Classifications

• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L15/00—Speech recognition
  • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L15/00—Speech recognition
  • G10L15/28—Constructional details of speech recognition systems
  • G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L15/00—Speech recognition
  • G10L15/28—Constructional details of speech recognition systems
  • G10L15/34—Adaptation of a single recogniser for parallel processing, e.g. by use of multiple processors or cloud computing
• • 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
  • G10L13/00—Speech synthesis; Text to speech 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
  • G10L15/00—Speech recognition
  • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
  • G10L2015/223—Execution procedure of a spoken command
• • G—PHYSICS
  • G10—MUSICAL INSTRUMENTS; ACOUSTICS
  • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
  • G10L15/00—Speech recognition
  • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
  • G10L2015/225—Feedback of the input speech

Definitions

• the present invention relates to the field of household appliances, and specifically to voice control of a household appliance.
• a voice controlled household appliance in the market generally uses several methods: one is connecting the household appliance to a mobile phone by using WIFI, and performing voice control on the household appliance by using a mobile APP, which is complex in operation; and one is adding a voice identification module and a voice database on the household appliance, and also combining online identification, but costs are relatively high.
• the present invention provides a more convenient household appliance with low costs and a method and a system for voice controlling the household appliance, where the household appliance may be a refrigerator, a washing machine, an oven, or the like.
• a method for voice controlling a household appliance includes a control device and a voice device, a wireless communication module in a wireless communication connection to a cloud server is disposed on the control device, and the voice device includes a voice collecting module and a voice output module.
• the method includes the following steps: collecting, by using the voice collecting module, a voice signal input by a user; sending the voice signal to the cloud server by using the wireless communication module for identification; receiving, by using the wireless communication module, a control instruction and instruction confirmation information that match the voice signal and that are fed back by the cloud server; outputting the instruction confirmation information in a voice signal manner by using the voice output module, and asking for feedback information of the user; and instructing, according to the feedback information, the control device whether to execute the control instruction.
• the foregoing household appliance is not provided with a voice identification module with relatively high costs, but directly identifies user voice online by using the cloud server, obtains the control instruction and the instruction confirmation information according to user semantics, and notifies the user of the instruction confirmation information in a voice manner, and only after the user confirms the instruction confirmation information and gives a feedback, the control device executes the control instruction. It is avoided that a control instruction not conforming to the user's real meaning is generated due to user's pronunciation or grammatical mistake, and this is more accurate.
• the control device executes the control instruction; or when the feedback information does not conform to user semantics, the control device does not execute the control instruction.
• the control device controls the voice output module to instruct the user in a voice signal manner to re-input a voice signal.
• the feedback information is a key signal generated by the user by triggering different feedback keys
• the control device determines, according to different key signals, whether the feedback information conforms to the user semantics. If the user performs a near-distance operation, whether the feedback information conforms to the user semantics may be directly confirmed by using a key, and the program design is more simple and direct.
• the key may be a physical key or a virtual key on a touchscreen.
• the feedback information is a voice feedback signal of the user
• the method includes: collecting the voice feedback signal by using the voice collecting module; sending the voice feedback signal to the cloud server by using the wireless communication module for identification and determining; receiving, by using the wireless communication module, a determining result fed back by the cloud server; and choosing, by the control device according to the determining result, to execute the control instruction or control the voice output module to inform the user in a voice signal manner to re-input a voice signal.
• a household appliance is provided.
• the household appliance is voice controlled by using the foregoing method.
• the present invention further provides a system for voice controlling a household appliance, including at least one household appliance and a cloud server.
• the household appliance is provided with a voice device and a control device, including: a voice collecting module disposed on the voice device, configured to collect a voice signal input by a user; a wireless communication module disposed on the control device, in a wireless communication connection to the cloud server, and configured to: send the voice signal to the cloud server for identification, and receive a control instruction and instruction confirmation information that match the voice signal and that are fed back by the cloud server; and a voice output module disposed on the voice device, configured to output the instruction confirmation information in a voice signal manner to ask for feedback information of the user, where the control device is instructed, according to the feedback information, whether to execute the control instruction.
