignored. The virtual assistant then generates candidate intents based on the candidate text representations of the second utterance and determines whether the candidate intents are executable. As described above, to determine whether a candidate intent is executable, in some implementations, the virtual assistant determines whether a task can be performed based on the executable intent. This determination can be based on the candidate text representations of the second utterance and on contextual information indicating the relationships between the candidate text representations.

[0301] As described above, a candidate text representation of the second utterance in audio stream 1312 could include “When is the next game, Siri?”. Based solely on this candidate text representation, the virtual assistant might not be able to determine whether a task can be performed, because the candidate text representation does not indicate which game the user is referring to. In some examples, the virtual assistant can determine the relationship between adjacent candidate text representations. For example, the virtual assistant determines that the candidate text representation of the first utterance (e.g., “Did you know that the Warriors played very well in their last game?”) is semantically, thematically, and / or temporally related to the candidate text representation of the second utterance (e.g., “When is the next game, Siri?”). Therefore, the virtual assistant can use contextual information associated with the relationship between the candidate text representations to determine whether a task can be performed. In this example, the contextual information indicates that when user 1310 asks “When is the next game, Siri?”, user 1310 is likely referring to a Golden State Warriors game. Therefore, the virtual assistant determines that the task can be performed based on the contextual information (e.g., performing the task of obtaining the Warriors' game schedule by searching the internet), thus determining that the candidate intent is an executable intent. Therefore, a virtual assistant can execute executable intentions and provide, for example, audio and / or visual output, such as "The Golden State Warriors' next game will begin tomorrow at 5:30 p.m.".

[0302] Now go to Figure 13B Contextual information associated with relationships between multiple audio streams (e.g., semantics, topic, time) can also be used to determine whether two or more audio streams are in the same audio session. (See reference) Figure 13B A virtual assistant operating on device 1320 (e.g., Figure 10 The virtual assistant 1000 shown receives a first audio stream 1342 containing utterances such as “What was the Warriors’ score in the game?” Similar to those described above, the virtual assistant generates candidate text representations of the first audio stream 1342, determines that the candidate text representations should not be ignored, generates candidate intents, determines that the candidate intents are executable intents, executes the executable intents, and provides audio and / or visual output 1346, such as “The Warriors beat the Knicks by a score of 123 to 112.”

[0303] In some implementations, when or after the virtual assistant outputs the execution result of an executable intent corresponding to the first audio stream 1342, the virtual assistant operating on device 1320 receives a second audio stream 1344 including utterances such as “When is the next game?”. In some implementations, the virtual assistant generates candidate text representations to represent the second audio stream 1344. The generation of candidate text representations of the second audio stream 1344 can be performed regardless of whether the second audio stream 1344 includes lexical triggers. For example, the virtual assistant can determine the temporal relationship between receiving the second audio stream 1344 and executing an executable intent corresponding to the first audio stream 1342. The virtual assistant also determines that the temporal relationship indicates that the second audio stream 1344 was received within a threshold time period from the execution of the executable intent, therefore lexical triggers in the second audio stream 1344 are not needed for generating candidate text representations of the second audio stream 1344.

[0304] After generating candidate text representations for the second audio stream 1344, a virtual assistant operating on device 1320 can determine whether the second audio stream 1344 is part of the same audio session that includes the first audio stream 1342. The virtual assistant can determine the relationships between the various candidate text representations of the first audio stream 1322 and the second audio stream 1344. For example, the virtual assistant determines that the candidate text representation of the first audio stream 1322 (e.g., “What was the Warriors’ score?”) is semantically, thematically, and / or temporally related to the candidate text representation of the second audio stream (e.g., “When is the next game?”). Therefore, the virtual assistant can use contextual information associated with the relationships between the various candidate text representations of the first and second audio streams to determine whether the audio streams are in the same audio session. Figure 13B In the example shown, the virtual assistant determines that the second audio stream 1344 is part of the same audio session that includes the first audio stream 1322 because the various candidate text representations of the audio streams are semantically and / or thematically relevant. Based on this determination, the virtual assistant generates candidate intents based on the candidate text representations of the second audio stream 1322, determines whether the candidate intents are executable intents, and if so, executes the executable intents. Therefore, the virtual assistant provides audio and / or visual output 1348, such as "The Golden State Warriors' next game starts tomorrow at 5:30 PM."

