CN112309378B - Voice recognition equipment and wake-up response method thereof as well as computer storage medium - Google Patents

Voice recognition equipment and wake-up response method thereof as well as computer storage medium Download PDF

Info

Publication number
CN112309378B
CN112309378B CN201910672104.XA CN201910672104A CN112309378B CN 112309378 B CN112309378 B CN 112309378B CN 201910672104 A CN201910672104 A CN 201910672104A CN 112309378 B CN112309378 B CN 112309378B
Authority
CN
China
Prior art keywords
direct
moment
voice recognition
equipment
wake
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910672104.XA
Other languages
Chinese (zh)
Other versions
CN112309378A (en
Inventor
何瑞澄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Midea Group Co Ltd
Guangdong Midea White Goods Technology Innovation Center Co Ltd
Original Assignee
Midea Group Co Ltd
Guangdong Midea White Goods Technology Innovation Center Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Midea Group Co Ltd, Guangdong Midea White Goods Technology Innovation Center Co Ltd filed Critical Midea Group Co Ltd
Priority to CN201910672104.XA priority Critical patent/CN112309378B/en
Priority to PCT/CN2019/123801 priority patent/WO2021012581A1/en
Publication of CN112309378A publication Critical patent/CN112309378A/en
Application granted granted Critical
Publication of CN112309378B publication Critical patent/CN112309378B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/283—Processing of data at an internetworking point of a home automation network
    • H04L12/2834—Switching of information between an external network and a home network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/2838—Distribution of signals within a home automation network, e.g. involving splitting/multiplexing signals to/from different paths
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/225—Feedback of the input speech
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Automation & Control Theory (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The application discloses a voice recognition device and a wake-up response method thereof, wherein a plurality of voice recognition devices form an area network, and the voice recognition devices are divided into a central device and at least one non-central device; the wake-up response method comprises the following steps: the central equipment collects voice signals and records the direct moment of the central equipment; the direct moment of the central equipment represents the moment when the voice signal is directly transmitted to the central equipment; receiving a direct moment of the non-central equipment, wherein the direct moment of the non-central equipment represents the moment of the voice signal direct to the non-central equipment; comparing the direct moment of the central equipment with the direct moment of the non-central equipment; and determining the voice recognition equipment to be responded, wherein the voice recognition equipment to be responded is the voice recognition equipment responding to the voice signal in the regional network. The wake-up response method of the present application enables a determination of one of a plurality of speech recognition devices responsive to the speech signal to respond to the speech signal.

