CN213092814U - Voice control system - Google Patents
Voice control system Download PDFInfo
- Publication number
- CN213092814U CN213092814U CN202021393072.4U CN202021393072U CN213092814U CN 213092814 U CN213092814 U CN 213092814U CN 202021393072 U CN202021393072 U CN 202021393072U CN 213092814 U CN213092814 U CN 213092814U
- Authority
- CN
- China
- Prior art keywords
- internet
- voice
- things
- recognition processing
- devices
- 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
Links
Images
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The application discloses speech control system includes: the system comprises a plurality of Internet of things devices and one or more voice recognition processing devices; the equipment of the Internet of things is distributed in the same or different spatial areas, networking is carried out on the equipment of the Internet of things based on a Wi-Fi Mesh protocol, and the equipment of the Internet of things is in communication connection through a formed Wi-Fi Mesh network; at least one of the plurality of Internet of things devices is provided with a voice acquisition module for acquiring audio signals and is configured to send the acquired audio signals to one or more voice recognition processing devices through a Wi-Fi Mesh network; the one or more voice recognition processing devices are configured to process the audio signals and send processed voice recognition processing results to one or more of the plurality of Internet of things devices; and the Internet of things equipment executes corresponding operation based on the voice recognition processing result. The method and the device can effectively expand the coverage area of the voice control system and can effectively reduce the load of the router.
Description
Technical Field
The application relates to a voice control system, in particular to a voice control system based on the Internet of things.
Background
With the continuous development of electronic technology, smart speakers have become popular in ordinary households. A user can control the intelligent household equipment through the intelligent sound box, such as turning on a television, setting the temperature of a refrigerator and the like; and songs on demand, online shopping and the like can be realized through the intelligent sound box. Nowadays, the common smart speakers in the market include mini smart speakers, tianmao smart speakers, millet AI speakers, and the like.
In the existing voice control system, the intelligent sound box generally realizes the functions of voice acquisition and semantic recognition, and sends an instruction to controlled intelligent home equipment in the system. Data forwarding is carried out between the intelligent sound box and the controlled intelligent household equipment through the router. All devices need to be connected to a router for data communication. Too many router connection devices will increase the load on the router. And, the way of forwarding data through the router will limit the coverage of the whole voice control system.
SUMMERY OF THE UTILITY MODEL
In order to solve the above problem, the present application provides a voice control system, including:
the system comprises a plurality of Internet of things devices and one or more voice recognition processing devices;
the plurality of Internet of things devices are distributed in the same or different spatial areas, are networked based on a Wi-Fi Mesh protocol and are in communication connection through a formed Wi-Fi Mesh network; at least one of the plurality of Internet of things devices is provided with a voice acquisition module for acquiring audio signals and is configured to send the acquired audio signals to the one or more voice recognition processing devices through the Wi-Fi Mesh network;
the one or more voice recognition processing devices are configured to process the audio signals and send processed voice recognition processing results to one or more of the plurality of internet of things devices;
one or more of the plurality of internet of things devices are configured to perform respective operations based on the speech recognition processing results.
Optionally, at least one of the one or more speech recognition processing devices is a local device disposed in the Wi-Fi Mesh network, or a cloud server connected to a router in the Wi-Fi Mesh network through a remote network.
Optionally, at least one of the one or more speech recognition processing devices is an internet of things device provided with a speech processing module and a semantic processing module or only provided with a speech processing module.
Optionally, at least one of the one or more speech recognition processing devices is a smart speaker.
Optionally, the cloud server has a voice processing module and a semantic processing module, or only has a semantic processing module.
Optionally, each spatial region is provided with at least one internet of things device including a voice acquisition module.
Optionally, the internet of things device including the voice acquisition module is an intelligent sound box.
Optionally, the internet of things device provided with the voice acquisition module has a trigger module for triggering acquisition when the audio signal in the current spatial region is monitored to exceed a preset intensity threshold.
Optionally, the one or more speech recognition processing devices are provided with a conversion module for performing format conversion on the audio signal, and an extraction module for performing keyword extraction.
Optionally, the plurality of internet of things devices include at least one of a household appliance, a lamp, a door lock, a switch, a socket, and a sound box.