[0305] Figures 14A to 14D An exemplary user interface for selecting a task from multiple tasks using context information is shown. As described above, one or more modules or components of the virtual assistant can provide previous execution results and / or context information (e.g., Figure 10The virtual assistant 1000 shown is based on the FTM 840 and CIE 860. In some implementations, context information may be provided to the task execution module 880 to select one or more tasks to be performed. (See reference...) Figure 14A The virtual assistant operating on device 1420 receives a first audio stream 1412, including phrases such as "Siri, play some music." Similar to the above regarding... Figure 12A As described, the virtual assistant determines the audio stream 1412, including word triggering, generating candidate text representations, determining not to ignore the candidate text representations, generating candidate intents, determining that the candidate intents are executable intents, and executing the executable intents. Therefore, the virtual assistant starts playing music and optionally provides audio and / or visual output 1424, such as "Here are some music you might like."

[0306] refer to Figure 14B In some implementations, while the virtual assistant is performing a previously determined executable intent (e.g., playing music), it receives a second audio stream 1414. The second audio stream 1414 may include another user request that may be semantically or thematically unrelated to the first audio stream 1412. For example, the second audio stream 1414 may include utterances such as “I want to send a message to my wife, Siri.” The virtual assistant operating on device 1420 may repeat processes similar to those described above and perform a second executable intent derived from the second audio stream 1414. Thus, the virtual assistant causes device 1420 to display a text messaging user interface 1426, for example, for composing text messages.

[0307] Go to Figure 14C In some implementations, when performing a previously determined executable intent (e.g., playing music and displaying a text messaging user interface for composing a text message), a virtual assistant operating on device 1420 receives a third audio stream 1416. The third audio stream 1416 may be associated with the execution of one or both of the previously determined executable intents. For example, the third audio stream 1416 may include utterances such as "Stop." Based on the third audio stream 1416, the virtual assistant may determine, for example, a first candidate intent to stop playing currently playing music and a second candidate intent to stop composing a text message. The virtual assistant may also determine that both the first and second candidate intents are executable intents because the corresponding tasks can be performed.

[0308] In some implementations, if multiple executable intentions exist, the virtual assistant selects a single task to be performed from among multiple tasks associated with the multiple executable intentions. In some implementations, the selection of the single task to be performed may be based on contextual information. For example, the virtual assistant obtains contextual information associated with a recent task initiated by the virtual assistant and selects a single task for execution based on such contextual information. In the example described above, the recent task initiated by the virtual assistant is displaying a user interface for composing a text message. Therefore, based on the contextual information associated with this recent task of displaying a user interface for composing a text message, the virtual assistant dispels ambiguity in the user request included in the third audio stream 1416 and selects to stop or cancel the task of composing a text message. Optionally, as Figure 14C As shown, the virtual assistant can provide audio and / or visual output 1432, such as "Okay, the message to your wife has been canceled."

[0309] In some implementations, if multiple executable intents exist, the virtual assistant selects a single task to perform from multiple tasks associated with those intents based on the user's choice. This is in... Figure 14D As shown, the virtual assistant outputs multiple task options. For example, the virtual assistant provides audio and / or visual output 1434 (e.g., "Do you want to stop playing music or cancel sending a message to your wife?") prompting the user 1410 to select a task. The virtual assistant receives the user's selection (e.g., "Stop playing music") from the audio stream 1418 and performs the task based on that selection. Optionally, as... Figure 14D As shown, the virtual assistant can provide audio and / or visual output 1436, such as "The music has stopped".

[0310] In some implementations, if multiple executable intents exist, the virtual assistant selects a single task to perform from the multiple tasks associated with the multiple executable intents based on the priority associated with each of the multiple tasks. For example, a virtual assistant (e.g., virtual assistant 1000) may receive a first audio stream including a phrase such as “What’s the weather like today, Siri?” Before the virtual assistant responds, it receives a second audio stream including a phrase such as “There’s been a car accident! Siri, call 911!” The virtual assistant determines a first executable intent to get weather information and a second executable intent to make an emergency call based on this audio stream. In some implementations, the virtual assistant may determine the priority associated with each of the multiple tasks to be performed and select a task based on the determined priority. In the example above, when the second audio stream is received after the first audio stream is received, the virtual assistant determines that the task associated with the second executable intent to make an emergency 911 call has a higher priority than the task associated with the first executable intent to get weather information. Therefore, the virtual assistant selects the task associated with the second executable intent for execution (e.g., making an emergency 911 call).

[0311] While the various embodiments described above involve specific types of contextual information, it should be understood that the technology may also use any type of contextual information, as described in U.S. Patent Application 15 / 694,267, filed September 1, 2017, entitled “Methods and Systems for Customizing Suggestions Using User-specific Information,” the entire contents of which are incorporated herein by reference.

