Method for a voice-activable device and corresponding device, device and vehicle

Abstract

The invention provides a method for voice-activatable equipment, a corresponding device, equipment and a vehicle. The method comprises the following steps: identifying vocabularies contained in voice input from a user, and judging whether the vocabularies comprise one wakeup word in a plurality of preset wakeup words or not; and when the judgment result is positive, activating the voice-activatable device by using an activation permission associated with the wake-up word so as to allow to start a function, corresponding to the activation permission, of the voice-activatable device, the plurality of wake-up words including a main wake-up word and an auxiliary wake-up word, and the auxiliary wake-up word including the main wake-up word and the auxiliary wake-up word. The activation permission associated with the main wake-up word is higher than the activation permission associated with the auxiliary wake-up word. Through authority isolation of the main wake-up word and the auxiliary wake-up word, the voice-activatable device can be activated and started more flexibly according to needs, and the more intelligent voice-activatable device is provided.

Description

Technical Field

[0001] The present invention relates to voice activation of devices, and more particularly to methods and apparatus for voice-activatable devices and corresponding voice-activatable devices, vehicles, computer devices, and non-transitory computer-readable storage media. Background Art

[0002] Smart devices based on voice interaction have become more and more popular. For example, they can be applied to fields such as vehicles, and can be household appliances, mobile phones, computers, etc. Before a user interacts with a smart device based on voice interaction, voice wake-up is usually involved. Specifically, before a user interacts with a smart device based on voice interaction, it is necessary to first wake up the smart device with voice to make it enter the working state from the sleep state so that it can process the user's subsequent voice commands. Generally, making the smart device change from the sleep state to the working state can be called wake-up.

[0003] At present, digital assistants (DAs) are one of the mainstream components of vehicles. Now, DAs are becoming more and more popular in vehicles of various brands and are becoming more and more intelligent. For example, DAs can understand the instructions of drivers / passengers and provide them with assistance in navigation, vehicle control, information query, making / receiving calls, sending messages, etc. Figure 1 An example of a DA applied to a vehicle on the market is shown. Typically, voice is the primary means of interaction between a user in a vehicle and a DA. In addition, gestures and facial expressions can be secondary means of interaction. With the support of artificial intelligence, the DA can receive the user's voice, analyze its semantic content, and then perform corresponding operations. In order to avoid misoperation, maintain a high recognition rate, or keep voice that is not recognized as just chatting rather than for commanding the DA, a wake-up word needs to be set so that the DA must be woken up first, and then the DA can receive and recognize subsequent voice commands.

[0004] Currently, most DAs are awakened by only one wake-up word. Each user can wake up the DA by the wake-up word, and the DA can then execute the user's subsequent voice instructions.

[0005] Some existing technologies have achieved the coexistence of multiple wake-up words in a voice-activated device to wake up the device, but these existing technologies do not involve the permission isolation of wake-up words. Taking Baidu DA as an example, 10 wake-up words can be set for it, including predefined wake-up words and custom wake-up words - up to 3 can be set, but these wake-up words have no permission isolation and can wake up Baidu DA equally so that all its functions can be activated by voice afterwards. Summary of the invention

[0006] An object of the present invention is to provide an improved voice wake-up and activation solution to solve or at least alleviate at least part of the above-mentioned problems in the prior art.

[0007] To this end, in a first aspect, the present invention provides a method for a voice-activatable device, the method comprising:

[0008] Identifying words contained in the voice input from the user, and determining whether the words include one of a plurality of preset wake-up words; and,

[0009] If the result of the determination is positive, activating the voice-activatable device with the activation permission associated with the one wake-up word to allow the function of the voice-activatable device corresponding to the activation permission to be enabled,

[0010] The multiple wake-up words include a primary wake-up word and a secondary wake-up word, and the activation permission associated with the primary wake-up word is higher than the activation permission associated with the secondary wake-up word.

[0011] In a second aspect, the present invention provides an apparatus for a voice-activatable device, the apparatus comprising:

[0012] a speech processing unit configured to: identify words contained in a speech input from a user, and determine whether the words include a wake-up word among a plurality of preset wake-up words; and

[0013] an activation management unit configured to: in a positive case, activate the voice-activatable device with the activation permission associated with the one wake-up word to allow the function of the voice-activatable device corresponding to the activation permission to be enabled,

[0014] The multiple wake-up words include a primary wake-up word and a secondary wake-up word, and the activation permission associated with the primary wake-up word is higher than the activation permission associated with the secondary wake-up word.

