CN112185377A - Method and device for solving intelligent voice repeated response - Google Patents
Method and device for solving intelligent voice repeated response Download PDFInfo
- Publication number
- CN112185377A CN112185377A CN202011042082.8A CN202011042082A CN112185377A CN 112185377 A CN112185377 A CN 112185377A CN 202011042082 A CN202011042082 A CN 202011042082A CN 112185377 A CN112185377 A CN 112185377A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- voice
- user
- data
- sound wave
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
- G10L17/22—Interactive procedures; Man-machine interfaces
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; 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
Abstract
The invention provides a method and a device for solving intelligent voice repeated response, wherein the method comprises the steps that a user issues a voice command, intelligent equipment receives the voice command and converts the voice command into a user sound wave intensity numerical value, each intelligent equipment transmits the user sound wave intensity numerical value to other intelligent equipment, each intelligent equipment compares the received user sound wave intensity data, when the intelligent equipment judges that the received user sound wave intensity data are lower than the user sound wave intensity data received by any other intelligent equipment, the intelligent equipment performs silence processing, and when the intelligent equipment judges that the received user sound wave intensity data are higher than the user sound wave intensity data received by other intelligent equipment, the intelligent equipment replies the voice command of the user. The method and the device provided by the invention can effectively ensure that the control interaction links are reduced, the signal transmission speed is accelerated, and the situations of repeated response and question answering of a plurality of devices can be effectively avoided.
Description
Technical Field
The invention relates to the technical field of voice recognition control, in particular to a method and a device for solving intelligent voice repeated response.
Background
Along with science and technology development, people have more and more smart devices in the family, and various smart devices all have intelligent voice response function, and voice response module has all been implanted to every equipment. However, with the diversification of devices, sometimes, when a user issues a voice command, the same brand of device may get multiple devices to answer simultaneously, or answer a question, that is, want to wake up the a device, and as a result, the a device does not wake up, but wakes up the B device. In a daily life scene, if a speaking person is far away from a microphone of the intelligent device, and noise, multipath reflection and reverberation exist around the speaking person, the quality of signals received by the microphone is also reduced, and the voice recognition rate is seriously influenced.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the prior art, and provide a method and a device for solving intelligent voice repeated response.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a method for solving intelligent voice repeated response comprises the following steps: and S01, the user issues a voice command. And S02, the intelligent device receives the voice command and converts the voice command into a user sound wave intensity value. And S03, each intelligent device transmits the user sound wave intensity value to other intelligent devices. And S04, each intelligent device compares the received sound wave intensity data of the user. When the intelligent device judges that the received user sound wave intensity data is lower than the user sound wave intensity data received by any other intelligent device, the intelligent device performs silent processing. When the intelligent device judges that the received user sound wave intensity data are higher than the user sound wave intensity data received by other intelligent devices, the intelligent device replies to the voice command of the user.
According to the method for solving the intelligent voice repeated response, interactive control links are reduced through network transmission, the intelligent equipment compares user sound wave data received by all intelligent equipment in the network, and equipment with the highest user sound wave data is automatically judged to perform voice response, so that the situation that multiple pieces of equipment repeatedly respond and answer questions is effectively avoided, and the problems that the voice recognition effect of the intelligent equipment is seriously influenced by the environment and the recognition efficiency is low are effectively avoided.
With respect to the above technical solution, further improvements as described below can be made.
According to the method for solving the intelligent voice repeated response of the present invention, in a preferred embodiment, in step S02, the intelligent device further converts the voice command into voice data. In step S03, each smart device also transmits voice data to other smart devices.
Through the steps, the intelligent device can conveniently calibrate the voice instruction of the user according to the voice data of the user.
Further, in a preferred embodiment, the method for solving the intelligent voice repeated response of the present invention further includes step S05, where each intelligent device compares the received voice data. When the intelligent device judges that the received voice data is lower than the voice data received by any other intelligent device, the intelligent device performs silence processing. When the intelligent device judges that the received voice data is higher than the voice data received by other intelligent devices, the intelligent device replies to the voice command of the user.
Because audio data and analytic mode that every equipment caught have some differences, through network transmission, link together all intelligent equipment, the speech data transmission that will resolve each other, carry out calibration many times to user's voice command, the higher intelligent equipment of speech data matching degree can be according to a plurality of analytic data of receipt and contrast to effectively reduce the wrong phenomenon of the voice command analytic of intelligent equipment receipt.