[0312] 5. Provide a natural language interaction process

[0313] Figures 15A to 15GA process 1500 according to various embodiments is illustrated for operating a virtual assistant to provide natural language interaction. For example, process 1500 may be performed using one or more electronic devices implementing the virtual assistant. In some examples, a client-server system (e.g., system 100) is used to perform process 1500, and the boxes of process 1500 may be divided in any way between the server (e.g., DA server 106) and the client devices. In other examples, the boxes of process 1500 may be divided between the server and multiple client devices (e.g., mobile phones and smartwatches). Therefore, while portions of process 1500 are described herein as being performed by a specific device of the client-server system, it should be understood that process 1500 is not limited thereto. In other examples, process 1500 may be performed using only client devices (e.g., user devices 104, 200, 400, 600, 900, 1120, 1220, 1320, or 1420) or only multiple client devices. In process 1500, some boxes are optionally combined, the order of some boxes is optionally changed, and some boxes are optionally omitted. In some examples, process 1500 may be combined to perform additional steps.

[0314] As mentioned above, always requiring the trigger phrase to be at the beginning of a user's utterance makes human-computer interaction cumbersome and the user interface less natural and efficient. The techniques described in this application (including those represented by process 1500) eliminate or reduce the need for such a requirement to guide each user's utterance with a trigger phrase. Instead, the trigger word or phrase can be placed in any part of an audio stream that may include one or more user utterances. Furthermore, the techniques described in this application do not require the use of trigger phrases comprising multiple words (e.g., "Hey Siri"). A single word (e.g., "Siri") can be used to direct the audio stream, including the user's utterance, toward the virtual assistant. This makes the communication more natural. Therefore, these techniques enhance device operability and make the user-device interface more efficient; additionally, by enabling users to use the device more quickly and efficiently, this reduces power consumption and extends the device's battery life.

[0315] refer to Figure 15A At box 1502, the first audio stream is received via a microphone (e.g., as shown in the image). Figure 9 The audio stream shown (912) comprises one or more utterances. At box 1504, it is determined whether the first audio stream includes lexical triggers. In some embodiments, lexical triggers are single-word lexical triggers. In some embodiments, the first audio stream comprises a first utterance, and the single-word lexical triggers are located in the portion of the first utterance excluding the beginning portion of the first utterance. Figure 9In the example described, the word trigger (e.g., “Siri”) is located at the end of the utterance (e.g., “Turn on the light, Siri.”).

[0316] At box 1506, to determine whether the first audio stream includes word triggers, the start point of the first audio stream is detected. As an example of detecting the start point of the first audio stream, at box 1508, it is detected that there was no speech activity before the first audio stream was received. At box 1510, it is determined whether the time without speech activity before the first audio stream was received exceeds a first threshold time period. At box 1512, based on the determined time without speech activity exceeding the first threshold time period, the start point of the first audio stream is determined based on the absence of speech activity before the first audio stream was received.

[0317] At box 1514, to determine whether the first audio stream includes word triggers, the end point of the first audio stream is detected. As an example of detecting the end point of the first audio stream, at box 1516, no speech activity is detected via a microphone after receiving one or more utterances of the first audio stream. At box 1518, it is determined whether the time of no speech activity after receiving one or more utterances of the first audio stream exceeds a second threshold time period. At box 1520, based on the determination that the time of no speech activity after receiving one or more utterances of the first audio stream exceeds the second threshold time period, the end point of the first audio stream is determined based on the absence of speech activity after receiving one or more utterances of the first audio stream.

[0318] As another example of detecting the end point of the first audio stream, at box 1522, the pre-configured duration for which the electronic device is configured to receive the first audio stream is obtained. (See reference) Figure 15B At box 1524, the end point of the first audio stream is determined based on the detected start point of the first audio stream and the pre-configured duration.

[0319] As another example of detecting the end point of the first audio stream, at box 1526, the size of the audio file, representing one or more utterances of the received first audio stream, is determined. At box 1528, the size of the audio file is compared with the capacity of the buffer storing the audio file. At box 1530, the end point of the first audio stream is determined based on the result of comparing the size of the audio file with the capacity of the buffer storing the audio file. The above relates to, for example... Figure 8 and Figure 9 Various implementation schemes for detecting the start and end points of an audio stream are described in detail.

[0320] At box 1532, in order to determine whether the first audio stream includes a word trigger (e.g., “Siri”), it is determined whether the word trigger is included between the start and end points of the first audio stream.

[0321] At box 1534, based on the determined first audio stream including lexical triggers, one or more candidate text representations of one or more utterances are generated. (See above reference.) Figure 8 The candidate text representation can be generated by a natural language engine (e.g., NLE820).