Description

Voice recognition equipment and wake-up response method thereof as well as computer storage medium
Technical Field
The present application relates to the field of voice wake-up, and in particular, to a voice recognition device, a wake-up response method thereof, and a computer storage medium.
Background
Techniques such as speech recognition and speech interaction have been applied to various fields, and devices equipped with a speech recognition system generally respond to speech signals after they are awakened when they receive the speech signals.
For a plurality of voice recognition devices in the same area, a situation that the voice recognition devices are simultaneously awakened and responded by voice signals may occur, but in a general application scenario, a user obviously only wakes up one voice recognition device, and the simultaneous awakening and responding of the plurality of voice recognition devices can cause a problem of mutual interference among the plurality of voice recognition devices, for example, a voice broadcast by one voice recognition device in response to the voice signals is received and responded by another voice recognition device, and vice versa, namely, the problem of mutual interference is generated.
Disclosure of Invention
The application provides a wake-up response method of voice recognition equipment, the voice recognition equipment and a computer storage medium, which are used for solving the problem of mutual interference caused by the fact that a plurality of voice recognition equipment responds to wake-up voice simultaneously in the prior art.
In order to solve the technical problems, the application provides a wake-up response method of a voice recognition device, wherein a plurality of voice recognition devices form a network, and the voice recognition devices are divided into a central device and at least one non-central device; the wake-up response method comprises the following steps: the central equipment collects voice signals and records the direct moment of the central equipment; the direct moment of the central equipment represents the moment when the voice signal is directly transmitted to the central equipment; receiving a direct moment of the non-central equipment, wherein the direct moment of the non-central equipment represents the moment of the voice signal direct to the non-central equipment; comparing the direct moment of the central equipment with the direct moment of the non-central equipment; and determining the voice recognition equipment to be responded, wherein the voice recognition equipment to be responded is the voice recognition equipment responding to the voice signal in the regional network.
In order to solve the technical problems, the application provides a wake-up response method of a voice recognition device, wherein a plurality of voice recognition devices form an area network, and the voice recognition devices are divided into a central device and at least one non-central device; the wake-up response method comprises the following steps: the non-central equipment collects voice signals and records the direct moment of the non-central equipment; the direct moment of the non-central device represents the moment when the voice signal is directly transmitted to the non-central device; transmitting the direct moment of the non-central equipment to the central equipment, and determining the voice recognition equipment to be responded by comparing the direct moment of the non-central equipment with the direct moment of the central equipment by the central equipment; the direct moment of the central equipment represents the moment that the voice signal is directly transmitted to the central equipment, and the voice recognition equipment to be responded is the voice recognition equipment responding to the voice signal in the regional network.
To solve the above technical problem, the present application provides a voice recognition device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor is used for executing the computer program to implement the steps of the wake-up response method.
To solve the above technical problem, the present application provides a computer storage medium in which a computer program is stored, which when executed implements the steps of the wake-up response method described above.
In the wake-up response method, a plurality of voice recognition devices form a network, wherein the voice recognition devices acquire voice signals and record the direct moment that the voice signals directly reach the voice recognition devices. The plurality of speech recognition devices are divided into a hub device and at least one non-hub device. The central equipment acquires the direct moment of the central equipment and receives the direct moment of the non-central equipment; and then comparing the direct moment of the device with the direct moment of the non-central device so as to determine the voice recognition device to be responded, namely the voice recognition device responding to the voice signal in the local area network. In the application, after the voice recognition equipment forming the network is awakened by the voice signal, the voice recognition equipment temporarily does not respond, and the central equipment determines which to respond, thereby avoiding the problem that a plurality of voice recognition equipment mutually interfere after responding.
Drawings
FIG. 1 is a schematic diagram of a network formed by interconnecting voice recognition devices according to the present application;
FIG. 2 is a schematic flow chart of the wake-up response method of the speech recognition device of the present application applied to a single area network;
FIG. 3 is a flow chart of the wake-up response method of the speech recognition device of the present application applied to a multi-area network;
FIG. 4 is a schematic diagram of a hub device side workflow of a wake-up response method of a speech recognition device of the present application;
FIG. 5 is a non-hub device side workflow diagram of a wake-up response method of a speech recognition device of the present application;
FIG. 6 is a schematic diagram illustrating the structure of an embodiment of a speech recognition apparatus according to the present application;
FIG. 7 is a schematic diagram of a computer storage medium according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solution of the present application for those skilled in the art, the following describes in further detail a wake-up response method of a speech recognition device, a speech recognition device and a computer storage medium provided by the present application with reference to the accompanying drawings and detailed description.
The wake-up response method is applied to the situation that a plurality of voice recognition devices can respond to the same voice signal, and for the situation, taking the home appliance field as an example, a plurality of home appliances exist in the same area or a plurality of adjacent areas, wherein the home appliances have voice recognition functions, namely, are used as the voice recognition devices. For example, voice recognition equipment such as televisions, air conditioners, refrigerators and the like exist in a living room area; the kitchen area is provided with voice recognition equipment such as a refrigerator, a microwave oven, a hot water kettle, an electric cooker and the like. When a user sends out a voice signal in a living room area, due to the sound propagation characteristic, a plurality of home appliances in the living room area can receive the voice signal and respond to the voice signal, and at the moment, the situation that a plurality of home appliances respond can occur, in this case, the sound responded by the home appliances A can be received and responded by the home appliances B again, and then mutual interference among the home appliances is caused, so that the user cannot respond normally. Also, for example, when a user sends out a voice signal between a living room area and a kitchen area, both areas can receive the voice signal and respond to the voice signal, and a problem of mutual interference may occur.
