CN112908330B - Voice wake-up method and device for terminal equipment and computer readable storage medium - Google Patents
Voice wake-up method and device for terminal equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112908330B CN112908330B CN202110237665.4A CN202110237665A CN112908330B CN 112908330 B CN112908330 B CN 112908330B CN 202110237665 A CN202110237665 A CN 202110237665A CN 112908330 B CN112908330 B CN 112908330B
- Authority
- CN
- China
- Prior art keywords
- voice
- awakening
- terminal
- wake
- historical
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012790 confirmation Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 10
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
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
-
- 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
- G10L15/28—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 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)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Electric Clocks (AREA)
Abstract
The invention provides a voice awakening method of terminal equipment, which comprises the steps of confirming historical awakening record data of an awakened terminal when receiving user voice reported by the awakened terminal, wherein the awakened terminal reports the user voice when failing to confirm that the user voice is the terminal awakening voice; confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data; and if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal. The invention also provides a device and a computer readable storage medium. The voice terminal equipment and the voice recognition method thereof record the historical awakening voice data of the voice terminal equipment, report the historical awakening voice data to the server when the voice terminal equipment cannot recognize the awakening voice, and improve the voice recognition effect of the voice terminal equipment in a mode of recognizing the voice of a user by the historical awakening voice data.
Description
Technical Field
The present invention relates to the field of voice recognition of a terminal device, and in particular, to a voice wake-up method and apparatus for a terminal device, and a computer-readable storage medium.
Background
Speech recognition is as the most convenient equipment to enable the mechanism, generally is applied to current terminal equipment, especially is arranged in intelligent terminal's application, and based on current terminal equipment who possesses speech recognition, because terminal equipment's hardware parameter or user's accent problem use, when awakening equipment through pronunciation, its speech recognition goes wrong easily, under the not good condition of speech recognition's effect, can appear the user and repeatedly output and awaken the condition that the speech still can't awaken terminal equipment up, influence user experience.
Disclosure of Invention
The invention mainly aims to provide a voice awakening method and device of terminal equipment and a computer readable storage medium, and aims to solve the technical problem that a user can not awaken the terminal equipment as long as repeatedly outputting awakening voice under the condition that the existing voice recognition effect is poor.
In order to achieve the above object, the present invention provides a voice wake-up method for a terminal device, where the voice wake-up method for the terminal device includes the following steps:
when receiving user voice reported by an awakened terminal, confirming historical awakening record data of the awakened terminal, wherein the awakened terminal reports the user voice when failing to confirm that the user voice is the terminal awakening voice;
confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data;
and if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal.
Optionally, the step of confirming whether the user voice is the terminal wake-up voice of the awakened terminal through the historical wake-up record data includes:
acquiring awakening conditions corresponding to the historical awakening record data;
and confirming whether the user voice meets the awakening condition or not, and obtaining whether the user voice is the terminal awakening voice of the awakened terminal or not according to a confirmation result.
Optionally, before the step of obtaining the wake condition corresponding to the historical wake-up record data, the method further includes:
and extracting data characteristics of the historical wake-up record data, and generating the wake-up condition according to the data characteristics.
Optionally, the step of confirming whether the user voice satisfies the wake-up condition includes:
analyzing the user voice to obtain a user voice parameter;
and confirming whether the user voice parameters meet the awakening conditions or not, wherein the awakening conditions comprise a plurality of voice parameter judgment conditions.
Optionally, before the step of obtaining the wake condition corresponding to the historical wake-up record data, the method further includes:
confirming whether the historical wake-up record data is updated;
and if the historical awakening record data is updated, executing the step of acquiring the awakening condition of the historical awakening record data.
Optionally, the step of confirming whether the historical wake-up record data is updated includes:
acquiring starting time of equipment on the awakened terminal;
and confirming whether the historical awakening record data is updated or not according to the comparison result of the data recording time of the historical awakening record data and the starting time of the equipment.
Optionally, after the step of confirming whether the historical wake-up record data is updated, the method further includes:
if the historical awakening record number is not updated, acquiring the last user voice information reported by the awakened terminal;
and generating a wake-up condition according to the acquired last user voice information.