[0322] At box 1536, in order to generate one or more candidate text representations, a speech-to-text conversion is performed on each of one or more utterances in the first audio stream to generate one or more candidate text representations. For example, the following can be performed: Figure 9 The audio stream 912 shown is converted from speech to text for each utterance to generate candidate text representations, including a first candidate text representation (e.g., “It’s too dark outside.”) and a second candidate text representation (e.g., “Turn on the light, Siri.”). At box 1538, a confidence level corresponding to one or more candidate text representations is determined.

[0323] refer to Figure 15C At box 1540, it is determined whether the virtual assistant should ignore at least one candidate text representation of one or more candidate text representations. At box 1542, in order to determine whether the virtual assistant should ignore at least one candidate text representation of one or more candidate text representations, it is determined whether the at least one candidate text representation includes a lexical trigger. At box 1544, based on the determination that the at least one candidate text representation does not include a lexical trigger, the probability that the utterance corresponding to the at least one candidate text representation does not refer to the virtual assistant is estimated. As described above, in Figure 9 In the example shown, the FTM of the virtual assistant operating on device 900 determines that candidate text representations (e.g., “It’s too dark outside.”) do not include lexical triggers. Furthermore, using a decision tree, the virtual assistant’s FTM can estimate the probability that a utterance corresponding to a particular first candidate text representation does not refer to the virtual assistant.

[0324] As an example of estimating the probability that a utterance corresponding to at least one candidate text representation does not refer to a virtual assistant, at box 1546, usage patterns with the virtual assistant are obtained (e.g., the frequency of asking a specific question at a specific time, such as...). Figure 10 and Figure 11A (As shown) Associated contextual information. At box 1548, based on the contextual information associated with the virtual assistant's usage patterns, the probability that a utterance corresponding to at least one candidate text representation does not refer to the virtual assistant is estimated.

[0325] As another example of estimating the probability that a utterance corresponding to at least one candidate text representation does not refer to a virtual assistant, at box 1550, sensory data (e.g., location data as described above) is acquired from one or more sensors communicatively coupled to an electronic device. At box 1552, based on the sensory data, the probability that a utterance corresponding to at least one candidate text representation does not refer to a virtual assistant is estimated.

[0326] As another example of estimating the probability that a utterance corresponding to at least one candidate text representation does not refer to a virtual assistant, it is determined how well the candidate text representation conforms to the language model (LM) and / or context-free grammar (CFG) corresponding to the recognition / valid request for a virtual assistant. For example, a candidate text representation such as “eat vegetables” may have a low degree of consistency with the LM and / or CFG, and is therefore unlikely to refer to a virtual assistant. Another candidate text representation such as “reserve a table for two” may have a high degree of consistency with the LM and / or CFG, and is therefore more likely to refer to a virtual assistant.

[0327] At box 1554, based on the estimated probability, it is determined whether the virtual assistant should ignore at least one candidate text representation of one or more candidate text representations. (As mentioned above regarding...) Figure 11A In one example, based on the context that the user frequently asks the virtual assistant about stock prices around 6 a.m. and that the current time is around 6 a.m., the virtual assistant can estimate that the probability that the utterance “Do you know what the stock price is?” does not refer to the virtual assistant is low (e.g., does not meet a threshold). Therefore, the virtual assistant determines not to ignore specific candidate text representations based on this estimated probability.

[0328] refer to Figure 15D In box 1556, based on the determined virtual assistant to ignore at least one candidate text representation, one or more candidate intents are generated based on candidate text representations of one or more candidate text representations other than the candidate text representation to be ignored. To generate candidate intents, in box 1558, one or more pre-relief intents corresponding to one or more candidate text representations of one or more utterances are obtained. In box 1560, one or more candidate intents corresponding to one or more candidate text representations other than the candidate text representation to be ignored are selected from the one or more pre-relief intents. (As mentioned above regarding...) Figure 10 As described, candidate intents can be generated by an FTM (e.g., FTM 1044).

[0329] At box 1562, it is determined whether one or more candidate intents include at least one executable intent. At box 1564, in order to determine whether one or more candidate intents include at least one executable intent, for each of the one or more candidate intents, it is determined whether the task can be executed. As described above, in some embodiments, this determination may be made by a CIE (e.g., Figure 10 The CIE 860 shown is used for execution. As an example of determining whether a task can be performed, in box 1566, context information associated with the virtual assistant's usage pattern is obtained. In box 1568, based on the context information associated with the virtual assistant's usage pattern, it is determined whether the task can be performed. (See above for reference.) Figure 11B An example of this determination based on usage patterns is shown.