For the voice recognition equipment, the mode of waking up before responding is adopted, namely, the voice recognition equipment is firstly waken up by a voice signal sent by a user, and then responds to the voice signal. In this regard, the present application introduces a selection determination mechanism between waking up and responding, i.e., after being woken up by a speech signal, it temporarily does not respond, and replies when it is determined that a response is required.
In particular, for a single area, a plurality of speech recognition devices are connected to each other to form an area network, wherein one speech recognition device acts as a hub device in the area network, and the hub device determines which speech recognition device in the area network responds to the speech signal.
For a plurality of areas, first, the central equipment of each area network determines the voice recognition equipment to be responded in the area network, and then, one first central equipment in all central equipment determines which area network is responded by the voice recognition equipment to be responded, so that the problem of mutual interference caused by the fact that the voice recognition equipment responds to the voice signals is solved.
In the application in the field of home appliances, since the central device needs to be able to cope with the voice signal of the user at any time to determine the device responding to the voice signal, a home appliance which is connected with a power supply for a long time and is basically not powered off is generally selected; and home appliances with the interactive screen are preferentially selected to be used as network center equipment, so that relevant settings can be conveniently carried out through the interactive screen. For example, a refrigerator serves as a center device.
In general, home devices in each area, such as a living room area and a kitchen area, may respectively form an area network, and the area network corresponds to the division of the areas, and in the network connection, the home devices in all areas in one home may be connected to each other to form an overall home device network without necessarily forming a separate area network.
The network formed by the application comprises a local area network formed by a WIFI wireless network, a local area network formed by a wired network, a local area network formed by Bluetooth mesh, a local area network formed by zigbee, a local area network formed by RS485, a local area network formed by LoRa, a local area network formed by 1394, a local area network formed by CAN and the like. Communication mechanisms of the constructed network include, but are not limited to, UDP, TCP/IP, HTTP, MQTT, coAP, etc., ensuring that each voice recognition device of the same network can perform information interaction quickly and reliably.
The wake-up response method of the present application will be described below, starting from a network constituted by a speech recognition device.
Referring to fig. 1, fig. 1 is a schematic diagram of a network formed by interconnecting voice recognition devices according to the present application. The area in fig. 1 is divided into a living room area a, a kitchen area B and a bedroom area C; in living room area a, the voice recognition apparatus includes: a refrigerator A1, a television A2 and an air purifier A3; in the kitchen area B, the voice recognition apparatus includes: a smoke exhaust ventilator B1, an electric cooker B2 and a wall breaking machine B3; in bedroom region C, the voice recognition apparatus includes: an air conditioner C1 and a humidifier C2. All speech recognition devices are connected to form a network, and the speech recognition devices in each region also form a regional network.
The voice devices in each local area network are divided into a central device and at least one non-central device, and the central device determines the voice recognition device to be responded to in the local area network. The central devices of all area networks are divided into a first central device and at least one second central device, and the first central device determines which area network to respond to the voice signal by the voice recognition device to respond to.
In some embodiments of the present application, the voice devices in the local area network are not only divided into a hub device and a non-hub device, but also further have wake-up priorities, where the wake-up priorities can be set by a manufacturer when leaving the factory of the voice recognition devices, and after the voice recognition devices are connected to form a network, the voice recognition device with the highest wake-up priority is automatically used as the hub device of the local area network; the wake-up priority can also be set when the network is built, set autonomously by a user, or set by a service provider building the network; according to the set wake-up priority, the voice recognition device with the highest wake-up priority serves as a central device of the network.
In the network shown in fig. 1, the priority order of the living room area a is A1 > A2 > A3, the priority order of the kitchen area B is B1 > B2 > B3, and the priority order of the bedroom area C is C1 > C2; wherein A1, B1 and C1 are respectively used as central devices of the regional networks where the respective devices are located. The priority ranking A1 > B1 > C1 is also arranged among the central devices of the regional networks, wherein A1 is used as a first central device, and B1 and C1 are used as second central devices.
The network shown in fig. 1 may implement wake-up responses in a single zone, as well as wake-up responses in multiple zones. Referring to fig. 2 and fig. 4, fig. 2 is a flow chart of the wake-up response method of the voice recognition device applied to a single area network, and fig. 4 is a flow chart of the wake-up response method of the voice recognition device applied to a multi-area network.
As shown in fig. 2, for the implementation of the wake-up response method in a single area network, the following steps are included.
S201: the voice recognition equipment collects voice signals and records the direct moment.
In the step, the voice recognition equipment mainly performs two actions, namely acquisition and recording. After the user, namely the signal source, sends out the voice signal, the voice recognition equipment can collect the voice signal, and each voice recognition equipment is different in collected voice signal due to different relative positions with the user. Voice recognition devices, in which the user is relatively far away, may not be able to collect voice signals, although in a regional network.
The voice recognition devices record the voice signals collected by the voice recognition devices, and the recording mechanisms of all the voice recognition devices in each regional network are the same so as to facilitate subsequent comparison calculation. The speech recognition device records the direct moment, which represents the moment when the speech signal is directed to the speech recognition device.
The to-be-responded voice recognition equipment for responding to the voice signal is required to be determined according to the direct moment, so that information is attached to the direct moment, and the voice recognition equipment is identified.
In this embodiment, when the voice recognition device collects the voice signal, the direct time of the voice signal is recorded, specifically, the direct time indicates the first time when the voice signal directly arrives at the voice recognition device, for example, the voice signal is "hello", and the direct time is the time when the first sound in "you" is received.