[0015] In a third aspect, the present invention provides a voice-activated device, the device comprising the apparatus according to the second aspect of the present invention.

[0016] In a fourth aspect, the present invention provides a vehicle comprising the voice-activatable device of the third aspect of the present invention.

[0017] In a fifth aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the method described in the first aspect of the present invention is executed.

[0018] In a sixth aspect, the present invention provides a non-transitory computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, cause the method described in the first aspect of the present invention to be executed.

[0019] According to the technical solution of the present invention, by using the main wake-up word and the secondary wake-up word corresponding to different activation permissions, the voice-activated device can be activated with the activation permission corresponding to each wake-up word, thereby realizing permission isolation based on the wake-up word, so that the voice-activated device can be activated and enabled more flexibly as needed, providing a smarter voice-activated device. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Non-limiting and non-exhaustive embodiments of the present invention are described, by way of example, with reference to the following drawings, in which:

[0021] Figure 1 An example of DA applied to vehicles on the market is shown;

[0022] Figure 2 A flow chart showing a method for a voice-activatable device according to an embodiment of the present invention is shown;

[0023] Figure 3 A schematic block diagram of a voice-activatable device according to an embodiment of the present invention is shown; and

[0024] Figure 4 Relevant components of a voice-activated device and in-vehicle applications according to an embodiment of the present invention are shown. DETAILED DESCRIPTION

[0025] In order to make the above and other features and advantages of the present invention clearer, the present invention is further described below in conjunction with the accompanying drawings. The accompanying drawings constitute a part of this application and are used to illustrate the present invention together with the embodiments of the present invention. For the purpose of clarity and simplification, detailed specific descriptions of known functions and structures of the devices, devices and / or equipment described herein will be omitted when they may obscure the subject matter of the present invention. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are only exemplary and non-restrictive.

[0026] The features described herein may be embodied in different forms and should not be construed as being limited to the embodiments described herein. Rather, the embodiments described herein are provided only to illustrate some of the many possible ways of implementing the devices and / or systems described herein, which will be apparent after understanding the disclosure of the present application.

[0027] As used herein, the term "and / or" includes any one of the associated listed items and any combination of any two or more of the associated listed items.

[0028] Although terms such as "first," "second," "third," and "fourth" may be used herein to describe various components, parts, portions, or elements, these components, parts, portions, or elements are not limited by these terms. Instead, these terms are only used to distinguish one component, part, portion, or element from another component, part, portion, or element. Therefore, without departing from the teachings of the present invention, a first component, part, portion, or element mentioned herein may also be referred to as a second component, part, portion, or element.

[0029] The terms used herein are only used to describe various embodiments and are not used to limit the present disclosure. Unless the context clearly indicates otherwise, "a", "an" and "the" are intended to include plural forms as well. The terms "include", "comprise" and "have" specify the presence of stated features, operations, components, elements and / or combinations thereof, but do not exclude the presence or addition of one or more other features, operations, components, elements and / or combinations thereof.

[0030] In the following description, many specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that the present invention does not need to be practiced using the specific details. In other cases, well-known steps or operations are not described in detail to avoid obscuring the present invention.

[0031] The basic concept of the present invention is to creatively implement permission isolation through multiple wake-up words so that voice-activated devices can be activated with activation permissions corresponding to each wake-up word. The voice-activated devices can be various intelligent devices based on voice interaction, such as home appliances, mobile phones, computer devices, etc., and can be applied to many fields such as vehicles.

[0032] The present invention is described below by way of example only with reference to the accompanying drawings.

[0033] Figure 2 The flowchart of a method 200 for a voice-activated device according to an embodiment of the present invention is schematically shown. The method 200 comprises steps S201 and S202.

[0034] In step S201, the vocabulary contained in the voice input from the user is identified, and it is determined whether the vocabulary includes one of the preset multiple wake-up words. This identification and judgment operation can be performed in various suitable ways, which are not described here. For example, determining whether the vocabulary includes one of the preset multiple wake-up words may include comparing the vocabulary with the multiple wake-up words. If the comparison result shows that there is a vocabulary that is the same as or matches one of the multiple wake-up words, the judgment result is affirmative; otherwise, the judgment result is negative.

