CN107705788A - The method of calibration and intelligent terminal of a kind of phonetic order - Google Patents
The method of calibration and intelligent terminal of a kind of phonetic order Download PDFInfo
- Publication number
- CN107705788A CN107705788A CN201710909063.2A CN201710909063A CN107705788A CN 107705788 A CN107705788 A CN 107705788A CN 201710909063 A CN201710909063 A CN 201710909063A CN 107705788 A CN107705788 A CN 107705788A
- Authority
- CN
- China
- Prior art keywords
- voice
- intelligent terminal
- instruction
- verification information
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000004044 response Effects 0.000 claims abstract description 83
- 238000012795 verification Methods 0.000 claims description 104
- 125000004122 cyclic group Chemical group 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1822—Parsing for meaning understanding
-
- 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
- G10L15/26—Speech to text systems
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
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)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present embodiments relate to artificial intelligence field, the method for calibration and intelligent terminal of a kind of phonetic order are disclosed.In the present invention, the method for calibration of phonetic order, applied to the first intelligent terminal, including：After the phonetic order for the operation for being used for the second intelligent terminal of instruction that user sends is received, voice response is made to phonetic order, voice response is carried only for the check information of equipment identification, check information is used for for the second intelligent terminal according to check information, detect and phonetic order is identified whether correctly, second intelligent terminal is effectively detected to identify whether correctly phonetic order, so as to correctly perform the operation indicated by phonetic order.
Description
Technical Field
The embodiment of the invention relates to the field of artificial intelligence, in particular to a voice instruction verification method and an intelligent terminal.
Background
Artificial Intelligence (AI) is a new technical science for studying and developing theories, methods, techniques and application systems for simulating, extending and expanding human Intelligence. It attempts to understand the essence of intelligence and produces a new intelligent machine that can react in a manner similar to human intelligence, a field of research including robotics, language recognition, image recognition, natural language processing, and expert systems. Since the birth of artificial intelligence, theories and technologies become mature day by day, and application fields are expanded continuously, so that science and technology products brought by the artificial intelligence in the future can be assumed to be 'containers' of human intelligence. Under this big background of artificial intelligence, people are to the continuous promotion of the demand of smart machine, and smart machine develops gradually towards the direction of volume miniaturization, function intensification, and various wearable smart machine begin to get into people's daily life, if: smart watches, smart glasses, and the like, people's daily life is becoming more and more away from smart devices.
However, the inventors found that at least the following problems exist in the prior art: with the increase of the number of smart devices and the increasing role played by smart devices in life, errors occur in recognizing voice commands issued by users by smart devices in many cases, so that operations indicated by the voice commands are executed incorrectly.
Disclosure of Invention
The embodiment of the invention aims to provide a voice instruction checking method and an intelligent terminal, so that the intelligent terminal can effectively detect whether the recognition of a voice instruction is correct or not, and accordingly, the operation indicated by the voice instruction is correctly executed.
In order to solve the above technical problem, an embodiment of the present invention provides a method for verifying a voice instruction, which is applied to a first intelligent terminal, and includes:
and after a voice instruction which is sent by a user and used for indicating the operation of the second intelligent terminal is received, making a voice response to the voice instruction, wherein the voice response carries verification information only used for equipment identification, and the verification information is used for the second intelligent terminal to detect whether the identification of the voice instruction is correct or not according to the verification information.
The embodiment of the invention also provides a voice instruction checking method, which is applied to a second intelligent terminal and comprises the following steps:
after receiving a voice instruction which is sent by a user and used for indicating the operation of the second intelligent terminal, recognizing the voice instruction;
after receiving a voice response made by the first intelligent terminal to the voice command, detecting whether the voice command is correctly identified according to verification information carried in the voice response and only used for equipment identification.
The embodiment of the invention also provides an intelligent terminal, which comprises: at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for verifying voice instructions.
Compared with the prior art, the voice response method and the voice response device have the advantages that after the voice command which is sent by the user and used for indicating the operation of the second intelligent terminal is received, the voice response is made to the voice command, the voice response carries the verification information only used for equipment identification, namely the voice response made by the first intelligent terminal carries the verification information only used for equipment identification, and the verification information is used for the second intelligent terminal to detect whether the voice command is correctly identified or not according to the verification information. Since the verification information is equivalently carried in the voice reply in the form of the password, only the equipment can identify, and the second intelligent terminal can effectively detect whether the identification of the voice command is correct or not according to the received verification information, so that the operation indicated by the voice command is correctly executed.