[0330] As another example of determining whether a task can be performed, in box 1570, context information associated with a previous task performed by the virtual assistant is obtained. In box 1572, based on the context information associated with a previous task performed by the virtual assistant, it is determined whether the task can be performed. (See above for reference.) Figures 12A to 12D An example of this determination based on a previous task performed by a virtual assistant is shown.

[0331] refer to Figure 15E As another example of determining whether a task can be performed, in box 1574, one or more relationships between one or more candidate text representations are determined. In box 1576, it is determined whether a task can be performed based on one or more relationships in one or more candidate text representations. (Reference above) Figures 13A to 13B An example of this determination based on one or more relationships is shown.

[0332] As another example of determining whether a task can be performed, at box 1578, sensory data (e.g., location data) is acquired from one or more sensors communicatively coupled to an electronic device. At box 1580, it is determined whether a task can be performed based on the sensory data.

[0333] As another example of determining whether a task can be executed, at box 1582, the confidence level associated with executing the task is estimated. At box 1584, it is determined whether the confidence level associated with executing the task meets a threshold confidence level. At box 1586, based on the determined confidence level associated with executing the task meeting the threshold confidence level, it is determined that the task can be executed.

[0334] At box 1588, based on the determined executable tasks, one or more candidate intents are identified, including at least one executable intent. For example, as referenced above. Figure 11ABased on contextual information (e.g., usage patterns and time), the virtual assistant determines that a specific candidate intent to obtain stock prices is an executable intent.

[0335] At box 1590, at least one executable intent is executed based on one or more identified candidate intents, including at least one executable intent. At box 1592, one or more tasks are executed based on at least one executable intent.

[0336] refer to Figure 15F In order to execute at least one executable intent, at box 1594, a first task for execution is selected from multiple tasks associated with multiple executable intents. As an example of selecting the first task for execution, at box 1596, contextual information associated with the most recent task initiated by the virtual assistant is obtained (e.g., displaying a user interface for composing text messages, such as...). Figure 14B (As shown). At box 1598, the first task is selected based on contextual information associated with the previous task performed by the virtual assistant.

[0337] As an example of selecting the first task to execute, in box 1600, multiple task options corresponding to multiple tasks associated with multiple executable intentions are output. In box 1602, user selection is received from the multiple task options. In box 1604, the first task to execute is selected based on the user selection. (See above for reference.) Figure 14D This demonstrates how to select a task to perform based on user choice.

[0338] As an example of selecting the first task to be performed, in box 1606, the priority associated with each of the multiple tasks is determined. In box 1608, the first task to be performed is selected based on the priority associated with each of the multiple tasks. In box 1610, the selected first task is performed. As described above, a higher-priority task (e.g., making an emergency call) is selected instead of a lower-priority task (e.g., reporting weather information).

[0339] At box 1612, output the result of executing at least one executable intent.

[0340] refer to Figure 15G At box 1614, a second audio stream is received via a microphone when executing at least one executable intent. At box 1616, one or more second candidate text representations are generated to represent the second audio stream. At box 1618, based on one or more second candidate text representations, it is determined whether the second audio stream is part of an audio session that includes the first audio stream.

[0341] At box 1620, as an example of determining whether a second audio stream is part of an audio session that includes a first audio stream, contextual information associated with executing at least one executable intent is obtained. At box 1622, based on the contextual information associated with executing at least one executable intent, it is determined whether the second audio stream is part of an audio session that includes a first audio stream.

[0342] At box 1624, as another example of determining whether a second audio stream is part of an audio session that includes a first audio stream, a relationship between the various candidate text representations of the first and second audio streams is determined. At box 1626, based on the relationship between the various candidate text representations of the first and second audio streams, it is determined whether the second audio stream is part of an audio session that includes the first audio stream.

[0343] At box 1628, one or more second candidate intents are generated based on one or more second candidate text representations, since the second audio stream is determined to be part of an audio session that includes the first audio stream.

[0344] At box 1630, determine whether one or more second candidate intents include at least one second executable intent. At box 1632, based on the determination that one or more second candidate intents include at least one second executable intent, execute at least one second executable intent. At box 1634, output the result of executing at least one second executable intent. (Reference above) Figures 12A to 12D Described Figure 15G An example of the process is shown in the image.

[0345] For purposes of explanation, the foregoing description has been given by reference to specific embodiments. However, the illustrative discussion above is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations are possible based on the teachings above. These embodiments were chosen and described in order to best explain the principles of these techniques and their practical applications. Others skilled in the art will thus be able to best utilize these techniques and the various embodiments with various modifications suitable for the particular intended use.