Optionally, the voice wake-up method of the terminal device further includes:
acquiring user awakening voice of an awakened terminal, and generating historical awakening record data by the user awakening voice;
and storing the historical wake-up record data.
In order to achieve the above object, the present invention further provides a voice wake-up device of a terminal device, where the voice wake-up device of the terminal device includes a controller, a processor, a storage, and a voice wake-up program of the terminal device, which is stored on the storage and can be run on the processor, and when the voice wake-up program of the terminal device is executed by the processor, the steps of the voice wake-up method of the terminal device are implemented.
The present invention also provides a computer-readable storage medium, which includes a processor, a storage, and a voice wake-up program of a terminal device stored on the storage and operable on the processor, and when being executed by the processor, the voice wake-up program of the terminal device implements the steps of the voice wake-up method of the terminal device as described above.
The invention provides a voice awakening method of terminal equipment, which is characterized in that when user voice reported by an awakened terminal is received, historical awakening record data of the awakened terminal is confirmed, wherein the awakened terminal reports the user voice when the user voice is not confirmed to be the terminal awakening voice; confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data; and if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal. According to the voice terminal equipment and the voice recognition method, the historical awakening voice data of the voice terminal equipment are recorded, the voice terminal equipment reports the recorded voice data to the server when the voice terminal equipment cannot recognize the awakening voice, and the voice recognition effect of the voice terminal equipment is improved in a mode that the historical awakening voice data recognizes the voice of a user, so that the awakening efficiency of the voice terminal equipment is improved.
Drawings
FIG. 1 is a schematic diagram of a terminal \ device structure of a hardware operating environment according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a voice wake-up method of a terminal device according to a first embodiment of the present invention;
fig. 3 is a detailed step diagram of step S20 of the voice wake-up method of the terminal device according to the present invention;
fig. 4 is a flowchart illustrating a voice wake-up method of a terminal device according to a third embodiment of the present invention.
The objects, features and advantages of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: when receiving user voice reported by an awakened terminal, confirming historical awakening record data of the awakened terminal, wherein the awakened terminal reports the user voice when failing to confirm that the user voice is the terminal awakening voice; confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data; and if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal.
Under the condition that the existing voice recognition effect is not good, the technical problem that a user repeatedly outputs a wake-up voice and still cannot wake up the terminal equipment can occur.
The present invention provides a solution: the historical awakening voice data of the voice terminal equipment is recorded, so that the historical awakening voice data is reported to the server when the voice terminal equipment cannot identify the awakening voice, the voice identification effect of the voice terminal equipment is improved in a mode that the historical awakening voice data identifies the voice of a user, and the awakening efficiency of the voice terminal equipment is improved.
As shown in fig. 1, fig. 1 is a schematic diagram of a terminal \ device structure of a hardware operating environment according to an embodiment of the present invention.
The terminal of the embodiment of the invention can be a PC, and can also be a mobile or non-mobile terminal device with a voice recognition function, such as a smart phone, a tablet computer, a portable computer and the like.
As shown in fig. 1, the terminal may include: a processor 101, a network interface 104, a user interface 103, a memory 105, and a communication bus 102. Wherein the communication bus 102 is used for enabling connection communication between these components.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 105, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a voice wake-up program of the terminal device.
In the terminal shown in fig. 1, the network interface 104 is mainly used for connecting a background server and performing data communication with the background server; the user interface 103 is mainly used for connecting a client (user side) and performing data communication with the client; and the processor 101 may be configured to invoke a voice wake-up procedure of the terminal device stored in the memory 105 and perform the following operations:
when receiving user voice reported by an awakened terminal, confirming historical awakening record data of the awakened terminal, wherein the awakened terminal reports the user voice when failing to confirm that the user voice is the terminal awakening voice;
confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data;
and if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
acquiring awakening conditions corresponding to the historical awakening record data;
and confirming whether the user voice meets the awakening condition or not, and obtaining whether the user voice is the terminal awakening voice of the awakened terminal or not according to a confirmation result.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
and extracting data characteristics of the historical wake-up record data, and generating the wake-up condition according to the data characteristics.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
analyzing the user voice to obtain a user voice parameter;
and confirming whether the user voice parameters meet the awakening conditions or not, wherein the awakening conditions comprise a plurality of voice parameter judgment conditions.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
confirming whether the historical wake-up record data is updated;
and if the historical awakening record data is updated, executing the step of acquiring the awakening condition of the historical awakening record data.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
acquiring starting time of equipment on the awakened terminal;
and confirming whether the historical awakening record data is updated or not according to the comparison result of the data recording time of the historical awakening record data and the starting time of the equipment.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
if the historical awakening record number is not updated, acquiring the last user voice information reported by the awakened terminal;
and generating a wake-up condition according to the acquired last user voice information.