In addition, before making a voice response to the voice command, the method further comprises the following steps: performing semantic recognition on the voice instruction; and generating a coding instruction for controlling the second intelligent terminal to execute the operation according to the operation of the second intelligent terminal indicated by the identified user, and taking the coding instruction as the verification information. The coding instruction for controlling the second intelligent terminal to execute the operation is used as the verification information, so that the verification information is more pertinent, namely the verification information is another expression mode of the operation indicated by the voice instruction, only equipment can recognize the expression mode, the auditory perception of natural people cannot be influenced, and the voice instruction identification method is beneficial to effectively detecting whether the second intelligent terminal identifies the voice instruction correctly or not and simultaneously improving the user experience.
In addition, verification information is carried in the voice response by: converting the verification information into ultrasonic waves or infrasonic waves according to a preset coding rule; the converted ultrasonic or infrasonic waves are superimposed into the voice response. Through the mode, the verification information is converted into the sound wave information to be carried in the voice response, so that whether the recognition of the voice instruction is correct or not is detected based on the better detection of the verification information in the voice response by the second intelligent terminal, the voice response heard by the user cannot be influenced on the premise that the second intelligent terminal can acquire the verification information from the voice response, and the user experience can be improved.
In addition, when verification error information fed back by the second intelligent terminal is received, prompt information is sent to a user; the verification error information is used for indicating that the second intelligent terminal incorrectly identifies the voice instruction, and the prompt information is used for requiring the user to send an instruction again. The prompt message used for indicating that the voice instruction is incorrectly identified by the second intelligent terminal is sent to the user, so that the user can conveniently send the instruction again in time, and the instruction operation required by the user can be better executed.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a flow chart illustrating a method for verifying a voice command according to a first embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for verifying a voice command according to a third embodiment of the present invention;
fig. 3 is a schematic structural diagram of an intelligent terminal according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments.
The first embodiment of the invention relates to a voice instruction checking method which is applied to a first intelligent terminal. The core of the embodiment is that after a voice instruction which is sent by a user and used for indicating the operation of the second intelligent terminal is received, a voice response is made to the voice instruction, the voice response carries verification information only used for equipment identification, and the verification information is used for the second intelligent terminal to detect whether the voice instruction is correctly identified according to the verification information, so that whether the intelligent terminal correctly identifies the voice instruction can be effectively detected, and the operation indicated by the voice instruction is correctly executed. The following describes implementation details of the voice instruction verification method according to the present embodiment in detail, and the following description is only provided for facilitating understanding of the implementation details and is not necessary for implementing the present solution.
In this embodiment, a method for verifying a voice instruction is applied to a first intelligent terminal, and a specific flow is shown in fig. 1, where the method includes:
step 101: and receiving a voice instruction sent by the user and used for indicating the operation of the second intelligent terminal.
Specifically, the first intelligent terminal receives a voice instruction issued by a user to instruct the operation of the second intelligent terminal. First intelligent terminal can be smart mobile phone, panel computer, intelligent wearing equipment etc. and second intelligent terminal can be smart door and window, intelligent desk lamp, intelligent equipment such as refrigerator. In this embodiment, the first smart terminal is an example of a smart phone, and the second smart terminal is an example of an intelligent desk lamp, but the invention is not limited thereto in practical application. For example, a mobile phone of a user receives a voice instruction sent by the user to instruct the intelligent desk lamp to turn on, that is, the mobile phone receives a voice instruction sent by the user to turn on the lamp.
Step 102: and performing semantic recognition on the voice command.
Specifically, the first intelligent terminal performs semantic recognition on the voice command, that is, the first intelligent terminal needs to understand the specific meaning of the received command, and can perform semantic recognition on the voice command based on the rule and the corpus stored in the first intelligent terminal. Such as: the received instruction can be segmented into a plurality of related semantic meta-components by using a semantic segmentation rule, and then semantic internal representation corresponding to each semantic meta-component is found out according to a semantic conversion rule (such as keyword matching). The first intelligent terminal establishes the logical relation among the semantic components by testing the relation among the semantic components to form full-text semantic recognition, and the processing process is mainly realized by looking up a semantic dictionary. In addition, in the process of carrying out semantic recognition on the received instruction by the first intelligent terminal, the received instruction and the recognized semantics can be stored, and a one-to-one correspondence relationship is established between the instruction and the recognized semantics, so that when the first intelligent terminal receives the instruction again, the first intelligent terminal can be preferentially matched with the stored instruction, and if the instruction is completely matched with the stored instruction, the semantics corresponding to the received instruction can be directly obtained, and the efficiency of semantic recognition can be improved.