[0346] While this disclosure and examples have been fully described with reference to the accompanying drawings, it should be noted that various changes and modifications will become apparent to those skilled in the art. It should be understood that such changes and modifications are considered to be included within the scope of this disclosure and examples as defined by the claims.

[0347] As described above, one aspect of this technology is to collect and use data available from various sources (e.g., contextual information associated with usage patterns of virtual assistants or devices) to improve human-computer interfaces, thereby providing more natural language interaction. This disclosure contemplates that, in some instances, such collected data may include personal information that uniquely identifies or can be used to contact or locate specific individuals. Such personal information may include demographic data, location-based data, telephone numbers, email addresses, Twitter IDs, home addresses, data or records related to a user's health or health level (e.g., vital sign measurements, medication information, exercise information), date of birth, or any other identifying information.

[0348] This disclosure recognizes that the use of such personal information data in the techniques of this invention can benefit users. For example, the personal information data can be used to deliver targeted content that is of interest to the user. Therefore, the use of such personal information data enables planned control over the delivered content. Furthermore, this disclosure also anticipates other uses of personal information data that are beneficial to the user. For example, health and fitness data can be used to provide insights into a user's overall health status or as positive feedback for individuals using technology to pursue health goals.

[0349] This disclosure also envisions that entities responsible for the collection, analysis, disclosure, transmission, storage, or other use of such personal information data will comply with established privacy policies and / or privacy practices. Specifically, such entities should implement and adhere to privacy policies and practices that are recognized as meeting or exceeding industry or governmental requirements for maintaining the privacy and security of personal information data. Such policies should be easily accessible to users and should be updated as data collection and / or use change. Personal information from users should be collected for the entity's lawful and reasonable purposes and not shared or sold outside of these lawful uses. Furthermore, such collection / sharing should only occur after the user's informed consent. Additionally, such entities should take any necessary steps to safeguard and protect access to such personal information data and ensure that others with access to such personal information data comply with their privacy policies and procedures. Furthermore, such entities may be subject to third-party evaluations to demonstrate their compliance with widely accepted privacy policies and practices. Moreover, policies and practices should be adapted to the specific types of personal information data collected and / or accessed, and to applicable laws and standards, including specific considerations regarding jurisdiction. For example, in the United States, the collection or acquisition of certain health data may be governed by federal and / or state laws, such as the Health Insurance Transfer and Accountability Act (HIPAA); while in other countries, health data may be subject to other regulations and policies and should be processed accordingly. Therefore, different privacy practices should be maintained for different types of personal data in each country.

[0350] Regardless of the foregoing, this disclosure also anticipates implementation schemes for users to selectively block the use or access to personal information data. That is, this disclosure anticipates providing hardware and / or software components to prevent or block access to such personal information data. For example, with regard to usage patterns that collect user activity, this technology can be configured to allow users to opt-in or opt-out to participate in the collection of personal information data before or during such collection. In another example, users can choose not to provide or share their activity information. In yet another example, users can choose to limit the duration for which user activity information is maintained or to completely prohibit usage patterns based on activity information. In addition to providing "opt-in" and "opt-out" options, this disclosure envisions providing notifications related to access to or use of personal information. For example, users can be notified when downloading an application that their personal information data will be accessed, and then reminded again just before the application accesses the personal information data.

[0351] Furthermore, the purpose of this disclosure is to manage and process personal information data to minimize the risk of unintentional or unauthorized access or use. Once data is no longer needed, this risk can be minimized by restricting data collection and deleting data. Additionally, and where applicable, including in certain health-related applications, data deidentification can be used to protect user privacy. Where appropriate, deidentification can be facilitated by removing specific identifiers (e.g., date of birth, etc.), controlling the amount or characteristics of stored data (e.g., collecting location data at the city level rather than address level), controlling how data is stored (e.g., aggregating data among users), and / or other methods.

[0352] Therefore, while this disclosure broadly covers the use of personal information data to implement one or more of the various disclosed embodiments, it is also contemplated that various embodiments can be implemented without access to such personal information data. That is, various embodiments of the present invention are not rendered inoperable due to the absence of all or part of such personal information data. For example, the likelihood of a user's utterance being directed toward a virtual assistant can be estimated based on non-personal information data or a minimal amount of personal information (e.g., content requested by a device associated with the user, other non-personal information available to the virtual assistant, or publicly available information).