According to the voice control system, free networking can be achieved among all Internet of things devices based on a Wi-Fi Mesh protocol, and communication connection is achieved through a formed Wi-Fi Mesh network. And each Internet of things device positioned in the Wi-Fi Mesh network can be used as a voice input device for sending the acquired audio signal to the voice recognition processing device for audio analysis, and can also be used as a controlled device for receiving the voice recognition processing result sent by the voice recognition processing device and executing corresponding operation. The voice control system Internet of things equipment can be distributed in the same or different spatial regions, and each Internet of things equipment can be used as node equipment in a Wi-Fi Mesh network to realize free networking. Any place where a node device of a Wi-Fi Mesh network is placed can have voice control over other devices in the network. Each Internet of things device has the functions of relaying and forwarding, and the coverage range of the voice control system is effectively expanded. In addition, each Internet of things device is independent, and even if some Internet of things device is abnormal, the normal work of other Internet of things devices cannot be influenced, and the reliability of the system is improved. In addition, only one or more devices in the whole Wi-Fi Mesh network are connected to the router, so that the load of the router is effectively reduced.
Each thing networking device can select whether to be equipped with pronunciation collection module, if be equipped with pronunciation collection module, then should correspond thing networking device and can carry out audio signal and gather. To a whole room voice control system, pronunciation collection module can be equipped with a plurality ofly, can set up at least one thing networking device including pronunciation collection module in every independent spatial region to realize the multilingual entry, increased speech recognition's scope. A plurality of internet of things devices comprising voice acquisition modules can be arranged when the space area is large, so that the voice control effect is guaranteed, and once one of the voice acquisition modules fails, the use of the whole system cannot be influenced.
The voice acquisition module directly sends the acquired audio signals to the voice recognition processing equipment without processing. The Internet of things equipment serving as the node only needs to acquire audio signals, complex data processing operation is not needed, the performance requirement on the Internet of things equipment is lowered, and the overall system cost is saved. After the voice recognition processing equipment processes the audio data to obtain a voice recognition processing result, the obtained processing result is directly sent to one or more pieces of Internet of things equipment, and the Internet of things equipment executes corresponding operation based on the voice recognition processing result. Data transmission is carried out between the Internet of things equipment and the voice recognition processing equipment through a Wi-Fi Mesh network, and one-to-many and many-to-many communication can be realized through the Wi-Fi Mesh, so that grouping control of the equipment can be realized in single communication, and the control is more intelligent and personalized.
According to the voice control system, the voice recognition processing equipment can be local equipment arranged in a Wi-Fi Mesh network, so that voice recognition can be realized locally. The voice recognition processing equipment can also be a cloud server connected with a router in the Wi-Fi Mesh network through a remote network, and online voice recognition is carried out through the cloud server. According to the voice control system, the voice control of the whole system can be realized by only arranging one voice recognition processing device locally through Mesh network networking, and the cost of the intelligent sound box control system is obviously reduced. Under the condition that the voice recognition processing equipment is not arranged locally, the system can be in butt joint with the existing voice cloud platform for online voice recognition, and the use scene of the system is expanded.
Drawings
Hereinafter, the present application will be further explained with reference to the drawings based on embodiments.
FIG. 1 schematically illustrates a schematic diagram of one embodiment of a speech control system according to the present application;
FIG. 2 schematically illustrates a schematic diagram of another embodiment of a speech control system according to the present application; and
fig. 3 schematically shows a schematic view of yet another embodiment of a speech control system according to the present application.
Detailed Description
The system of the present application will be described in detail below with reference to the figures and specific embodiments. It is to be understood that the embodiments shown in the drawings and described below are merely illustrative and not restrictive of the application.
FIG. 1 shows a schematic diagram of one embodiment of a speech control system according to the present application. The voice control system includes:
a plurality of internet of things devices 1 and one or more voice recognition processing devices 2;
the multiple pieces of Internet of things equipment 1 are distributed in the same or different spatial areas, and the multiple pieces of Internet of things equipment 1 are networked based on a Wi-Fi Mesh protocol and are in communication connection through a formed Wi-Fi Mesh network; at least one of the plurality of internet of things devices 1 is provided with a voice acquisition module for acquiring audio signals, the plurality of internet of things devices 1 are divided into internet of things devices 11 containing the voice acquisition module and internet of things devices 12 not containing the voice acquisition module according to whether the voice acquisition module is arranged or not, and the voice acquisition module is configured to send the acquired audio signals to one or more voice recognition processing devices 2 through a Wi-Fi Mesh network;
the one or more voice recognition processing devices 2 are configured to process the audio signals, and send the processed voice recognition processing results to one or more of the internet of things devices 1;
one or more of the plurality of internet of things devices 1 are configured to perform corresponding operations based on the received voice recognition processing result.