Furthermore, semantic recognition is carried out on the received voice command, and conversion on different planes can be carried out on different commands received by the first intelligent terminal by using the latest result of artificial intelligence, namely, by using the multi-path dynamic selection and the automatic recombination technology of a knowledge base. Therefore, the grammar, the semantics and the common sense planes can be connected into an organic whole, the advantages of the traditional system can be inherited, and the self-growing function of the system can be realized. Of course, in addition to the above manner, semantic recognition may be performed on the received instruction based on the statistical result, the artificial neural network, and the like, and any method for performing semantic recognition on the received instruction is within the protection scope of the present embodiment, and is not described in detail herein.
Step 103: a voice response is made to the voice command, the voice response carrying verification information for device identification only.
Specifically, the first intelligent terminal makes a voice response to the voice command, and the voice response carries verification information only used for equipment identification. Before making a voice response to the voice command, the first intelligent terminal can generate a coding command for controlling the second intelligent terminal to execute the operation according to the operation of the second intelligent terminal indicated by the identified user; and taking the coding instruction as check information. The person skilled in the art can implement by computer program, according to the operation of the second intelligent terminal indicated by the identified user, to generate coded instructions for controlling the second intelligent terminal to execute the operation, and therefore, the detailed description is omitted here. The coding instruction for controlling the second intelligent terminal to execute the operation is used as the verification information, so that the verification information is more pertinent, namely the verification information is another expression mode of the operation indicated by the voice instruction, and whether the voice instruction is correctly identified by the second intelligent terminal is effectively detected.
In practical application, the first intelligent terminal can also calculate a check code of the coding instruction according to a preset check algorithm, the check code is used as check information, and the preset check algorithm can be parity check, hamming check and cyclic redundancy check.
In the embodiment of the present invention, the verification information is carried in the voice response, and can be implemented in the following manner: converting the verification information into ultrasonic waves or infrasonic waves according to a preset coding rule; the converted ultrasonic or infrasonic waves are superimposed into the voice response.
For example, the coded instructions generated by the first intelligent terminal for controlling the second intelligent terminal to perform the operations indicated by the voice instructions may be represented as 1010 in binary code. For example, the coded instruction generated by the smart phone of the user for controlling the smart desk lamp to perform the "turn on" operation is 1010, and 1010 is used as the verification information. The verification information is converted into infrasonic waves according to a preset coding rule, and the preset coding rule can be preset by a person skilled in the art according to actual needs. For example, the preset encoding rule is as follows: a "1" corresponds to a frequency of 19Hz, and a "0" corresponds to a frequency of 17 Hz. The verification information, i.e., the coding instructions 1010, can be converted into infrasonic waves having frequencies in the order of 19HZ, 17HZ, 19HZ, 17HZ according to a preset coding rule. The converted infrasonic wave is superposed into a voice response, the voice response is a piece of voice information, for example, the voice response made by the smart phone of the user to the voice command of turning on the light is 'good', and the converted infrasonic wave is superposed into the voice response of 'good'. The user can ensure that the sent voice command is successfully identified by the mobile phone according to the received good voice response, and because the verification information superposed in the voice response is infrasonic waves, the frequency of the infrasonic waves is less than 20HZ and is out of the frequency range which can be identified by human ears, the user can not identify the verification information, and only the equipment can identify the verification information carried in the voice response. The method 1 realizes that the verification information only used for equipment identification is carried in the voice reply.
It should be noted that, in the embodiment, the verification information is converted into the infrasonic wave as an example, but in practical application, the verification information may also be converted into the ultrasonic wave, which is similar to the method of converting the verification information into the infrasonic wave, and thus the description thereof is omitted. In this embodiment, the coded command is represented by binary, and in practical application, the coded command may be represented by a common counting method such as decimal, hexadecimal, and the like.
By the method, the verification information is converted into the sound wave information to be carried in the voice response, so that the second intelligent terminal can better detect whether the voice instruction is correctly identified based on the verification information in the voice response.
It should be noted that, when receiving the verification error information fed back by the second intelligent terminal, the first intelligent terminal sends a prompt message to the user; the verification error information is used for indicating that the second intelligent terminal incorrectly identifies the voice instruction, and the prompt information is used for requiring the user to send an instruction again. For example, when receiving the verification error information fed back by the smart desk lamp, the smart phone of the user sends a prompt message to the user, that is, the smart desk lamp may incorrectly identify the voice command sent by the user, which results in a verification error, and then the verification error information is fed back to the mobile phone of the user.