Further, the processor 101 may call the voice wake-up program of the terminal device stored in the memory 105, and further perform the following operations:
acquiring user awakening voice of an awakened terminal, and generating historical awakening record data by the user awakening voice;
and storing the historical wake-up record data.
Referring to fig. 2, fig. 2 is a first embodiment of a voice wake-up method of a terminal device according to the present invention, where the voice wake-up method of the terminal device is applied to an electric bicycle charging pile, and the voice wake-up method of the terminal device includes:
step S10, when receiving a user voice reported by a wakened terminal, confirming historical wakening record data of the wakened terminal, wherein the wakened terminal reports the user voice when failing to confirm that the user voice is a terminal wakening voice;
the method comprises the steps of receiving user voice reported by a awakened terminal according to a voice awakening function application of current terminal equipment, wherein the awakened terminal is equipment applying a voice awakening function, the awakened terminal is received user voice information which cannot be recognized as awakening voice, namely the awakened terminal receives user voice initiated by a user according to the current voice awakening function application, recognizes the received user voice based on stored user voice recognition data, and reports the user voice to a server for voice recognition when the user voice cannot be recognized as the awakening voice so as to improve the voice recognition effect of the awakened terminal. According to the technical content, receiving user voice reported by a awakened terminal, and confirming historical awakening record data of the awakened terminal based on the received user voice, wherein the historical awakening record data is pre-stored, and is based on awakening data corresponding to the awakened terminal, and the historical awakening record data is unique data information of the awakened terminal and can be defined as a storage mark of a device identifier of the awakened terminal. Furthermore, in the terminal device where the current historical wake-up record data is located, historical wake-up record data of one or more terminal devices with a voice wake-up function may be stored, so that the currently stored historical wake-up record data of the awakened terminal is confirmed according to the received user voice reported by the awakened terminal. Further, the data content of the historical wake-up recording data is mainly based on data parameters of the awakened terminal when the terminal is successfully awakened by the user voice, and includes, but is not limited to, user audio data of the wake-up voice, the awakened time, the wake-up period, the wake-up user data, and other parameter information capable of improving the audio recognition effect.
Step S20, confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data;
according to the stored historical awakening record data corresponding to the awakened terminal, whether the user voice is the terminal awakening voice of the awakened terminal is confirmed through the historical awakening record data, wherein when the operation that whether the user voice is the terminal awakening voice of the awakened terminal is confirmed through the historical awakening record data, the operation can be defined as recognizing the user voice through the historical awakening record data, whether the user voice is the terminal awakening voice of the awakened terminal is confirmed according to a recognition result, and the detailed data information of the historical awakening record data is related, and when the user data is recognized, the user data can be recognized through the matching degree of the user voice and the historical awakening record data; or identifying the user voice based on the corresponding judgment condition generated by the historical awakening record data to obtain a related identification result, and then obtaining whether the user voice is the identification result of the terminal awakening voice of the awakened terminal.
And step S30, if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal.
And identifying the received user voice according to the stored historical awakening record data of the awakened terminal, if the user voice is confirmed to be the terminal awakening voice according to the historical awakening record data, namely the user voice is consistent with the historical awakening record data in matching, or the detailed information of the user voice meets the judgment condition of the historical awakening record data, confirming that the user voice is the terminal awakening voice, and based on the condition, issuing a starting instruction to the awakened terminal to awaken the application of the awakened terminal.
