WO2020224346A1

WO2020224346A1 - Control device and operation method therefor, and speech interaction device and operation method therefor

Info

Publication number: WO2020224346A1
Application number: PCT/CN2020/081165
Authority: WO
Inventors: 汤跃忠
Original assignee: 北京京东尚科信息技术有限公司; 北京京东世纪贸易有限公司
Priority date: 2019-05-09
Filing date: 2020-03-25
Publication date: 2020-11-12
Also published as: CN111754997A; CN111754997B

Abstract

The present disclosure provides a control device and an operation method therefor, and a speech interaction device and an operation method therefor. The operation method for the control device comprises: receiving multiple pieces of parameter information sent by multiple speech interaction devices respectively, the multiple pieces of parameter information being sent by the multiple speech interaction devices when a first speech input from a user at the same moment is acquired; determining demand information of the user according to the first speech input; according to the multiple pieces of parameter information and the demand information, determining that a first speech interaction device among the multiple speech interaction devices is the device interacting with the user; and sending a wake-up instruction to the first speech interaction device, and sending a non-wake-up instruction to the speech interaction devices among the multiple speech interaction devices except the first speech interaction device. The first speech input comprises a predetermined speech input and a speech input which characterizes a demand of the user.

Description

Control device and operation method thereof, and voice interaction device and operation method thereof

This application claims the priority of the Chinese patent application CN201910388450.5 filed on May 9, 2019, the content of which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of Internet technology, and more specifically, to a control device and an operation method thereof, and a voice interaction device and an operation method thereof.

Background technique

With the rapid development of Internet technology and computer technology, voice interaction technology has emerged to free hands and improve the efficiency of interaction between users and electronic devices.

In the process of realizing the concept of the present disclosure, the inventor found that there are at least the following problems in the prior art: With the popularization of intelligence and IoT technologies, modern homes are often equipped with multiple voice interaction devices that can interact with users. And in order to realize the so-called management of multiple voice interaction devices, the multiple voice interaction devices often originate from the same supplier, so the multiple voice interaction devices have the same wake-up language, then when the multiple voice interaction devices are closer At this time, the multiple voice interaction devices are often awakened in response to the wake-up words sent by the user at the same time, and when the user performs voice interaction with the voice interaction device, the multiple voice interaction devices often respond at the same time, which undoubtedly makes The interactive scene is noisy and chaotic, which reduces the user experience.

Summary of the invention

In view of this, the present disclosure provides a control device and an operation method thereof, and a voice interaction device and an operation method thereof that can improve the interactive experience.

A first aspect of the present disclosure provides an operating method of a control device, the method includes: receiving multiple parameter information sent by multiple voice interaction devices, and the multiple parameter information is collected by the multiple voice interaction devices. It is sent when the user's first voice input at the same time; according to the first voice input, the user's demand information is determined; according to the multiple parameter information and the demand information, the multiple voices are determined The first voice interaction device in the interaction device is a device that interacts with the user; and sends a wake-up instruction to the first voice interaction device, and sends a wake-up instruction to the plurality of voice interaction devices except for the first voice interaction device The other voice interaction device in the sends a non-wake-up instruction, wherein the first voice input includes a predetermined voice input and a voice input that characterizes the needs of the user.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes performance parameters of the voice interaction device, and the determining the first voice interaction device according to the multiple parameter information and the demand information includes: The matching relationship between the performance parameters of each voice device in the device and the demand information determines the first voice interaction device.

According to an embodiment of the present disclosure, the above-mentioned parameter information further includes location information of the user, and the first step is determined based on the matching relationship between the performance parameter of each voice device in the plurality of voice interaction devices and the demand information. A voice interaction device includes: at least one second voice interaction device that determines that the performance parameters of the multiple voice interaction devices match the user's demand information; and according to the parameter information sent by the at least one second voice interaction device It is determined that one of the at least one second voice interaction device is the first voice interaction device, wherein the location information of the user characterizes the location of the user relative to the voice interaction device.

According to an embodiment of the present disclosure, the aforementioned parameter information includes operation information of a voice interaction device, the non-wake-up instruction includes a sleep instruction and a hibernation instruction, and the sending a non-wake-up instruction to the other voice interaction device includes: according to the other voice The operation information of the interaction device, determining whether the other voice interaction device performs the first operation when collecting the first voice input; and sending the sleep instruction to the other voice interaction device performing the first operation, The other voice interaction device of the first operation sends the sleep instruction, wherein the voice interaction device is in a sleep state in response to the sleep instruction, and the sleep state includes performing the first operation and responding to the collected user A state in which voice input does not respond; the voice interaction device is in a dormant state in response to the dormant instruction, and the dormant state includes a state in which no operation is performed.

According to an embodiment of the present disclosure, the above method further includes: receiving first voice information sent by the first voice interaction device when the user's second voice input is collected, and the first voice information is related to the Corresponding to the second voice input; determine whether the first voice information is general voice information; and if the first voice information is the general voice information, send the first voice information to the multiple voice interaction devices One voice message.

According to an embodiment of the present disclosure, the above method further includes: receiving a recovery request sent by the first voice interaction device, the recovery request being collected by the first voice interaction device after the user’s third voice input or preview Suppose it is sent when the user’s voice input is not collected within a time period; and a restoration instruction is sent to the multiple voice interaction devices, so that the multiple voice interaction devices are restored to the time before collecting the first voice input status.

According to an embodiment of the present disclosure, after sending a wake-up instruction to the first voice interaction device, the above method further includes: monitoring the operation of the first voice interaction device, and determining whether the first voice interaction device performs a third operation In the case where the first voice interaction device performs the third operation, sending a synchronization request to the first voice interaction device; and receiving the first voice interaction device sent in response to the synchronization request The execution progress information of the third operation.

According to an embodiment of the present disclosure, the above method further includes: in a case where at least one parameter information respectively sent by at least one voice interaction device among the multiple voice interaction devices is received again, re-determining the first voice interaction device; The acquisition request sent by the re-determined first voice interaction device under the condition that the user’s fourth voice input is collected; and in response to the re-determined acquisition request of the first voice interaction device, The re-determined first voice interaction device sends the execution progress information.

The second aspect of the present disclosure provides an operation method of a voice interaction device. The method includes: when the user's first voice input is collected, sending parameter information to the control device to determine whether the voice interaction device is the first voice interaction device; when the voice interaction device is the first voice interaction device In the case of the device, the wake-up instruction sent by the control device is received, in response to the wake-up instruction being in the wake-up state; in the case that the voice interaction device is not the first voice interaction device, the non-received instruction sent by the control device is received. The wake-up instruction is in a non-wake-up state in response to the non-wake-up instruction, wherein the first voice input includes a predetermined voice input and a voice input that represents the user's needs.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes performance parameters of the voice interaction device, and before sending the parameter information to the control device, the above-mentioned method further includes: acquiring the performance parameters.

According to an embodiment of the present disclosure, the above-mentioned parameter information further includes location information of the user. Before sending the parameter information to the control device, the method further includes: determining the user according to the collected first voice input of the user The location information of the user, wherein the location information of the user represents the location of the user relative to the voice interaction device.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes operation information of the voice interaction device, and the non-wake-up instruction includes a sleep instruction and a hibernation instruction, wherein: when the operation information indicates that the voice interaction device performs the first operation , The received non-wake-up instruction is the sleep instruction, in response to the sleep instruction being in a sleep state, the sleep state includes a state in which the first operation is performed and the collected voice input of the user is not responded; In the case where the operation information indicates that the voice interaction device has not performed the first operation, the received non-wake-up instruction is the sleep instruction, in response to the sleep instruction being in the sleep state, the sleep state includes The state of not performing any operations.

According to an embodiment of the present disclosure, after the voice interaction device is switched to the awake state, the above method further includes: collecting the user's voice input in real time; in the case of collecting the user's second voice input, determining the second voice input corresponding to the second voice input. 2. Whether the voice information is general voice information; and in the case of determining that the second voice information corresponding to the second voice input is general voice information, sending the second voice information to the control device, so that the control device sends the second voice information to multiple The voice interaction device enables multiple voice interaction devices to perform operations corresponding to the second voice information.

According to an embodiment of the present disclosure, the above method further includes: determining the first voice information corresponding to the second voice input when the voice interaction device is in an awake state and the second voice input of the user is collected Whether it is general voice information; and if it is determined that the first voice information is general voice information, sending the first voice information to the control device. And/or the above method further includes: receiving second voice information belonging to the general voice information sent by the control device; and executing a second operation according to the second voice information, and the second operation is the same as the first 2. The voice input corresponds to the voice information.

According to an embodiment of the present disclosure, the above method further includes: when the voice interaction device is in an awake state and the user's third voice input is collected or the user's voice input is not collected within a preset time period, Sending a restoration request to the control device; and/or, the above method further includes: receiving a restoration instruction sent by the control device, and switching the current state to a state before the first voice input is collected.

According to an embodiment of the present disclosure, the above method further includes: when the voice interaction device is in an awake state and a third operation is performed, in response to a synchronization request sent by the control device, sending the control device The execution progress information of the third operation.

According to an embodiment of the present disclosure, the above method further includes: when the voice interaction device is in an awake state and a fourth voice input of the user is collected, sending an acquisition request to the control device; receiving the control The apparatus sends the execution progress information in response to the acquisition request; and executes the third operation according to the execution progress information, wherein the third operation corresponds to the fourth voice input.

A third aspect of the present disclosure provides a control device. The device includes: a parameter information receiving module, configured to receive multiple parameter information sent by multiple voice interaction devices, and the multiple parameter information is the multiple voice The interaction device sends the first voice input of the user at the same time; the demand information determination module is used to determine the demand information of the user according to the first voice input; the first device determination module is used to According to the multiple parameter information and the demand information, it is determined that the first voice interaction device among the multiple voice interaction devices is the device that interacts with the user; and the instruction sending module is configured to send the first voice The interaction device sends a wake-up instruction, and sends a non-wake-up instruction to voice interaction devices other than the first voice interaction device among the multiple voice interaction devices, wherein the first voice input includes a predetermined voice input and a characterizing Voice input that describes user needs.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes performance parameters of a voice interaction device, and the first device determining module is specifically configured to: according to the performance parameters of each voice device in the plurality of voice interaction devices and the demand information To determine the first voice interaction device.