Claims

1. A method comprising: At an electronic device (900) having one or more processors, memory, and microphones: A first audio stream is received via the microphone, the first audio stream comprising one or more utterances; Determine whether the first audio stream includes word triggers; Based on the determination that the first audio stream includes the word trigger, generate one or more candidate text representations of the one or more utterances; Based on sensory data obtained from one or more sensors of the electronic device and the usage patterns of the virtual assistant, it is determined whether the virtual assistant should ignore at least one candidate text representation of the one or more candidate text representations; Based on the determination that the virtual assistant should ignore at least one candidate text representation, one or more candidate intents are generated based on the candidate text representations of the one or more candidate text representations other than the at least one candidate text representation to be ignored; Determine whether the one or more candidate intents include at least one executable intent; If it is determined that the one or more candidate intents include at least one executable intent, then execute the at least one executable intent; Output the result of executing the at least one executable intent.

2. The method according to claim 1, wherein the lexical trigger is a single-word lexical trigger.

3. The method of claim 2, wherein the first audio stream comprises a first utterance, and wherein the lexical trigger of the single word is located in the portion of the first utterance excluding the beginning portion of the first utterance.

4. The method according to any one of claims 1 to 2, wherein determining whether the first audio stream includes word triggering comprises: Detect the start point of the first audio stream; Detect the end point of the first audio stream; as well as Determine whether a word trigger is included between the start point and the end point of the first audio stream.

5. The method of claim 4, wherein detecting the start point of the first audio stream comprises: No voice activity was detected via the microphone prior to the receipt of the first audio stream; Determine whether the time during which there was no voice activity before the first audio stream was received exceeds a first threshold time period; as well as The start point of the first audio stream is determined based on the fact that there was no voice activity for more than the first threshold time period.

6. The method of claim 4, wherein detecting the end point of the first audio stream comprises: The microphone detects that there is no speech activity after the reception of the first audio stream or the one or more utterances. Determine whether the time during which there is no speech activity after receiving the one or more utterances of the first audio stream exceeds a second threshold time period; as well as The end point of the first audio stream is determined based on the fact that there has been no speech activity for a period of time exceeding a second threshold time period after the receipt of the one or more utterances of the first audio stream.

7. The method of claim 4, wherein detecting the end point of the first audio stream comprises: Obtain the pre-configured duration, i.e., the time during which the electronic device is configured to receive the first audio stream; as well as The end point of the first audio stream is determined based on the detected start point of the first audio stream and the pre-configured duration.

8. The method of claim 4, wherein detecting the end point of the first audio stream comprises: Determine the size of the audio file, which represents one or more utterances of the received first audio stream; Compare the size of the audio file with the capacity of the buffer storing the audio file; as well as The end point of the first audio stream is determined based on the result of comparing the size of the audio file with the capacity of the buffer storing the audio file.

9. The method according to any one of claims 1 to 3 and 5 to 8, wherein the one or more utterances of the first audio stream include at least one utterance that is not directed at the virtual assistant.

10. The method according to any one of claims 1 to 3 and 5 to 8, wherein generating one or more candidate text representations of the one or more utterances comprises: Perform speech-to-text conversion on each of the one or more utterances in the first audio stream to generate the one or more candidate text representations; as well as Determine the confidence level corresponding to the one or more candidate text representations.

11. The method according to any one of claims 1 to 3 and 5 to 8, wherein determining whether the virtual assistant should ignore the at least one candidate text representation of the one or more candidate text representations comprises: Determine whether the at least one candidate text representation includes the word trigger; as well as Based on determining that the at least one candidate text representation does not include the word trigger, the probability that the utterance corresponding to the at least one candidate text representation does not refer to the virtual assistant is estimated; as well as Based on the estimated probability, determine whether the virtual assistant should ignore at least one candidate text representation of the one or more candidate text representations.

12. The method of claim 11, wherein estimating the probability that the utterance corresponding to the at least one candidate text representation does not refer to the virtual assistant comprises: Based on the time-related usage patterns of the virtual assistant, the probability that the utterance corresponding to the at least one candidate text representation does not refer to the virtual assistant is estimated.

13. The method of claim 11, wherein estimating the probability that the utterance corresponding to the at least one candidate text representation does not refer to the virtual assistant comprises: Based on the sensory data, the probability that the utterance corresponding to the at least one candidate text representation does not refer to the virtual assistant is estimated.

14. The method according to any one of claims 1 to 3, 5 to 8, and 12 to 13, wherein generating the one or more candidate intents based on the candidate text representations of the one or more candidate text representations other than the at least one candidate text representation to be ignored comprises: Obtain one or more pre-relief intentions corresponding to the one or more candidate text representations of the one or more utterances; as well as From the one or more pre-relief intentions, select the one or more candidate intentions that correspond to the one or more candidate text representations other than the at least one candidate text representation to be ignored.