[0035] In step S202, when the judgment result in step S201 is affirmative, the voice-activatable device is activated with the activation permission associated with the one wake-up word to allow the function of the voice-activatable device corresponding to the activation permission to be enabled.

[0036] According to the present invention, the preset multiple wake-up words include a main wake-up word and a secondary wake-up word, and the activation authority associated with the main wake-up word is higher than the activation authority associated with the secondary wake-up word.

[0037] In one embodiment, the primary wake-up word is associated with a primary activation permission, and the functions corresponding to the primary activation permission include all functions of the voice-activatable device, and the secondary wake-up word is associated with a secondary activation permission, and the functions corresponding to the secondary activation permission include a portion of the functions of the voice-activatable device.

[0038] In one embodiment, the voice-activatable device is a device for a vehicle. In this case, the primary activation authority may correspond to the authority of the driver of the vehicle (e.g., authority for operations related to vehicle driving), and the secondary activation authority may correspond to the authority of the occupant of the vehicle (e.g., authority for operations other than operations related to vehicle driving).

[0039] It is advantageous to implement permission isolation through primary and secondary wake-up words. For example, when a voice-activated device is used in a vehicle, the user of the vehicle can use an appropriate wake-up word to activate the voice-activated device according to his or her current identity in the vehicle (driver or passenger) to enable functions or applications corresponding to his or her current identity and / or to change the parameters of functions and applications corresponding to his or her current identity. As a result, voice-activated devices can be smarter and can be used more flexibly, while creating conditions for preventing non-drivers from affecting vehicle driving and taking driving safety into consideration.

[0040] In one embodiment, multiple secondary wake-up words can be preset. Depending on the situation, the activation permissions associated with each secondary wake-up word can be the same, for example, to provide users of voice-activated devices with more choices in the selection of wake-up words, thereby providing users with a more interesting and flexible use experience; or, the activation permissions associated with each secondary wake-up word can be different, for example, to facilitate users of voice-activated devices to select appropriate wake-up words in a targeted manner according to the device functions they expect to use. In the case where the voice-activated device is used in a vehicle, presetting multiple secondary wake-up words helps provide users with a more comfortable and interesting travel experience.

[0041] It is contemplated that the method for a voice-activatable device of the present invention may include other possible steps. In one embodiment, the method includes receiving a subsequent voice instruction from the user after step S202. The subsequent voice instruction may be an instruction to instruct the activation of a function of the voice-activatable device. If the function instructed to be enabled is within the activation permissions associated with the wake-up word used by the user to activate the device, that is, in the list of functions corresponding to the activation permissions, then in response to receiving the subsequent voice instruction, the function of the device is enabled; otherwise, the function of the device will not be enabled-in this case, feedback may optionally be provided to the user to indicate that the function instructed to be enabled exceeds the activation permissions.

[0042] The speech from the user, such as any of the above-mentioned voice input and subsequent voice commands, can be received via a voice receiving component suitable for receiving voice information inside or outside the voice-activated device. The voice receiving component can be, for example, a built-in microphone of the voice-activated device or a microphone communicatively coupled to the voice-activated device.

[0043] Additionally, the feedback may be in various possible forms, such as visual feedback suitable for display via a display device inside or outside the voice-activated device or auditory feedback suitable for providing via a voice output component inside or outside the voice-activated device.

[0044] Figure 3 A schematic block diagram of a voice-activatable device 300 according to an embodiment of the present invention is shown. The voice-activatable device 300 comprises an apparatus 301 for the voice-activatable device 300. The apparatus 301 comprises a voice processing unit 302 and an activation management unit 303.

[0045] The voice processing unit 302 is configured to identify words contained in the voice input from the user, and determine whether the words include one of the preset multiple wake-up words.

[0046] The activation management unit 303 is configured to: when the judgment result of the voice processing unit 302 is affirmative, activate the voice-activatable device with the activation permission associated with the one wake-up word to allow the function of the voice-activatable device corresponding to the activation permission to be enabled.

[0047] According to the present invention, the preset multiple wake-up words include a main wake-up word and a secondary wake-up word, and the activation authority associated with the main wake-up word is higher than the activation authority associated with the secondary wake-up word.