Specifically, in a preferred embodiment, in step S03, the smart device completes data transmission through the bluetooth mesh network.
Through the topological structure of the Bluetooth mesh network, the reduction of control interaction links can be effectively ensured, and the signal transmission speed is accelerated.
Further, in a preferred embodiment, the method for solving the smart voice repeat response of the present invention further includes step S06, the smart device measures a relative distance between the user and the smart device according to the received user sound wave intensity signal, and transmits relative distance data to other smart devices, and the smart device compares the received relative distance data to determine whether the smart device is the smart device closest to the user.
According to the steps, the corresponding intelligent equipment which needs to be awakened by the user can be further determined according to the distance, so that high-level intelligent voice service is effectively expanded.
Further, in a preferred embodiment, the intelligent device calculates the plane position coordinates where the user issues the instruction according to the received relative distance data, so as to determine whether the intelligent device is the intelligent device corresponding to the user requirement.
According to the steps, the corresponding intelligent equipment which needs to be awakened by the user can be further determined according to the real-time plane coordinates of the user, so that the intelligent voice service of a higher level is effectively expanded.
Specifically, in a preferred embodiment, in step S06, the smart device performs data transmission through the bluetooth mesh network.
By the same principle, the control interaction links can be effectively reduced and the signal transmission speed is increased through the topological structure of the Bluetooth mesh network.
The device for solving the intelligent voice repeated answer according to the second aspect of the invention comprises: intelligent equipment and network transmission module. The intelligent equipment is internally provided with a voice instruction receiving module for receiving a voice instruction issued by a user, a voice instruction converting module for converting the voice instruction into user sound wave intensity and voice data, a data receiving module for receiving the user sound wave intensity and the voice data of other intelligent equipment, a data comparing module for judging the user sound wave intensity and the voice data and a reply module for responding to the user voice instruction. The network transmission module is used for data transmission among the intelligent devices.
Obviously, the device for solving the intelligent voice repeated response related by the invention can effectively implement the method for solving the intelligent voice repeated response, and through the topological structure of the Bluetooth mesh network, the signal transmission speed is accelerated, simultaneously the signal intensity and the voice data received by all the voice devices are compared, the device with the highest signal intensity is automatically judged to carry out voice response, and simultaneously, the voice command of the user is calibrated for a plurality of times according to the voice data of the user received by a plurality of devices, so that the repeated response and the answer inquiry of a plurality of devices can be effectively avoided.
With respect to the above technical solution, further improvements as described below can be made.
Further, in a preferred embodiment, a calculation module is further provided in the smart device, and is configured to calculate a relative distance between the user and the smart device and a plane position coordinate where the user issues an instruction.
In particular, in a preferred embodiment, the network transmission module comprises a bluetooth mesh network.
Compared with the prior art, the invention has the advantages that: through the topological structure of bluetooth mesh network for signal transmission speed compares signal strength and sound parameter that all speech equipment received simultaneously, and the equipment that judges signal strength is the highest automatically carries out the pronunciation answer, and according to the user speech data that a plurality of equipment received simultaneously, carries out calibration many times to user's voice command, thereby can effectively avoid a plurality of equipment repetitive response and answer the not condition of asking to take place.
Drawings
The invention will be described in more detail hereinafter on the basis of embodiments and with reference to the accompanying drawings. Wherein:
fig. 1 schematically shows a flow of a method for solving intelligent voice repeat response according to an embodiment of the present invention.
In the drawings, like parts are provided with like reference numerals. The figures are not drawn to scale.
Detailed Description
The invention will be further explained in detail with reference to the figures and the embodiments without thereby limiting the scope of protection of the invention.
Fig. 1 schematically shows a flow of a method for solving intelligent voice repeat response according to an embodiment of the present invention.
Example 1
As shown in fig. 1, the method for solving the problem of repeated intelligent voice response according to the embodiment of the present invention includes the following steps: and S01, the user issues a voice command. And S02, the intelligent device receives the voice command and converts the voice command into a user sound wave intensity value. And S03, each intelligent device transmits the user sound wave intensity value to other intelligent devices through the Bluetooth mesh network. And S04, each intelligent device in the network compares the received user sound wave intensity data. When the intelligent device judges that the received user sound wave intensity data is lower than the user sound wave intensity data received by any other intelligent device in the network, the intelligent device performs silence processing. When the intelligent device judges that the received user sound wave intensity data is higher than the user sound wave intensity data received by all other intelligent devices in the network, the intelligent device replies to the voice command of the user.