In this embodiment, the historical wake-up voice data of the voice terminal device is recorded, so that the voice terminal device reports the recorded historical wake-up voice data to the server when the voice terminal device fails to recognize the wake-up voice, and the voice recognition effect of the voice terminal device is improved by recognizing the voice of the user through the historical wake-up voice data, thereby improving the wake-up efficiency of the voice terminal device.
Referring to fig. 3, fig. 3 is a detailed step diagram of step S20 of the voice wake-up method of the terminal device of the present invention, where the step of confirming whether the user voice is the terminal wake-up voice of the awakened terminal through the historical wake-up record data includes:
step S21, acquiring the awakening condition corresponding to the historical awakening record data;
step S22, confirming whether the user voice meets the awakening condition, and obtaining whether the user voice is the terminal awakening voice of the awakened terminal according to the confirmed result.
In this embodiment, after the historical wake-up record data stored in the awakened terminal is confirmed based on the user voice reported by the current awakened terminal, the user voice is identified by the historical wake-up record data to determine whether the user voice is the terminal wake-up voice. And acquiring a wake-up condition corresponding to the historical wake-up record data, and judging whether the user voice is a terminal wake-up voice according to the wake-up condition. The wake-up conditions are generated according to the detailed data content of the historical wake-up record data, that is, the wake-up conditions are generated according to the detailed data content of the historical wake-up record data, so that on the premise that the historical wake-up record data includes historical wake-up parameters of multiple dimensions, the wake-up conditions also include multiple wake-up conditions, and on the premise that the historical wake-up record data includes, but is not limited to, user audio data of wake-up voice, wake-up time, wake-up period, wake-up user data, the wake-up conditions also include audio judgment conditions, wake-up time range, wake-up time period, wake-up user identification, and the like, and the data judgment conditions corresponding to the historical wake-up record data. Therefore, before the step of obtaining the wake-up condition corresponding to the historical wake-up record data, the method further includes:
and extracting data characteristics of the historical wake-up record data, and generating the wake-up condition according to the data characteristics.
According to the current confirmed historical awakening record data of the awakened terminal, extracting the data characteristics of the historical awakening record data, and generating the awakening condition according to the data characteristics, wherein the data characteristics can be limited to characteristic data information based on all historical data information in the historical awakening record data, so that the generated awakening condition improves the judgment accuracy of the user voice. In addition, on the premise that the wake-up condition generated by the data feature is multiple, that is, on the premise that the wake-up condition includes multiple voice parameter determination conditions such as an audio determination condition, a wake-up time range, a wake-up time period, and a wake-up user identity, the priority based on the determination condition may be defined in the multiple voice parameter determination conditions in the wake-up condition, for example, the wake-up user identity is the highest priority, based on the condition content of the corresponding wake-up condition generated by the data feature. To increase the wake-up probability of the awakened terminal when recognizing the user voice,
the step of identifying the operation content of the user voice according to the historical wake-up record data and determining whether the user voice meets the wake-up condition comprises the following steps:
analyzing the user voice to obtain a user voice parameter;
and confirming whether the user voice parameters meet the awakening conditions or not, wherein the awakening conditions comprise a plurality of voice parameter judgment conditions.
After receiving user voice reported by a awakened terminal, identifying whether the user voice is terminal awakening voice of the awakened terminal or not according to awakening conditions corresponding to historical awakening record data corresponding to the awakened terminal, analyzing the user voice to obtain user voice parameters on the basis of identification operation of the user voice, wherein the user voice parameters relate to specific condition information in the awakening conditions, and the user voice parameters obtained by analyzing the user voice are related to the specific condition information in the awakening conditions so as to judge the user voice parameters one by one according to the awakening conditions. In addition, the application of the wake-up condition is involved, and a corresponding judgment result is obtained according to the priority of the voice parameter judgment condition in the wake-up condition corresponding to the user voice parameter, for example, when the voice parameter judgment condition with the highest priority is the identity of the wake-up user, if the user who initiates the user voice is a predetermined user, the user voice is directly judged to be the terminal wake-up condition, and the like, and the specific setting can be correspondingly set according to the related functional setting condition.
Further, before the step of obtaining the wake-up condition corresponding to the historical wake-up record data, the method further includes:
confirming whether the historical wake-up record data is updated;
and if the historical awakening record data is updated, executing the step of acquiring the awakening condition of the historical awakening record data.
When the historical wake-up record data corresponding to the awakened terminal is used for confirming whether the user voice is the terminal wake-up voice, whether the historical wake-up record data is the latest data or not is required to be confirmed, namely whether the historical wake-up record data is updated or not is confirmed, wherein when the historical wake-up record data is judged to be the latest record data or not, judgment can be carried out through the service time of the awakened terminal, namely whether the historical wake-up record data is updated or not is confirmed, and the method comprises the following steps:
acquiring starting time of equipment on the awakened terminal;
and confirming whether the historical awakening record data is updated or not according to the comparison result of the data recording time of the historical awakening record data and the starting time of the equipment.
According to the data transmission connection relation of the current awakened terminal, when the data transmission connection relation is not disconnected, acquiring the last equipment starting time of the awakened terminal, wherein the last equipment starting time is the equipment starting time of the awakened terminal which is awakened and started last time, confirming whether the historical awakening record data is updated or not according to the equipment starting time, comparing the record time of the historical awakening record data with the equipment starting time, and confirming whether the historical awakening data is updated or not according to a comparison result.
As shown above, when the starting time of the device on the terminal to be wakened is consistent with the data recording time of the historical wakening record data, it is obtained that the historical wakening record data is updated, and thus, a corresponding wakening condition is obtained based on the historical wakening record data so as to verify the reported user data. And when it is confirmed that the historical wake-up record data is inconsistent with the device activation time, after the step of confirming that the historical wake-up record data is not updated, the method further includes:
if the historical awakening record number is not updated, acquiring the last user voice information reported by the awakened terminal;
and generating a wake-up condition according to the acquired last user voice information.
When the equipment starting time based on the current terminal to be awakened is inconsistent with the data recording time of the historical awakening record data, confirming that the historical awakening record data is not updated, thus obtaining the last user voice information reported by the awakened terminal, wherein the last user voice information is the voice information used for voice awakening and starting of the terminal to be awakened, the voice information is used for generating an awakening condition, the awakening condition is used for verifying the received user voice, the awakening condition is generated based on the last user voice information, and the voice parameter judgment condition of the awakening condition is consistent with the voice parameter judgment condition of the historical awakening record data.
In this embodiment, the historical wake-up voice data of the voice terminal device is recorded, so that the voice terminal device reports the recorded historical wake-up voice data to the server when the voice terminal device fails to recognize the wake-up voice, and the voice recognition effect of the voice terminal device is improved by recognizing the voice of the user through the historical wake-up voice data, thereby improving the wake-up efficiency of the voice terminal device.
Further, referring to fig. 4, fig. 4 is a third embodiment of the voice wake-up method of the terminal device of the present invention, and based on the first and second embodiments shown in fig. 2 and 3, the voice wake-up method of the terminal device further includes:
step S40, obtaining user awakening voice of the awakened terminal, and generating historical awakening record data by the user awakening voice;
and step S50, storing the historical wake-up record data.
In this embodiment, a user wake-up voice of a woken-up terminal is acquired according to a currently connected woken-up terminal, where the user wake-up voice is a normal wake-up and starts voice information of the woken-up terminal, and when the user wake-up voice of the woken-up terminal is acquired, if the woken-up terminal is a history starting device, the user wake-up voice of the woken-up terminal can be acquired based on history wake-up information of the woken-up terminal, and at this time, the user wake-up voice is a history wake-up voice; or when the awakened terminal is awakened and started based on user voice initiated by a user, automatically reporting the user voice of the successfully awakened equipment to the server so that the server generates corresponding historical awakening record data through the user voice when receiving the user voice. And storing the generated historical awakening record data into a preset data storage, wherein when the historical awakening record data is stored, the equipment identifier of the awakened terminal is used as a mark for storage, so that when the awakened terminal reports the voice of the user, the corresponding historical awakening record data can be directly confirmed.
The present invention also provides a computer-readable storage medium, in which a voice wake-up program of a terminal device is stored, and when executed, the voice wake-up program of the terminal device implements the following operations:
when receiving user voice reported by an awakened terminal, confirming historical awakening record data of the awakened terminal, wherein the awakened terminal reports the user voice when failing to confirm that the user voice is the terminal awakening voice;
confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data;
and if the user voice is confirmed to be a terminal awakening voice, issuing an enabling instruction to the awakened terminal.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
acquiring awakening conditions corresponding to the historical awakening record data;
and confirming whether the user voice meets the awakening condition or not, and obtaining whether the user voice is the terminal awakening voice of the awakened terminal or not according to a confirmation result.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
and extracting data characteristics of the historical wake-up record data, and generating the wake-up condition according to the data characteristics.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
analyzing the user voice to obtain a user voice parameter;
and confirming whether the user voice parameters meet the awakening conditions or not, wherein the awakening conditions comprise a plurality of voice parameter judgment conditions.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
confirming whether the historical wake-up record data is updated;
and if the historical awakening record data is updated, executing the step of acquiring the awakening condition of the historical awakening record data.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
acquiring starting time of equipment on the awakened terminal;
and confirming whether the historical awakening record data is updated or not according to the comparison result of the data recording time of the historical awakening record data and the starting time of the equipment.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
if the historical awakening record number is not updated, acquiring the last user voice information reported by the awakened terminal;
and generating a wake-up condition according to the acquired last user voice information.
Further, the voice wake-up program of the terminal device, when executed, implements the following operations:
acquiring user awakening voice of an awakened terminal, and generating historical awakening record data by the user awakening voice;
and storing the historical wake-up record data.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (5)
1. A voice wake-up method of a terminal device is characterized by comprising the following steps:
when receiving user voice reported by an awakened terminal, confirming historical awakening record data of the awakened terminal, wherein the awakened terminal reports the user voice when failing to confirm that the user voice is the terminal awakening voice;
confirming whether the user voice is the terminal awakening voice of the awakened terminal or not through the historical awakening record data, wherein the starting time of equipment on the awakened terminal is obtained, whether the historical awakening record data is updated or not is confirmed according to the comparison result of the data recording time of the historical awakening record data and the starting time of the equipment, the awakening condition corresponding to the historical awakening record data is obtained when the historical awakening record data is confirmed to be updated, if the historical awakening record data is not updated, the last user voice information reported by the awakened terminal is obtained, the awakening condition is generated according to the obtained last user voice information, whether the user voice meets the awakening condition is confirmed, whether the user voice is the terminal awakening voice of the awakened terminal or not is obtained according to the confirmation result, and the historical awakening record data is pre-stored, based on the awakened terminal corresponding to historical awakening data, the historical awakening record data is unique data information of the awakened terminal, the awakened terminal is used as an identifier, and data characteristics of the historical awakening record data are extracted to generate the awakening condition;
and if the user voice is confirmed to be the terminal awakening voice, issuing an enabling instruction to the awakened terminal.
2. The voice wakeup method of claim 1, wherein said step of confirming whether said user voice satisfies said wakeup condition includes:
analyzing the user voice to obtain a user voice parameter;
and confirming whether the user voice parameters meet the awakening conditions or not, wherein the awakening conditions comprise a plurality of voice parameter judgment conditions.
3. A voice wake-up method for a terminal device according to any of the claims 1 to 2, characterised in that the voice wake-up method for a terminal device further comprises:
acquiring user awakening voice of an awakened terminal, and generating historical awakening record data by the user awakening voice;
and storing the historical wake-up record data.
4. A voice wake-up apparatus of a terminal device, the voice wake-up apparatus of the terminal device comprising a controller, a processor, a storage, and a voice wake-up program of the terminal device stored on the storage and operable on the processor, wherein the voice wake-up program of the terminal device, when executed by the processor, implements the steps of the voice wake-up method of the terminal device according to any one of claims 1 to 3.
5. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a processor, a storage, and a voice wake-up program of a terminal device stored on the storage and operable on the processor, the voice wake-up program of the terminal device implementing the steps of the voice wake-up method of the terminal device according to any one of claims 1-3 when executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110237665.4A CN112908330B (en) | 2021-03-04 | 2021-03-04 | Voice wake-up method and device for terminal equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110237665.4A CN112908330B (en) | 2021-03-04 | 2021-03-04 | Voice wake-up method and device for terminal equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112908330A CN112908330A (en) | 2021-06-04 |
| CN112908330B true CN112908330B (en) | 2022-08-09 |
Family
ID=76108184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110237665.4A Active CN112908330B (en) | 2021-03-04 | 2021-03-04 | Voice wake-up method and device for terminal equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112908330B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116105308A (en) * | 2021-11-11 | 2023-05-12 | 青岛海尔空调器有限总公司 | Control method and device for voice air conditioner, voice air conditioner and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN107895573A (en) * | 2017-11-15 | 2018-04-10 | 百度在线网络技术（北京）有限公司 | Method and device for identification information |
| CN110111767A (en) * | 2018-01-31 | 2019-08-09 | 通用汽车环球科技运作有限责任公司 | Multi-language voice auxiliary is supported |
| CN110192248A (en) * | 2017-01-20 | 2019-08-30 | 三星电子株式会社 | Voice input processing method and electronic equipment for supporting this method |
| CN111599352A (en) * | 2020-06-01 | 2020-08-28 | 聆感智能科技(深圳)有限公司 | Voice wake-up method and device, computer equipment and storage medium |
-
2021
- 2021-03-04 CN CN202110237665.4A patent/CN112908330B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106297777A (en) * | 2016-08-11 | 2017-01-04 | 广州视源电子科技股份有限公司 | A kind of method and apparatus waking up voice service up |
| CN110192248A (en) * | 2017-01-20 | 2019-08-30 | 三星电子株式会社 | Voice input processing method and electronic equipment for supporting this method |
| CN107895573A (en) * | 2017-11-15 | 2018-04-10 | 百度在线网络技术（北京）有限公司 | Method and device for identification information |
| CN110111767A (en) * | 2018-01-31 | 2019-08-09 | 通用汽车环球科技运作有限责任公司 | Multi-language voice auxiliary is supported |
| CN111599352A (en) * | 2020-06-01 | 2020-08-28 | 聆感智能科技(深圳)有限公司 | Voice wake-up method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112908330A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107276864B (en) | Method, device and system for controlling household appliances by intelligent voice equipment | |
| CN107199971B (en) | Vehicle-mounted voice interaction method, terminal and computer readable storage medium | |
| CN108172223A (en) | Voice instruction recognition method, device and server and computer readable storage medium | |
| CN107220532B (en) | Method and apparatus for recognizing user identity through voice | |
| EP1981256A1 (en) | Speech recognition method and system and speech recognition server | |
| CN103679452A (en) | Payment authentication method, device thereof and system thereof | |
| CN111261151B (en) | Voice processing method and device, electronic equipment and storage medium | |
| WO2008118869A1 (en) | Apparatus and methods of sharing contact information between mobile communication devices using short message service | |
| CN107544272A (en) | terminal control method, device and storage medium | |
| CN111326154B (en) | Voice interaction method and device, storage medium and electronic equipment | |
| CN103944983A (en) | Error correction method and system for voice control instruction | |
| CN112908330B (en) | Voice wake-up method and device for terminal equipment and computer readable storage medium | |
| CN105227557A (en) | A kind of account number processing method and device | |
| CN112017663A (en) | Voice generalization method and device and computer storage medium | |
| CN111445909A (en) | Intelligent lock with voice control function and control method thereof | |
| CN111787125B (en) | Information interaction system and method | |
| CN113299294B (en) | Task type dialogue robot interaction method, device, equipment and storage medium | |
| CN111225115B (en) | Information providing method and device | |
| CN110364155A (en) | Voice control error-reporting method, electric appliance and computer readable storage medium | |
| CN111343348A (en) | Application method, system, device and storage medium of interactive voice response menu | |
| US20140343947A1 (en) | Methods and systems for managing dialog of speech systems | |
| CN112199470A (en) | Session-based customer complaint service method, intelligent terminal and storage medium | |
| WO2012155588A1 (en) | Method and apparatus for automatically identifying pin code | |
| CN112581957B (en) | Computer voice control method, system and related device | |
| CN112542166B (en) | Voice interaction method and 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 |