According to an embodiment of the present disclosure, the above-mentioned parameter information further includes location information of the user, and the first device determining module includes: a first determining sub-module configured to determine the performance parameters of the multiple voice interaction devices and the At least one second voice interaction device that matches the user’s demand information; and a second determining submodule, configured to determine the at least one first voice interaction device according to the user’s location information in the parameter information sent by the at least one second voice interaction device One of the two voice interaction devices is the first voice interaction device, wherein the location information of the user represents the location of the user relative to the voice interaction device.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes operation information of the voice interaction device, the non-wake-up instruction includes a sleep instruction and a sleep instruction, and the instruction sending module includes: an operation determination sub-module for interacting according to the other voice The operation information of the device determines whether the other voice interaction device performs the first operation when collecting the first voice input; and the instruction sending sub-module is configured to send the other voice interaction device that performs the first operation A sleep instruction to send the sleep instruction to other voice interaction devices that have not performed the first operation, wherein the voice interaction device is in a sleep state in response to the sleep instruction, and the sleep state includes performing the first operation and The collected voice input of the user is not responding; the voice interaction device is in a sleep state in response to the sleep instruction, and the sleep state includes a state where no operation is performed.

According to an embodiment of the present disclosure, the above-mentioned control device further includes a first voice information receiving module, configured to receive the first voice information sent by the first voice interaction device when the second voice input of the user is collected, The first voice information corresponds to the second voice input; a first voice information determining module is used to determine whether the first voice information is general voice information; and a first voice information sending module is used to If the first voice information is the general voice information, sending the first voice information to the multiple voice interaction apparatuses.

According to an embodiment of the present disclosure, the above-mentioned control device further includes: a recovery request receiving module that receives a recovery request sent by the first voice interaction device, and the recovery request is collected by the first voice interaction device after collecting The third voice input or sending when the user's voice input is not collected within a preset time period; and the instruction sending module is also used for: when the recovery request receiving module receives the recovery request, Sending a recovery instruction to the multiple voice interaction devices to restore the multiple voice interaction devices to a state before collecting the first voice input.

According to an embodiment of the present disclosure, the above-mentioned control device further includes: an operation monitoring module, configured to monitor the operation performed by the first voice interaction device after the instruction sending module sends the wake-up instruction, and determine the first Whether the voice interaction device performs the third operation; a synchronization request sending module, configured to send a synchronization request to the first voice interaction device when it is determined that the first voice interaction device performs the third operation; and The progress information receiving module is configured to receive the execution progress information of the third operation sent by the first voice interaction device in response to the synchronization request.

According to an embodiment of the present disclosure, the above-mentioned first device determining module is further configured to: when the parameter information receiving module again receives at least one parameter information respectively sent by at least one voice interaction device among the multiple voice interaction devices , Re-determine the first voice interaction device. The above-mentioned control device further includes: an acquisition request receiving module configured to receive an acquisition request sent by the re-determined first voice interaction device when the user's fourth voice input is collected; and first progress information transmission A module for sending the execution progress information to the re-determined first voice interaction device in response to the acquisition request of the re-determined first voice interaction device.

A fourth aspect of the present disclosure provides a voice interaction device, including: a parameter information sending module, configured to send parameter information to a control device when the user's first voice input is collected to determine the voice interaction device Whether it is the first voice interaction device; the instruction receiving module is configured to: in the case that the voice interaction device is the first voice interaction device, receive the wake-up instruction sent by the control device; when the voice interaction device is not the first voice interaction device In the case of a voice interaction device, receiving a non-wake-up instruction sent by the control device; and a state switching module, configured to: in a case where the instruction receiving module receives the wake-up instruction, respond to the wake-up instruction to The current state is switched to the wake-up state; in the case that the instruction receiving module receives the non-wake-up instruction, in response to the non-wake-up instruction, the current state is switched to the non-wake-up state, wherein the first voice input includes A predetermined voice input and a voice input that characterizes the user's needs.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes performance parameters of the voice interaction device, and the above-mentioned voice interaction device further includes: a performance parameter acquisition module for sending the parameter information to the control device by the parameter information sending module Before information, obtain the performance parameters.

According to an embodiment of the present disclosure, the above-mentioned parameter information further includes the position information of the user, and the above-mentioned voice interaction device further includes: a position information determining module configured to determine the user’s position information according to the collected first voice input of the user Location information, where the location information of the user represents the location of the user relative to the voice interaction device.

According to an embodiment of the present disclosure, the above-mentioned parameter information includes operation information of the voice interaction device, and the non-wake-up instruction includes a sleep instruction and a hibernation instruction, wherein: when the operation information indicates that the voice interaction device performs the first operation The non-wake-up instruction received by the instruction receiving module is the sleep instruction, and the state switching module switches the current state to the sleep state in response to the sleep instruction, and the sleep state includes performing the first operation and The collected voice input of the user is not responding; when the operation information indicates that the voice interaction device has not performed the first operation, the non-awakening instruction received by the instruction receiving module is the sleep instruction, The state switching module switches the current state to the sleep state in response to the sleep instruction, and the sleep state includes a state where no operation is performed.

According to an embodiment of the present disclosure, the above-mentioned voice interaction device further includes: a second voice information determining module, configured to determine the second voice information in the wake-up state and the second voice input of the user is collected Whether the first voice information corresponding to the voice input is general voice information; the second voice information sending module is configured to send the first voice information to the control device when it is determined that the first voice information is general voice information; And or alternatively, the above-mentioned voice interaction device further includes: a second voice information receiving module, configured to receive second voice information belonging to the general voice information sent by the control device; and an operation execution module, configured to perform according to the second voice information Voice information, perform a second operation, and the second operation corresponds to the voice input corresponding to the second voice information.

According to an embodiment of the present disclosure, the above-mentioned voice interaction device further includes a recovery request sending module, which is used for those who are in an awake state and collect the third voice input of the user or have not collected the voice input of the user within a preset time period. In this case, a restoration request is sent to the control device; and/or the instruction receiving module is also used to receive a restoration instruction sent by the control device; the state switching module is also used to respond to the restoration instruction to change the current The state is switched to the state before the first voice input is collected.

According to an embodiment of the present disclosure, the above-mentioned voice interaction device further includes: a second progress information sending module, configured to respond to the synchronization request sent by the control device in the wake-up state and perform the third operation, The control device sends execution progress information of the third operation.

According to an embodiment of the present disclosure, the above-mentioned voice interaction device further includes: an acquisition request sending module, configured to send the acquisition request to the control device when the user is in the awake state and the fourth voice input of the user is collected. Request; a second progress information receiving module for receiving the execution progress information sent by the control device in response to the acquisition request; and an operation execution module for performing the third operation according to the execution progress information , Wherein the third operation corresponds to the fourth voice input.

A fifth aspect of the present disclosure provides an electronic device, including the aforementioned control device and the aforementioned voice interaction device.

A sixth aspect of the present disclosure provides an electronic device, including: one or more processors; a storage device, for storing one or more programs, wherein when the one or more programs are used by the one or more When the two processors are executed, the one or more processors are caused to execute the above-mentioned operation method of the control device and/or the above-mentioned operation method of the voice interaction device.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the above-mentioned control method of the smart home system when executed.

Another aspect of the present disclosure provides a computer program that includes computer-executable instructions that, when executed, are used to implement the operation method of the above-mentioned control device and/or the above-mentioned voice interaction device Method of operation.

According to the embodiments of the present disclosure, it is possible to at least partially solve the technical problem in the prior art that multiple voice interaction devices will be awakened in response to the user's wake-up words at the same time at the same time, thereby causing noisy and chaotic interaction scenes between the user and the smart device. And therefore, by determining a technical solution of a voice interaction device as the only device to be awakened based on multiple parameter information sent by multiple voice interaction devices, a noisy interaction environment is avoided, thereby improving user experience.

Description of the drawings

Through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, the above and other objectives, features, and advantages of the present disclosure will be more apparent. In the accompanying drawings:

FIG. 1 schematically shows an application scenario of a control device and an operation method thereof, and a voice interaction device and an operation method thereof according to an embodiment of the present disclosure;

Fig. 2A schematically shows a flowchart of an operation method of a control device according to an embodiment of the present disclosure;

Fig. 2B schematically shows an operation flowchart of determining a first voice interaction device according to an embodiment of the present disclosure;

FIG. 2C schematically shows an operation flowchart of sending a non-wake-up instruction to other voice interaction devices according to an embodiment of the present disclosure;

Fig. 3 schematically shows a flowchart of an operation method of a control device according to a second embodiment of the present disclosure;

Fig. 4 schematically shows a flowchart of an operation method of a control device according to a third embodiment of the present disclosure;

Fig. 5A schematically shows a flowchart of an operation method of a control device according to a fourth embodiment of the present disclosure;

FIG. 5B schematically shows an application scenario diagram of the operation method shown in FIG. 5A;

FIG. 5C schematically shows a flowchart of the operation method of the control device according to the fifth embodiment of the present disclosure;

Fig. 6A schematically shows a flow chart of the operation method of the voice interaction device according to the first embodiment of the present disclosure;

FIG. 6B schematically shows a flowchart of the operation method of the voice interaction device according to the second embodiment of the present disclosure;

Fig. 7A schematically shows a flowchart of an operation method of a voice interaction device according to a third embodiment of the present disclosure;

FIG. 7B schematically shows a flowchart of the operation method of the voice interaction device according to the fourth embodiment of the present disclosure;

FIG. 8 schematically shows a flowchart of an operation method of a voice interaction device according to a fifth embodiment of the present disclosure;

Fig. 9A schematically shows a flowchart of an operation method of a voice interaction device according to a sixth embodiment of the present disclosure;

FIG. 9B schematically shows a flowchart of the operation method of the voice interaction device according to the seventh embodiment of the present disclosure;

Fig. 10 schematically shows a structural block diagram of a control device according to an embodiment of the present disclosure;

Fig. 11 schematically shows a structural block diagram of a voice interaction device according to an embodiment of the present disclosure;

Fig. 12 schematically shows a block diagram of an electronic device suitable for performing an operating method of a control device or an operating method of a voice interaction device according to an embodiment of the present disclosure.

Detailed ways

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. However, it should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concept of the present disclosure.

The terminology used here is only for describing specific embodiments, and is not intended to limit the disclosure. The terms "including", "including", etc. used herein indicate the existence of the described features, steps, operations and/or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

All terms (including technical and scientific terms) used herein have meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

In the case of using an expression similar to "at least one of A, B, C, etc.", generally speaking, it should be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "having A, B and C" At least one of the "systems" shall include but not limited to systems having A alone, B alone, C alone, A and B, A and C, B and C, and/or systems having A, B, C, etc. ).

The embodiment of the present disclosure provides an operating method of a control device capable of improving interactive experience. The method includes: receiving multiple parameter information sent by multiple voice interaction devices, where the multiple parameter information is It is sent when the first voice input of the user at the same time is collected; the user's demand information is determined according to the first voice input; the first voice interaction device among the multiple voice interaction devices is determined according to multiple parameter information and demand information It is a device that interacts with a user; and sends a wake-up instruction to the first voice interaction device, and sends a non-wake-up instruction to voice interaction devices other than the first voice interaction device among the multiple voice interaction devices. Wherein, the first voice input includes a predetermined voice input and a voice input that characterizes user needs.