Compared with the prior art, the embodiment of the invention makes a voice response to the voice instruction after receiving the voice instruction which is sent by the user and used for indicating the operation of the second intelligent terminal, wherein the voice response carries the verification information only used for equipment identification, that is, the voice response made by the first intelligent terminal carries the verification information only used for equipment identification, and the verification information is equivalently carried in the voice response in a form of a secret code. Converting the verification information into ultrasonic waves or infrasonic waves according to a preset coding rule; the converted ultrasonic or infrasonic waves are superimposed into the voice response. The verification information carried in the voice response can be identified only by the equipment, and the second intelligent terminal can effectively detect whether the voice command is correctly identified according to the identified verification information, so that the operation indicated by the voice command is correctly executed. The prompt message used for indicating that the voice instruction is incorrectly identified by the second intelligent terminal is sent to the user, so that the user can conveniently send the instruction again in time, and the instruction operation required by the user can be better executed.
The second embodiment of the invention relates to a voice instruction checking method which is applied to a first intelligent terminal. The second embodiment is substantially the same as the first embodiment, and mainly differs therefrom in that: in the first embodiment, the verification information is converted into ultrasonic waves or infrasonic waves according to a preset encoding rule; and the converted ultrasonic waves or infrasonic waves are superposed in the voice response, so that the verification information only used for equipment identification is carried in the voice response. In the present embodiment, however, the verification information is converted into sound waves according to a preset coding rule, and the sound waves are divided into L sub-sound waves; inserting sub-sound waves in sequence every first preset time length in a voice response; the duration of the sub-sound wave is less than 1/N of the first preset duration, and N is greater than a preset threshold, so that verification information only recognized by equipment is carried in a voice response.
In the second embodiment of the present invention, the verification information only for device identification is carried in the voice reply, and it can be understood that the coded instruction generated by the first intelligent terminal for controlling the second intelligent terminal to execute the operation indicated by the voice instruction may be represented as 1010 by a binary code. For example, the coded instruction generated by the smart phone of the user for controlling the smart desk lamp to perform the "turn on" operation is 1010, and 1010 is used as the verification information. The verification information is converted into sound waves according to a preset coding rule, wherein the sound waves can be ultrasonic waves, infrasonic waves and sound waves within the human ear recognition range, and the preset coding rule can be preset by a person skilled in the art according to actual needs. For example, the preset encoding rule is as follows: a "1" corresponds to a frequency of 500Hz, and a "0" corresponds to a frequency of 700 Hz. The verification information, i.e., the coded instructions 1010, may be converted into sound waves having a frequency order of 500HZ, 700HZ, according to a preset coding rule. The sound wave is divided into L sub-sound waves, for example, the sound wave may be divided into 5 sub-sound waves, and the time duration of each sub-sound wave is 0.1 millisecond. Inserting sub-sound waves in sequence every first preset time length in a voice response; and the duration of the sub-sound wave is less than 1/N of the first preset duration, and N is greater than a preset threshold. If the duration of the sub-sound wave is much less than the first preset duration, then the sub-sound wave is inserted into the voice response, and the voice response recognized by the person is indistinguishable from the voice response that had not been previously inserted, and only the device can recognize the sub-sound wave inserted in the voice response. Thus, N may be set to 1000, and if the duration of the sub-sound wave is less than 1/1000 for the first predetermined duration, it may be considered that the duration of the sub-sound wave is much less than the first predetermined duration, and only the device may recognize the sub-sound wave inserted in the voice response.
The voice response is a piece of voice information, for example, the user's smartphone responds "good" to the voice command "turn on" for a period of 2 seconds. The first preset time period may be set by a person skilled in the art according to actual requirements, for example, 5 sub-sound waves are sequentially inserted into a voice response with a time duration of 2 seconds, and the first preset time period may be set to 0.4 second, that is, 1 sub-sound wave is inserted every 0.4 second, so that 5 sub-sound waves are sequentially inserted into a voice response with a time duration of 2 seconds. Since the duration of each sub-sound wave is 0.1 millisecond, 0.1 millisecond is far shorter than the first preset duration of 0.4 second, the sub-sound waves are inserted for a very short period of time, natural people can not distinguish the sub-sound waves, and the intelligent device can easily identify the details. By means of the method 2, the verification information only recognized by the equipment is carried in the voice response.
It should be noted that, in the embodiment, the verification information is converted into the sound wave within the human ear recognition range as an example, but in practical application, the verification information may also be converted into the ultrasonic wave or the infrasonic wave, which is similar to the method of converting the verification information into the sound wave within the human ear recognition range, and is not described herein again. In this embodiment, the coded command is represented by binary, and in practical application, the coded command may be represented by a common counting method such as decimal, hexadecimal, and the like.
By the method, the verification information is converted into the sound wave information to be carried in the voice response, so that the second intelligent terminal can better detect whether the voice instruction is correctly identified based on the verification information in the voice response.