• the control device executes the control instruction; or when the feedback information does not conform to user semantics, the control device does not execute the control instruction.
• the control device controls the voice output module to instruct the user in a voice signal manner to re-input a voice signal.
• the household appliance is provided with a feedback key
• the feedback information is a key signal generated by the user by triggering different feedback keys
• the control device determines, according to different key signals, whether the feedback information conforms to the user semantics. If the user performs a near- distance operation, whether the feedback information conforms to the user semantics may be directly confirmed by using a key, and the program design is more simple and direct.
• the feedback information is a voice feedback signal of the user;
• the voice collecting module collects the voice feedback signal and sends the voice feedback signal to the cloud server by using the wireless communication module for identification, and the cloud server identifies and determines whether the feedback information conforms to the user semantics, and notifies the control device of a determining result; and the control device executes the control instruction according to the determining result or controls the voice output module to instruct the user in a voice signal manner to re-input a voice signal.
• FIG. 1 is a schematic diagram of a system for voice controlling a household appliance
• FIG. 2 is a structural diagram of a system for voice controlling a household appliance
• FIG. 3 is a flowchart of a method for voice controlling a household appliance
• FIG. 4 is a preferred flowchart of a method for voice controlling a household appliance.
• An embodiment of the present invention provides a system for voice controlling a household appliance, including at least one household appliance 1 and a cloud server 100.
• the household appliance 1 is provided with a voice device 2 and a control device 3.
• FIG. 1 is a schematic diagram of the system for controlling a household appliance by using voice.
• the system further includes: a voice collecting module 21 disposed on the voice device 2, configured to collect a voice signal input by a user; a wireless communication module 31 disposed on the control device 3, in a wireless communication connection to the cloud server 100, configured to: send the voice signal to the cloud server 100 for identification, and receive a control instruction and instruction confirmation information that match the voice signal and fed back by the cloud server 100; and a voice output module 22 disposed on the voice device 2, configured to output the instruction confirmation information in a voice signal manner to ask for feedback information of the user, where the control device 3 is instructed, according to the feedback information, whether to execute the control instruction.
• a voice collecting module 21 disposed on the voice device 2, configured to collect a voice signal input by a user
• a wireless communication module 31 disposed on the control device 3, in a wireless communication connection to the cloud server 100, configured to: send the voice signal to the cloud server 100 for identification, and receive a control instruction and instruction confirmation information that match the voice signal and fed back by the cloud server 100
• a voice output module 22 disposed
• the household appliance 1 is a washing machine, and when the user needs to perform a special washing operation, for example, gives voice "Dehydrate only for ten minutes", the voice collecting module 21 collects the voice signal, and transmits the voice signal to the cloud server 100 by using the wireless communication module 31 disposed on the control device 3.
• the voice collecting module 21 includes a conversion component that converts an acoustic signal into an electrical signal, for example, a microphone.
• the voice collecting module 21 may further include a voice processing unit, configured to perform digital processing and noise reduction on the voice signal, to facilitate transmission performed by the wireless communication module 31.
• the wireless communication module 31 may be directly or indirectly connected to the cloud server, and specifically includes, but is not limited to, wireless transmission manners such as WIFI, Bluetooth, and Zigbee, for data or instruction transmission.
• wireless transmission manners such as WIFI, Bluetooth, and Zigbee
• the cloud server 100 After receiving the voice signal, the cloud server 100 identifies the voice signal, matches the identified voice signal "Dehydrate only for ten minutes" with a control instruction stored in the cloud, or recalculates a corresponding control instruction, and then sends the control instruction and instruction confirmation information to the wireless communication module 31.
• the instruction confirmation information is output in a voice signal manner by using the voice output module 32 to ask for feedback information of the user.
• control device 3 executes the control instruction; or when the feedback information does not conform to user semantics, the control device 3 does not execute the control instruction.
• control device 3 controls the voice output module 32 to instruct the user in a voice signal manner to re- input a voice signal.
• An existing household appliance includes a voice identification module, and needs a smart voice neural network processing chip and a local storage unit.
• the local storage unit needs storage space to store a lot of command words and corresponding control instructions, but still cannot completely meet diversified semantic requirements of users.
• the washing machine in this embodiment is not provided with a voice identification module with relatively high costs, but directly identifies user voice online by using the cloud server 100, obtains the control instruction and the instruction confirmation information according to the user semantics, and notifies the user of the instruction confirmation information in a voice manner.