Another embodiment of the present disclosure provides an operating method of a voice interaction device capable of improving interactive experience. The method includes: sending parameter information to the control device to determine the voice when the user’s first voice input is collected. Whether the interaction device is the first voice interaction device; in the case that the voice interaction device is the first voice interaction device, receive the wake-up instruction sent by the control device to respond to the wake-up instruction in the wake-up state; when the voice interaction device is not the first voice interaction device In the case of the device, a non-wake-up instruction sent by the control device is received to respond to the non-wake-up instruction in a non-wake-up state, wherein the first voice input includes a predetermined voice input and a voice input that represents the user's needs.

Fig. 1 schematically shows an application scenario of a control device and an operation method thereof, and a voice interaction device and an operation method thereof according to an embodiment of the present disclosure. It should be noted that FIG. 1 is only an example of application scenarios in which the embodiments of the present disclosure can be applied to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used for other applications. Equipment, system, environment or scenario.

As shown in FIG. 1, the application scenario 100 includes multiple voice interaction devices, a network 120, and a user 130. The network 120 may be a local area network, for example, a wireless network, etc., for example.

Wherein, at least two of the multiple voice interaction devices may interact with each other via the network 120, for example, and the multiple voice interaction devices are smart electronic devices that can interact with the user through voice.

Specifically, the multiple voice interaction devices may be, for example, smart home devices, which may specifically include smart lamps 111, smart TVs, smart set-top boxes, smart speakers, smart air conditioners 112, smart water heaters 113, smart refrigerators 114, smart curtains, and smart washing machines 115. , Smart air purifiers, smart game consoles, smart projectors, etc.; or, for example, may include smart bathroom equipment, such as smart showers, smart bathtubs, smart bath heaters, smart vanity mirrors, smart toilets, etc.; or, for specific examples, it may also Including smart kitchen equipment, such as smart range hoods, smart hot water boilers, smart gas hoods, smart cabinets, smart dishwashers, smart microwave ovens, and smart ovens.

According to an embodiment of the present disclosure, the plurality of voice interaction devices can receive a user's voice input, and can switch in response to the voice input when the voice input includes a wake-up word (for example, "dingdongdingdong", etc.) To wake up state, to receive user instructions, and perform corresponding operations according to user instructions.

According to an embodiment of the present disclosure, the plurality of voice interaction devices, for example, further have sensors, such as a sound sensor or a distance sensor, etc., which are used to realize the user's voice input according to the sound source or infrared detection when the user's voice input is received. Positioning to measure the user's location information relative to itself.

According to an embodiment of the present disclosure, the multiple voice interaction apparatuses may also interact with a network device that provides the network 120, for example, to send the measured location information to the network device, so that the network device determines the interaction with the user according to the location information. The first voice interaction device enables the multiple voice interaction devices to work under the control of the network device.

According to the embodiment of the present disclosure, the user 130 may, for example, also control the multiple voice interaction devices through an application program installed in other electronic devices, and may set one voice interaction device among the multiple voice interaction devices through the application program. If the device is a control device, and the other devices are controlled devices, the multiple voice interaction devices send the position information measured according to the voice input to the control device, so that the control device determines the first voice interaction device to interact with the user according to the position information , So that the multiple voice interaction devices work under the control of the set control device.

For example, as shown in Figure 1, when the user 130 speaks a voice that includes the wake-up word "Ding Dong Ding Dong, help me play Dao Xiang", multiple voice interaction devices smart lamps 111, smart air conditioners 112, smart water heaters 113, smart Part or all of the refrigerator 114 and the smart washing machine 115 can receive the voice input, and the voice interaction device that receives the voice input will set parameter information (which may include its own function information and/or detected user location information) It is sent to the network device or the determined control device, and the network device or the determined control device determines that the smart refrigerator 114 with music playback function and close to the user is the first voice interaction device according to the received parameter information. During the interaction, the smart refrigerator 114 is awakened under the control of the network device or the determined control device, while the smart lamp 111, the smart air conditioner 112, the smart water heater 113, and the smart washing machine 115 are under the control of the network device or the determined control device Keeping the non-awakened state can avoid the noisy and chaotic voice interaction scene caused by multiple voice interaction devices being awakened, and improve user experience.

It should be noted that the operation method of the control device provided in the embodiments of the present disclosure may generally be executed by a certain control device, and the operation method of the voice interaction device may be executed by any one of multiple voice interaction devices. Correspondingly, the control device provided by the embodiment of the present disclosure can generally be set in a network device or any voice interaction device (for example, in a certain control device), and the voice interaction device may refer to the voice interaction devices 111 to 115 in FIG. . The operation method of the control device provided by the embodiment of the present disclosure can also be executed by other electronic equipment that is different from the voice interaction device and can communicate with the voice interaction device. Correspondingly, the control device provided by the embodiment of the present disclosure can also be set in other electronic equipment that is different from the voice interaction device and can communicate with the voice interaction device.

It can be understood that the types and numbers of voice interaction devices and networks 120 in FIG. 1 are only illustrative, and any type and number of voice interaction devices and cloud devices can be provided according to implementation needs.

FIG. 2A schematically shows a flowchart of an operation method of a control device according to an embodiment of the present disclosure, FIG. 2B schematically shows an operation flowchart of determining a first voice interaction device according to an embodiment of the present disclosure, and FIG. 2C schematically An operation flowchart of sending a non-wake-up instruction to another voice interaction device according to an embodiment of the present disclosure is shown.

As shown in FIG. 2A, the operation method of the control device includes operation S201 to operation S204.

In operation S201, multiple parameter information respectively sent by multiple voice interaction apparatuses are received.

Specifically, the multiple parameter information may be sent when multiple voice interaction devices receive the first voice input of a certain user at the same time. Correspondingly, the voice interaction device has a voice collection function, such as a voice collector, etc. The multiple voice interaction devices may be voice interaction devices capable of collecting the user's first voice input within a spatial range, for example, if the user has If there are n voice interaction devices, the multiple voice interaction devices involved in operation S201 are some or all of the n voice interaction devices. For example, the multiple voice interaction devices may be part or all of the smart lamp 111, smart air conditioner 112, smart water heater 113, smart refrigerator 114, and smart washing machine 115 in FIG. 1.

Wherein, when the user issues a voice command "Ding Dong Ding Dong, play Dao Xiang for me", multiple voice interaction devices 111 to 115 can receive the first voice input by collecting the voice command. Then, when the multiple voice interaction devices 111-115 receive the first voice input, they respectively send parameter information to the control device for the control device to receive.

According to an embodiment of the present disclosure, the first voice input may specifically include a predetermined voice input and a voice input that characterizes user needs. Wherein, the predetermined voice input may be, for example, a voice input corresponding to a wake-up word (for example, "Ding Dong Ding Dong") of the voice interaction device. The wake-up word may be, for example, a wake-up word preset when the voice interactive device is shipped from the factory, or a wake-up word customized by the user. Among them, the voice input that characterizes the user's needs is the voice input corresponding to other voices except the wake-up word, for example, it can be "Play Daoxiang for me".

According to an embodiment of the present disclosure, the parameter information may include, for example, attribute parameters and/or performance parameters of the voice interaction device, where the attribute parameters may include, for example, the brand and model of the voice interaction device, and the performance parameters may include, for example, the voice interaction device. Functions (such as playing music, playing video, temperature control, lighting), and the working parameters of the voice interaction device (such as lighting brightness, sound quality, screen resolution, temperature adjustment range, etc.).

In operation S202, the demand information of the user is determined according to the first voice input.

According to the embodiment of the present disclosure, when the control device is integrated into a certain voice interaction device, the certain voice interaction device may also perform voice recognition analysis on the first voice input after collecting the first voice input, thereby obtaining the user Demand information. The user's demand information is specifically obtained by recognizing and analyzing the voice input that represents the user's demand in the first voice input. For example, when the voice input that characterizes the user's needs is "Play Daoxiang for me", the demand information obtained can be, for example, playing music; when the voice input that characterizes the user's needs is "Playing lossless music for me", the demand information is obtained. For example, it can be playing music and high sound quality. Among them, the specific implementation method of recognizing and analyzing speech can adopt any speech recognition method in the prior art, which is not limited in the present disclosure.

In operation S203, the first voice interaction device among the multiple voice interaction devices is determined to be the device that interacts with the user according to multiple parameter information and demand information.

According to an embodiment of the present disclosure, when the multiple parameter information includes performance parameters, the operation S203 may specifically include, for example, first determining the matching relationship between the multiple parameter information and the demand information, and then determining the voice matching the parameter information and the demand information The interaction device is the first voice interaction device. For example, when the demand information is to play music, it can be determined that the parameter information that has a music play function matches the demand information, and the voice interaction device corresponding to the parameter information is the first voice interaction device. When the demand information is to play music and high sound quality, first determine that the parameter information that characterizes the music playing function matches the demand information, and then determine that the parameter information that characterizes high sound quality has a higher degree of matching with the demand information, and then it can be determined that the matching degree is high The voice interaction device corresponding to the parameter information is the first voice interaction device.

According to the embodiments of the present disclosure, in order to be able to select the first voice interaction device alternatively when there are multiple voice interaction devices matching performance parameters and demand information, thereby further avoiding multiple voice interaction devices responding to user instructions. Noisy environment. The parameter information sent by the voice interaction device may, for example, further include user location information used to characterize the location of the user relative to the voice interaction device.

Correspondingly, the multiple voice interaction devices, for example, should also have the function of analyzing and processing the collected voice input. Specifically, the voice interaction device may determine the distance of the user relative to itself according to the strength of the voice signal after collecting the voice input of the user. Then the position information included in the sent parameter information may be a distance value. Alternatively, the multiple voice interaction devices may also be provided with a sensor capable of positioning the user, and the trigger condition of the sensor operation is that the voice interaction device collects the first voice input, and the sensor may be collected by the voice interaction device, for example. The sound source of the voice input realizes the positioning of the user, or it can also realize the positioning of the user through infrared detection and other technologies to obtain the user's location information included in the user information. The location information can be a distance value or a voice interaction The location of the device is the coordinate value of the user's location obtained by the origin positioning. It is understandable that the location information of the user described above is only used as an example to facilitate understanding of the present disclosure, and the location information may also include, for example, the space where the user is determined.

As shown in FIG. 2B, operation S203 may specifically include operation S213 to operation S223. In operation S213, determine at least one second voice interaction device whose performance parameter matches the user's demand information among the plurality of voice interaction devices; in operation S223, according to the user's location information in the parameter information sent by the at least one second voice interaction device , It is determined that one of the at least one second voice interaction device is the first voice interaction device. Specifically, the second voice interaction device that can meet the needs of the user is determined according to the performance parameters of multiple voice interaction devices. Then, the second voice interaction device whose location information characterizes the closest distance to the user is selected as the first voice interaction device.