[0048] Depending on circumstances, the voice processing unit 302 may be configured to perform other desired functions; however, it is possible that the other desired functions are implemented by separate units or modules.

[0049] In one embodiment, the voice processing unit 302 may include a wake-up word recognition module (not shown) and a subsequent voice command recognition module (not shown).

[0050] The wake-up word recognition module can be a small module with low power consumption and configured to be always running with a voice recognition function. Specifically, the wake-up word recognition module of the voice processing unit 302 is configured to recognize the vocabulary contained in the voice input from the user. The wake-up word recognition module of the voice processing unit 302 is also configured to determine whether the vocabulary includes one of the preset multiple wake-up words.

[0051] The subsequent voice instruction recognition module may be another voice recognition module having a voice recognition function. The subsequent voice instruction recognition module is configured to recognize subsequent voice instructions from a user after the voice-activatable device 300 is activated.

[0052] Depending on the circumstances, the activation management unit 303 may be configured to perform other desired functions, such as functions related to wake-up word / activation permission management; however, it is possible for the other desired functions to be implemented by separate units or modules.

[0053] In one embodiment, the activation management unit 303 is configured to receive user input and perform corresponding functions in response thereto. For example, the user input may be an input indicating the addition / deletion of a wake-up word; in this case, in response to receiving the user input, the activation management unit 303 may add / delete the wake-up word accordingly, thereby implementing the management of the wake-up word. For another example, the user input may indicate an activation permission associated with a certain wake-up word; in this case, in response to receiving the user input, the activation management unit 303 may associate the wake-up word with the indicated activation permission accordingly, thereby implementing the management of the activation permission.

[0054] Figure 4The relevant components and related applications of a voice-activated device according to an embodiment of the present invention are shown. In this embodiment, the voice-activated device is a DA for a vehicle.

[0055] exist Figure 4 The voice processing unit and activation management unit of the DA, as well as related in-vehicle applications (such as media, navigation, vehicle control, information query, making / receiving calls, sending messages, etc.) are shown. The driver / passenger can use a wake-up word to activate the DA. The wake-up word can be one of multiple preset wake-up words. After the DA is activated, the driver / passenger can use subsequent voice commands to enable the function corresponding to the activation permission associated with the wake-up word, such as media, navigation, vehicle control, information query, making / receiving calls, sending messages, etc. The preset multiple wake-up words can be stored in advance in a memory inside or outside the DA so that they can be called by the voice processing unit and activation management unit of the DA when needed.

[0056] For example, in Figure 4 A primary wake-up word and a secondary wake-up word are shown in the figure. The primary wake-up word is set to be associated with the primary activation permission, and the functions corresponding to the primary activation permission include all functions of the DA. In addition, the secondary wake-up word is set to be associated with the secondary activation permission, and the functions corresponding to the secondary activation permission include some functions of the DA. After the voice processing unit of the DA recognizes the primary wake-up word, the activation management unit of the DA activates the DA with the primary activation permission associated with the primary wake-up word to allow all functions of the DA to be enabled (i.e., with permission to execute all functions). After the voice processing unit of the DA recognizes the secondary wake-up word, the activation management unit of the DA activates the DA with the secondary activation permission associated with the secondary wake-up word to allow some functions of the DA to be enabled (i.e., with permission to execute some functions).

[0057] Figure 4 Also shown are some other operations that can be performed through the DA's activation management unit, such as adding / deleting wake-up words, presetting function permissions, etc.

[0058] The specific features, operations and details described above with respect to the method for a voice-activated device of the present invention may also be similarly applied to the apparatus for a voice-activated device of the present invention, or vice versa. In addition, each step of the method of the present invention described above may be performed by a corresponding component or unit of the apparatus of the present invention.

[0059] It should be understood that the various units of the voice-activated device of the present invention can be implemented by software, hardware, firmware or a combination thereof. The various units can be embedded in the processor of the computer device in the form of hardware or firmware or independent of the processor, or can be stored in the memory of the computer device in the form of software for the processor to call to perform the operation of the various units. The various units can each be implemented as an independent component or module, or two or more units can be implemented as a single component or module.

[0060] It should be understood by those skilled in the art that Figure 3 and Figure 4 The schematic diagrams of the voice-activatable device shown in the figure are merely exemplary block diagrams of partial structures related to the scheme of the present invention, and do not constitute limitations on the computer device, processor or computer program embodying the scheme of the present invention. A specific computer device, processor or computer program may include more or fewer components or modules than shown in the figure, or combine or split certain components or modules, or have different arrangements of components or modules.