• a voice identification module and a storage unit do not need to be mounted in the household appliance, thereby reducing costs.
• control device 3 determines whether to execute the control instruction. Therefore, it can be ensured that a user requirement is accurately expressed, and no misoperation is generated, and this is more secure and reliable.
• the washing machine 1 may be provided with a feedback key 4, the feedback information is a key signal generated by the user by triggering different feedback keys 4, and the control device 3 determines, according to different key signals, whether the feedback information conforms to the user semantics.
• the user may still give a feedback by using voice.
• the feedback information is a voice feedback signal of the user
• the voice collecting module 21 collects the voice feedback signal and sends the voice feedback signal to the cloud server 100 by using the wireless communication module 31 for identification
• the cloud server 100 identifies and determines whether the feedback information conforms to the user semantics, and notifies the control device 3 of a determining result
• the control device 3 executes the control instruction according to the determining result or controls the voice output module to instruct the user in a voice signal manner to re-input a voice signal.
• the cloud server 100 instructs the control device 3 by using the wireless communication module 31 to execute the control instruction.
• the cloud server 100 instructs the control device 3 by using the wireless communication module 31 not to execute the control instruction.
• the cloud server 100 instructs the control device 3 by using the wireless communication module 31 to control the voice output module 32 to instruct the user in a voice signal manner to re-input a voice signal.
• FIG. 3 is a flowchart of the method for voice controlling a household appliance.
• the control method is applied to a washing machine end, and corresponds to the foregoing system for voice controlling a household appliance.
• a washing machine is in a communication connection to a cloud server, the washing machine includes a control device 3 and a voice device 2, a wireless communication module 31 in a wireless communication connection to the cloud server 100 is disposed on the control device 3, and the voice device 2 includes a voice collecting module 21 and a voice output module 22.
• the method includes the following steps:
• Step S102 Collect, by using the voice collecting module 21 , a voice signal input by a user.
• Step S104 Send the voice signal to the cloud server 100 by using the wireless communication module 31 for identification.
• Step S106 Receive, by using the wireless communication module 31 , a control instruction and instruction confirmation information that match the voice signal and that are fed back by the cloud server 100.
• Step S108 Output the instruction confirmation information in a voice signal manner by using the voice output module 22, and ask for feedback information of the user.
• Step S110 Instruct, according to the feedback information, the control device 3 whether to execute the control instruction.
• control device 3 executes the control instruction; or when the feedback information does not conform to user semantics, the control device 3 does not execute the control instruction.
• control device 3 controls the voice output module 32 to instruct the user in a voice signal manner to re- input a voice signal.
• the washing machine 1 may be provided with a feedback key 4, the feedback information is a key signal generated by the user by triggering different feedback keys 4, and the control device 3 determines, according to different key signals, whether the feedback information conforms to the user semantics. If the feedback information conforms to the user semantics, it is directly confirmed by using the key, so that the program design is more simple and direct.
• FIG. 4 is a preferred flowchart of a method for voice controlling a household appliance. As shown in FIG. 4, following the foregoing steps, the method further includes:
• Step S1 Collect the voice feedback signal by using the voice collecting module 21.
• Step S114 Send the voice feedback signal to the cloud server 100 by using the wireless communication module 31 for identification and determining.
• Step S116 Receive, by using the wireless communication module 31, a determining result fed back by the cloud server 100.
• Step S118. choose, by the control device 3 according to the determining result, to execute the control instruction or control the voice output module 32 to instruct the user in a voice signal manner to re-input a voice signal.
• the cloud server 100 instructs the control device 3 by using the wireless communication module 31 to execute the control instruction.
• the cloud server 100 instructs the control device 3 by using the wireless communication module 31 not to execute the control instruction.
• the cloud server 100 instructs the control device 3 by using the wireless communication module 31 to control the voice output module 32 to instruct the user in a voice signal manner to re-input a voice signal.

Landscapes

• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Acoustics & Sound (AREA)
• Audiology, Speech & Language Pathology (AREA)
• Human Computer Interaction (AREA)
• Health & Medical Sciences (AREA)
• Computational Linguistics (AREA)
• Multimedia (AREA)
• Computing Systems (AREA)
• Mathematical Physics (AREA)
• Theoretical Computer Science (AREA)
• Telephonic Communication Services (AREA)
• Control Of Washing Machine And Dryer (AREA)
• Selective Calling Equipment (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=65019544

Family Applications (1)

Country Status (3)

Families Citing this family (5)

Family Cites Families (14)

• 2018
  • 2018-01-26 CN CN201810075595.5A patent/CN110085219A/zh active Pending
  • 2018-12-07 WO PCT/IB2018/059760 patent/WO2019145769A1/en unknown
  • 2018-12-07 EP EP18833709.1A patent/EP3743914A1/de active Pending

Also Published As

Similar Documents

Legal Events