According to an embodiment of the present disclosure, the first voice interaction device determined in operation S203 may be, for example, the smart refrigerator 114 described with reference to FIG. 1, which will not be repeated here.

In operation S204, a wake-up instruction is sent to the first voice interaction device, and a non-wake-up instruction is sent to other voice interaction devices among the plurality of voice interaction devices except the first voice interaction device.

According to the embodiment of the present disclosure, since the wake-up instruction is sent to the first voice interaction device, the first voice interaction device can switch from the state before receiving the first voice input to the wake-up state in response to the wake-up instruction; The voice interaction device sends a non-wake-up instruction. Therefore, other voice interaction devices can switch from the state before receiving the first voice input to the non-wake state.

According to an embodiment of the present disclosure, the non-awake state may be, for example, a state in which no response is made to the first voice input; or, the non-awake state may also be a state in which the voice interaction device does not perform any operation, that is, similar to shutting down. status.

According to an embodiment of the present disclosure, the above-mentioned operation S204 may specifically be: sending a wake-up instruction to the smart refrigerator 114 in reference to FIG. 1, and the smart refrigerator 114 is awakened in response to the wake-up instruction, and can perform voice interaction with the user, and send a voice to the smart refrigerator 114. The voice interaction device that receives the first voice input among the lamp 111, the smart air conditioner 112, the smart water heater 113, and the smart washing machine 115 sends a non-wake-up instruction, and the voice interaction devices switch to the non-wake state in response to the non-wake-up instruction, that is, The state where voice interaction with the user is not possible.

According to the embodiment of the present disclosure, considering that some voice interaction devices may perform operations before collecting the first voice input in other voice interaction devices, which are similar to lighting, cooling, etc., and do not affect the interaction process between the first voice interaction device and the user. Operations, such as operations that do not make a sound. In this case, if the part of the voice interaction device is directly switched to a state similar to shutting down, the user experience may be affected. For example, before the user sends out the voice command "Ding Dong Ding Dong, help me play Dao Xiang" in a dark space, the smart lamp 111 in the dark space performs the lighting operation. At this time, if the first voice interaction device is determined In the case of a smart refrigerator 114, issuing an instruction to the smart lamp 111 to switch the smart lamp 111 to a state of not performing any operation (that is, a state of not performing a lighting operation) will undoubtedly bring a poor user experience.

In order to avoid the above-mentioned defects, as shown in FIG. 2C, the non-wake-up instruction issued by the operation S204 may include a sleep instruction and a sleep instruction, and the parameter information sent by multiple voice interaction devices may also include operation information of the voice interaction device. To characterize the operation performed by the voice interaction device when the first voice input is collected. Correspondingly, operation S204 may specifically include operation S214 to operation S224, for example.

In operation S214, according to the operation information of other voice interaction devices, it is determined whether the other voice interaction device performs the first operation when collecting the first voice input; in operation S224, the sleep instruction is sent to other voice interaction devices that perform the first operation, and Other voice interaction devices that have not performed the first operation send a sleep instruction. The first operation may specifically be an operation that does not affect the interaction process between the first voice interaction device and the user, and the type of operation included in the first operation may be set according to actual requirements. When another voice interaction device receives a sleep instruction, it can switch to the sleep state in response to the sleep instruction. The sleep state may specifically be able to perform the first operation and collect voice input, but does not respond to the collected voice input of the user status. When other voice interaction devices receive the sleep instruction, they can switch to the sleep state in response to the sleep instruction. The sleep state may be a state in which no operation is performed, for example, it may be a shutdown state.

In summary, the operating method of the control device of the present disclosure determines the only device among the multiple voice interaction devices as the awakened device through the received parameter information, which is used to interact with the user, compared with the multiple voice interaction devices in the prior art. The technical solution in which voice interaction devices are all awakened can avoid the defect of noisy and chaotic interaction scenes caused by multiple voice interaction devices interacting with the user at the same time, and thus improve user experience.

Fig. 3 schematically shows a flowchart of an operation method of a control device according to a second embodiment of the present disclosure.

In addition to operations S201 to S204 described in FIG. 2A, the operation method of the control device according to an embodiment of the present disclosure may further include operations S305 to S307 as shown in FIG. 3.

In operation S305, the first voice information sent by the first voice interaction device when the user's second voice input is collected is received. Wherein, the first voice information corresponds to the second voice input.

The second voice input may specifically be a voice input corresponding to the voice used to send instructions to multiple voice interaction devices, and the instruction may specifically be similar to "turn off all devices" or "I'm going out", etc. Multiple voice interaction devices can be universal and require multiple voice interaction devices to respond to voice instructions. Because the voice instruction requires multiple voice interaction devices to work together to achieve the effect that the user wants, if only the first voice The interaction device performs a corresponding operation in response to the second voice information corresponding to the second voice input, which cannot well meet the needs of the user.

According to the embodiments of the present disclosure, after the first voice interaction device is switched to the awake state, the user's voice input can be collected in real time, and corresponding operations can be performed in response to the user's voice input. Taking into account the above problems, when the collected voice input of the user is the second voice input, the first voice interaction device first determines whether the corresponding first voice information is general voice information, that is, multiple voice interaction devices can be universal, And the voice information that multiple voice interaction devices respond together is required; if it is general voice information, the first voice information corresponding to the second voice input should be sent to the control device to notify the control device that the voice command requires multiple voice interaction devices to share carry out. Specifically, the cloud system or the first voice interaction device pre-stores a list of general voice information as a reference for determining whether it is general voice information.

The first voice information may specifically correspond to the second voice input, and can characterize the second voice input and the information that can be recognized by the electronic device. For example, it may be a binary code or character sequence obtained by converting the second voice input. And so on; or after the speech input is recognized and processed, then the binary code or character sequence obtained is converted.

In operation S306, it is determined whether the first voice information is general voice information.

According to an embodiment of the present disclosure, the operation S306 may specifically be to compare the first voice information with a general voice information list stored in the cloud system or pre-stored by the control device, if the first voice information is in the general voice list Information, it is determined that the first voice information is general voice information; or, operation S306 can also be specifically implemented by the following operations: use the first voice information as the input of the pre-trained deep learning model, and the output result is the binary classification As a result, it can be characterized as universal language information or not universal language information. It can be understood that the foregoing method is only an example for implementing operation S306, which is not limited in the present disclosure. It is also understandable that the control device can avoid the defect of inaccurate judgment result caused by the difference between the general voice information stored in the control device and the first voice interaction device by determining whether the first voice information is general voice information again.

In operation S307, in a case where the first voice information is general voice information, the first voice information is sent to multiple voice interaction devices, so that the multiple voice interaction devices perform an operation corresponding to the second voice input.

Considering that the second voice input corresponding to the first voice information belonging to the general voice information requires the cooperative operation of multiple voice interaction devices to meet the needs of the user, therefore, when it is determined that the first voice information is general voice information Next, the first voice information is sent to multiple voice interaction devices, and the multiple voice interaction devices respond to the operations of the first voice information to complete the same activities as the user needs, and meet the user needs, for example, when the second voice input When it is "I want to go out" or "Turn off all devices", it can indicate that the user's intention is to turn off all voice interaction devices, and the multiple voice interaction devices can perform operations corresponding to the first voice information, such as shutdown operations. To meet the needs of users, while ensuring that the interactive scene is not noisy and chaotic, the response operation of the voice interactive device can be made more in line with user needs.

According to the embodiments of the present disclosure, in the above-mentioned application scenario, in order to prevent the voice interaction device itself from being turned off after receiving the first voice information, the voice interaction device may be turned on by performing a corresponding operation again. After receiving the first voice information, the voice interaction apparatus may determine whether to perform an operation corresponding to the second voice input, for example, according to the current state. If the current state matches the first voice information, the operation corresponding to the second voice input is performed, and if the current state does not match the first voice information, the operation corresponding to the second voice input is not performed.

Fig. 4 schematically shows a flowchart of the operation method of the control device according to the third embodiment of the present disclosure.

According to an embodiment of the present disclosure, when the first voice interaction device collects the user's third voice input or does not collect the user's voice input within a preset time period, it is considered that the user may no longer need to interact with the user at this time. The first voice interaction device interacts. Or, in the case that the user’s voice input is not collected within the preset time period, the user can also be issued a questioning voice similar to "Master, master, are you still listening?" or "Master, are you still there?" If the user’s voice input is still not collected after the inquiry voice is issued, it can be determined that the user no longer needs to interact with the first voice interaction device at this time. Wherein, the third voice input may specifically be a voice input corresponding to an instruction similar to "sleep" issued by the user.

In this case, considering that operations such as playing broadcast or music may be performed before the first voice interaction device and/or other voice interaction devices receive the first voice input, the user often wishes to end the interaction with the first voice interaction device Later, the first voice interaction device and/or other voice interaction devices can continue to play broadcast or music operations. Therefore, after the first voice interaction device determines that the user no longer needs to interact with the first voice interaction device, the control device Send a resume request that characterizes the end of the interaction.

Correspondingly, in addition to operations S201 to S204 described in FIG. 2A, as shown in FIG. 4, the operation method of the control device of the embodiment of the present disclosure may further include S408 to S409. In operation S408, a recovery request sent by the first voice interaction device is received, and the recovery request is sent by the first voice interaction device when the user's third voice input is collected or the user's voice input is not collected within a preset time period; And in operation S409, a recovery instruction is sent to the multiple voice interaction devices, so that the multiple voice interaction devices are restored to the state before the first voice input of the user is collected. Specifically, the multiple voice interaction devices are restored to the state of playing music or radio before collecting the first voice input, so as to continue to perform operations such as playing radio or music to the user to meet user needs.

Fig. 5A schematically shows a flowchart of an operation method of a control device according to a fourth embodiment of the present disclosure.

In addition to operations S201 to S204 described in FIG. 2A, the operation method of the control device of the embodiment of the present disclosure may also include operations S510 to S512 as shown in FIG. 5A.

In operation S510, the operation of the first voice interaction device is monitored, and it is determined whether the first voice interaction device performs a third operation. In operation S511, when the first voice interaction device performs the third operation, a synchronization request is sent to the first voice interaction device; in operation S512, the execution progress of the third operation sent by the first voice interaction device in response to the synchronization request is received information.

According to an embodiment of the present disclosure, after the first voice interaction device is determined, and the first voice interaction device is switched to the awake state, the control device may, for example, monitor the operation of the first voice interaction device in real time, and determine in real time Whether the monitored operation is the third operation. The third operation may specifically be an operation that takes longer than a preset time to execute in response to the user's voice input, for example, it may be a broadcast operation, such as playing music, reading e-books, playing radio, or playing videos; or Operations with complex processes, such as online shopping.