The central equipment in the embodiment of the application collects voice signals and records the direct moment of the central equipment, wherein the direct moment of the central equipment refers to the first moment when the voice signals directly reach the central equipment; and the non-central equipment collects the voice signal and records the direct moment of the non-central equipment, wherein the direct moment of the non-central equipment refers to the first moment when the voice signal directly reaches the central equipment. I.e. the moment of arrival of the speech recognition device, is the first moment when the speech signal is directed to the speech recognition device.
In the area a of this embodiment, the direct time recorded by the device A1 is denoted as TA1, the direct time recorded by the device A2 is denoted as TA2, and the direct time recorded by the device A3 is denoted as TA3.
S202: the hub device receives the direct moment of the non-hub device.
After the voice recognition equipment records the direct moment, the non-central equipment sends the direct moment recorded by the non-central equipment to the central equipment. In this embodiment, the hub device A1 receives the direct time sent by the non-hub device.
S203: the central equipment compares the direct moment of the central equipment with the direct moment of the non-central equipment, and determines the voice recognition equipment to be responded.
In the step, the central equipment compares the direct moment of the central equipment with the direct moment of the non-central equipment, so as to determine the equipment to be recognized responding to the voice signal in the regional network. Specifically, the central equipment adopts a sequencing algorithm to compare the arrival times, and sequencing of all the arrival times is obtained, so that the earliest arrival time is obtained. The voice recognition device corresponding to the earliest direct moment represents the voice recognition device which collects the voice signal first, and the earlier the direct moment is, the larger the user is, the more likely the voice signal is sent to the voice recognition device. The voice recognition equipment corresponding to the earliest direct moment is the voice recognition equipment to be responded.
The ordering algorithm includes, but is not limited to, insert ordering, hill ordering, select ordering, heap ordering, bubble ordering, fast ordering, merge ordering, calculate ordering, bucket ordering, radix ordering, and the like. In this embodiment, the order of the direct time is TA2 < TA1 < TA3.
And determining the voice recognition equipment to be responded according to the comparison of the direct moments. There are various ways of specifying the process.
For example: after the earliest direct moment is obtained, the corresponding voice recognition equipment can be determined to be the voice recognition equipment to be responded.
Also for example: after the earliest direct moment is obtained, responding to the fact that the earliest direct moment is the direct moment of the central equipment, namely if the earliest direct moment is the direct moment of the central equipment, determining the central equipment as the voice recognition equipment to be responded.
Responding to the situation that the earliest direct moment is the direct moment of the non-central equipment, namely the earliest direct moment is the direct moment of the non-central equipment, and the earliest direct moment is TA2; the time difference between the direct time of the hub device and the earliest direct time is further calculated, i.e. the time difference δ=ta1-TA 2 is calculated.
Comparing the time difference delta and the wake-up threshold delta d The method comprises the steps of carrying out a first treatment on the surface of the If the time difference delta is greater than the wake-up threshold delta d Determining the voice recognition equipment corresponding to the earliest direct moment as the voice recognition equipment to be responded; responsive to the time difference delta being less than or equal to the wake threshold delta d And determining the central equipment as the voice recognition equipment to be responded.
The wake-up threshold is set in a number of ways. For example, the wake-up threshold is a value set in advance. The wake-up threshold can also be adjusted according to the specific use environment of the voice recognition equipment, for example, when the relative positions of the voice recognition equipment in the same network are concentrated, the wake-up threshold can be correspondingly reduced; when the relative positions of the voice recognition devices in the same network are more dispersed, the wake-up threshold can be correspondingly increased.
When the direct moment is compared and analyzed, the obtained earliest direct moment may be two or more, and at this time, the device responding to the voice signal is further determined according to the wake-up priority ordering of the voice recognition devices, that is, the voice recognition device with the highest priority is determined as the voice recognition device to be responded in the voice recognition device corresponding to the earliest direct moment.
S204: the hub device sends a notification to the non-hub device whether to respond to the voice signal.
After determining the speech recognition device to be responded to the speech signal, the hub device may send a notification to the non-hub device, i.e. to all speech recognition devices in the area network that are awakened but have not responded, whether to respond to the speech signal, which may be specific to the response or not, or the determined device information of the speech recognition device that responds to the speech signal. It is also possible to send only a notification to the speech recognition device to be responded, the other speech recognition devices that did not receive the notification do not respond, and the speech recognition devices that received the notification do respond.
S205: the to-be-responded to voice recognition device responds to the voice signal.
The determined speech recognition device may respond to the speech signal while the other speech recognition devices do not. It is ensured that only one speech recognition device responds to the speech signal without causing problems of mutual interference.
The method shown in fig. 2 is applied to voice wake-up recognition of a single area network, and after the voice recognition device in the single area network is woken up by voice information, the voice recognition device does not respond immediately, but after the central device of the single area network determines the responding device, the voice recognition device responds again.
The wake-up response method for the multi-area network is implemented based on the confirmation of the voice recognition device to be responded to in the single-area network shown in fig. 2. Specifically, the multi-area network is a plurality of interconnected area networks, the hub devices of each area network are interconnected and divided into a first hub device and at least one second hub device, and after each area network determines that the area network is to respond to the voice recognition device, the first hub device further confirms the voice recognition device responding to the voice signal.
The steps of the wake-up response method implemented by each lan in the multi-lan are not repeated, and referring to fig. 3, the wake-up response method of the multi-lan further includes the following steps.
S301: the second central device sends the second direct moment to the first central device, and the first central device receives the second direct moment.