[0061] In one embodiment, a computer device is provided, which includes a memory and a processor, and a computer instruction is stored on the memory, and the computer instruction causes the method of the present invention to be executed when executed by the processor. The computer device can be broadly a server, a vehicle terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected by a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory can provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, each step of the method for a voice-activated device of the present invention is performed.

[0062] The present invention can be implemented as a non-transitory computer-readable storage medium having computer instructions stored thereon, which cause the method of the present invention to be executed when executed by a processor. In one embodiment, the computer program is distributed on a plurality of computer devices or processors coupled to a network so that the computer program is stored, accessed and executed in a distributed manner by one or more computer devices or processors. One or more method steps / operations can be performed by one or more computer devices or processors, and one or more other method steps / operations can be performed by one or more other computer devices or processors. One or more computer devices or processors can perform a single method step / operation, or perform two or more method steps / operations.

[0063] It will be appreciated by those skilled in the art that all or part of the steps of the method for a voice-activated device of the present invention may be performed by a computer program to instruct related hardware such as a computer device or a processor, and the computer program may be stored in a non-transitory computer-readable storage medium, and when the computer program is executed, the steps of the method for a voice-activated device of the present invention are performed. Depending on the circumstances, any reference to memory, storage, database or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magnetic storage device, optical storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0064] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

Claims

1. A method for a voice-activatable device, comprising: Identify words contained in the voice input from the user, and determine whether the words include one of a plurality of preset wake-up words; as well as, If the result of the determination is positive, activating the voice-activatable device with the activation permission associated with the one wake-up word to allow the function of the voice-activatable device corresponding to the activation permission to be enabled, The multiple wake-up words include a primary wake-up word and a secondary wake-up word, and the activation permission associated with the primary wake-up word is higher than the activation permission associated with the secondary wake-up word.

2. The method according to claim 1, wherein: The multiple wake-up words include multiple secondary wake-up words, and the activation authority associated with each of the secondary wake-up words is the same.

3. The method according to claim 1, wherein: The primary wake-up word is associated with a primary activation permission, and the functions corresponding to the primary activation permission include all functions of the voice-activatable device; and The secondary wake-up word is associated with a secondary activation permission, and a function corresponding to the secondary activation permission includes a portion of a function of the voice-activatable device.

4. The method according to any one of claims 1 to 3, wherein: The voice-activatable device includes a digital assistant for a vehicle.

5. The method according to claim 3, wherein: The voice-activatable device is for a vehicle, the primary activation authority corresponds to an authority of a driver of the vehicle, and the secondary activation authority corresponds to an authority of an occupant of the vehicle.

6. An apparatus for a voice-activatable device, comprising: a speech processing unit configured to: identify words contained in a speech input from a user, and determine whether the words include a wake-up word among a plurality of preset wake-up words; and an activation management unit configured to: in a positive case, activate the voice-activatable device with the activation permission associated with the one wake-up word to allow the function of the voice-activatable device corresponding to the activation permission to be enabled, The multiple wake-up words include a primary wake-up word and a secondary wake-up word, and the activation permission associated with the primary wake-up word is higher than the activation permission associated with the secondary wake-up word.

7. The device according to claim 6, wherein: The multiple wake-up words include multiple secondary wake-up words, and the activation authority associated with each of the secondary wake-up words is the same.

8. The device according to claim 6, wherein: The primary wake-up word is associated with a primary activation permission, and the functions corresponding to the primary activation permission include all functions of the voice-activatable device. The secondary wake-up word is associated with a secondary activation permission, and a function corresponding to the secondary activation permission includes a portion of a function of the voice-activatable device.

9. The device according to any one of claims 6 to 8, wherein: The voice-activatable device includes a digital assistant for a vehicle.

10. A voice-activated device comprising the apparatus according to any one of claims 6-9.

11. A vehicle comprising a voice-activatable device according to claim 10.

12. A computer device comprising a memory and a processor, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the method according to any one of claims 1 to 5 is executed.

13. A non-transitory computer-readable storage medium having computer instructions stored thereon, which when executed by a processor cause the method according to any one of claims 1 to 5 to be performed.

Images