After the synchronization request is sent, the execution progress information of the third operation sent by the first voice interaction device in response to the synchronization request can be received. The execution progress information may be the length of time the third operation has been executed, or the third operation has been executed. The ratio of the execution time to the total time required to execute the third operation, etc. According to an embodiment of the present disclosure, after receiving the execution progress information of the third operation, for example, the stored progress information may also be stored and updated.

Fig. 5B schematically shows an application scenario diagram of the operation method of the control device shown in Fig. 5A; Fig. 5C schematically shows a flowchart of the operation method of the control device according to the fifth embodiment of the present disclosure.

As shown in FIG. 5B, the operation method of the control device of the embodiment of the present disclosure can be applied to a home scene, for example, in which smart speakers are configured in the living room 501, the bedroom 502, the bedroom 503, and the bedroom 504, then in FIG. 2A The multiple voice interaction devices described may be smart speakers configured in the living room 501, bedroom 502, bedroom 503, and bedroom 504. When the user speaks a voice command including a wake-up word in the living room 501, the four smart speakers Then, the first voice input can be collected, and the smart speaker in the living room 501 can be awakened through operations S201 to S204.

According to an embodiment of the present disclosure, when the user moves from the position of the living room 501 shown in the left side diagram in FIG. 5B to the bedroom 502 shown in the right side diagram in FIG. 5B, the user generally needs to wake up the smart speaker in the bedroom 502. The smart speaker in the living room 501 is put to sleep, so the voice command including the wake-up word will be spoken again, and the device that can collect the voice input of the wake-up word among the multiple voice interaction devices will send parameter information to the control device again . Therefore, in addition to operations S201 to S204 shown in FIG. 2A, the operation method of the control device of the embodiment of the present disclosure may also include operation S513 shown in FIG. 5C: when at least one voice of the multiple voice interaction devices is received again In the case of at least one piece of parameter information respectively sent by the interaction device, the first voice interaction device is re-determined. Specifically, operations S201 to S203 may be repeatedly performed to re-determine the first voice interaction device. In the application scenario of FIG. 5B, the re-determined first voice interaction device is the smart speaker in the bedroom 502. Similarly, after the first voice interaction device is re-determined, the method can also send a message to the re-determined first voice The interactive device (the smart speaker in the bedroom 502) sends a wake-up instruction to switch the re-determined first voice interaction device to the wake-up state, and the first voice input is received to other than the re-determined first voice interaction device The other devices in the send a non-wake-up instruction to switch the previously determined first voice interaction device (such as the smart speaker in the living room 501) and other devices to the non-wake state.

According to an embodiment of the present disclosure, when the user provides the voice instruction including the wake-up word again, the previously determined first voice interaction device may also fail to collect the voice instruction provided again because of being too far away from the user. In this case, the operating method of the control device may also send a sleep instruction to the first voice interaction device currently in the awake state after re-determining the first voice interaction device, so that the previous first voice interaction device switches to the sleep state , To avoid the consumption of additional power.

According to an embodiment of the present disclosure, when the user instructs the first voice interaction device to perform the third operation described in FIG. 5A, that is, the user listens to music or listens to content with a long duration such as broadcasting, after moving from the living room 501 to the bedroom 502 When waking up the smart speaker in the bedroom 502 and sleeping the smart speaker in the living room 501, it is more hoped that the smart speaker in the bedroom 502 can continue to perform operations such as playing following the execution progress of the smart speaker in the living room 501. Therefore, the present disclosure The operation method of the control device of the embodiment may further include operations S514 to S515 described in FIG. 5C.

In operation S514, an acquisition request sent by the re-determined first voice interaction device when the user’s fourth voice input is collected is received; in operation S515, in response to the re-determined acquisition request of the first voice interaction device, Send the execution progress information to the re-determined first voice interaction device.

Among them, considering that the user hopes that the smart speaker in the bedroom 502 can continue to perform operations such as playing following the execution progress of the smart speaker in the living room 501, and according to the operation method of the control device described in FIG. 5A, it can be seen that the control device receives the third operation in real time. Therefore, through the above operations S514 to S515, when the user can issue an instruction such as "continue" or "continue playing", the smart speaker in the bedroom 502 can collect the fourth voice corresponding to the instruction In the case of input, an acquisition request is sent to the control device to acquire the execution progress information of the third operation, and the third operation is continued to be executed according to the acquired execution progress information.

In summary, the operating method of the control device of the embodiment of the present disclosure responds to the user's voice input, and the re-determined first voice interaction device can continue to perform the third operation that was not completed by the previous first voice interaction device, so that The intelligent system composed of multiple voice interaction devices can provide users with smooth services and avoid the repeated execution of some operations, thereby avoiding the defect of wasting user time and effectively improving user experience.

Fig. 6A schematically shows a flow chart of the operation method of the voice interaction device according to the first embodiment of the present disclosure, and Fig. 6B schematically shows the flow chart of the operation method of the voice interaction device according to the second embodiment of the present disclosure.

As shown in FIG. 6A, the operation method of the voice interaction device includes operation S601.

In operation S601, parameter information is transmitted to the control device.

According to an embodiment of the present disclosure, the operation S601 may be specifically executed when the voice interaction device collects the user's first voice input, so that the control device determines whether the voice interaction device is the first voice interaction device according to the parameter information .

According to an embodiment of the present disclosure, the first voice input may specifically include a predetermined voice input and a voice input that characterizes user needs. For details, please refer to the description of operation S201 in FIG. 2A, which will not be repeated here.

According to an embodiment of the present disclosure, the parameter information may include performance parameters of the voice interaction device, for example. In this case, as shown in FIG. 6B, before performing operation S601, the operation method of the voice interaction apparatus may further include operation S604 to obtain performance parameters. Among them, the performance parameters may be obtained locally by the voice interaction device, or obtained from a server or cloud that provides services to the voice interaction device.

According to the embodiments of the present disclosure, in order to facilitate the control device to more accurately determine the unique first voice interaction device, the parameter information may further include location information of the user, for example. As shown in FIG. 6B, before performing operation S601, the operation method may further include operation S605: determining the location information of the user according to the collected first voice input of the user. The method for determining the location information of the user is detailed in the description of the location information in FIG. 2C, which will not be described in detail here.

According to the embodiment of the present disclosure, the parameter information includes not only performance parameters, but also user location information. As shown in FIG. 6B, the operation method of the voice interaction device includes operation S604 and operation S605 at the same time. The operation S604 may be performed before or after the operation S605, which is not limited in the present disclosure, as long as the operations S604 to S605 are all performed before the operation S601.

According to the embodiment of the present disclosure, it is considered that when the voice interaction device is the first voice interaction device, the wake-up instruction sent by the control device through operation S204 is received. As shown in FIG. 6A, the operation method of the voice interaction device may further include operation S602, receiving a wake-up instruction sent by the control device, so as to be in the wake-up state in response to the wake-up instruction. The operation S602 may specifically be: upon receiving the wake-up instruction, in response to the wake-up instruction, switch the current state to the wake-up state to interact with the user.

According to an embodiment of the present disclosure, it is considered that when the voice interaction device is the first voice interaction device, a non-wake-up instruction sent by the control device through operation S204 is received. As shown in FIG. 6A, the operation method of the voice interaction device may further include operation S603, receiving a non-wake-up instruction sent by the control device, so as to be in a non-wake-up state in response to the non-wake-up instruction. The operation S603 may specifically be: when a non-wake-up command is received, in response to the non-wake-up command, first determine whether the current state is a non-wake-up state, if not, switch the current state to the wake-up state in response to the non-wake-up command to Avoid responding to voice commands used.

Wherein, when the voice interaction device is not the first voice interaction device, the received non-wake-up instruction may specifically include a sleep instruction or a hibernation instruction, for example. Correspondingly, in order to prevent the voice interaction device from stopping performing the first operation due to receiving the sleep instruction when performing the first operation. The parameter information sent in operation S601 may also include operation information of the voice interaction device, for example. Therefore, when the operation information indicates that the voice interaction device performs the first operation, the received non-wake-up instruction is the sleep instruction sent by the control device through operation S224 in FIG. 2C. In response to the sleep instruction, the voice interaction device is in the sleep state, i.e. The state switches to sleep state. When the operation information indicates that the voice interaction device does not perform the first operation, the received non-wake-up instruction is the sleep instruction sent by the control device through operation S224 in FIG. 2C. In response to the sleep instruction, the voice interaction device is in a sleep state, i.e. The state switches to sleep state. Among them, the sleep state refers to a state where the first operation can be performed but does not respond to the collected user's voice input; the sleep state refers to a state where no operation is performed.

In summary, the voice interaction device of the embodiment of the present disclosure is controlled by the control device to switch its working state, instead of directly switching the working state to the wake-up state after the user's wake-up words are collected, and when it is switched to the wake-up state, Other voice interaction devices are in a non-awake state, so that the defect of a noisy and chaotic working environment of the voice interaction device can be avoided, and thus the user experience is improved. And when the voice interaction device is not the first voice interaction device, when the first operation is performed, the received instruction of the control device is a sleep instruction that can continue to perform the first operation, which can improve user experience to a certain extent.

Fig. 7A schematically shows a flowchart of an operation method of a voice interaction device according to a third embodiment of the present disclosure.

According to an embodiment of the present disclosure, when the voice interaction device is the first voice interaction device, after switching to the awake state, it can perform voice interaction with the user to perform an operation corresponding to the user's voice instruction.

According to the embodiment of the present disclosure, considering some voice commands of the user, such as "turn off all devices" or "I am going out", it is necessary to coordinate operations through multiple voice interaction devices to achieve the desired effect of the user, so as shown in Figure 7A As shown, the operation method of the voice interaction device in the embodiment of the present disclosure further includes operation S706 to operation S707 after operation S602. In operation S706, when the second voice input of the user is collected, it is determined whether the first voice information corresponding to the second voice input is general voice information; and in operation S707, it is determined whether the first voice information corresponding to the second voice input is When the information is general voice information, the first voice information is sent to the control device, so that the control device sends the first voice information to multiple voice interaction devices that have collected the first voice input through operations S305 to S307, so that The multiple voice interaction devices perform operations corresponding to the second voice input.

According to an embodiment of the present disclosure, the above-mentioned operation S707 may specifically recognize the collected voice input first, for example, may recognize a keyword of the voice input, and if the recognized keyword is a preset keyword, determine the The voice input of is the second voice input, and then it is determined whether the first voice information corresponding to the second voice input is general voice information. Specifically, it can be the first voice information corresponding to the second voice input with the voice interaction device or cloud system The list of general voice information stored in the database is compared, and if the first voice information corresponding to the second voice input is the voice information in the general voice information list, it is determined that the first voice information corresponding to the second voice input is the general voice Information; if the first voice information corresponding to the second voice input is not the voice information in the general voice information list, it is determined that the first voice information corresponding to the second voice input is not general voice information. The second voice input and the first voice information may be the second voice input and the first voice information described in operation S305 and operation S306 in FIG. 3, and details are not described herein again.