In the multi-area network, the first central equipment needs to compare the direct moments of the voice recognition equipment to be responded in all the area networks so as to determine the voice recognition equipment responding to the voice signals, wherein the voice recognition equipment to be responded is the voice recognition equipment responding to the voice signals judged in the single area network; in the application of the multi-area network, the voice recognition equipment to be responded determined by the single area network does not respond immediately; but rather the first hub device then confirms from the plurality of speech recognition devices to be responded to which speech signal is responded to, i.e. determines the speech recognition device that ultimately responded to the speech signal. In this step S301, the second hub device sends the second direct moment to the first hub device, where the second direct moment is the direct moment of the to-be-responded speech recognition device in the area where the second hub device is located.
For example, in the area a, comparing TA1, TA2 and TA3 by A1, and determining that the voice recognition device to be responded is A2; in the area B, B1 compares TB1, TB2 and TB3, and determines that the voice recognition equipment to be responded is B3; in the area C, TC1 and TC2 are compared by C1, and the device to be responded is determined to be C1.
B1 sends the direct moment TB3 of the to-be-responded voice recognition device B3 of the regional network to A1, C1 also sends the direct moment TC1 to A1, and the direct moment TA2 of the to-be-responded voice recognition device A2 determined by A1 is determined by the to-be-responded voice recognition device.
S302: the first hub device compares the second arrival time with the first arrival time to determine a speech recognition device responsive to the speech signal.
The first central equipment compares the direct moment of each voice recognition equipment to be responded, namely a first direct moment and a second direct moment, wherein the first direct moment is the direct moment of the voice recognition equipment to be responded in the area network where the first central equipment is located.
The comparison process in the present step S302 is similar to the comparison process in the above step S203, and detailed description thereof will be omitted. Comparing the first direct moment with the second direct moment to obtain the earliest direct moment; and determining the response voice signal of the voice recognition equipment corresponding to the earliest direct moment.
For example, the first arrival time and the second arrival time may be compared to obtain the earliest arrival time; the speech recognition device corresponding to the earliest direct moment is determined to respond to the speech signal.
For example, the first direct time and the second direct time are compared to obtain the earliest direct time; if the earliest direct moment is the first direct moment, the first central equipment responds to the voice signal; if the earliest direct moment is the second direct moment, calculating a moment difference value between the first direct moment and the earliest direct moment; comparing the time difference value with a wake-up threshold value, and if the time difference value is larger than the wake-up threshold value, responding to the voice signal by the voice recognition equipment corresponding to the earliest direct time; and if the time difference value is less than or equal to the wake-up threshold value, responding to the voice signal by the first central equipment.
In this example, A1 compares TA2, TB3, TC1; thereby determining a speech recognition device, e.g. B3, responsive to the speech signal. Similarly, there may be two or more earliest direct moments, and at this time, the device that responds to the speech signal is further determined according to the wake-up priority ranking of the speech recognition devices, that is, the speech recognition device that has the highest priority among the speech recognition devices corresponding to the earliest direct moment is determined as the speech recognition device to be responded.
S303: the first hub device sends a notification to other voice recognition devices in the multi-zone network of whether to respond to the voice signal.
After determining the voice recognition device responding to the voice signal, the first central device may send the notification directly to the whole network, i.e. to the plurality of area networks, or may first send the notification to the central devices of the respective area networks, and then send the notification to the non-central devices by the respective central devices. Likewise, it may be transmitted only to the speech recognition device that responds to the speech signal, and the other device does not respond without receiving the notification.
S304: the determined speech recognition device is responsive to the speech signal.
The step S304 is similar to the step S205 described above, and will not be repeated.
The method shown in fig. 3 is applied to multi-area voice wake-up recognition, and after each area determines the voice device to which the area should respond, the first central device further determines which area of the voice device to respond to, so that only one voice recognition device is guaranteed to respond to the voice signal.
In the networks to which fig. 2 and 3 are applied, the voice recognition devices have the ranks of the wake priorities, so that when the voice recognition device of the highest priority fails, the voice recognition device of the next wake priority can be determined as the hub device or the first hub device according to the ranks of the wake priorities.
For the voice recognition equipment, whether the voice recognition equipment is the highest awakening priority in the area network or not can be periodically detected, and whether the voice recognition equipment is the highest awakening priority or not can also be detected when the area network is changed; if the highest wake-up priority in the current area network is detected, namely, the highest wake-up priority in the area network is detected, the central equipment is operated.
The wake-up response method is realized in the network, and is based on the fact that the voice recognition equipment in the network has wake-up priority ordering, and the voice recognition equipment can be used as network center equipment to compare the direct moments. Thus, for a speech recognition device newly added to the network, a wake-up mechanism consistent with the present embodiment is also required, and the relevant settings may be made by the hub device.
The hub device may obtain device information of the voice recognition devices joining the network. Analyzing the equipment information according to the preset rule so as to reorder the wake-up priorities of the voice recognition equipment in the network.
Each voice recognition device is provided with a voice recognition system, and the voice recognition system determines a wake-up priority, a voice recognition algorithm, a wake-up template and the like. If the newly joined speech recognition device has a different speech recognition system, i.e. it has a different wake priority setting, the network hub device may reorder according to its own wake priority setting. Such as networks A1-A2-A3, a newly joined speech recognition device A4 with wake priorities set to be greater than A3 may reorder the wake priorities to A1 > A2 > A4 > A3.
If the newly joined speech recognition device has the same speech recognition system, i.e. it has the same wake-up priority setting, the wake-up priority of the speech recognition device that joined the network first will be higher. For example, the newly added speech recognition device A3 has the same speech recognition system as the previous A3, and the previous A3 is a31, the newly added as a32, and the reordering of wake priorities is A1 > A2 > a31 > a32.
For the network of the present embodiment, all steps in which the wake-up response method is implemented may be completed within the network, so that the voice recognition device of the present embodiment may operate offline.
In the single area network formed by the interconnection of the above voice recognition devices, the voice recognition devices can operate as two roles, one as a hub device and the other as a non-hub device. For each voice recognition device, the voice recognition device can be used as a central device and has stronger and more functions; the device can be used as a non-central device and has the function of light weight.