In the embodiment of the voice control system provided by the application, at least one of the internet of things devices 1 is provided with a voice acquisition module. This thing networking device 1 accessible pronunciation collection module gathers the audio signal in the environment to send the audio signal who gathers for speech recognition processing equipment 2 through Wi-Fi Mesh network.
The voice recognition processing device 2 performs signal analysis and processing on the received audio signal, and then sends a voice recognition processing result obtained through processing to the internet of things device 3. And after receiving the voice recognition processing result, the corresponding Internet of things equipment executes corresponding operation according to the voice recognition processing result.
According to the voice control system, free networking can be achieved among all Internet of things devices based on a Wi-Fi Mesh protocol, and communication connection is achieved through a formed Wi-Fi Mesh network. And each Internet of things device positioned in the Wi-Fi Mesh network can be used as a voice input device for sending the acquired audio signal to the voice recognition processing device for audio analysis, and can also be used as a controlled device for receiving the voice recognition processing result sent by the voice recognition processing device and executing corresponding operation. The Internet of things equipment can be distributed in the same or different spatial regions, and each Internet of things equipment can be used as node equipment in a Wi-Fi Mesh network to realize free networking. Any place where a node device of a Wi-Fi Mesh network is placed can have voice control over other devices in the network. Each Internet of things device has the functions of relaying and forwarding, and the coverage range of the voice control system is effectively expanded. In addition, each Internet of things device is independent, and even if some Internet of things device is abnormal, the normal work of other Internet of things devices cannot be influenced, and the reliability of the system is improved. In addition, only one or more devices in the whole Wi-Fi Mesh network are connected to the router, so that the load of the router is effectively reduced.
The voice acquisition module directly sends the acquired audio signals to the voice recognition processing equipment without processing. The Internet of things equipment serving as the node only needs to acquire audio signals, complex data processing operation is not needed, the performance requirement on the Internet of things equipment is lowered, and the overall system cost is saved. After the voice recognition processing equipment processes the audio data to obtain a voice recognition processing result, the obtained processing result is directly sent to one or more pieces of Internet of things equipment, and the Internet of things equipment executes corresponding operation based on the voice recognition processing result. Data transmission is carried out between the Internet of things equipment and the voice recognition processing equipment through a Wi-Fi Mesh network, and one-to-many and many-to-many communication can be realized through the Wi-Fi Mesh, so that grouping control of the equipment can be realized in single communication, and the control is more intelligent and personalized.
According to the voice control system, the voice recognition processing equipment can be local equipment arranged in a Wi-Fi Mesh network, so that voice recognition can be realized locally. The voice recognition processing equipment can also be a cloud server connected with a router in the Wi-Fi Mesh network through a remote network, and online voice recognition is carried out through the cloud server. The voice control system and the voice control method have the advantages that the Mesh network is adopted, the voice control of the whole system can be realized by only arranging one voice recognition processing device locally, and the cost of the voice control system is obviously reduced. Under the condition that the voice recognition processing equipment is not arranged locally, the system can be in butt joint with the existing voice cloud platform for online voice recognition, and the use scene of the system is expanded.
It should be understood that, in the embodiment of the present application, each of the multiple internet of things devices may select whether to configure the voice acquisition module. If the voice acquisition module is arranged, the corresponding Internet of things equipment can acquire audio signals. To a whole room voice control system, pronunciation collection module can be equipped with a plurality ofly, can set up at least one thing networking device including pronunciation collection module in every independent spatial region to realize the multilingual entry, increased speech recognition's scope. A plurality of internet of things devices comprising voice acquisition modules can be arranged when the space area is large, so that the voice control effect is guaranteed, and once one of the voice acquisition modules fails, the use of the whole system cannot be influenced. As a specific implementation mode, all the Internet of things equipment can be provided with the voice acquisition modules, or at least two of the Internet of things equipment are provided with the voice acquisition modules and have a plurality of audio data input, so that the purpose of improving the reliability of the whole system is achieved.