According to an embodiment of the present disclosure, after the second voice information is sent to the control device through the above operation S707, the control device can send the first voice information to multiple voice interaction devices through the operations S305 to S307 described with reference to FIG. 3, This allows multiple voice interaction devices to perform operations corresponding to the second voice input, such as a shutdown operation, to meet the user's needs, thereby ensuring that the interaction scene is not noisy and chaotic, and making the response operation of the voice interaction device more in line with the user demand.

Fig. 7B schematically shows a flowchart of the operation method of the voice interaction device according to the fourth embodiment of the present disclosure.

According to an embodiment of the present disclosure, regardless of whether the voice interaction device is the first voice interaction device, the voice interaction device can receive the voice information sent by the control device through operation S307. Correspondingly, as shown in FIG. 7B, the operation method of the voice interaction device of the embodiment of the present disclosure may further include operation S708 to operation S709. In operation S708, the second voice information belonging to the general voice information sent by the control device is received; in operation S709, a second operation is performed according to the second voice information, and the second operation corresponds to a voice input corresponding to the second voice information.

In the case where the voice interaction device is the first voice interaction device, operations S708 to S709 are performed after operation S707 described in FIG. 7A. At this time, the second voice information is the first voice information sent in operation S707.

In the case where the voice interaction device is not the first voice interaction device, operations S708 to S709 are performed after operation S603 described in FIG. 6A. At this time, the second voice information is the first voice information determined by the control device to be general voice information through operation S306.

Fig. 8 schematically shows a flowchart of an operation method of a voice interaction device according to a fifth embodiment of the present disclosure.

After the voice interaction device is the first voice interaction device and is switched to the awake state, it can be determined whether the user still needs to interact with the voice interaction device in response to the user's voice input or self-determination. Among them, the implementation of determining whether the user still needs to interact is described in detail above, and will not be repeated here.

In this case, considering that the voice interaction device and/or other voice interaction device may perform operations such as playing broadcast or music before receiving the first voice input, and the user often hopes that the voice interaction device will end the interaction with the voice interaction device. The device and/or other voice interaction devices can continue operations such as broadcasting or music. Therefore, after the voice interaction device determines that the user no longer needs to interact, it may send a resume request that characterizes the end of the interaction to the control device. Therefore, as shown in FIG. 8, after operation S602, the operation method of the embodiment of the present disclosure may further include operation S810, when the user's third voice input is collected or the user's voice input is not collected within a preset time period. To send a recovery request to the control device.

Correspondingly, after receiving the recovery request, the control device can send recovery instructions to multiple voice interaction devices through operations S408 to S409 to restore the multiple voice interaction devices to the state before collecting the user's first voice input . Specifically, the multiple voice interaction devices can be restored to the state of playing music or radio before collecting the first voice input, so as to continue to play radio or music to the user to meet the user's needs.

Therefore, as shown in FIG. 8, regardless of whether the voice interaction device is the first voice interaction device, operation S811 can be performed to receive a recovery instruction from the control device to switch the current state to the one before the first voice input is collected in response to the recovery instruction. status. Wherein, in a case where the voice interaction device is the first voice interaction device, operation S811 is performed after operation S810. In a case where the voice interaction device is not the first voice interaction device, operation S811 is performed after operation S603.

Fig. 9A schematically shows a flowchart of an operation method of a voice interaction device according to a sixth embodiment of the present disclosure.

According to the embodiment of the present disclosure, after the voice interaction device is switched to the awake state through operation S602, as shown in FIG. 9A, the operation method of the voice interaction device of the embodiment of the present disclosure further includes operation S912. When the third operation is performed, respond In the synchronization request sent by the control device, the execution progress information of the third operation is sent to the control device in real time to update the execution progress of the third operation to the control device in real time. In the application scenario described in FIG. 5B, the control device is After the first voice interaction device is re-determined, operations S514 to S515 described in FIG. 5C can be performed, so that after the first voice interaction device is switched to the non-awake state under the control of the control device, the re-determined first voice The interactive device continues to perform the third operation, so that the intelligent system composed of multiple voice interactive devices can provide users with smooth services, avoid the repeated execution of some operations, and therefore can avoid the defect of wasting user time, and effectively improve user experience. For the content, please refer to the description of FIG. 5B to FIG. 5C, which will not be repeated here.

Fig. 9B schematically shows a flowchart of the operation method of the voice interaction device according to the seventh embodiment of the present disclosure.

According to the embodiment of the present disclosure, after the voice interaction device is not the first voice interaction device and is switched to the sleep state by operation S603, the first voice input corresponding to the first voice instruction issued by the user again can also be collected, and When the user's first voice input is received again, the parameter information is re-transmitted to the control device through an operation similar to operation S601, so that the control device re-determines the first voice interaction device through operation S513.

According to the embodiment of the present disclosure, in the case where the voice interaction device is the first voice interaction device after re-determination and switches to the wake-up state in response to the wake-up instruction sent by the control device, as shown in FIG. 9B, the operation of the voice interaction device The method may further include operations S913 to S914.

In operation S913, when the fourth voice input of the user is collected, an acquisition request is sent to the control device; in operation S914, the execution progress information of the third operation sent by the control device in response to the acquisition request is received; and in operation S915, Perform the third operation according to the execution progress information. Wherein, the fourth voice input may specifically be a voice input corresponding to the user's voice command "continue" or "continue playing". For details, please refer to the description of operation S514 in FIG. 5C, which will not be repeated here.

In summary, the voice interaction device of the embodiment of the present disclosure can make the re-determined first voice interaction device continue to execute the first voice interaction device executed by the original first voice interaction device in response to the user's voice instruction through the above operations S913 to S915. Three operations, thereby avoiding repeated execution of some operations, and thus avoiding the defect of wasting user time, and effectively improving user experience.

Fig. 10 schematically shows a structural block diagram of a control device according to an embodiment of the present disclosure.

As shown in FIG. 10, the control device 1000 includes a parameter information receiving module 1001, a demand information determining module 1002, a first device determining module 1003, and an instruction sending module 1004.

The parameter information receiving module 1001 is configured to receive multiple parameter information respectively sent by multiple voice interaction devices (operation S201), and the multiple parameter information is when the multiple voice interaction devices collect the first voice input of the user at the same time Sent.

The requirement information determining module 1002 is configured to determine the requirement information of the user according to the first voice input (operation S202). Wherein, the first voice input includes a predetermined voice input and a voice input that characterizes the needs of the user.

The first device determining module 1003 is configured to determine the first voice interaction device among the multiple voice interaction devices as the device that interacts with the user according to multiple parameter information and demand information (operation S203).

The instruction sending module 1004 is configured to send a wake-up instruction to the first voice interaction device, and send a non-wake-up instruction to voice interaction devices other than the first voice interaction device among the multiple voice interaction devices (operation S204).

According to an embodiment of the present disclosure, the above-mentioned parameter information includes performance parameters of the voice interaction device, and the first device determining module 1003 is specifically configured to: determine according to the matching relationship between the performance parameters of each voice device in the multiple voice interaction devices and the demand information The first voice interaction device.

According to an embodiment of the present disclosure, the aforementioned parameter information further includes location information of the user. As shown in FIG. 10, the first device determination module 1003 may include a first determination sub-module 10031 and a second determination sub-module 10032. The first determining submodule 10031 is configured to determine at least one second voice interaction device whose performance parameters match the user's demand information among the multiple voice interaction devices (operation S213). The second determining submodule 10032 is configured to determine one of the at least one second voice interaction device as the first voice interaction device according to the user's location information in the parameter information sent by the at least one second voice interaction device (operation S223). Among them, the location information of the user represents the location of the user relative to the voice interaction device.

According to an embodiment of the present disclosure, the aforementioned parameter information includes operation information of the voice interaction device, and the non-wake-up instruction includes a sleep instruction and a sleep instruction. As shown in FIG. 10, the above-mentioned instruction sending module 1004 may include an operation determining sub-module 10041 and an instruction sending sub-module 10042. The operation determining sub-module 10041 is configured to determine whether the other voice interaction device performs the first operation when collecting the first voice input according to the operation information of the other voice interaction device (operation S214). The instruction sending submodule 10042 is configured to send a sleep instruction to other voice interaction devices that perform the first operation, and send a sleep instruction to other voice interaction devices that do not perform the first operation (operation S224). Wherein, the voice interaction device is in a sleep state in response to the sleep instruction, and the sleep state includes a state in which the first operation is performed and does not respond to the collected voice input of the user; the voice interaction device responds to the sleep instruction In a sleep state, the sleep state includes a state where no operation is performed.

According to an embodiment of the present disclosure, as shown in Fig. 10, the above-mentioned control device 1000 may further include a first voice information receiving module 1005, a first voice information determining module 1006, and a first voice information sending module 1007, for example. The first voice information receiving module 1005 is configured to receive first voice information sent by the first voice interaction device when the user's second voice input is collected (operation S305), where the first voice information corresponds to the second voice input . The first voice information determining module 1006 is used to determine whether the first voice information is general voice information (operation S306). The first voice information sending module 1007 is configured to send the first voice information to multiple voice interaction devices (operation S307) when the first voice information is general voice information (operation S307), so that the multiple voice interaction devices execute the second voice Enter the corresponding operation.

According to an embodiment of the present disclosure, as shown in FIG. 10, the aforementioned control device 1000 may, for example, further include a restoration request receiving module 1008, which is configured to receive a restoration request sent by the first voice interaction device (operation S408), The restoration request is sent by the first voice interaction device when the user's third voice input is collected or the user's voice input is not collected within a preset time period; accordingly, the above-mentioned instruction sending module 1004 is also used to receive the restoration request When the module 1008 receives the recovery request, it sends a recovery instruction to the multiple voice interaction devices to restore the multiple voice interaction devices to the state before collecting the first voice input (operation S409).

According to an embodiment of the present disclosure, as shown in FIG. 10, the aforementioned control device 1000 may further include an operation monitoring module 1009, a synchronization request sending module 1010, and a first progress information receiving module 1011, for example. The operation monitoring module 1009 is configured to monitor the operation performed by the first voice interaction device after the command sending module sends the wake-up instruction, and determine whether the first voice interaction device performs the third operation (operation S510). The synchronization request sending module 1010 is configured to send a synchronization request to the first voice interaction device when it is determined that the first voice interaction device performs the third operation (operation S511). The first progress information receiving module 1011 is configured to receive the execution progress information of the third operation sent by the first voice interaction device in response to the synchronization request (operation S512).