Compared with the prior art, the embodiment of the invention makes a voice response to the voice instruction after receiving the voice instruction which is sent by the user and used for indicating the operation of the second intelligent terminal, wherein the voice response carries the verification information only used for equipment identification, that is, the voice response made by the first intelligent terminal carries the verification information only used for equipment identification, and the verification information is equivalently carried in the voice response in a form of a secret code. Converting the verification information into sound waves according to a preset coding rule, and dividing the sound waves into L sub-sound waves; and inserting the sub-sound waves in the voice response in sequence every first preset time, and superposing the verification information to the voice response in such a way, so that the verification information can only be identified by the equipment, and then the second intelligent terminal effectively detects whether the identification of the voice instruction is correct according to the identified verification information, thereby correctly executing the operation indicated by the voice instruction. The prompt message used for indicating that the voice instruction is incorrectly identified by the second intelligent terminal is sent to the user, so that the user can conveniently send the instruction again in time, and the instruction operation required by the user can be better executed.
The third embodiment of the invention relates to a voice instruction checking method which is applied to a second intelligent terminal. The third embodiment is substantially the same as the first embodiment, and mainly differs therefrom in that: in a first embodiment, the method for verifying the voice command is applied to a first intelligent terminal, the first intelligent terminal makes a voice response to the voice command after receiving the voice command which is sent by a user and used for indicating the operation of a second intelligent terminal, the voice response carries verification information only used for equipment identification, and the verification information is used for the second intelligent terminal to detect whether the voice command is correctly identified according to the verification information. In this embodiment, the method for verifying the voice command is applied to the second intelligent terminal, and the second intelligent terminal recognizes the voice command after receiving the voice command sent by the user to instruct the second intelligent terminal to operate; after receiving a voice response made by the first intelligent terminal to the voice command, detecting whether the voice command is correctly identified according to verification information carried in the voice response and only used for equipment identification.
In this embodiment, a method for verifying a voice instruction is applied to a second intelligent terminal, and a specific flow is shown in fig. 2, where the method includes:
step 201: and receiving a voice instruction sent by the user and used for indicating the operation of the second intelligent terminal.
Specifically, the second intelligent terminal receives a voice instruction issued by a user for instructing an operation of the second intelligent terminal. The second intelligent terminal can be intelligent devices such as intelligent doors and windows, intelligent desk lamps and intelligent refrigerators. In this embodiment, the second intelligent terminal is an intelligent desk lamp, but the second intelligent terminal is not limited to this in practical application. For example, a mobile phone of a user receives a voice instruction sent by the user to instruct the intelligent desk lamp to turn on the lamp, that is, the intelligent desk lamp receives the voice instruction of turning on the lamp sent by the user.
Step 202: and performing semantic recognition on the voice command.
Specifically, the second intelligent terminal performs semantic recognition on the voice command. Since the semantic recognition performed on the voice command by the first intelligent terminal in step 202 is substantially the same as that performed on the voice command by the first intelligent terminal in step 102 in the first embodiment, in order to avoid repetition, the step of performing semantic recognition on the voice command is not described herein again.
Step 203: and receiving a voice response made by the first intelligent terminal to the voice command.
For example, the second intelligent terminal receives a voice response made by the first intelligent terminal to the voice command. In combination with the first embodiment, the first intelligent terminal takes a smart phone as an example, and the second intelligent terminal takes a smart desk lamp as an example, that is, the smart desk lamp receives a voice response made by the mobile phone to the voice command of turning on the lamp, and the voice response carries verification information only used for device identification.
Step 204: it is checked whether the recognition of the speech instruction is correct, if so, step 205 is performed, and if not, step 206 is performed.
Specifically, the second intelligent terminal detects whether the voice command is correctly recognized according to the verification information which is carried in the voice response and only used for equipment recognition. If the verification information is the coding instruction in step 103, the second intelligent terminal may generate a coding instruction for controlling the second intelligent terminal to execute the operation according to the operation of the second intelligent terminal indicated by the identified user after recognizing the voice instruction sent by the user. The second intelligent terminal compares the coding instruction generated by the second intelligent terminal with the coding instruction corresponding to the verification information carried in the voice reply of the identified first intelligent terminal, if the two coding instructions are the same, the identification of the voice instruction by the second intelligent terminal is considered to be correct, and the step 205 can be entered for executing the voice instruction. If the two coded commands are not the same, the recognition of the voice command by the second intelligent terminal is deemed to be incorrect, and the process proceeds to step 206.
It should be noted that, if the check code calculated according to the preset check algorithm is used in the check information of the first intelligent terminal, the second intelligent terminal also needs to calculate the check code by using the same check algorithm when detecting whether the identification of the voice instruction is correct.
Step 205: and executing the voice instruction.
For example, when the intelligent desk lamp detects that the voice command of turning on the lamp is correctly identified, the voice command is executed, that is, the operation of turning on the lamp is executed.