15. The method according to any one of claims 1 to 3, 5 to 8, and 12 to 13, wherein determining whether the one or more candidate intents include at least one executable intent comprises: For each of the one or more candidate intents, determine whether the task can be executed; as well as Based on the determination that the task can be performed, the one or more candidate intents are determined to include at least one executable intent.

16. The method of claim 15, wherein determining whether the task can be performed comprises: Obtain contextual information associated with the usage pattern of the virtual assistant; as well as Based on the contextual information associated with the usage pattern of the virtual assistant, it is determined whether the task can be performed.

17. The method of claim 15, wherein determining whether the task can be performed comprises: Obtain context information associated with previous tasks performed by the virtual assistant; as well as Based on the context information associated with the previous task performed by the virtual assistant, it is determined whether the task can be performed.

18. The method of claim 15, wherein determining whether the task can be performed comprises: Determine one or more relationships between the candidate text representations; Determine whether the task can be performed based on the one or more relationships between the one or more candidate text representations.

19. The method of claim 15, wherein determining whether the task can be performed comprises: Sensory data is acquired from one or more sensors communicatively coupled to the electronic device; as well as Determine whether the task can be performed based on the sensory data.

20. The method of claim 15, wherein determining whether the task can be performed comprises: Estimate the confidence level associated with performing the task; Determine whether the confidence level associated with performing the task meets a threshold confidence level; as well as The task is determined to be executable based on the confidence level associated with performing the task meeting the threshold confidence level.

21. The method according to any one of claims 1 to 3, 5 to 8, 12 to 13, and 16 to 20, wherein performing the at least one executable intent comprises: Perform one or more tasks according to the at least one executable intent.

22. The method according to any one of claims 1 to 3, 5 to 8, 12 to 13, and 16 to 20, wherein the one or more candidate intentions comprise a plurality of executable intentions, and wherein executing the at least one executable intention comprises: Select a first task to be executed from among the multiple tasks associated with the multiple executable intentions; as well as Perform the selected first task.

23. The method of claim 22, wherein selecting the first task for execution from the plurality of tasks associated with the plurality of executable intentions comprises: Obtain context information associated with the latest task initiated by the virtual assistant; as well as The first task is selected based on the contextual information associated with a previous task performed by the virtual assistant.

24. The method of claim 22, wherein selecting the first task for execution from the plurality of tasks associated with the plurality of executable intentions comprises: The output corresponds to multiple task options for the multiple tasks associated with the multiple executable intentions; Receive user selections from the multiple task options; as well as The first task is selected based on the user's choice.

25. The method of claim 22, wherein selecting the first task for execution from the plurality of tasks associated with the plurality of executable intentions comprises: Determine the priority associated with each of the plurality of tasks; as well as The first task to be performed is selected based on the priority associated with each of the plurality of tasks.

26. The method according to any one of claims 1 to 3, 5 to 8, 12 to 13, 16 to 20, and 23 to 25, wherein the one or more procedures further include instructions for performing the following operations: When performing the at least one executable intent, a second audio stream is received via the microphone; Generate one or more second candidate text representations to represent the second audio stream; Based on the one or more second candidate text representations, determine whether the second audio stream is part of an audio session that includes the first audio stream; Based on the determination that the second audio stream is part of the audio session including the first audio stream, one or more second candidate intents are generated based on the one or more second candidate text representations; Determine whether the one or more second candidate intents include at least one second executable intent; Execute the at least one second executable intent if it is determined that the one or more second candidate intents include at least one second executable intent; as well as Output the result of executing the at least one second executable intent.

27. The method of claim 26, wherein determining whether the second audio stream is part of the audio session including the first audio stream comprises: Obtain context information associated with executing the at least one executable intent; as well as Based on the context information associated with executing the at least one executable intent, it is determined whether the second audio stream is part of the audio session that includes the first audio stream.

28. The method of claim 26, wherein determining whether the second audio stream is part of the audio session including the first audio stream comprises: Determine the relationship between the candidate text representations of the first audio stream and the second audio stream; as well as Based on the relationship between the candidate text representations of the first audio stream and the second audio stream, it is determined whether the second audio stream is part of the audio session that includes the first audio stream.

29. The method according to any one of claims 1 to 3, 5 to 8, 12 to 13, 16 to 20, 23 to 25 and 27 to 28, wherein the usage pattern of the virtual assistant is associated with the time of day.

30. An electronic device (900), comprising: One or more processors; Memory; as well as One or more programs are stored in the memory, the one or more programs including instructions for performing the method according to any one of claims 1 to 29.

31. A computer-readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, said one or more programs including instructions, when executed by said one or more processors, to cause the electronic device to perform the method according to any one of claims 1 to 29.

Images