According to an embodiment of the present disclosure, the above-mentioned first device determining module 1003 is further configured to re-determine when the parameter information receiving module 1001 again receives at least one parameter information respectively sent by at least one voice interaction device among the multiple voice interaction devices The first voice interaction device (operation S513). As shown in FIG. 10, the above-mentioned control device 1000 may further include, for example, an acquisition request receiving module 1012 and a first progress information sending module 1013. The acquisition request receiving module 1012 is configured to receive the re-determined first voice interaction device that has collected the user’s information. An acquisition request sent in the case of a fourth voice input (operation S514). The first progress information sending module 1013 is configured to send execution progress information to the re-determined first voice interaction device in response to the re-determined acquisition request of the first voice interaction device (operation S515).

According to the embodiments of the present disclosure, any number of modules, submodules, units, and subunits, or at least part of the functions of any number of them, may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be split into multiple modules for implementation. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), System-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or hardware or firmware in any other reasonable way that integrates or encapsulates the circuit, or can be implemented by software, hardware, and firmware. Any one of these implementations or an appropriate combination of any of them can be implemented. Alternatively, one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be at least partially implemented as a computer program module, and the computer program module may perform corresponding functions when it is executed.

For example, the parameter information receiving module 1001, the demand information determining module 1002, the first device determining module 1003, the instruction sending module 1004, the first voice information receiving module 1005, the first voice information determining module 1006, and the first voice information sending module 1007, Recovery request receiving module 1008, operation monitoring module 1009, synchronization request sending module 1010, first progress information receiving module 1011, acquisition request receiving module 1012, first progress information sending module 1013, first determining submodule 10031, and second determining submodule Any number of the module 10032, the operation determination sub-module 10041, and the instruction sending sub-module 10042 may be combined into one module for implementation, or any one of the modules may be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to the embodiment of the present disclosure, the parameter information receiving module 1001, the demand information determining module 1002, the first device determining module 1003, the instruction sending module 1004, the first voice information receiving module 1005, the first voice information determining module 1006, and the first voice Information sending module 1007, recovery request receiving module 1008, operation monitoring module 1009, synchronization request sending module 1010, first progress information receiving module 1011, acquisition request receiving module 1012, first progress information sending module 1013, first determining submodule 10031 And at least one of the second determining submodule 10032, the operation determining submodule 10041, and the instruction sending submodule 10042 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA) , System-on-chip, system-on-substrate, system-on-package, application-specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way to integrate or package the circuit, or by software, hardware and firmware Any one of the three implementation methods or an appropriate combination of any of them can be implemented. Or, the parameter information receiving module 1001, the demand information determining module 1002, the first device determining module 1003, the instruction sending module 1004, the first voice information receiving module 1005, the first voice information determining module 1006, and the first voice information sending module 1007, Recovery request receiving module 1008, operation monitoring module 1009, synchronization request sending module 1010, first progress information receiving module 1011, acquisition request receiving module 1012, first progress information sending module 1013, first determining submodule 10031, and second determining submodule At least one of the module 10032, the operation determining sub-module 10041, and the instruction sending sub-module 10042 may be at least partially implemented as a computer program module, and when the computer program module is run, it may perform a corresponding function.

Fig. 11 schematically shows a structural block diagram of a voice interaction device according to an embodiment of the present disclosure.

As shown in FIG. 11, the voice interaction device 1100 includes a parameter information sending module 1101, an instruction receiving module 1102, and a state switching module 1103.

The parameter information sending module 1101 is configured to send parameter information to the control device when the user's first voice input is collected (operation S601) to determine whether the voice interaction device is the first voice interaction device. Wherein, the first voice input includes a predetermined voice input and a voice input that characterizes user needs.

The instruction receiving module 1102 is configured to receive a wake-up instruction sent by the control device when the voice interaction device is the first voice interaction device. The state switching module 1103 is configured to switch the current state to the wake-up state in response to the wake-up instruction when the instruction receiving module 1102 receives the wake-up instruction (operation S602). Alternatively, the instruction receiving module 1102 is configured to receive a non-wake-up instruction sent by the control device when the voice interaction device is not the first voice interaction device. The state switching module 1103 is configured to switch the current state to the non-awakening state in response to the non-awakening instruction when the instruction receiving module 1102 receives the non-awakening instruction (operation S603).

According to an embodiment of the present disclosure, the above parameter information includes performance parameters of the voice interaction device. As shown in FIG. 11, the above-mentioned voice interaction device 1100 may, for example, further include a performance parameter obtaining module 1104 for obtaining performance parameters before the parameter information sending module 1101 sends parameter information to the control device (operation S604).

According to an embodiment of the present disclosure, the aforementioned parameter information further includes location information of the user. As shown in FIG. 11, the above-mentioned voice interaction device 1100 may further include, for example, a location information determining module 1105, configured to determine the location information of the user according to the collected first voice input of the user (operation S605). Among them, the location information of the user represents the location of the user relative to the voice interaction device.

According to an embodiment of the present disclosure, the aforementioned parameter information includes operation information of the voice interaction device, and the non-wake-up instruction includes a sleep instruction and a sleep instruction. In the case where the operation information indicates that the voice interaction device performs the first operation, the non-wake-up instruction received by the instruction receiving module 1102 is a sleep instruction, and the state switching module 1103 switches the current state to the sleep state in response to the sleep instruction. It includes a state where the first operation is performed and the collected voice input of the user is not responded. Or, when the operation information indicates that the voice interaction device does not perform the first operation, the non-wake-up instruction received by the instruction receiving module 1102 is a sleep instruction, and the state switching module 1103 switches the current state to the sleep state in response to the sleep instruction. The state includes the state where no operation is performed.

According to an embodiment of the present disclosure, as shown in FIG. 11, the aforementioned voice interaction device 1100 may further include, for example, a second voice information determining module 1106 and a second voice information sending module 1107. The second voice information determining module 1106 is configured to determine whether the first voice information corresponding to the second voice input is general voice information when the user is in an awake state and the second voice input of the user is collected (operation S706). The second voice information sending module 1107 is configured to send the first voice information to the control device when it is determined that the first voice information is general voice information (operation S707). And/or, as shown in FIG. 11, the voice interaction apparatus 1100 may further include a second voice information receiving module 1108 and an operation execution module 1109, for example. The second voice information receiving module 1108 is configured to receive second voice information belonging to general voice information sent by the control device (operation S708). The operation execution module 1109 is configured to perform a second operation according to the second voice information, and the second operation corresponds to a voice input corresponding to the second voice information (operation S709).

According to an embodiment of the present disclosure, as shown in FIG. 11, the above-mentioned voice interaction device 1100 may, for example, further include a recovery request sending module 1110, which is configured to be in an awake state and collect the user's third voice input or within a preset time period. If the user's voice input is not collected, a recovery request is sent to the control device (operation S810). And/or, the instruction receiving module 1102 is further configured to receive a recovery instruction sent by the control device; the state switching module 1103 is also configured to switch the current state to the state before the first voice input is collected in response to the recovery instruction (operation S811).

According to an embodiment of the present disclosure, as shown in FIG. 11, the above-mentioned voice interaction device 1100 may, for example, further include a second progress information sending module 1111, which is configured to respond to the control device when it is in an awake state and the third operation is performed. The sent synchronization request sends the execution progress information of the third operation to the control device (operation S912).

According to an embodiment of the present disclosure, as shown in FIG. 11, the above-mentioned voice interaction apparatus 1100 may further include an acquisition request sending module 1112, a second progress information receiving module 1113, and an operation execution module, for example. The acquisition request sending module 1112 is configured to send an acquisition request to the control device when the user is in the awake state and the fourth voice input of the user is collected (operation S913). The second progress information receiving module 1113 is configured to receive the execution progress information sent by the control device in response to the acquisition request (operation S914). The operation execution module is configured to execute the third operation according to the execution progress information (operation S915). The third operation corresponds to the fourth voice input, and the operation execution module may specifically be the operation execution module 1109 described above.

For example, the parameter information sending module 1101, the instruction receiving module 1102, the state switching module 1103, the performance parameter obtaining module 1104, the location information determining module 1105, the second voice information determining module 1106, the second voice information sending module 1107, the second voice information Any number of the receiving module 1108, the operation execution module 1109, the recovery request sending module 1110, the second progress information sending module 1111, the acquisition request sending module 1112, and the second progress information receiving module 1113 can be combined into one module for implementation, or Any one of these modules can be split into multiple modules. Or, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to the embodiment of the present disclosure, the parameter information sending module 1101, the instruction receiving module 1102, the state switching module 1103, the performance parameter acquiring module 1104, the position information determining module 1105, the second voice information determining module 1106, and the second voice information sending module 1107 At least one of the second voice information receiving module 1108, the operation execution module 1109, the restoration request sending module 1110, the second progress information sending module 1111, the acquisition request sending module 1112, and the second progress information receiving module 1113 may be at least partially Implemented as a hardware circuit, such as field programmable gate array (FPGA), programmable logic array (PLA), system on chip, system on substrate, system on package, application specific integrated circuit (ASIC), or can be integrated by circuit Or encapsulated in any other reasonable way such as hardware or firmware, or implemented in any one of the three implementation ways of software, hardware, and firmware, or an appropriate combination of any of them. Or, the parameter information sending module 1101, the instruction receiving module 1102, the state switching module 1103, the performance parameter acquiring module 1104, the location information determining module 1105, the second voice information determining module 1106, the second voice information sending module 1107, the second voice information At least one of the receiving module 1108, the operation execution module 1109, the recovery request sending module 1110, the second progress information sending module 1111, the acquisition request sending module 1112, and the second progress information receiving module 1113 may be at least partially implemented as a computer program module When the computer program module is running, it can execute the corresponding function.

According to an embodiment of the present disclosure, an electronic device is also provided, which can be used to perform the operation method of the control device described in FIGS. 2A to 5C, and can also be used to perform the voice interaction described with reference to FIGS. 6A to 9B How to operate the device. Correspondingly, the electronic device includes both the control device described with reference to FIG. 10 and the voice interaction device described in FIG. 11. The electronic device may be integrated and controlled in any one of the multiple voice interaction devices described with reference to FIG. The electronic device formed by the device, or the control device and the voice interaction device may be two functional modules in the electronic device, and the two functional modules can interact, which will not be repeated here.

Fig. 12 schematically shows a block diagram of an electronic device suitable for performing an operating method of a control device or an operating method of a voice interaction device according to an embodiment of the present disclosure. The electronic device shown in FIG. 12 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 12, an electronic device 1200 according to an embodiment of the present disclosure includes a processor 1201, which can be loaded into a random access memory (RAM) 1203 according to a program stored in a read only memory (ROM) 1202 or from a storage part 1208 The program executes various appropriate actions and processing. The processor 1201 may include, for example, a general-purpose microprocessor (for example, a CPU), an instruction set processor and/or a related chipset and/or a special purpose microprocessor (for example, an application specific integrated circuit (ASIC)), and so on. The processor 1201 may also include on-board memory for caching purposes. The processor 1201 may include a single processing unit or multiple processing units for performing different actions of a method flow according to an embodiment of the present disclosure.