As a specific implementation manner, each spatial region may be provided with at least one internet of things device including a voice acquisition module. Therefore, audio data can be input into each independent space area, so that voice control can be realized in any space area, and the coverage range of a voice control system is further expanded. Each independent space region can be comprehensively considered based on factors such as the size and the cost of the region, and the number of the Internet of things devices comprising the voice acquisition module is set. For example, in consideration of cost reduction, only one internet of things device including a voice acquisition module may be arranged in each independent space region, and other internet of things devices may serve as a common control unit. When the space area is large, a plurality of internet of things devices comprising the voice acquisition module can be deployed according to the space area environment for better voice control experience.
The internet of things equipment provided with the voice acquisition module can be an intelligent sound box and can also be other internet of things equipment provided with the voice acquisition module.
The internet of things equipment provided with the voice acquisition module is provided with a trigger module which triggers acquisition when monitoring that the audio signal in the current space region exceeds a preset intensity threshold value, and triggers acquisition of the audio signal in the environment when the trigger module monitors that the audio signal in the current space region exceeds the preset intensity threshold value. After the internet of things equipment collects the audio signals, the audio signals are sent to the voice recognition processing equipment.
The voice recognition processing equipment is provided with a conversion module for carrying out format conversion on the audio signal and an extraction module for extracting keywords. After analysis processing operations such as format conversion, keyword extraction and the like are carried out on the audio signals, corresponding voice recognition processing results are generated and sent to the Internet of things equipment, and the Internet of things equipment executes corresponding operations after receiving the voice recognition processing results.
It should be understood that a plurality of internet of things devices of the present application include at least one of a home appliance, a door lock, a lamp, a switch, and a socket.
In one embodiment of the present application, at least one of the one or more speech recognition processing devices may be a local device disposed in a Wi-Fi Mesh network. Specifically, the voice recognition processing device may be an internet of things device provided in a Wi-Fi Mesh network. The Internet of things equipment can integrate two modules, namely a voice processing module and a semantic processing module, and carries out voice processing and semantic processing on collected audio signals so as to obtain a voice recognition processing result. Of course, the internet of things device may also be integrated with only a voice processing module, and only performs voice processing on the acquired audio signal. Specifically, referring to fig. 1, the voice processing module and the semantic processing module in the voice recognition processing device 2 may also be integrated in the internet of things device 1 (e.g., integrated in the internet of things device 11 having a voice acquisition module).
In another embodiment, at least one of the one or more speech recognition processing devices may also be a cloud server connected to a router in the Wi-Fi Mesh network via a remote network. The cloud server can integrate two modules, namely a voice processing module and a semantic processing module, and performs voice processing and semantic processing on the acquired audio signals so as to obtain a voice recognition processing result. The cloud server may also have only a semantic processing module. The local Internet of things equipment which is only provided with the voice processing module sends the audio signal subjected to voice processing to the cloud server, and the cloud server performs further semantic processing to finally obtain a voice recognition processing result.
FIG. 2 shows a schematic diagram of one embodiment of a speech control system according to the present application. In this embodiment, the voice recognition processing device is a local device 21 disposed in the Wi-Fi Mesh network, and is located in the same Wi-Fi Mesh network as other internet of things devices.
As shown in fig. 2, after the internet of things device 11 including the voice collection module collects the audio data, the audio data is sent to the voice recognition processing device 21 through the Wi-Fi Mesh network. After the voice local recognition is performed by the voice recognition processing device 21, a voice recognition processing result is generated based on the voice recognition processing result, and the voice recognition processing result is sent to the internet of things device 11/12 through the Wi-Fi Mesh network. And the data transmission of the audio data and the voice recognition processing result can realize local communication only through a Wi-Fi Mesh network without a router.
As a specific embodiment, the voice recognition processing device as the local device may be a device provided with a voice recognition processing module. In addition, the voice recognition processing device as the local device may further have a semantic processing module, and specifically, the voice recognition processing device as the local device may be an intelligent sound box, or may be other local internet of things devices having the voice recognition processing module and/or the semantic processing module, such as an intelligent lamp, a switch, and the like. The audio signals are collected through the intelligent sound box, and voice recognition processing is carried out on the audio signals to obtain a voice recognition processing result.
For example, when a user performs voice control in the bedroom 1, the internet of things device 11 provided with the voice acquisition module in the bedroom 1 acquires audio data of the user, and directly sends the audio data to the voice recognition processing device 21 in the living room through the Wi-Fi Mesh network for voice local recognition, and the voice recognition processing device 21 can directly send a voice recognition processing result to a corresponding internet of things device in the Wi-Fi Mesh network, so that the corresponding internet of things device executes corresponding operation.