Step 206: and feeding back the checking error information to the first intelligent terminal.
For example, if the intelligent desk lamp incorrectly identifies the voice command of turning on the lamp, the intelligent desk lamp feeds back verification error information to the intelligent mobile phone of the user to prompt the mobile phone that the voice command is incorrectly identified by the intelligent desk lamp. The mobile phone of the user can prompt the user to send the voice command again, so that the command of the user can be executed in time.
Compared with the prior art, the embodiment of the invention identifies the voice command after receiving the voice command which is sent by the user and used for indicating the operation of the second intelligent terminal; after receiving a voice response made by the first intelligent terminal to the voice command, detecting whether the voice command is correctly identified according to verification information carried in the voice response and only used for equipment identification. Since the verification information is equivalently carried in the voice reply in the form of the password, only the equipment can identify, and the second intelligent terminal can effectively detect whether the identification of the voice command is correct or not according to the received verification information, so that the operation indicated by the voice command is correctly executed. When the voice instruction is detected to be incorrectly identified, the verification error information is fed back to the first intelligent terminal, so that the user can be reminded of re-sending the instruction in time, and the instruction operation required by the user can be better executed.
The steps of the above methods are divided for clarity, and the implementation may be combined into one step or split some steps, and the steps are divided into multiple steps, so long as the same logical relationship is included, which are all within the protection scope of the present patent; it is within the scope of the patent to add insignificant modifications to the algorithms or processes or to introduce insignificant design changes to the core design without changing the algorithms or processes.
A fourth embodiment of the present invention relates to an intelligent terminal, a schematic structural diagram of the intelligent terminal is shown in fig. 3, and the intelligent terminal includes: at least one processor 301; and a memory 302 communicatively coupled to the at least one processor 301; the memory 302 stores instructions executable by the at least one processor 301, and the instructions are executed by the at least one processor 301, so that the at least one processor 301 can execute the verification method of the voice instruction in the above method embodiment.
Where the memory 302 and the processor 301 are coupled in a bus, the bus may comprise any number of interconnected buses and bridges, the buses coupling one or more of the various circuits of the processor 301 and the memory 302. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor 301 is transmitted over a wireless medium through an antenna, which further receives the data and transmits the data to the processor 301.
The processor 301 is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And memory 302 may be used to store data used by processor 301 in performing operations.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (10)
1. A voice instruction checking method is applied to a first intelligent terminal and is characterized by comprising the following steps:
after a voice instruction which is sent by a user and used for indicating the operation of a second intelligent terminal is received, a voice response is made to the voice instruction, the voice response carries verification information only used for equipment identification, and the verification information is used for the second intelligent terminal to detect whether the voice instruction is correctly identified or not according to the verification information.
2. The method for verifying the voice command of claim 1, further comprising, before said making the voice response to the voice command:
performing semantic recognition on the voice instruction;
generating a coding instruction for controlling the second intelligent terminal to execute the operation according to the identified operation of the second intelligent terminal indicated by the user;
and taking the coding instruction as the check information.
3. The method for verifying the voice command of claim 1, further comprising, before said making the voice response to the voice command:
performing semantic recognition on the voice instruction;
generating a coding instruction for controlling the second intelligent terminal to execute the operation according to the identified operation of the second intelligent terminal indicated by the user;
calculating a check code of the coding instruction according to a preset check algorithm;
and taking the check code as the check information.
4. The method for verifying the voice command according to claim 3, wherein the verification algorithm specifically comprises any one of the following:
parity check, hamming check, cyclic redundancy check.
5. The method of claim 1, wherein the verification information is carried in the voice reply by:
converting the verification information into ultrasonic waves or infrasonic waves according to a preset coding rule;
and superposing the converted ultrasonic waves or infrasonic waves into the voice response.
6. The method of claim 1, wherein the verification information is carried in the voice reply by:
converting the verification information into sound waves according to a preset coding rule, and dividing the sound waves into L sub-sound waves;
inserting the sub-sound waves in the voice response in sequence every other first preset time length; and the duration of the sub-sound wave is less than 1/N of the first preset duration, and N is greater than a preset threshold.
7. The method for verifying the voice command according to claim 1, further comprising:
sending prompt information to a user when the verification error information fed back by the second intelligent terminal is received; the verification error information is used for indicating that the second intelligent terminal incorrectly identifies the voice instruction, and the prompt information is used for requiring the user to send an instruction again.
8. A voice instruction checking method is applied to a second intelligent terminal and is characterized by comprising the following steps:
after a voice instruction which is sent by a user and used for indicating the operation of the second intelligent terminal is received, recognizing the voice instruction;
after receiving a voice response made by the first intelligent terminal to the voice command, detecting whether the voice command is correctly recognized or not according to the verification information which is carried in the voice response and is only used for equipment recognition.