In the RAM 1203, various programs and data required for the operation of the electronic device 1200 are stored. The processor 1201, the ROM 1202, and the RAM 1203 are connected to each other through a bus 1204. The processor 1201 executes various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 1202 and/or RAM 1203. It should be noted that the program may also be stored in one or more memories other than the ROM 1202 and RAM 1203. The processor 1201 may also execute various operations of the method flow according to the embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 1200 may further include an input/output (I/O) interface 1205, and the input/output (I/O) interface 1205 is also connected to the bus 1204. The electronic device 1200 may also include one or more of the following components connected to the I/O interface 1205: an input part 1206 including a keyboard, a mouse, etc.; including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and An output section 1207 of a speaker and the like; a storage section 1208 including a hard disk and the like; and a communication section 1209 including a network interface card such as a LAN card, a modem, and the like. The communication section 1209 performs communication processing via a network such as the Internet. The driver 1210 is also connected to the I/O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed, so that the computer program read therefrom is installed into the storage portion 1208 as needed.

According to the embodiment of the present disclosure, the method flow according to the embodiment of the present disclosure may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication part 1209, and/or installed from the removable medium 1211. When the computer program is executed by the processor 1201, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to the embodiments of the present disclosure, the above-described systems, devices, devices, modules, units, etc. may be implemented by computer program modules.

The present disclosure also provides a computer-readable storage medium. The computer-readable storage medium may be included in the device/device/system described in the above embodiment; or it may exist alone without being assembled into the device/ In the device/system. The aforementioned computer-readable storage medium carries one or more programs, and when the aforementioned one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but not limited to: portable computer disk, hard disk, random access memory (RAM), read-only memory (ROM) , Erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include one or more memories other than the ROM 1202 and/or RAM 1203 and/or ROM 1202 and RAM 1203 described above.

The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions, and operations of the system, method, and computer program product according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the above-mentioned module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions. It should also be noted that, in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be It is realized by a combination of dedicated hardware and computer instructions.

Those skilled in the art can understand that the features described in the various embodiments of the present disclosure and/or the claims can be combined or/or combined in various ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the various embodiments of the present disclosure and/or the features described in the claims can be combined and/or combined in various ways. All these combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only, and are not intended to limit the scope of the present disclosure. Although the respective embodiments are described above, this does not mean that the measures in the respective embodiments cannot be advantageously used in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and these substitutions and modifications should fall within the scope of the present disclosure.

Claims

An operation method of a control device includes:

Receiving multiple pieces of parameter information respectively sent by multiple voice interaction devices, the multiple pieces of parameter information being sent by the multiple voice interaction devices when the first voice input of the user at the same time is collected;

Determine the demand information of the user according to the first voice input;

Determine, according to the multiple parameter information and the demand information, the first voice interaction device among the multiple voice interaction devices as the device that interacts with the user; and

Sending a wake-up instruction to the first voice interaction device, and sending a non-wake-up instruction to voice interaction devices other than the first voice interaction device among the multiple voice interaction devices,

Wherein, the first voice input includes a predetermined voice input and a voice input characterizing the needs of the user.
The method according to claim 1, wherein the parameter information includes performance parameters of a voice interaction device, and determining the first voice interaction device according to the multiple parameter information and the demand information comprises:

The first voice interaction device is determined according to the matching relationship between the performance parameter of each voice device in the multiple voice interaction devices and the demand information.
The method according to claim 2, wherein the parameter information further includes location information of the user, and the matching relationship between the performance parameter of each voice device in the plurality of voice interaction devices and the demand information , Determining that the first voice interaction device includes:

Determining at least one second voice interaction device of the plurality of voice interaction devices whose performance parameters match the user's demand information; and

Determining one of the at least one second voice interaction device as the first voice interaction device according to the user's location information in the parameter information sent by the at least one second voice interaction device,

Wherein, the location information of the user represents the location of the user relative to the voice interaction device.
The method of claim 1, wherein the parameter information includes operation information of a voice interaction device, the non-wake-up instruction includes a sleep instruction and a hibernation instruction, and sending a non-wake-up instruction to the other voice interaction device includes:

According to the operation information of the other voice interaction device, determine whether the other voice interaction device performs the first operation when collecting the first voice input; and

Sending the sleep instruction to other voice interaction devices that perform the first operation, and send the sleep instruction to other voice interaction devices that do not perform the first operation,

Wherein, the voice interaction device is in a sleep state in response to the sleep instruction, and the sleep state includes a state in which the first operation is performed and does not respond to the collected voice input of the user; the voice interaction device responds to the sleep instruction In a sleep state, the sleep state includes a state where no operation is performed.
The method according to claim 1, further comprising:

Receiving first voice information sent by the first voice interaction device when a second voice input of the user is collected, where the first voice information corresponds to the second voice input;

Determining whether the first voice information is general voice information; and

If the first voice information is the general voice information, sending the first voice information to the multiple voice interaction apparatuses.
The method according to claim 1, further comprising:

Receive a recovery request sent by the first voice interaction device, where the recovery request is collected by the first voice interaction device within the third voice input of the user or the user's voice input is not collected within a preset time period Send in case of; and

Sending a recovery instruction to the multiple voice interaction devices to restore the multiple voice interaction devices to a state before collecting the first voice input.
The method according to claim 1, wherein after sending a wake-up instruction to the first voice interaction device, the method further comprises:

Monitor the operation of the first voice interaction device, and determine whether the first voice interaction device performs a third operation;

When the first voice interaction device performs the third operation, sending a synchronization request to the first voice interaction device; and

Receiving execution progress information of the third operation sent by the first voice interaction apparatus in response to the synchronization request.
The method according to claim 7, further comprising:

In a case where at least one parameter information respectively sent by at least one voice interaction device among the multiple voice interaction devices is received again, re-determine the first voice interaction device;

Receiving the acquisition request sent by the re-determined first voice interaction device when the user's fourth voice input is collected; and

In response to the acquisition request of the re-determined first voice interaction device, sending the execution progress information to the re-determined first voice interaction device.
An operation method of a voice interaction device includes:

When the user's first voice input is collected, sending parameter information to the control device to determine whether the voice interaction device is the first voice interaction device;

In the case that the voice interaction device is the first voice interaction device, receiving a wake-up instruction sent by the control device to respond to the wake-up instruction to be in a wake-up state;

In the case that the voice interaction device is not the first voice interaction device, receiving a non-wake-up instruction sent by the control device in response to the non-wake-up instruction being in a non-wake-up state, wherein the first voice input includes a predetermined Voice input and voice input characterizing the needs of the user.
The method according to claim 9, wherein the parameter information includes performance parameters of the voice interaction device, and before sending the parameter information to the control device, the method further comprises: acquiring the performance parameters.
The method according to claim 10, wherein the parameter information further includes location information of the user, and before sending the parameter information to the control device, the method further includes:

The location information of the user is determined according to the collected first voice input of the user, wherein the location information of the user represents the location of the user relative to the voice interaction device.
The method according to claim 9, wherein the parameter information includes operation information of a voice interaction device, and the non-wake-up instruction includes a sleep instruction and a sleep instruction, wherein:

In the case where the operation information indicates that the voice interaction device performs the first operation, the received non-wake-up instruction is the sleep instruction, in response to the sleep instruction being in the sleep state, the sleep state includes executing the The first operation and the state of not responding to the collected voice input of the user;

In the case where the operation information indicates that the voice interaction device has not performed the first operation, the received non-wake-up instruction is the sleep instruction, in response to the sleep instruction being in the sleep state, the sleep state includes The state of not performing any operations.
The method according to claim 9, wherein:

The method also includes:

In the case where the voice interaction device is in an awake state and the second voice input of the user is collected, determining whether the first voice information corresponding to the second voice input is general voice information; and

In the case of determining that the first voice information is general voice information, send the first voice information to the control device; and/or

The method also includes:

Receiving second voice information belonging to the general voice information sent by the control device; and

Perform a second operation according to the second voice information, and the second operation corresponds to a voice input corresponding to the second voice information.
The method according to claim 9, wherein:

The method further includes: when the voice interaction device is in an awake state and the user's third voice input is collected or the user's voice input is not collected within a preset time period, sending to the control device Reinstatement request; and/or

The method further includes: receiving a recovery instruction sent by the control device, and switching the current state to a state before collecting the first voice input.
The method according to claim 9, wherein the method further comprises:

When the voice interaction device is in the awake state and the third operation is performed, in response to the synchronization request sent by the control device, the execution progress information of the third operation is sent to the control device.
The method according to claim 15, wherein the method further comprises:

When the voice interaction device is in an awake state and the fourth voice input of the user is collected, sending an acquisition request to the control device;

Receiving the execution progress information sent by the control device in response to the acquisition request; and

Execute the third operation according to the execution progress information,

Wherein, the third operation corresponds to the fourth voice input.
A control device includes:

The parameter information receiving module is configured to receive multiple parameter information respectively sent by multiple voice interaction devices, and the multiple parameter information is sent by the multiple voice interaction devices when the first voice input of the user at the same time is collected of;

A demand information determination module, configured to determine demand information of the user according to the first voice input;

A first device determining module, configured to determine, according to the multiple parameter information and the demand information, that the first voice interaction device among the multiple voice interaction devices is a device that interacts with the user; and

An instruction sending module, configured to send a wake-up instruction to the first voice interaction device, and send a non-wake-up instruction to voice interaction devices other than the first voice interaction device among the multiple voice interaction devices,

Wherein, the first voice input includes a predetermined voice input and a voice input characterizing the needs of the user.
A voice interaction device includes:

The parameter information sending module is configured to send parameter information to the control device when the user's first voice input is collected, so as to determine whether the voice interaction device is the first voice interaction device;

Command receiving module for:

In a case where the voice interaction device is the first voice interaction device, receiving a wake-up instruction sent by the control device;

In the case that the voice interaction device is not the first voice interaction device, receiving a non-wake-up instruction sent by the control device; and

State switching module for:

In the case that the instruction receiving module receives the wake-up instruction, in response to the wake-up instruction, switch the current state to the wake-up state;

In the case that the instruction receiving module receives the non-wake-up instruction, in response to the wake-up instruction, switch the current state to the non-wake-up state,

Wherein, the first voice input includes a predetermined voice input and a voice input characterizing the needs of the user.
An electronic device including:

The control device according to claim 17; and

The voice interaction device according to claim 18.
An electronic device including:

One or more processors;

Storage device for storing one or more programs,

Wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to execute:

The method according to any one of claims 1-8; and/or

The method according to any one of claims 9-16.
A computer-readable storage medium with executable instructions stored thereon, which when executed by a processor causes the processor to:

Perform the method according to any one of claims 1-8; and/or

Perform the method according to any one of claims 9-16.