In the field of household appliances, for large-scale household appliances such as refrigerators, televisions and the like, a voice recognition system with stronger functions can be loaded in the large-scale household appliances, so that the large-scale household appliances can be used as central equipment; for small household appliances, such as electric rice cookers, electric kettles and the like, a voice recognition system with a lightweight function can be loaded in the small household appliances, so that the small household appliances are used as non-central equipment only.
Referring to fig. 4, fig. 4 is a schematic workflow diagram of a central device end of a wake-up response method of a voice recognition device according to the present application, for a voice recognition device capable of being used as a central device of a network, to implement steps of the wake-up response method. The method for realizing the wake-up response as the network central equipment comprises the following steps.
S401: and collecting voice signals and recording the direct moment of the central equipment.
For the hub device in each area network, this step S401 is completed in the above step S201, which is not described in detail.
S402: the direct moment of the non-hub device is received.
The step S402 corresponds to the step S202, and is not described in detail.
S403: comparing the direct moment of the central equipment with the direct moment of the non-central equipment, and determining the voice recognition equipment to be responded in the regional network.
The step S403 is similar to the step S203, and detailed description thereof is omitted.
The steps of the method for implementing the single-area wake-up response method are described by taking the voice recognition device as the role of the central device, wherein the specific details of each step are also described above, so that the details of the operation of the central device are not repeated. The voice recognition apparatus of the present embodiment can determine one voice recognition apparatus in response to a voice signal from among a plurality of voice recognition apparatuses, thereby avoiding the problem of mutual interference in response.
Further, for a multi-area network, the hub device is further divided into a first hub device and a second hub device, and for the first hub device, it further performs the following steps.
S404: the first hub device receives the second direct moment.
The step S404 is completed in the step S301, and details are not repeated.
S406: the first arrival time and the second arrival time are compared to determine a speech recognition device responsive to the speech signal.
The step S406 is similar to the step S302, and detailed description thereof is omitted.
For the second hub device, it then performs the following steps.
S405: the second hub device transmits the second direct moment to the first hub device to compare the first direct moment with the second direct moment by the first hub device to determine a speech recognition device responsive to the speech signal.
The step S405 is completed in the above steps S301 to S302, and detailed description thereof will be omitted.
Further, in the multi-zone network, the first hub device further determines which of the zone networks to respond to the voice signal by the voice recognition device.
From the perspective of the non-hub device, please refer to fig. 5, and fig. 5 is a schematic workflow diagram of the non-hub device end of the wake-up response method of the voice recognition device according to the present application. The voice recognition device is used as a non-central device, and the wake-up response method of the embodiment comprises the following steps.
S501: and collecting voice signals and recording the direct moment of non-central equipment.
The step S501 is similar to the step S201, and is to obtain the direct moment, and the specific process is not described again.
S502: and sending the direct moment of the non-central equipment to the central equipment, so that the central equipment compares the direct moment of the non-central equipment with the direct moment of the central equipment to determine the voice recognition equipment to be responded.
As a non-central device, it does not respond to the voice signal immediately after collecting the voice signal, but records the direct moment, then transmits the direct moment to the central device for analysis and comparison, and the central device confirms the voice recognition device responding to the voice signal.
In this embodiment, the steps of the voice recognition device in implementing the wake-up response method are described by using the voice recognition device as a non-hub device, where specific details of each step are described above, so that details of operation of the non-hub device are not described again. The voice recognition device of the embodiment does not respond immediately after receiving the voice signal, but decides whether to respond after receiving the notification, thereby avoiding the problem of mutual interference caused by simultaneous response with other voice recognition devices.
The above wake-up response method is implemented by a voice recognition device, and thus the present application also proposes a voice recognition device, referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of the voice recognition device of the present application, where the voice recognition device 100 may be a home appliance, and includes a voice collector 11, a processor 12 and a memory 13 connected to each other, and the voice recognition device 100 of the present embodiment may implement the above wake-up response method. The voice collector 11 is used for collecting voice signals, the memory 13 stores a computer program, and the processor 12 is used for executing the computer program to implement the wake-up response method.
Specifically, the voice collector 11 is configured to collect a voice signal; the processor 12 is configured to record the direct moments of the speech recognition devices and compare all the direct moments to determine the speech recognition devices that respond to the speech signal; a notification is sent to the other speech recognition device whether to respond to the speech signal.
Alternatively, the voice collector 11 is configured to collect a voice signal; the processor 12 is configured to record a arrival time of the speech recognition device, send the arrival time to the hub device, and determine whether to respond according to the received notification of whether to respond to the speech signal sent by the hub device.
The processor 12 may be an integrated circuit chip having signal processing capabilities. Processor 12 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
For the method of the above embodiment, which may exist in the form of a computer program, the present application proposes a computer storage medium, please refer to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of the computer storage medium of the present application. The computer storage medium 200 of the present embodiment stores therein a computer program 21 that can be executed to implement the method in the above embodiment.
The computer storage medium 200 of this embodiment may be a medium that may store program instructions, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disc, or may be a server that stores the program instructions, and the server may send the stored program instructions to other devices for execution, or may also self-execute the stored program instructions.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description is only of embodiments of the present application, and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and the drawings of the present application or directly or indirectly applied to other related technical fields are included in the scope of the present application.