9. The method for verifying the voice command according to claim 8, wherein after detecting whether the recognition of the voice command is correct, the method further comprises:
executing the voice instruction if the voice instruction is correctly identified;
and if the voice instruction is incorrectly recognized, feeding back verification error information to the first intelligent terminal, wherein the verification error information is used for indicating that the voice instruction is incorrectly recognized by the second intelligent terminal.
10. An intelligent terminal, comprising:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of verifying a voice instruction according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710909063.2A CN107705788A (en) | 2017-09-29 | 2017-09-29 | The method of calibration and intelligent terminal of a kind of phonetic order |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710909063.2A CN107705788A (en) | 2017-09-29 | 2017-09-29 | The method of calibration and intelligent terminal of a kind of phonetic order |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107705788A true CN107705788A (en) | 2018-02-16 |
Family
ID=61175798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710909063.2A Pending CN107705788A (en) | 2017-09-29 | 2017-09-29 | The method of calibration and intelligent terminal of a kind of phonetic order |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107705788A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448734A (en) * | 2018-09-20 | 2019-03-08 | 李庆湧 | Unlocking terminal equipment and application starting method and device based on vocal print |
| CN109760055A (en) * | 2019-01-30 | 2019-05-17 | 盈科视控(北京)科技有限公司 | A kind of method and system that the figure for robot communicates |
| CN109877829A (en) * | 2019-01-30 | 2019-06-14 | 盈科视控(北京)科技有限公司 | A kind of figure communication dispatch method and system for robot |
| CN111312230A (en) * | 2019-11-27 | 2020-06-19 | 南京创维信息技术研究院有限公司 | Voice interaction monitoring method and device for voice dialogue platform |
| CN112116803A (en) * | 2020-09-04 | 2020-12-22 | 北京小米移动软件有限公司 | Information processing method and device, electronic device and storage medium |
| CN112349279A (en) * | 2020-06-16 | 2021-02-09 | 深圳Tcl新技术有限公司 | Remote semantic recognition method, device, equipment and computer readable storage medium |
| CN112634899A (en) * | 2021-01-31 | 2021-04-09 | 成都市玄上科技有限公司 | Method for interactive control by using sound signal |
| CN113611305A (en) * | 2021-09-06 | 2021-11-05 | 云知声（上海）智能科技有限公司 | Voice control method, system, equipment and medium in autonomous learning home scene |
| CN114121002A (en) * | 2021-11-15 | 2022-03-01 | 歌尔微电子股份有限公司 | Electronic device, interactive module and control method and control device thereof |
| CN114743542A (en) * | 2022-04-29 | 2022-07-12 | 青岛海尔科技有限公司 | Voice processing method and device, storage medium and electronic device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102820972A (en) * | 2012-08-17 | 2012-12-12 | 刘欣 | Authentication method based on sound wave |
| CN103152106A (en) * | 2013-03-13 | 2013-06-12 | 荆效民 | Ultrasonic information pushing method and system based on audio |
| CN103941686A (en) * | 2014-04-14 | 2014-07-23 | 美的集团股份有限公司 | Voice control method and system |
| CN104200806A (en) * | 2014-09-05 | 2014-12-10 | 马金保 | Intelligent household linkage control method and system |
| CN106572241A (en) * | 2016-10-21 | 2017-04-19 | 北京巡声巡影科技服务有限公司 | Method and device for displaying information |
| EP3160151A1 (en) * | 2014-06-17 | 2017-04-26 | LG Electronics Inc. | Video display device and operation method therefor |
| CN106788779A (en) * | 2016-11-09 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | Beacon frame information method, wireless aps and terminal in wireless aps |
| CN106782523A (en) * | 2016-11-16 | 2017-05-31 | 上海卓易云汇智能技术有限公司 | The control method and device of phonetic function |
-
2017
- 2017-09-29 CN CN201710909063.2A patent/CN107705788A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102820972A (en) * | 2012-08-17 | 2012-12-12 | 刘欣 | Authentication method based on sound wave |
| CN103152106A (en) * | 2013-03-13 | 2013-06-12 | 荆效民 | Ultrasonic information pushing method and system based on audio |
| CN103941686A (en) * | 2014-04-14 | 2014-07-23 | 美的集团股份有限公司 | Voice control method and system |
| EP3160151A1 (en) * | 2014-06-17 | 2017-04-26 | LG Electronics Inc. | Video display device and operation method therefor |
| CN104200806A (en) * | 2014-09-05 | 2014-12-10 | 马金保 | Intelligent household linkage control method and system |