It should be understood that, in the embodiment of the present application, each of the multiple internet of things devices may select whether to configure the voice acquisition module. If be equipped with this corresponding thing networking device of voice acquisition module and can carry out audio signal and gather. A whole room system voice acquisition module can be equipped with a plurality ofly, sets up at least one thing networking device including voice acquisition module in every independent spatial region to realize the multilingual entry, increased speech recognition's scope. A plurality of internet of things devices comprising voice acquisition modules can be arranged when the space area is large, so that the voice control effect is guaranteed, and once one of the voice acquisition modules fails, the use of the whole system cannot be influenced. As a specific implementation mode, all the Internet of things equipment can be provided with the voice acquisition modules, or at least two of the Internet of things equipment are provided with the voice acquisition modules and have a plurality of audio data input, so that the purpose of improving the reliability of the whole system is achieved.
As a specific implementation manner, each spatial region may be provided with at least one internet of things device including a voice acquisition module. Therefore, audio data can be input into each independent space area, so that voice control can be realized in any space area, and the coverage range of a voice control system is further expanded. Each independent space region can be comprehensively considered based on factors such as the size and the cost of the region, and the number of the Internet of things devices comprising the voice acquisition module is set. For example, in consideration of cost reduction, only one internet of things device including a voice acquisition module may be arranged in each independent space region, and other internet of things devices may serve as a common control unit. When the space area is large, a plurality of internet of things devices comprising the voice acquisition module can be deployed according to the space area environment for better voice control experience.
The internet of things equipment provided with the voice acquisition module can be an intelligent sound box and can also be other internet of things equipment provided with the voice acquisition module.
The internet of things equipment provided with the voice acquisition module is provided with a trigger module which triggers acquisition when monitoring that the audio signal in the current space region exceeds a preset intensity threshold value, and triggers acquisition of the audio signal in the environment when the trigger module monitors that the audio signal in the current space region exceeds the preset intensity threshold value. After the internet of things equipment collects the audio signals, the audio signals are sent to the voice recognition processing equipment.
The voice recognition processing equipment is provided with a conversion module for carrying out format conversion on the audio signal and an extraction module for extracting keywords. After analysis processing operations such as format conversion, keyword extraction and the like are carried out on the audio signals, corresponding voice recognition processing results are generated and sent to the Internet of things equipment, and the Internet of things equipment executes corresponding operations after receiving the voice recognition processing results.
It should be understood that a plurality of internet of things devices of the present application include at least one of a home appliance, a lamp, a door lock, a switch, and a socket.
FIG. 3 shows a schematic diagram of one embodiment of a speech control system according to the present application. In this embodiment, the speech recognition processing device 2 is a cloud server 22 disposed in the cloud.
As shown in fig. 3, after the internet of things device 11 including the voice acquisition module acquires audio data, the audio data is sent to the router through the root node of the Wi-Fi Mesh network, and the router sends the audio data to the voice recognition processing device 22 located at the cloud. After the voice recognition processing device 22 performs voice online recognition, the voice recognition processing result is sent to the root node through the router, and then forwarded to the internet of things device 11/12 in the Wi-Fi Mesh network by the root node. It should be understood that, in the present application, the root node is a node device connected to a router in the Wi-Fi Mesh network, and when the root node fails, the Wi-Fi Mesh network reselects a new node connected to the external IP network, thereby avoiding a system problem caused by a local failure and improving the reliability of the system.
For example, when a user performs voice control in the bedroom 1, the internet of things device provided with the voice acquisition module in the bedroom 1 acquires audio data of the user, forwards the audio data to the cloud server through the root node in the Wi-Fi Mesh network for voice online identification, the cloud server returns the processing result to the root node, and the root node sends the processing result to the corresponding internet of things device in the Wi-Fi Mesh network to control the corresponding internet of things device to execute corresponding operation.