According to the method for solving the intelligent voice repeated response, the topological structure of the Bluetooth mesh network can effectively ensure that the control interaction links are reduced, the signal transmission speed is accelerated, the intelligent equipment compares the user sound wave data received by all intelligent equipment in the network, and automatically judges the equipment with the highest user sound wave data to perform voice response, so that the situations that a plurality of pieces of equipment repeatedly respond and answer questions are avoided effectively, and the problems that the voice recognition effect of the intelligent equipment is seriously influenced by the environment and the recognition efficiency is low are avoided effectively.
Further, as shown in fig. 1, in the present embodiment, in step S02, the smart device also converts the voice instruction into voice data. In step S03, each smart device also transmits voice data to other smart devices. Through the steps, the intelligent device can conveniently calibrate the voice instruction of the user according to the voice data of the user. Further, in this embodiment, the method for solving the smart voice repeated response further includes step S05, where each smart device compares the received voice data. When the intelligent device judges that the received voice data is lower than the voice data received by any other intelligent device, the intelligent device performs silence processing. When the intelligent device judges that the received voice data is higher than the voice data received by other intelligent devices, the intelligent device replies to the voice command of the user. Because audio data and analytic mode that every equipment caught have some differences, through network transmission, link together all intelligent equipment, the speech data transmission that will resolve each other, carry out calibration many times to user's voice command, the higher intelligent equipment of speech data matching degree can be according to a plurality of analytic data of receipt and contrast to effectively reduce the wrong phenomenon of the voice command analytic of intelligent equipment receipt.
Further, in this embodiment, the method for solving the problem of repeated responses to the intelligent voice further includes step S06, the intelligent device measures a relative distance between the user and the intelligent device according to the received user sound wave intensity signal, and transmits relative distance data to other intelligent devices through the bluetooth mesh network, and the intelligent device compares the received relative distance data to determine whether the intelligent device is the intelligent device closest to the user. According to the steps, the corresponding intelligent equipment which needs to be awakened by the user can be further determined according to the distance, so that high-level intelligent voice service is effectively expanded. Furthermore, in this embodiment, the intelligent device calculates the plane position coordinate where the user issues the instruction according to the received relative distance data, so as to determine whether the intelligent device is the intelligent device corresponding to the user requirement. According to the steps, the corresponding intelligent equipment which needs to be awakened by the user can be further determined according to the real-time plane coordinates of the user, so that the intelligent voice service of a higher level is effectively expanded. By the same principle, the control interaction links can be effectively reduced and the signal transmission speed is increased through the topological structure of the Bluetooth mesh network.
In a specific use scene, supposing that a bedroom, a kitchen and a living room of a user all have an intelligent voice device, when needing control equipment, 3 devices with the same platform (the same awakening mode) can possibly answer simultaneously, when the user calls in the kitchen, user sound wave intensity values and voice matching degree data received by the 3 intelligent voice devices are transmitted and sent through mesh networking, and finally the user sound wave intensity values and the voice matching degree data of the intelligent voice device in the kitchen are compared to be the highest, so that the intelligent voice device in the kitchen answers the user.
Example 2
The device for solving the problem of intelligent voice repeated response of the embodiment of the invention comprises the following steps: intelligent equipment and network transmission module. The intelligent equipment is internally provided with a voice instruction receiving module for receiving a voice instruction issued by a user, a voice instruction converting module for converting the voice instruction into user sound wave intensity and voice data, a data receiving module for receiving the user sound wave intensity and the voice data of other intelligent equipment, a data comparing module for judging the user sound wave intensity and the voice data and a reply module for responding to the user voice instruction. The network transmission module is used for data transmission among the intelligent devices. Further, in this embodiment, a calculation module is further disposed in the smart device, and is configured to calculate a relative distance between the user and the smart device and a plane position coordinate where the user issues an instruction. Specifically, in this embodiment, the network transmission module includes a bluetooth mesh network.
Obviously, the device for solving the intelligent voice repeated response related by the invention can effectively implement the method for solving the intelligent voice repeated response, and through the topological structure of the Bluetooth mesh network, the signal transmission speed is accelerated, simultaneously the signal intensity and the voice data received by all the voice devices are compared, the device with the highest signal intensity is automatically judged to carry out voice response, and simultaneously, the voice command of the user is calibrated for a plurality of times according to the voice data of the user received by a plurality of devices, so that the repeated response and the answer inquiry of a plurality of devices can be effectively avoided.