| CN106572241A (en) * | 2016-10-21 | 2017-04-19 | 北京巡声巡影科技服务有限公司 | Method and device for displaying information |
| CN106788779A (en) * | 2016-11-09 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | Beacon frame information method, wireless aps and terminal in wireless aps |
| CN106782523A (en) * | 2016-11-16 | 2017-05-31 | 上海卓易云汇智能技术有限公司 | The control method and device of phonetic function |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448734A (en) * | 2018-09-20 | 2019-03-08 | 李庆湧 | Unlocking terminal equipment and application starting method and device based on vocal print |
| CN109760055A (en) * | 2019-01-30 | 2019-05-17 | 盈科视控(北京)科技有限公司 | A kind of method and system that the figure for robot communicates |
| CN109877829A (en) * | 2019-01-30 | 2019-06-14 | 盈科视控(北京)科技有限公司 | A kind of figure communication dispatch method and system for robot |
| CN111312230A (en) * | 2019-11-27 | 2020-06-19 | 南京创维信息技术研究院有限公司 | Voice interaction monitoring method and device for voice dialogue platform |
| CN111312230B (en) * | 2019-11-27 | 2023-10-20 | 南京创维信息技术研究院有限公司 | Voice interaction monitoring method and device for voice conversation platform |
| CN112349279A (en) * | 2020-06-16 | 2021-02-09 | 深圳Tcl新技术有限公司 | Remote semantic recognition method, device, equipment and computer readable storage medium |
| CN112349279B (en) * | 2020-06-16 | 2024-08-20 | 深圳Tcl新技术有限公司 | Remote semantic recognition method, device, equipment and computer readable storage medium |
| CN112116803A (en) * | 2020-09-04 | 2020-12-22 | 北京小米移动软件有限公司 | Information processing method and device, electronic device and storage medium |
| CN112634899A (en) * | 2021-01-31 | 2021-04-09 | 成都市玄上科技有限公司 | Method for interactive control by using sound signal |
| CN113611305A (en) * | 2021-09-06 | 2021-11-05 | 云知声（上海）智能科技有限公司 | Voice control method, system, equipment and medium in autonomous learning home scene |
| CN114121002A (en) * | 2021-11-15 | 2022-03-01 | 歌尔微电子股份有限公司 | Electronic device, interactive module and control method and control device thereof |
| CN114743542A (en) * | 2022-04-29 | 2022-07-12 | 青岛海尔科技有限公司 | Voice processing method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107705788A (en) | The method of calibration and intelligent terminal of a kind of phonetic order | |
| JP6828001B2 (en) | Voice wakeup method and equipment | |
| US20190385594A1 (en) | Method and apparatus for selecting voice-enabled device and intelligent computing device for controlling the same | |
| CN112100349A (en) | Multi-turn dialogue method and device, electronic equipment and storage medium | |
| CN111737987B (en) | Intention recognition method, device, equipment and storage medium | |
| CN109256125B (en) | Off-line voice recognition method and device and storage medium | |
| WO2014096506A1 (en) | Method, apparatus, and computer program product for personalizing speech recognition | |
| CN110942763B (en) | Speech recognition method and device | |
| CN113674746B (en) | Man-machine interaction method, device, equipment and storage medium | |
| CN103578468A (en) | Method for adjusting confidence coefficient threshold of voice recognition and electronic device | |
| WO2020233363A1 (en) | Speech recognition method and device, electronic apparatus, and storage medium | |
| CN115587598A (en) | Multi-turn dialogue rewriting method, equipment and medium | |
| CN112687298A (en) | Voice wake-up optimization method, device, system, storage medium and electronic equipment | |
| CN101266791A (en) | Method for cooperatively recognizing voice command and related system thereof | |
| US11475069B2 (en) | Corpus processing method, apparatus and storage medium | |
| US20230316952A1 (en) | System and method for bidirectional automatic sign language translation and production | |
| US20230140997A1 (en) | Method and Apparatus for Selecting Sample Corpus Used to Optimize Translation Model | |
| CN107767866A (en) | Information transferring method and smart machine between smart machine | |
| US20220122593A1 (en) | User-friendly virtual voice assistant | |
| CN113992468A (en) | Smart home voice control method | |
| CN106254186A (en) | A kind of interactive voice control system for identifying | |
| US11646021B2 (en) | Apparatus for voice-age adjusting an input voice signal according to a desired age | |
| CN113516977B (en) | Keyword recognition method and system | |
| WO2024255262A1 (en) | Voice wake-up method and device supporting wake-up word customization | |
| CN106297783A (en) | A kind of interactive voice identification intelligent terminal |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180216 |