Claims (17)

1. A wake-up response method of a speech recognition device, wherein a plurality of speech recognition devices constitute a plurality of area networks, a plurality of the area networks are connected to each other, the plurality of speech recognition devices in each area network are divided into a hub device and at least one non-hub device, the hub devices of the plurality of area networks are divided into a first hub device and at least one second hub device, the wake-up response method comprising:
the central equipment in each regional network collects voice signals and records the direct moment of the central equipment; the direct moment of the central equipment represents the moment that the voice signal directly reaches the central equipment;
the central equipment in each regional network receives the direct moment of the non-central equipment in the same regional network, wherein the direct moment of the non-central equipment represents the moment of the voice signal direct to the non-central equipment;
The hub device in each regional network compares the direct moment of the hub device with the direct moment of the non-hub device;
determining voice recognition equipment to be responded in each regional network, wherein the voice recognition equipment to be responded is voice recognition equipment responding to the voice signals in the corresponding regional network;
the first central equipment receives a second direct moment, wherein the second direct moment is the direct moment of the voice recognition equipment to be responded of the regional network where the second central equipment is located;
the first central equipment compares the second direct time with a first direct time to determine a voice recognition equipment responding to the voice signal, wherein the first direct time is the direct time of the voice recognition equipment to be responded of the area network where the first central equipment is located.
2. The wake-up response method of claim 1, wherein the comparing the direct time of the hub device to the direct time of the non-hub device determines a voice recognition device to be responded to, comprising:
comparing the direct moment of the central equipment with the direct moment of the non-central equipment to obtain the earliest direct moment;
And determining the voice recognition equipment corresponding to the earliest direct moment as the voice recognition equipment to be responded.
3. The wake-up response method of claim 1, wherein the comparing the direct time of the hub device to the direct time of the non-hub device determines a voice recognition device to be responded to, comprising:
comparing the direct moment of the central equipment with the direct moment of the non-central equipment to obtain the earliest direct moment;
judging whether the earliest direct moment is the direct moment of the central equipment or not;
responding to the earliest direct moment as the direct moment of the central equipment, and determining the central equipment as the voice recognition equipment to be responded;
responding to the earliest direct moment not being the direct moment of the central equipment, and calculating a moment difference value between the direct moment of the central equipment and the earliest direct moment;
comparing the time difference value with a wake-up threshold value;
determining the voice recognition equipment corresponding to the earliest direct moment as the voice recognition equipment to be responded according to the fact that the moment difference value is larger than the awakening threshold value;
and responding to the time difference value being smaller than or equal to the wake-up threshold value, and determining the central equipment as the voice recognition equipment to be responded.
4. A wake-up response method according to claim 2 or 3, wherein the plurality of speech recognition devices have wake-up priorities; the determining that the voice recognition device corresponding to the earliest direct moment is the voice recognition device to be responded comprises:
and determining the voice recognition equipment with the highest wake-up priority as the voice recognition equipment to be responded in the voice recognition equipment corresponding to the earliest direct moment.
5. The wake-up response method of claim 1, wherein the wake-up response method further comprises:
the hub device sends a notification to the non-hub device whether to respond to the voice signal.
6. The wake-up response method of claim 1, wherein the comparing the second direct time and the first direct time to determine a speech recognition device responsive to the speech signal comprises:
comparing the first direct moment with the second direct moment to obtain the earliest direct moment;
and determining the voice recognition equipment corresponding to the earliest direct moment to respond to the voice signal.
7. The wake-up response method of claim 6, wherein the plurality of voice recognition devices have wake-up priorities; the determining that the voice recognition device corresponding to the earliest direct moment responds to the voice signal comprises the following steps:
And determining the voice recognition equipment with the highest wake-up priority from the voice recognition equipment corresponding to the earliest direct moment to respond to the voice signal.
8. The wake-up response method of claim 1, wherein the comparing the second direct time of day and the first direct time of day of the first hub device to determine a speech recognition device responsive to the speech signal comprises:
comparing the moment of the first direct moment with the moment of the second direct moment to obtain the earliest direct moment;
judging whether the earliest direct moment is the first direct moment or not;
determining that the first hub device is responsive to the voice signal in response to the earliest direct moment being the first direct moment;
responsive to the earliest direct moment not being the first direct moment, calculating a moment difference between the first direct moment and the earliest direct moment;
comparing the time difference value with a wake-up threshold value;
determining that the voice recognition equipment corresponding to the earliest direct moment responds to the voice signal in response to the moment difference value being larger than the awakening threshold value;
and in response to the time difference being less than or equal to the wake threshold, determining that the first hub device is responsive to the voice signal.
9. The wake-up response method of claim 8, wherein the plurality of voice recognition devices have wake-up priorities; the determining that the voice recognition device corresponding to the earliest direct moment responds to the voice signal comprises the following steps:
and determining the voice recognition equipment with the highest wake-up priority from the voice recognition equipment corresponding to the earliest direct moment to respond to the voice signal.
10. The wake-up response method of claim 1, wherein the wake-up response method further comprises:
the first hub device sends a notification to other voice recognition devices in the plurality of regional networks of whether to respond to the voice signal.
11. A wake-up response method of a speech recognition device, wherein a plurality of speech recognition devices constitute a plurality of area networks, a plurality of the area networks are connected to each other, the plurality of speech recognition devices in each area network are divided into a hub device and at least one non-hub device, the hub devices of the plurality of area networks are divided into a first hub device and at least one second hub device, the wake-up response method comprising:
the non-central equipment in each regional network collects voice signals and records the direct moment of the non-central equipment; the direct moment of the non-hub device represents the moment when the voice signal is directly directed to the non-hub device;
The non-central device in each regional network sends the direct moment of the non-central device to the central device in the same regional network so that the central device in each regional network compares the direct moment of the non-central device with the direct moment of the central device to determine the voice recognition device to be responded in each regional network;
the direct moment of the central equipment represents the moment that the voice signal is directly transmitted to the central equipment, and the voice recognition equipment to be responded is corresponding voice recognition equipment responding to the voice signal in the regional network;
the first central equipment receives a second direct moment, wherein the second direct moment is the direct moment of the voice recognition equipment to be responded of the regional network where the second central equipment is located;
the first central equipment compares the second direct time with a first direct time to determine a voice recognition equipment responding to the voice signal, wherein the first direct time is the direct time of the voice recognition equipment to be responded of the area network where the first central equipment is located.
12. The wake-up response method of claim 11, wherein the hub device compares a direct time of the hub device with a direct time of the non-hub device to determine a voice recognition device to be responded to, comprising:
The central equipment compares the direct moment of the central equipment with the direct moment of the non-central equipment to obtain the earliest direct moment;
and determining the voice recognition equipment corresponding to the earliest direct moment as the voice recognition equipment to be responded.
13. The wake-up response method of claim 11, wherein the comparing the direct time of the hub device to the direct time of the non-hub device determines a voice recognition device to be responded to, comprising:
comparing the direct moment of the central equipment with the direct moment of the non-central equipment to obtain the earliest direct moment;
judging whether the earliest direct moment is the direct moment of the central equipment or not;
responding to the earliest direct moment as the direct moment of the central equipment, and determining the central equipment as the voice recognition equipment to be responded;
responding to the earliest direct moment not being the direct moment of the central equipment, and calculating a moment difference value between the direct moment of the central equipment and the earliest direct moment;
comparing the time difference value with a wake-up threshold value;
determining the voice recognition equipment corresponding to the earliest direct moment as the voice recognition equipment to be responded according to the fact that the moment difference value is larger than the awakening threshold value;
And responding to the time difference value being smaller than or equal to the wake-up threshold value, and determining the central equipment as the voice recognition equipment to be responded.
14. The wake-up response method of claim 12 or 13, wherein the plurality of speech recognition devices have wake-up priorities; the determining that the voice recognition device corresponding to the earliest direct moment is the voice recognition device to be responded comprises:
and determining the voice recognition equipment with the highest wake-up priority as the voice recognition equipment to be responded in the voice recognition equipment corresponding to the earliest direct moment.
15. The wake-up response method of claim 11, wherein the wake-up response method further comprises:
and receiving a notification sent by the central equipment whether to respond to the voice signal.
16. A speech recognition device, characterized in that the speech recognition device comprises a processor and a memory; stored in the memory is a computer program, the processor being adapted to execute the computer program to carry out the steps of the method according to any one of claims 1-15.
17. A computer storage medium, characterized in that the computer storage medium stores a computer program that is executed to implement the steps of the method according to any of claims 1-15.
CN201910672104.XA 2019-07-24 2019-07-24 Voice recognition equipment and wake-up response method thereof as well as computer storage medium Active CN112309378B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910672104.XA CN112309378B (en) 2019-07-24 2019-07-24 Voice recognition equipment and wake-up response method thereof as well as computer storage medium
PCT/CN2019/123801 WO2021012581A1 (en) 2019-07-24 2019-12-06 Voice recognition device and wake-up response method therefor, and computer storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910672104.XA CN112309378B (en) 2019-07-24 2019-07-24 Voice recognition equipment and wake-up response method thereof as well as computer storage medium