In this embodiment, the speech recognition processing device 22 located at the cloud end may integrate two modules, namely a speech processing module and a semantic processing module, and perform speech processing and semantic processing on the acquired audio signal, so as to obtain a speech recognition processing result. The cloud server may also have only a semantic processing module. The local Internet of things equipment which is only provided with the voice processing module sends the audio signal subjected to voice processing to the cloud server, and the cloud server performs further semantic processing to finally obtain a voice recognition processing result. The internet of things equipment which is located locally and is only provided with the voice processing module firstly converts the audio signals into word signals, then uploads the word signals to the cloud server for semantic processing, and the cloud server returns semantic conversion results to the internet of things equipment. For example: the user says in bedroom 1: the 'lamp of the living room is turned on', the internet of things device 11 located in the bedroom 1 converts the audio signal into a text signal, then the text signal is transmitted to the cloud server to be processed, and the cloud server returns the device ID and the control state which need to be actually controlled to the internet of things device so as to control the internet of things device.
It should be understood that, in the embodiment of the present application, each of the multiple internet of things devices may select whether to configure the voice acquisition module. If be equipped with this corresponding thing networking device of voice acquisition module and can carry out audio signal and gather. A whole room system voice acquisition module can be equipped with a plurality ofly, sets up at least one thing networking device including voice acquisition module in every independent spatial region to realize the multilingual entry, increased speech recognition's scope. A plurality of internet of things devices comprising voice acquisition modules can be arranged when the space area is large, so that the voice control effect is guaranteed, and once one of the voice acquisition modules fails, the use of the whole system cannot be influenced. As a specific implementation mode, all the Internet of things equipment can be provided with the voice acquisition modules, or at least two of the Internet of things equipment are provided with the voice acquisition modules and have a plurality of audio data input, so that the purpose of improving the reliability of the whole system is achieved.
As a specific implementation manner, each spatial region may be provided with at least one internet of things device including a voice acquisition module. Therefore, audio data can be input into each independent space area, so that voice control can be realized in any space area, and the coverage range of a voice control system is further expanded. Each independent space region can be comprehensively considered based on factors such as the size and the cost of the region, and the number of the Internet of things devices comprising the voice acquisition module is set. For example, in consideration of cost reduction, only one internet of things device including a voice acquisition module may be arranged in each independent space region, and other internet of things devices may serve as a common control unit. When the space area is large, a plurality of internet of things devices comprising the voice acquisition module can be deployed according to the space area environment for better voice control experience.
The internet of things equipment provided with the voice acquisition module can be an intelligent sound box and can also be other internet of things equipment provided with the voice acquisition module.
The internet of things equipment provided with the voice acquisition module is provided with a trigger module which triggers acquisition when monitoring that the audio signal in the current space region exceeds a preset intensity threshold value, and triggers acquisition of the audio signal in the environment when the trigger module monitors that the audio signal in the current space region exceeds the preset intensity threshold value. After the internet of things equipment collects the audio signals, the audio signals are sent to the voice recognition processing equipment.
The voice/voice processing equipment is provided with a conversion module for carrying out format conversion on the audio signal and an extraction module for extracting keywords. After analysis processing operations such as format conversion, keyword extraction and the like are carried out on the audio signals, corresponding voice recognition processing results are generated and sent to the Internet of things equipment, and the Internet of things equipment executes corresponding operations after receiving the voice recognition processing results.
It should be understood that a plurality of internet of things devices of the present application include at least one of a home appliance, a lamp, a door lock, a switch, and a socket.
The voice control system provided by the application can be applied to various scenes such as intelligent home, intelligent office, intelligent factory and the like, and is not limited herein.
While various embodiments of aspects of the present application have been described for purposes of this disclosure, they are not to be construed as limiting the teachings of the present disclosure to these embodiments. Features disclosed in one particular embodiment are not limited to that embodiment, but may be combined with features disclosed in different embodiments. For example, one or more features and/or operations of a system according to the present application described in one embodiment may also be applied separately, in combination, or in whole in another embodiment. It will be understood by those skilled in the art that there are many more alternative embodiments and variations possible and that various changes and modifications may be made to the system described above without departing from the scope defined by the claims of the present application.
Claims (10)
1. A voice control system, comprising:
the system comprises a plurality of Internet of things devices and one or more voice recognition processing devices;
the plurality of Internet of things devices are distributed in the same or different spatial areas, are networked based on a Wi-FiMesh protocol and are in communication connection through a formed Wi-FiMesh network; at least one of the plurality of Internet of things devices is provided with a voice acquisition module for acquiring audio signals and is configured to send the acquired audio signals to the one or more voice recognition processing devices through the Wi-Fi Mesh network;
the one or more voice recognition processing devices are configured to process the audio signals and send processed voice recognition processing results to one or more of the plurality of internet of things devices;
one or more of the plurality of internet of things devices are configured to perform respective operations based on the speech recognition processing results.