According to the embodiment, the method and the device for solving the problem of repeated responses of intelligent infant care can effectively ensure that the control interaction links are reduced and the signal transmission speed is increased through the topological structure of the Bluetooth mesh network, and the intelligent equipment can automatically judge the equipment with the highest user sound wave data to perform voice response by comparing the user sound wave data received by all intelligent equipment in the network, so that the situations that multiple equipment repeatedly corresponds and answers questions are not asked can be effectively avoided, and the problems that the voice recognition effect of the intelligent equipment is seriously influenced by the environment and the recognition efficiency is low are effectively avoided.
While the invention has been described with reference to a preferred embodiment, various modifications may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the technical features mentioned in the embodiments can be combined in any way as long as there is no structural conflict. It is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (10)
1. A method for solving intelligent voice repeated response is characterized by comprising the following steps:
s01, a user issues a voice command;
s02, the intelligent device receives the voice command and converts the voice command into a user sound wave intensity numerical value;
s03, each intelligent device transmits the user sound wave intensity value to other intelligent devices;
s04, each intelligent device compares the received user sound wave intensity data; wherein the content of the first and second substances,
when the intelligent equipment judges that the received user sound wave intensity data is lower than the user sound wave intensity data received by any other intelligent equipment, the intelligent equipment performs silent processing;
when the intelligent device judges that the received user sound wave intensity data are higher than the user sound wave intensity data received by other intelligent devices, the intelligent device replies to the voice command of the user.
2. The method for solving intelligent voice repeat request according to claim 1,
in step S02, the smart device further converts the voice command into voice data;
in step S03, each smart device also transmits voice data to other smart devices.
3. The method for solving the intelligent voice repeated answer as claimed in claim 2, further comprising step S05, comparing the received voice data by each intelligent device; wherein the content of the first and second substances,
when the intelligent equipment judges that the received voice data is lower than the voice data received by any other intelligent equipment, the intelligent equipment performs silence processing;
when the intelligent device judges that the received voice data is higher than the voice data received by other intelligent devices, the intelligent device replies to the voice command of the user.
4. The method for solving the problem of repeated responses to intelligent voice as claimed in any one of claims 1 to 3, wherein in step S03, the intelligent device completes data transmission through the Bluetooth mesh network.
5. The method for solving the problem of repeated responses to intelligent voices as claimed in any one of claims 1 to 3, further comprising step S06, wherein the intelligent device measures the relative distance between the user and the intelligent device according to the received signal of the intensity of the sound wave of the user, and transmits the relative distance data to other intelligent devices, and the intelligent device compares the relative distance data to determine whether the intelligent device is the intelligent device closest to the user.
6. The method of claim 5, wherein the intelligent device calculates the plane position coordinates of the user when issuing the command according to the received relative distance data, so as to determine whether the intelligent device is the intelligent device corresponding to the user's requirement.
7. The method for solving the problem of repeated responses to intelligent voice as claimed in claim 5, wherein in step S06, the intelligent device performs data transmission through Bluetooth mesh network.
8. An apparatus for resolving intelligent voice repeat responses, comprising:
the intelligent device and the network transmission module; wherein the content of the first and second substances,
the intelligent equipment is internally provided with a voice instruction receiving module for receiving a voice instruction issued by a user, a voice instruction converting module for converting the voice instruction into user sound wave intensity and voice data, a data receiving module for receiving the user sound wave intensity and the voice data of other intelligent equipment, a data comparing module for judging the user sound wave intensity and the voice data and a reply module for responding to the user voice instruction;
the network transmission module is used for data transmission among the intelligent devices.
9. The apparatus according to claim 8, wherein the intelligent device further comprises a computing module for computing a relative distance between the user and the intelligent device and a plane position coordinate where the user issues the command.
10. The apparatus for solving smart voice repeat request as claimed in claim 8 or 9, wherein the network transmission module comprises bluetooth mesh network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011042082.8A CN112185377A (en) | 2020-09-28 | 2020-09-28 | Method and device for solving intelligent voice repeated response |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011042082.8A CN112185377A (en) | 2020-09-28 | 2020-09-28 | Method and device for solving intelligent voice repeated response |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112185377A true CN112185377A (en) | 2021-01-05 |
Family
ID=73945316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011042082.8A Pending CN112185377A (en) | 2020-09-28 | 2020-09-28 | Method and device for solving intelligent voice repeated response |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112185377A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022252938A1 (en) * | 2021-05-31 | 2022-12-08 | 华为技术有限公司 | Voice interactive response method and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320742A (en) * | 2018-01-31 | 2018-07-24 | 广东美的制冷设备有限公司 | Voice interactive method, smart machine and storage medium |
| CN108922524A (en) * | 2018-06-06 | 2018-11-30 | 西安Tcl软件开发有限公司 | Control method, system, device, Cloud Server and the medium of intelligent sound equipment |
| CN110310637A (en) * | 2019-06-25 | 2019-10-08 | 重庆信络威科技有限公司 | A kind of sound control method and system based on distributed multi-microphone and bluetooth Mesh |
| CN110808886A (en) * | 2019-10-18 | 2020-02-18 | 珠海格力电器股份有限公司 | Voice equipment control method and device, storage medium and voice equipment |
| CN111294258A (en) * | 2020-02-10 | 2020-06-16 | 成都捷顺宝信息科技有限公司 | Voice interaction system and method for controlling intelligent household equipment |
-
2020
- 2020-09-28 CN CN202011042082.8A patent/CN112185377A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108320742A (en) * | 2018-01-31 | 2018-07-24 | 广东美的制冷设备有限公司 | Voice interactive method, smart machine and storage medium |
| CN108922524A (en) * | 2018-06-06 | 2018-11-30 | 西安Tcl软件开发有限公司 | Control method, system, device, Cloud Server and the medium of intelligent sound equipment |
| CN110310637A (en) * | 2019-06-25 | 2019-10-08 | 重庆信络威科技有限公司 | A kind of sound control method and system based on distributed multi-microphone and bluetooth Mesh |
| CN110808886A (en) * | 2019-10-18 | 2020-02-18 | 珠海格力电器股份有限公司 | Voice equipment control method and device, storage medium and voice equipment |
| CN111294258A (en) * | 2020-02-10 | 2020-06-16 | 成都捷顺宝信息科技有限公司 | Voice interaction system and method for controlling intelligent household equipment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022252938A1 (en) * | 2021-05-31 | 2022-12-08 | 华为技术有限公司 | Voice interactive response method and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100583238C (en) | System and method enabling acoustic barge-in | |
| US8719035B2 (en) | Method and apparatus for recognizing and reacting to user personality in accordance with speech recognition system | |
| US9117436B2 (en) | Sound processing apparatus and sound processing method | |
| CN108681440A (en) | A kind of smart machine method for controlling volume and system | |
| CN205508398U (en) | Intelligent robot with high in clouds interactive function | |
| US20020087306A1 (en) | Computer-implemented noise normalization method and system | |
| EP3711306A1 (en) | Interactive system for hearing devices | |
| CN105556592A (en) | Detecting self-generated wake expressions | |
| KR20190037363A (en) | Method and apparatus for processing voice information | |
| CN102197422A (en) | Audio source proximity estimation using sensor array for noise reduction | |
| CN109600699B (en) | System for processing service request, method and storage medium thereof | |
| US20150120304A1 (en) | Speaking control method, server, speaking device, speaking system, and storage medium | |
| CN110383798A (en) | Acoustic signal processing device, acoustics signal processing method and hands-free message equipment | |
| WO2020152324A1 (en) | Signal processing device, system and method for processing audio signals | |
| CN112185377A (en) | Method and device for solving intelligent voice repeated response | |
| CN112581960A (en) | Voice wake-up method and device, electronic equipment and readable storage medium | |
| CN111986652A (en) | Vehicle-mounted intelligent voice system testing and evaluating method | |
| KR101145401B1 (en) | Test equipment and method for speech recognition performance of Robot | |
| CN111326159B (en) | Voice recognition method, device and system | |
| CN113241085A (en) | Echo cancellation method, device, equipment and readable storage medium | |
| US10070244B1 (en) | Automatic loudspeaker configuration | |
| CN110277093B (en) | Audio signal detection method and device | |
| US10777198B2 (en) | Apparatus for determining speech properties and motion properties of interactive robot and method thereof | |
| CN111292723A (en) | Voice recognition system | |
| CN111108550A (en) | Information processing device, information processing terminal, information processing method, and program |
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 |