Publications (2)

Publication Number Publication Date
CN112309378A CN112309378A (en) 2021-02-02
CN112309378B true CN112309378B (en) 2023-11-03

Family

ID=74193225

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910672104.XA Active CN112309378B (en) 2019-07-24 2019-07-24 Voice recognition equipment and wake-up response method thereof as well as computer storage medium

Country Status (2)

Country Link
CN (1) CN112309378B (en)
WO (1) WO2021012581A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113259736B (en) * 2021-05-08 2022-08-09 深圳市康意数码科技有限公司 Method for controlling television through voice and television
CN115223548B (en) * 2021-06-29 2023-03-14 达闼机器人股份有限公司 Voice interaction method, voice interaction device and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107919119A (en) * 2017-11-16 2018-04-17 百度在线网络技术（北京）有限公司 Method, apparatus, equipment and the computer-readable medium of more equipment interaction collaborations
CN108667697A (en) * 2018-04-28 2018-10-16 新华三技术有限公司 Voice control conflict resolution method and device and voice control system
CN109215663A (en) * 2018-10-11 2019-01-15 北京小米移动软件有限公司 Equipment awakening method and device
CN109377987A (en) * 2018-08-31 2019-02-22 百度在线网络技术（北京）有限公司 Exchange method, device, equipment and the storage medium of intelligent sound equipment room
CN109391528A (en) * 2018-08-31 2019-02-26 百度在线网络技术（北京）有限公司 Awakening method, device, equipment and the storage medium of speech-sound intelligent equipment
CN109754798A (en) * 2018-12-20 2019-05-14 歌尔股份有限公司 Multitone case synchronisation control means, system and speaker

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9652959B2 (en) * 2015-04-07 2017-05-16 Vivint, Inc. Smart wake
US10681032B2 (en) * 2016-06-01 2020-06-09 Ov Loop, Inc. System and method for voice authentication
CN105957519B (en) * 2016-06-30 2019-12-10 广东美的制冷设备有限公司 Method and system for simultaneously performing voice control on multiple regions, server and microphone
CN108831448B (en) * 2018-03-22 2021-03-02 北京小米移动软件有限公司 Method and device for controlling intelligent equipment through voice and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107919119A (en) * 2017-11-16 2018-04-17 百度在线网络技术（北京）有限公司 Method, apparatus, equipment and the computer-readable medium of more equipment interaction collaborations
CN108667697A (en) * 2018-04-28 2018-10-16 新华三技术有限公司 Voice control conflict resolution method and device and voice control system
CN109377987A (en) * 2018-08-31 2019-02-22 百度在线网络技术（北京）有限公司 Exchange method, device, equipment and the storage medium of intelligent sound equipment room
CN109391528A (en) * 2018-08-31 2019-02-26 百度在线网络技术（北京）有限公司 Awakening method, device, equipment and the storage medium of speech-sound intelligent equipment
CN109215663A (en) * 2018-10-11 2019-01-15 北京小米移动软件有限公司 Equipment awakening method and device
CN109754798A (en) * 2018-12-20 2019-05-14 歌尔股份有限公司 Multitone case synchronisation control means, system and speaker

Also Published As

Publication number Publication date
WO2021012581A1 (en) 2021-01-28
CN112309378A (en) 2021-02-02

Similar Documents

Publication Publication Date Title
CN111862988B (en) Voice recognition device, wake-up response method thereof, and computer storage medium
US9431014B2 (en) Intelligent placement of appliance response to voice command
US9846443B2 (en) Methods and systems for data interchange between a network-connected thermostat and cloud-based management server
US9887854B2 (en) Method and apparatus for dynamically changing group control mode by using user intervention information
US9143332B2 (en) Method and tool for wireless communications with sleeping devices in a wireless sensor control network
CN112309378B (en) Voice recognition equipment and wake-up response method thereof as well as computer storage medium
CN109240100A (en) Intelligent home furnishing control method, equipment, system and storage medium
CN104865835A (en) Intelligent household system based on ZigBee
CN111862964B (en) Voice recognition equipment and wake-up response method thereof as well as computer storage medium
CN115309062B (en) Control method and device of equipment, storage medium and electronic device
CN114302328B (en) Control method, device and system of intelligent equipment
CN115312048B (en) Equipment awakening method and device, storage medium and electronic device
CN114265327A (en) Dormancy control method and device for intelligent household equipment, processor and electronic equipment
CN115148204B (en) Voice wakeup processing method and device, storage medium and electronic device
KR102566857B1 (en) Home Automation System Device Power Optimization
CN117542356A (en) Voice wake-up method of intelligent equipment, storage medium and electronic device
CN112015102A (en) Upgrading method and device of intelligent control switch, intelligent control switch and storage medium
CN116483449A (en) Equipment awakening method and device, storage medium and electronic device
CN117527459A (en) Control method and device of intelligent equipment, storage medium and electronic device
CN104581792A (en) Zigbee backup system
CN113709714A (en) Networking method, bath controller and control device thereof, and water heater system
CN117542355A (en) Distributed voice awakening method and device, storage medium and electronic device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant