CN113539264A - Voice instruction data transmission method and system for voice-controlled electrically operated gate - Google Patents
Voice instruction data transmission method and system for voice-controlled electrically operated gate Download PDFInfo
- Publication number
- CN113539264A CN113539264A CN202110788315.7A CN202110788315A CN113539264A CN 113539264 A CN113539264 A CN 113539264A CN 202110788315 A CN202110788315 A CN 202110788315A CN 113539264 A CN113539264 A CN 113539264A
- Authority
- CN
- China
- Prior art keywords
- control
- control voice
- instruction
- voice
- command
- 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.)
- Granted
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000007906 compression Methods 0.000 claims description 78
- 230000006835 compression Effects 0.000 claims description 75
- 230000008569 process Effects 0.000 claims description 30
- 230000011218 segmentation Effects 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 24
- 238000013500 data storage Methods 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000004886 process control Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 5
- 241000287107 Passer Species 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05F—DEVICES FOR MOVING WINGS INTO OPEN OR CLOSED POSITION; CHECKS FOR WINGS; WING FITTINGS NOT OTHERWISE PROVIDED FOR, CONCERNED WITH THE FUNCTIONING OF THE WING
- E05F15/00—Power-operated mechanisms for wings
- E05F15/70—Power-operated mechanisms for wings with automatic actuation
- E05F15/77—Power-operated mechanisms for wings with automatic actuation using wireless control
-
- 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
- G10L15/20—Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech
-
- 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
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
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)
- Computer Networks & Wireless Communication (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention provides a voice instruction data transmission method and a system for controlling an electrically operated gate by voice, wherein the method comprises the following steps: acquiring control voice of the electric door; identifying control voice to obtain a control voice instruction; analyzing the voice control instruction according to the control voice to obtain an instruction analysis result; transmitting the control voice command according to the command analysis result; and receiving a control voice command, executing the control voice command, and controlling the electric door to open and close. The voice instruction data transmission method and system for the voice control electric door can efficiently and accurately control the electric door to be opened and closed.
Description
Technical Field
The invention relates to the technical field of electrically operated gates, in particular to a voice instruction data transmission method and system for a voice-controlled electrically operated gate.
Background
Electric doors are various doors driven by a motor. The electric door plays a decisive role in our daily life, is safe, beautiful, convenient and fast, and greatly improves our life quality. The electric door has manual control and automatic control in use and control so as to meet the opening and closing requirements of users on the industrial door.
In the prior art, when the electrically operated gate is continuously and frequently controlled, control confusion is often caused, so that the electrically operated gate cannot be normally used due to the control failure phenomenon.
Disclosure of Invention
The present invention is directed to a method and system for transmitting voice command data of a voice-controlled electric door, so as to solve the problems mentioned in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a voice command data transmission method for controlling an electrically operated gate by voice comprises the following steps:
acquiring control voice of the electric door;
recognizing the control voice to obtain a control voice instruction;
analyzing the control voice command according to the control voice to obtain a command analysis result;
transmitting the control voice command according to the command analysis result;
and receiving the control voice command, executing the control voice command, and controlling the electric door to be opened and closed.
Preferably, recognizing the control speech includes:
performing voice processing on the control voice, and performing noise reduction processing on the control voice to obtain a first processing control voice;
separating the control keywords by the control voice in the middle of the first processing control voice to obtain a second processing control voice; the second processing control voice comprises one or more control keywords;
and obtaining a control voice instruction in an instruction database according to the second processing control voice and the control keyword.
Preferably, when a control voice instruction is obtained in an instruction database according to the control keyword according to the second processing control voice, if the control keyword is multiple, the control voice instruction is obtained in the instruction database according to the control keyword through multiple threads concurrently;
and carrying out time analysis on the control voice instruction, sequentially acquiring the sequence of the control keywords corresponding to the control voice instruction in the control voice, and carrying out time sequence arrangement on the control voice instruction according to the sequence to form an instruction analysis result.
Preferably, the transmitting the control voice command according to the command analysis result includes:
judging a control voice instruction to be transmitted, and judging whether the control voice instruction transmission exists within preset time;
when control voice command transmission exists, analyzing the control voice command, if the control voice command to be transmitted and the control voice command transmitted last are of the same control property, sending the control voice command to be transmitted according to a first sending frequency, if the control voice command to be transmitted and the control voice command transmitted last are not of the same control property, further analyzing the control voice command to be transmitted and the control voice command transmitted last, when the control property of the control voice command transmitted last is off, and the control voice command to be transmitted is on, sending the control voice command to be transmitted according to the first sending frequency, when the control property of the control voice command transmitted last is on, and the control property of the control voice command to be transmitted is off, and sending the control voice command to be transmitted according to a second sending frequency, wherein the second sending frequency is longer than the first sending frequency in time interval.
Preferably, the control voice is further compressed before being transmitted; the compression process includes:
acquiring the size of the control voice instruction; performing form conversion on the control voice, converting the control voice instruction into a data packet form, and calculating the size of the data packet of the control voice instruction to obtain the size of the control voice instruction;
segmenting the control voice instruction; performing data segmentation on the control voice command from the initial character to the final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmentation byte threshold;
configuring a compression scheme for the control voice instruction; determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction, and obtaining a compression scheme related to the control voice instruction;
compressing the uncompressed data according to the compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in the uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and determining a data storage position according to the process change marking information, and performing compression storage according to the data storage position.
A voice command data transmission system for voice-controlled electrically operated doors, comprising: the voice recognition system comprises a voice acquisition module, a voice recognition module, an instruction analysis module, an instruction transmission module and an execution control module;
the voice acquisition module is used for acquiring control voice of the electric door;
the voice recognition module is used for recognizing the control voice acquired by the voice acquisition module and acquiring a control voice instruction;
the instruction analysis module is used for analyzing the control voice instruction to obtain an instruction analysis result;
the instruction transmission module is used for transmitting the control voice instruction according to the instruction analysis result and transmitting the control voice instruction to the execution control module;
and the execution control module is used for receiving the control voice command, executing the control voice command and controlling the electric door to be opened and closed.
Preferably, the speech recognition module includes: the voice processing unit, the voice separating unit and the instruction generating unit;
the voice processing unit is used for performing voice processing on the control voice and performing noise reduction processing on the control voice to obtain a first processing control voice;
the voice separation unit is used for controlling voice to separate and process the control keywords in the middle of the first processing control voice to obtain a second processing control voice; the second processing control voice comprises one or more control keywords;
and the instruction generating unit is used for obtaining a control voice instruction in an instruction database according to the second processing control voice and the control keyword.
Preferably, when the instruction generating unit obtains a control voice instruction according to the control keyword in an instruction database according to the second processing control voice, if the control keyword is multiple, the instruction generating unit obtains the control voice instruction according to the control keyword by multiple threads concurrently in the instruction database;
when the instruction analysis module analyzes the control voice instruction, time analysis is carried out on the control voice instruction according to the control voice, the sequence of the control keywords corresponding to the control voice instruction appearing in the control voice is sequentially obtained, and the control voice instruction is subjected to time sequence arrangement according to the sequence to form an instruction analysis result.
Preferably, the instruction transmission module includes: a judgment unit and a condition unit;
the judging unit is used for judging the control voice command to be transmitted and judging whether the control voice command transmission exists in the preset time;
the condition unit is used for transmitting according to the judgment result obtained by the judgment unit, when control voice command transmission exists, the control voice command is analyzed, if the control voice command to be transmitted and the last transmitted control voice command have the same control property, the control voice command to be transmitted is transmitted according to a first transmission frequency, if the control voice command to be transmitted and the last transmitted control voice command do not have the same control property, the control voice command to be transmitted and the last transmitted control voice command are further analyzed, when the control property of the last transmitted control voice command is off, and the control property of the control voice command to be transmitted is on, the control voice command to be transmitted is transmitted according to the first transmission frequency, and when the control property of the last transmitted control voice command is on, and when the control property of the control voice command to be transmitted is off, transmitting the control voice command to be transmitted according to a second transmission frequency, wherein the second transmission frequency is longer than the first transmission frequency in time interval.
Preferably, the instruction transmission module further includes a compression unit, and the condition unit compresses the control voice instruction by the compression unit before transmitting according to the determination result obtained by the determination unit, where the compression unit includes: the system comprises a metering division small unit, a compression configuration small unit and a compression storage small unit;
the measurement division small unit is used for carrying out form conversion on the control voice, converting the control voice instruction into a data packet form, and obtaining the size of the control voice instruction by calculating the size of the data packet of the control voice instruction; performing data segmentation on the control voice command from the initial character to the final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmented byte threshold;
the compression configuration small unit is used for determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction to obtain a compression scheme related to the control voice instruction;
the compression storage small unit is used for compressing the uncompressed data according to the compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in the uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and determining a data storage position according to the process change marking information, and performing compression storage according to the data storage position.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram illustrating steps of a voice command data transmission method according to the present invention;
FIG. 2 is a diagram illustrating a second step of the voice command data transmission method according to the present invention;
FIG. 3 is a flowchart illustrating a fourth step of the voice command data transmission method according to the present invention;
FIG. 4 is a schematic diagram of a voice command data transmission system according to the present invention;
FIG. 5 is a diagram illustrating a speech recognition module in the voice command data transmission system according to the present invention;
fig. 6 is a schematic diagram of an instruction transmission module in the voice instruction data transmission system according to the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
As shown in fig. 1, an embodiment of the present invention provides a method for transmitting voice command data of a voice-controlled electrically operated gate, including:
step one, acquiring control voice of the electric door;
step two, recognizing the control voice to obtain a control voice instruction;
analyzing the control voice command according to the control voice to obtain a command analysis result;
step four, transmitting the control voice command according to the command analysis result;
and step five, receiving the control voice command, executing the control voice command, and controlling the electric door to be opened and closed.
According to the technical scheme, when the electric door is controlled through voice, firstly, the control voice of the electric door is obtained, the control voice is recognized after the control voice of the electric door is collected, the control information in the control voice is recognized, the control voice instruction is obtained according to the control information, then, the control voice instruction is analyzed, the attribute information of the control voice instruction is analyzed, an instruction analysis result is obtained, then, the control voice instruction is transmitted according to the instruction analysis result, and finally, the control voice instruction is executed after the control voice instruction is received, so that the electric door is controlled.
Above-mentioned technical scheme has realized the control to the electrically operated gate through pronunciation, not only facilitates the use nimble operation for it is more convenient to the control of electrically operated gate, can realize the continuous control to the electrically operated gate moreover, avoids the electrically operated gate slow response, the control failure phenomenon appears. In addition, through transmitting the control voice command according to the command analysis result, the control of the electric door can be accurately realized for each control information in the control voice, the control failure and the control confusion when a plurality of control information appear in the control voice are avoided, the accuracy of the electric door to be controlled and the sensitivity of the electric door are improved, moreover, the electric door is opened or closed without manual operation when the electric door is controlled by voice, the manpower is saved, the additional payment of the manpower consumption cost is also not needed, and the cost consumption is effectively reduced.
As shown in fig. 2, in an embodiment provided by the present invention, recognizing the control speech includes:
performing voice processing on the control voice, and performing noise reduction processing on the control voice to obtain a first processing control voice;
separating the control keywords by the control voice in the middle of the first processing control voice to obtain a second processing control voice; the second processing control voice comprises one or more control keywords;
and obtaining a control voice instruction in an instruction database according to the second processing control voice and the control keyword.
According to the technical scheme, when the control voice is recognized, the control voice is subjected to voice processing firstly, at least the control voice is subjected to noise reduction processing during the voice processing, other voices which are obtained together with the control voice of the electric door are removed to obtain first processing control voice, then the control keywords are processed in the first processing control voice to obtain second processing control voice, wherein the second processing control voice is the control keywords in the first processing control voice, the control keywords can be expanded and set, and the default control keywords comprise: and finally, matching an instruction template matched with the control keyword in an instruction database according to the second processing control voice, and obtaining a control voice instruction according to specific information in the first processing control voice.
According to the technical scheme, the voice control is performed through voice processing to the control voice, so that interference voice in the control voice is removed, influence of the interference voice on the control voice is avoided, accuracy of the control voice is improved, control error probability of the electric door controlled through the voice is reduced, and when a control instruction is obtained, a control instruction template is stored in an instruction database, the control voice instruction can be obtained according to the first processing control voice on the basis of the instruction template, efficiency of obtaining the control voice instruction is improved, further speed of controlling the electric door is improved, and control over the electric door can be rapidly achieved.
In one embodiment provided by the invention, when a control voice instruction is obtained in an instruction database according to the control keyword according to the second processing control voice, if the control keyword is multiple, the control voice instruction is obtained in the instruction database according to the control keyword through multiple threads;
when the control voice instruction is analyzed according to the control voice, time analysis is carried out on the control voice instruction, the sequence of the control keywords corresponding to the control voice instruction appearing in the control voice is sequentially obtained, and the control voice instruction is subjected to time sequence arrangement according to the sequence to form an instruction analysis result.
According to the technical scheme, when the control voice command is obtained in the command database according to the control keyword according to the second processing control voice, at least one control keyword exists in the control voice, and when a plurality of control keywords exist in the control voice, the control voice command is obtained by processing in a plurality of threads at the same time. According to the technical scheme, when the control voice instruction is analyzed according to the control voice, the control voice instruction is subjected to time analysis, and as the control voice is obtained in real time, a plurality of control keywords may continuously exist in the obtained control voice, the sequence of the control voice instruction corresponding to the control voice is determined according to the control voice, the time sequence of the control voice instruction is obtained, and the control voice instruction is subjected to time sequence arrangement according to the time sequence of the control voice instruction, so that an instruction analysis result is obtained.
According to the technical scheme, the memory is enlarged by creating the threads, so that the shared memory among the threads is enlarged, more data can be processed simultaneously, the processing efficiency can be effectively improved, and the time consumed by controlling the voice instruction is prolonged. According to the technical scheme, the control voice commands are subjected to time sequence arrangement according to the control voice to obtain the command analysis result, so that the control voice commands can be transmitted and executed according to the sequence of the obtained control voice, even if a plurality of control voice commands occur, the control voice commands can be transmitted and executed according to the time sequence, the electric door can be orderly controlled, the control disorder of the electric door is avoided, and meanwhile, the accuracy of controlling the electric door can be improved.
As shown in fig. 3, in an embodiment provided by the present invention, transmitting the control voice command according to the command analysis result includes:
judging a control voice instruction to be transmitted, and judging whether the control voice instruction transmission exists within preset time;
when control voice command transmission exists, analyzing the control voice command, if the control voice command to be transmitted and the control voice command transmitted last are of the same control property, sending the control voice command to be transmitted according to a first sending frequency, if the control voice command to be transmitted and the control voice command transmitted last are not of the same control property, further analyzing the control voice command to be transmitted and the control voice command transmitted last, when the control property of the control voice command transmitted last is off, and the control voice command to be transmitted is on, sending the control voice command to be transmitted according to the first sending frequency, when the control property of the control voice command transmitted last is on, and the control property of the control voice command to be transmitted is off, and sending the control voice command to be transmitted according to a second sending frequency, wherein the second sending frequency is longer than the first sending frequency in time interval.
When the control voice command is transmitted according to the command analysis result, firstly, the control voice command to be transmitted is judged, whether the control voice command transmission exists in the preset time is judged, the preset time refers to the time consumed by the electric door from the closed state to the open state, if the control voice command transmission is stored in the preset time, the control property of the control voice command is analyzed, when the control voice command to be transmitted and two adjacent control voice commands of the control voice command transmitted last are the same control property, the control voice command to be transmitted is transmitted according to the first transmission frequency, and when the control voice command to be transmitted and the two adjacent control voice commands of the control voice command transmitted last are not the same control property, the two adjacent control voice commands are further analyzed, if the control property of the last transmitted control voice command is off and the control property of the control voice command to be transmitted is on, the control voice command to be transmitted is transmitted according to a first transmission frequency, if the control property of the last transmitted control voice command is on and the control property of the control voice command to be transmitted is off, the control voice command to be transmitted is transmitted according to a second transmission frequency, and in the process, the second transmission frequency is lower than the first transmission frequency.
According to the technical scheme, when the control voice command is transmitted according to the command analysis result, the control voice command is transmitted according to time sequence arrangement according to the command analysis result, the control property of the control voice command is also considered during transmission, continuous and same control can be performed on the electric door, when the control is required to be opened continuously, the electric door does not need to be opened again after the electric door is closed, the use good feeling of passers to the electric door is improved, the electric door can enable the passers to pass through the safety door when the control voice command is executed through the first sending frequency and the second sending frequency, and the safety guarantee is improved.
In one embodiment provided by the present invention, the control speech is further compressed before being transmitted; the compression process includes:
acquiring the size of the control voice instruction; performing form conversion on the control voice, converting the control voice instruction into a data packet form, and calculating the size of the data packet of the control voice instruction to obtain the size of the control voice instruction;
segmenting the control voice instruction; performing data segmentation on the control voice command from the initial character to the final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmentation byte threshold;
configuring a compression scheme for the control voice instruction; determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction, and obtaining a compression scheme related to the control voice instruction;
compressing the uncompressed data according to the compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in the uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and determining a data storage position according to the process change marking information, and performing compression storage according to the data storage position.
The technical proposal controls the voice to be compressed before being transmitted; wherein the compression treatment is carried out according to the following steps: firstly, acquiring the size of a control voice instruction; when the size of the control voice instruction is obtained, performing form conversion on the control voice, converting the control voice instruction into a data packet form, and obtaining the size of the control voice instruction by calculating the size of the data packet of the control voice instruction; then, segmenting the control voice command; when the control voice command is divided, the control voice command is divided from a starting character to a final character according to a division standard so as to obtain a plurality of uncompressed data, wherein the division standard can be an uncompressed data size threshold or a divided byte threshold, and one of the uncompressed data size threshold and the divided byte threshold is selected as a division standard; then, configuring a compression scheme for the control voice command; when a compression scheme is configured for the control voice instruction, determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction to obtain the compression scheme related to the control voice instruction; finally, compressing the uncompressed data according to a compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and calculating a compression deviation according to the process change mark information, combining the compression deviation with a threshold standard to obtain a compressed data storage address, calculating a flag bit data storage address according to the compression deviation, the threshold standard and the number information, and then storing the compressed data according to the storage address.
According to the technical scheme, the data packet transmission overhead is reduced through compression processing of the data packet for controlling the voice command, the network resource utilization rate is improved, meanwhile, the data packet can be prevented from being blocked and lost, and the effectiveness and accuracy of electric door control are ensured.
As shown in fig. 4, the present invention provides a voice command data transmission system for voice controlling an electric door, comprising: the voice recognition system comprises a voice acquisition module, a voice recognition module, an instruction analysis module, an instruction transmission module and an execution control module;
the voice acquisition module is used for acquiring control voice of the electric door;
the voice recognition module is used for recognizing the control voice acquired by the voice acquisition module and acquiring a control voice instruction;
the instruction analysis module is used for analyzing the control voice instruction to obtain an instruction analysis result;
the instruction transmission module is used for transmitting the control voice instruction according to the instruction analysis result and transmitting the control voice instruction to the execution control module;
and the execution control module is used for receiving the control voice command, executing the control voice command and controlling the electric door to be opened and closed.
The voice command data transmission system of the voice control electrically operated gate that above-mentioned technical scheme provided includes: the voice recognition system comprises a voice acquisition module, a voice recognition module, an instruction analysis module, an instruction transmission module and an execution control module; when the electrically operated gate is controlled through voice, firstly, the voice acquisition module acquires control voice of the electrically operated gate, the control voice is identified through the voice recognition module after the control voice of the electrically operated gate is acquired, control information in the control voice is recognized, and a control voice instruction is obtained according to the control information, then, the control voice instruction is analyzed through the instruction analysis module, attribute information of the control voice instruction is analyzed, so that an instruction analysis result is obtained, then the control voice instruction is transmitted according to the instruction analysis result through the instruction transmission module, and finally, the control voice instruction is executed after the execution control module receives the control voice instruction, so that the control of the electrically operated gate is realized.
Above-mentioned technical scheme has realized the control to the electrically operated gate through pronunciation, not only facilitates the use nimble operation for it is more convenient to the control of electrically operated gate, can realize the continuous control to the electrically operated gate moreover, avoids the electrically operated gate slow response, the control failure phenomenon appears. In addition, instruction transmission module can make and can both accurately realize the control to the electrically operated gate to every control information in the control pronunciation through transmitting the control voice command according to instruction analysis result, control failure and control confusion appear when a plurality of control information appear in the control pronunciation, thereby improve the accuracy that the electrically operated gate is controlled and the sensitivity of electrically operated gate, and need not manual operation when controlling the electrically operated gate through the pronunciation and make the electrically operated gate open or close, the manpower has been saved, also need not additionally to pay manpower consumption cost simultaneously, the consumption of cost has effectively been saved.
As shown in fig. 5, in an embodiment provided by the present invention, the speech recognition module includes: the voice processing unit, the voice separating unit and the instruction generating unit;
the voice processing unit is used for performing voice processing on the control voice and performing noise reduction processing on the control voice to obtain a first processing control voice;
the voice separation unit is used for controlling voice to separate and process the control keywords in the middle of the first processing control voice to obtain a second processing control voice; the second processing control voice comprises one or more control keywords;
the instruction generating unit is used for obtaining a control voice instruction in an instruction database according to the second processing control voice and the control keyword
The above technical solution includes in the voice recognition module: the voice processing unit, pronunciation separating unit and instruction generating unit, the speech recognition module is when discerning control voice, carry out speech processing to control voice through the speech processing unit earlier, at least, carry out noise reduction to control voice when speech processing, will acquire other pronunciation that obtain simultaneously when the control voice to the electrically operated gate gets rid of, obtain first processing control voice, then speech separating unit will control the keyword processing in first processing control voice, obtain second processing control voice, wherein, second processing control voice is the control keyword in first processing control voice, control keyword can expand and set for, acquiescent control keyword includes: and finally, the instruction generating unit matches an instruction template matched with the control keyword in an instruction database according to the second processing control voice, and obtains a control voice instruction according to specific information in the first processing control voice.
According to the technical scheme, the voice processing unit is used for carrying out voice processing on the control voice to remove the interference voice in the control voice, the influence of the interference voice on the control voice is avoided, the accuracy of the control voice is improved, the control error probability of the electrically operated door controlled by the voice is reduced, and when the command generating unit obtains a control command, the control command template is stored in the command database, the control voice command can be obtained according to the first processing control voice on the basis of the command template, the efficiency of obtaining the control voice command is improved, the speed of controlling the electrically operated door is further improved, the control on the electrically operated door can be rapidly realized, in addition, the control keywords are separated through the voice separating unit, and the complexity of obtaining the control voice command in the command generating unit is reduced.
In an embodiment provided by the present invention, when obtaining a control voice instruction according to the control keyword in an instruction database according to the second processing control voice, if there are a plurality of control keywords, the instruction generating unit obtains the control voice instruction according to the control keyword in the instruction database through a plurality of threads concurrently;
when the instruction analysis module analyzes the control voice instruction, time analysis is carried out on the control voice instruction according to the control voice, the sequence of the control keywords corresponding to the control voice instruction appearing in the control voice is sequentially obtained, and the control voice instruction is subjected to time sequence arrangement according to the sequence to form an instruction analysis result.
In the technical scheme, the instruction generating unit has at least one control keyword in the control voice in the process of obtaining the control voice instruction according to the control keyword in the instruction database according to the second processing control voice, and when a plurality of control keywords exist in the control voice, the control voice instruction is obtained by processing in a plurality of threads at the same time. According to the technical scheme, when the control voice instruction is analyzed, the instruction analysis module analyzes the time of the control voice instruction, and the control voice is obtained in real time, so that a plurality of control keywords may continuously exist in the obtained control voice, therefore, the sequence of the control voice instruction corresponding to the control voice is determined according to the control voice, the time sequence of the control voice instruction is obtained, the control voice instruction is arranged according to the time sequence of the control voice instruction, and an instruction analysis result is obtained.
According to the technical scheme, the multiple threads are created in the instruction generation unit, the memory is enlarged by creating the multiple threads, so that the shared memory among the threads is enlarged, more data can be processed simultaneously, the processing efficiency can be effectively improved, and the time consumed by controlling the voice instructions is prolonged. According to the technical scheme, the instruction analysis module carries out time sequence arrangement on the control voice instructions according to the control voice to obtain the instruction analysis result, so that the control voice instructions can be transmitted and executed according to the sequence of the obtained control voice, even if a plurality of control voice instructions occur, the control voice instructions can also be transmitted and executed according to the time sequence, the electric door can be controlled orderly, the confusion of the electric door control is avoided, and meanwhile, the accuracy of the electric door control can be improved.
As shown in fig. 6, in an embodiment provided by the present invention, the instruction transmission module includes: a judgment unit and a condition unit;
the judging unit is used for judging the control voice command to be transmitted and judging whether the control voice command transmission exists in the preset time;
the condition unit is used for transmitting according to the judgment result obtained by the judgment unit, when control voice command transmission exists, the control voice command is analyzed, if the control voice command to be transmitted and the last transmitted control voice command have the same control property, the control voice command to be transmitted is transmitted according to a first transmission frequency, if the control voice command to be transmitted and the last transmitted control voice command do not have the same control property, the control voice command to be transmitted and the last transmitted control voice command are further analyzed, when the control property of the last transmitted control voice command is off, and the control property of the control voice command to be transmitted is on, the control voice command to be transmitted is transmitted according to the first transmission frequency, and when the control property of the last transmitted control voice command is on, and when the control property of the control voice command to be transmitted is off, transmitting the control voice command to be transmitted according to a second transmission frequency, wherein the second transmission frequency is longer than the first transmission frequency in time interval.
The technical scheme comprises the following steps in an instruction transmission module: a judgment unit and a condition unit; when the control voice command is transmitted through the command transmission module according to a command analysis result, the control voice command to be transmitted is judged through the judging unit, whether the control voice command transmission exists in the preset time or not is judged, the preset time refers to the time consumed by the electric door from the closed state to the open state, then the control voice command is transmitted through the condition unit according to the judgment result obtained by the judging unit, if the control voice command transmission is stored in the preset time, the control property of the control voice command is analyzed, when the control voice command to be transmitted and two adjacent control voice commands of the control voice command transmitted last are the same, the control voice command to be transmitted is transmitted according to a first transmission frequency, and when the control voice command to be transmitted and the two adjacent control voice commands of the control voice command transmitted last are not the same, and further analyzing the two adjacent control voice commands, if the control property of the last transmitted control voice command is off and the control property of the control voice command to be transmitted is on, transmitting the control voice command to be transmitted according to a first transmission frequency, and if the control property of the last transmitted control voice command is on and the control property of the control voice command to be transmitted is off, transmitting the control voice command to be transmitted according to a second transmission frequency, wherein the second transmission frequency is lower than the first transmission frequency in the process.
According to the technical scheme, the instruction transmission module transmits the control voice instruction according to the time sequence arrangement according to the instruction analysis result, and the control property of the control voice instruction is also considered during transmission, so that the electric door can be continuously and identically controlled, when the control is continuously required to be opened, the electric door does not need to be opened again after being closed, so that the use of passers-by to the electric door is improved, and the passers-by can pass through the safety door by the electric door when the control voice instruction is executed through the first sending frequency and the second sending frequency, and the safety guarantee is improved.
In an embodiment provided by the present invention, the instruction transmission module further includes a compression unit, and the condition unit compresses the control voice instruction by the compression unit before transmitting according to the determination result obtained by the determination unit, where the compression unit includes: the system comprises a metering division small unit, a compression configuration small unit and a compression storage small unit;
the measurement division small unit is used for carrying out form conversion on the control voice, converting the control voice instruction into a data packet form, and obtaining the size of the control voice instruction by calculating the size of the data packet of the control voice instruction; performing data segmentation on the control voice command from the initial character to the final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmented byte threshold;
the compression configuration small unit is used for determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction to obtain a compression scheme related to the control voice instruction;
the compression storage small unit is used for compressing the uncompressed data according to the compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in the uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and determining a data storage position according to the process change marking information, and performing compression storage according to the data storage position.
The technical scheme is that a compression unit is further arranged in the instruction transmission module, the compression unit is used for compressing the control voice instruction, and the compression unit comprises a metering segmentation small unit, a compression configuration small unit and a compression storage small unit; when a control voice instruction is compressed, acquiring the size of the control voice instruction and segmenting the control voice instruction through a metering and segmenting small unit, performing form conversion on the control voice when the size of the control voice instruction is acquired, converting the control voice instruction into a data packet form, and calculating the size of the data packet of the control voice instruction to obtain the size of the control voice instruction; when the control voice command is segmented, performing data segmentation on the control voice command from a starting character to a final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmentation byte threshold; determining which uncompressed data are compressed in the plurality of uncompressed data through a compression configuration small unit according to the size of the control voice instruction to obtain a compression scheme related to the control voice instruction, so as to realize the purpose of configuring the compression scheme for the control voice instruction; finally, compressing the uncompressed data according to a compression scheme through a small compression storage unit to obtain control voice instruction compression information; removing and compressing invalid information in uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and calculating a compression deviation according to the process change mark information, combining the compression deviation with a threshold standard to obtain a compressed data storage address, calculating a flag bit data storage address according to the compression deviation, the threshold standard and the number information, and then storing the compressed data according to the storage address.
According to the technical scheme, the compression unit can be used for compressing the data packet of the control voice command, the data packet transmission overhead is reduced, the network resource utilization rate is improved, meanwhile, the data packet can be prevented from being blocked and lost, and the effectiveness and accuracy of electric door control are ensured.
It will be understood by those skilled in the art that the first and second embodiments of the present invention are merely directed to different stages of application.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A voice command data transmission method for controlling an electric door by voice is characterized by comprising the following steps:
acquiring control voice of the electric door;
recognizing the control voice to obtain a control voice instruction;
analyzing the control voice command according to the control voice to obtain a command analysis result;
transmitting the control voice command according to the command analysis result;
and receiving the control voice command, executing the control voice command, and controlling the electric door to be opened and closed.
2. The voice instruction data transmission method according to claim 1, wherein recognizing the control voice includes:
performing voice processing on the control voice, and performing noise reduction processing on the control voice to obtain a first processing control voice;
separating the control keywords by the control voice in the middle of the first processing control voice to obtain a second processing control voice; the second processing control voice comprises one or more control keywords;
and obtaining a control voice instruction in an instruction database according to the second processing control voice and the control keyword.
3. The voice instruction data transmission method according to claim 2, wherein when a control voice instruction is obtained in an instruction database according to the control keyword according to the second processing control voice, if the control keyword is plural, the control voice instruction is obtained in the instruction database according to the control keyword through a plurality of threads concurrently;
when the control voice instruction is analyzed according to the control voice, time analysis is carried out on the control voice instruction, the sequence of the control keywords corresponding to the control voice instruction appearing in the control voice is sequentially obtained, and the control voice instruction is subjected to time sequence arrangement according to the sequence to form an instruction analysis result.
4. The voice command data transmission method according to claim 1, wherein transmitting the control voice command according to the command analysis result includes:
judging a control voice instruction to be transmitted, and judging whether the control voice instruction transmission exists within preset time;
when control voice command transmission exists, analyzing the control voice command, if the control voice command to be transmitted and the control voice command transmitted last are of the same control property, sending the control voice command to be transmitted according to a first sending frequency, if the control voice command to be transmitted and the control voice command transmitted last are not of the same control property, further analyzing the control voice command to be transmitted and the control voice command transmitted last, when the control property of the control voice command transmitted last is off, and the control voice command to be transmitted is on, sending the control voice command to be transmitted according to the first sending frequency, when the control property of the control voice command transmitted last is on, and the control property of the control voice command to be transmitted is off, and sending the control voice command to be transmitted according to a second sending frequency, wherein the second sending frequency is longer than the first sending frequency in time interval.
5. The voice instruction data transmission method according to claim 4, wherein the control voice is further subjected to compression processing before transmission; the compression process includes:
acquiring the size of the control voice instruction; performing form conversion on the control voice, converting the control voice instruction into a data packet form, and calculating the size of the data packet of the control voice instruction to obtain the size of the control voice instruction;
segmenting the control voice instruction; performing data segmentation on the control voice command from the initial character to the final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmentation byte threshold;
configuring a compression scheme for the control voice instruction; determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction, and obtaining a compression scheme related to the control voice instruction;
compressing the uncompressed data according to the compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in the uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and determining a data storage position according to the process change marking information, and performing compression storage according to the data storage position.
6. A voice command data transmission system for voice-controlled electrically operated gate, comprising: the voice recognition system comprises a voice acquisition module, a voice recognition module, an instruction analysis module, an instruction transmission module and an execution control module;
the voice acquisition module is used for acquiring control voice of the electric door;
the voice recognition module is used for recognizing the control voice acquired by the voice acquisition module and acquiring a control voice instruction;
the instruction analysis module is used for analyzing the control voice instruction to obtain an instruction analysis result;
the instruction transmission module is used for transmitting the control voice instruction according to the instruction analysis result and transmitting the control voice instruction to the execution control module;
and the execution control module is used for receiving the control voice command, executing the control voice command and controlling the electric door to be opened and closed.
7. The voice command data transmission system according to claim 6, wherein the voice recognition module comprises: the voice processing unit, the voice separating unit and the instruction generating unit;
the voice processing unit is used for performing voice processing on the control voice and performing noise reduction processing on the control voice to obtain a first processing control voice;
the voice separation unit is used for controlling voice to separate and process the control keywords in the middle of the first processing control voice to obtain a second processing control voice; the second processing control voice comprises one or more control keywords;
and the instruction generating unit is used for obtaining a control voice instruction in an instruction database according to the second processing control voice and the control keyword.
8. The voice instruction data transmission system according to claim 7, wherein the instruction generation unit obtains, when obtaining a control voice instruction according to the control keyword in an instruction database according to the second process control voice, a control voice instruction according to the control keyword in the instruction database concurrently by a plurality of threads if the control keyword is plural;
when the instruction analysis module analyzes the control voice instruction, time analysis is carried out on the control voice instruction according to the control voice, the sequence of the control keywords corresponding to the control voice instruction appearing in the control voice is sequentially obtained, and the control voice instruction is subjected to time sequence arrangement according to the sequence to form an instruction analysis result.
9. The voice command data transmission system according to claim 6, wherein the command transmission module comprises: a judgment unit and a condition unit;
the judging unit is used for judging the control voice command to be transmitted and judging whether the control voice command transmission exists in the preset time;
the condition unit is used for transmitting according to the judgment result obtained by the judgment unit, when control voice command transmission exists, the control voice command is analyzed, if the control voice command to be transmitted and the last transmitted control voice command have the same control property, the control voice command to be transmitted is transmitted according to a first transmission frequency, if the control voice command to be transmitted and the last transmitted control voice command do not have the same control property, the control voice command to be transmitted and the last transmitted control voice command are further analyzed, when the control property of the last transmitted control voice command is off, and the control property of the control voice command to be transmitted is on, the control voice command to be transmitted is transmitted according to the first transmission frequency, and when the control property of the last transmitted control voice command is on, and when the control property of the control voice command to be transmitted is off, transmitting the control voice command to be transmitted according to a second transmission frequency, wherein the second transmission frequency is longer than the first transmission frequency in time interval.
10. The voice instruction data transmission system according to claim 6, wherein the instruction transmission module further includes a compression unit, the condition unit performs compression processing on the control voice instruction by the compression unit before transmission according to the determination result obtained by the determination unit, and the compression unit includes: the system comprises a metering division small unit, a compression configuration small unit and a compression storage small unit;
the measurement division small unit is used for carrying out form conversion on the control voice, converting the control voice instruction into a data packet form, and obtaining the size of the control voice instruction by calculating the size of the data packet of the control voice instruction; performing data segmentation on the control voice command from the initial character to the final character according to a segmentation standard to obtain a plurality of uncompressed data, wherein the segmentation standard is an uncompressed data size threshold or a segmented byte threshold;
the compression configuration small unit is used for determining which uncompressed data are compressed in the plurality of uncompressed data according to the size of the control voice instruction to obtain a compression scheme related to the control voice instruction;
the compression storage small unit is used for compressing the uncompressed data according to the compression scheme to obtain control voice instruction compression information; removing and compressing invalid information in the uncompressed data to obtain compressed data, and acquiring process change marking information, wherein the process change marking information comprises: flag bit data and number information; and determining a data storage position according to the process change marking information, and performing compression storage according to the data storage position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110788315.7A CN113539264B (en) | 2021-07-13 | 2021-07-13 | Voice command data transmission method and system for voice-controlled electric door |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110788315.7A CN113539264B (en) | 2021-07-13 | 2021-07-13 | Voice command data transmission method and system for voice-controlled electric door |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113539264A true CN113539264A (en) | 2021-10-22 |
| CN113539264B CN113539264B (en) | 2023-10-13 |
Family
ID=78127551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110788315.7A Active CN113539264B (en) | 2021-07-13 | 2021-07-13 | Voice command data transmission method and system for voice-controlled electric door |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113539264B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114553622A (en) * | 2022-02-08 | 2022-05-27 | 珠海格力电器股份有限公司 | Voice data transmission method and device and voice terminal equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105909118A (en) * | 2016-05-30 | 2016-08-31 | 中山市福瑞卫浴设备有限公司 | Acoustic control electrically-operated gate type shower room |
| CN106373566A (en) * | 2016-08-25 | 2017-02-01 | 深圳市元征科技股份有限公司 | Data transmission control method and device |
| CN108428449A (en) * | 2017-02-14 | 2018-08-21 | 张凤鹏 | The system and method for speech recognition infrared induction control restroom door in high ferro motor-car |
| CN110266316A (en) * | 2019-05-08 | 2019-09-20 | 阿里巴巴集团控股有限公司 | A kind of data compression, decompressing method, device and equipment |
| US20200401339A1 (en) * | 2019-06-24 | 2020-12-24 | Western Digital Technologies, Inc. | Flash memory polling |
| CN112346885A (en) * | 2020-10-19 | 2021-02-09 | 深圳Tcl新技术有限公司 | Electronic device control method, device, equipment and computer readable storage medium |
-
2021
- 2021-07-13 CN CN202110788315.7A patent/CN113539264B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105909118A (en) * | 2016-05-30 | 2016-08-31 | 中山市福瑞卫浴设备有限公司 | Acoustic control electrically-operated gate type shower room |
| CN106373566A (en) * | 2016-08-25 | 2017-02-01 | 深圳市元征科技股份有限公司 | Data transmission control method and device |
| CN108428449A (en) * | 2017-02-14 | 2018-08-21 | 张凤鹏 | The system and method for speech recognition infrared induction control restroom door in high ferro motor-car |
| CN110266316A (en) * | 2019-05-08 | 2019-09-20 | 阿里巴巴集团控股有限公司 | A kind of data compression, decompressing method, device and equipment |
| US20200401339A1 (en) * | 2019-06-24 | 2020-12-24 | Western Digital Technologies, Inc. | Flash memory polling |
| CN112346885A (en) * | 2020-10-19 | 2021-02-09 | 深圳Tcl新技术有限公司 | Electronic device control method, device, equipment and computer readable storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114553622A (en) * | 2022-02-08 | 2022-05-27 | 珠海格力电器股份有限公司 | Voice data transmission method and device and voice terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113539264B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103700370B (en) | A kind of radio and television speech recognition system method and system | |
| CN108962255B (en) | Emotion recognition method, emotion recognition device, server and storage medium for voice conversation | |
| CN102982811B (en) | Voice endpoint detection method based on real-time decoding | |
| CN104123939A (en) | Substation inspection robot based voice interaction control method | |
| CN112289323B (en) | Voice data processing method and device, computer equipment and storage medium | |
| CN104575504A (en) | Method for personalized television voice wake-up by voiceprint and voice identification | |
| CN106409289A (en) | Environment self-adaptive method of speech recognition, speech recognition device and household appliance | |
| CN108172219A (en) | The method and apparatus for identifying voice | |
| CN112735482A (en) | Endpoint detection method and system based on combined deep neural network | |
| CN111161726B (en) | Intelligent voice interaction method, device, medium and system | |
| CN110176228A (en) | A kind of small corpus audio recognition method and system | |
| CN110428853A (en) | Voice activity detection method, Voice activity detection device and electronic equipment | |
| CN109347708A (en) | A kind of audio recognition method, device, household appliance, Cloud Server and medium | |
| CN113539264B (en) | Voice command data transmission method and system for voice-controlled electric door | |
| CN111326139B (en) | Language identification method, device, equipment and storage medium | |
| CN111210824B (en) | Voice information processing method and device, electronic equipment and storage medium | |
| CN112863485A (en) | Accent voice recognition method, apparatus, device and storage medium | |
| CN112466287B (en) | Voice segmentation method, device and computer readable storage medium | |
| CN112543371A (en) | Video data processing method, device, terminal and storage medium | |
| CN117456995A (en) | Interactive method and system of pension service robot | |
| CN115910045B (en) | Model training method and recognition method for voice wake-up word | |
| CN112802498A (en) | Voice detection method and device, computer equipment and storage medium | |
| CN111048068B (en) | Voice wake-up method, device and system and electronic equipment | |
| CN114792518A (en) | Voice recognition system based on scheduling domain technology, method thereof and storage medium | |
| CN113921000A (en) | Online instruction word voice recognition method and system in noise environment |
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 |