2. The voice control system according to claim 1, wherein at least one of the one or more voice recognition processing devices is a local device provided in the Wi-Fi Mesh network or a cloud server connected to a router in the Wi-Fi Mesh network through a remote network.
3. The voice control system according to claim 2, wherein at least one of the one or more voice recognition processing devices is an internet of things device provided with a voice processing module and a semantic processing module or provided with only a voice processing module.
4. The voice control system of claim 2, wherein at least one of the one or more voice recognition processing devices is a smart speaker.
5. The voice control system according to claim 2, wherein the cloud server has a voice processing module and a semantic processing module, or only a semantic processing module.
6. The voice control system of claim 1, wherein at least one internet of things device comprising a voice acquisition module is provided for each spatial region.
7. The voice control system of claim 6, wherein the Internet of things device comprising the voice acquisition module is a smart sound box.
8. The voice control system according to claim 1, wherein the internet of things device provided with the voice acquisition module has a trigger module for triggering acquisition when the audio signal in the current spatial region is monitored to exceed a preset intensity threshold.
9. The voice control system according to claim 1, wherein a conversion module for performing format conversion on the audio signal and an extraction module for performing keyword extraction are provided in the one or more voice recognition processing devices.
10. The voice control system of claim 1, wherein the plurality of internet of things devices comprises at least one of a home appliance, a lamp, a door lock, a switch, a socket, and a sound box.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202021393072.4U CN213092814U (en) | 2020-07-15 | 2020-07-15 | Voice control system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202021393072.4U CN213092814U (en) | 2020-07-15 | 2020-07-15 | Voice control system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN213092814U true CN213092814U (en) | 2021-04-30 |
Family
ID=75624779
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202021393072.4U Active CN213092814U (en) | 2020-07-15 | 2020-07-15 | Voice control system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN213092814U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113703331A (en) * | 2021-08-27 | 2021-11-26 | 武汉市惊叹号科技有限公司 | Distributed control system based on integrated platform of Internet of things |
-
2020
- 2020-07-15 CN CN202021393072.4U patent/CN213092814U/en active Active
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113703331A (en) * | 2021-08-27 | 2021-11-26 | 武汉市惊叹号科技有限公司 | Distributed control system based on integrated platform of Internet of things |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3640936B1 (en) | Apparatus control device, method, and apparatus having same | |
CN104635501B (en) | Intelligent home furnishing control method and system | |
CN105208583B (en) | Method and device for configuring intelligent household electrical appliance to access network and intelligent equipment | |
CN105847099B (en) | Internet of things implementation system and method based on artificial intelligence | |
CN103941686B (en) | Sound control method and system | |
CN105392185B (en) | A kind of networking method of smart machine, apparatus and system | |
CN106597868A (en) | Intelligent home control system | |
US11250846B2 (en) | Voice enabled searching for wireless devices associated with a wireless network and voice enabled configuration thereof | |
CN112151013A (en) | Intelligent equipment interaction method | |
CN104902583A (en) | Infrared transmission WIFI networking method and system | |
CN105429883A (en) | Long connection method of multiple intelligent devices and server equipment and intelligent device | |
CN113053369A (en) | Voice control method and device of intelligent household appliance and intelligent household appliance | |
CN213092814U (en) | Voice control system | |
CN209373365U (en) | Wireless centralized manager and intelligent management system | |
CN111884887A (en) | Voice interaction method and device, storage medium and electronic device | |
CN115633292B (en) | Omnidirectional microphone flexible networking system and method of multistage cascade built-in loudspeaker | |
CN107770009B (en) | Control device, method, storage medium and equipment | |
CN104793508B (en) | Networking control method, device and system for household appliances | |
CN113992646B (en) | Internet of things equipment protocol integration method and system | |
CN110620711B (en) | Intelligent household client and multi-gateway control method thereof | |
CN113674738A (en) | Whole-house distributed voice system and method | |
CN104954462A (en) | High-concurrency extensible smart home communication method and high-concurrency extensible smart home communication system | |
CN104284011A (en) | Information processing method and electronic device | |
WO2018103623A1 (en) | Terminal control method and apparatus, and terminal system | |
CN105607498B (en) | A kind of matched method, apparatus of smart home device, equipment and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant |