WO2017206725A1 - 一种智能冰箱、服务器及语言控制系统和方法 - Google Patents

一种智能冰箱、服务器及语言控制系统和方法 Download PDF

Info

Publication number
WO2017206725A1
WO2017206725A1 PCT/CN2017/084959 CN2017084959W WO2017206725A1 WO 2017206725 A1 WO2017206725 A1 WO 2017206725A1 CN 2017084959 W CN2017084959 W CN 2017084959W WO 2017206725 A1 WO2017206725 A1 WO 2017206725A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice signal
password
module
smart refrigerator
voice
Prior art date
Application number
PCT/CN2017/084959
Other languages
English (en)
French (fr)
Inventor
杨世清
王岩
陈海雷
Original Assignee
合肥华凌股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 合肥华凌股份有限公司 filed Critical 合肥华凌股份有限公司
Publication of WO2017206725A1 publication Critical patent/WO2017206725A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/28—Constructional details of speech recognition systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/2803—Home automation networks
    • H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM]
    • G05B19/4185—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS], computer integrated manufacturing [CIM] characterised by the network communication
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
    • H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
    • F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
    • F25D2500/00—Problems to be solved
    • F25D2500/06—Stock management
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/26—Pc applications
    • G05B2219/2642—Domotique, domestic, home control, automation, smart house
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command

Definitions

  • the present invention relates to the field of smart refrigerators, and in particular, to a smart refrigerator, a server, and a language control system and method.
  • refrigerators not only have the function of preserving food, but also become part of the home network, which can provide more intelligent services for family members.
  • the control method of the traditional refrigerator can not meet the needs of human-computer interaction of the smart refrigerator, and the voice control technology has not been widely used in the home appliance industry because of poor real-time performance, low recognition rate and low reliability.
  • the technical problem to be solved by the present invention is to provide a smart refrigerator, server and language control system and method for the deficiencies of the prior art.
  • a smart refrigerator includes: a main control module and a voice module, wherein the voice module is configured to collect a voice signal, and transmit the voice signal to the main control module
  • the master control module is configured to determine, according to the voice signal transmitted by the voice module and the pre-stored password set, whether to control the smart refrigerator to perform an operation corresponding to the voice signal.
  • the beneficial effects of the present invention are: determining, by the main control module, whether the smart refrigerator is controlled to perform the operation corresponding to the voice signal according to the voice signal transmitted by the voice module and the pre-stored password set, thereby realizing offline recognition of the voice signal and improving voice signal recognition.
  • the present invention can also be improved as follows.
  • the main control module is specifically configured to: match the voice signal and the password in the password set to obtain a matching result; and determine, according to the matching result, whether to control the smart refrigerator to perform the corresponding voice signal operating.
  • the main control module is further configured to send the voice signal and the matching result to a server connected thereto, so that the server updates the password set according to the voice signal and the matching result.
  • main control module is further configured to receive the updated password set sent by the server, and replace the pre-stored password set according to the updated password set.
  • the beneficial effect of adopting the above further solution is that the ability of the main control module to recognize the password in the password set can be continuously improved.
  • the password set includes a plurality of password subsets, each of the password subsets being composed of passwords having different voices but the same semantics.
  • a server comprising: a receiving module, configured to receive a voice signal sent by a main control module of the smart refrigerator, and a matching result corresponding to the voice signal; and an update module, And a sending module, configured to send, according to the voice signal received by the receiving module, the pre-stored password set, the sending module, configured to send, to the smart refrigerator, the updated password set of the update module.
  • the beneficial effects of the present invention are: receiving the voice signal sent by the main control module of the smart refrigerator, and the matching result corresponding to the voice signal, and updating the pre-stored password set according to the voice signal and the matching result.
  • the online update of the password set can be implemented, and the ability of the main control module to recognize the password in the password set is improved.
  • the present invention can also be improved as follows.
  • the server further includes: an identification module, configured to perform automatic voice recognition on the voice signal, and obtain a recognition result; the sending module is further configured to send the result recognized by the identification module to the smart refrigerator .
  • a voice control system comprising: a communication module, the smart refrigerator in the above embodiment, and the server in the above embodiment, wherein the smart refrigerator and the smart refrigerator The server is connected by the communication module.
  • the invention has the beneficial effects that the voice signal transmitted by the voice module and the password in the password set are matched by the main control module of the smart refrigerator to obtain a matching result, and the voice signal and the matching result are sent to the server through the communication module, and the server
  • the voice signal and the matching result update the pre-stored password set, and send the updated password set to the smart refrigerator, and the smart refrigerator receives and replaces the previously pre-stored password set according to the updated password set, so that the password set is updated online. And continuously improve the ability of the main control module to recognize the password in the password set.
  • a voice control method comprising: the following steps: Step 1. Acquire a voice signal; Step 2. Determine according to the voice signal and a pre-stored password set. Whether to control the smart refrigerator to perform an operation corresponding to the voice signal.
  • the invention has the beneficial effects that: determining whether to control the smart refrigerator to perform the operation corresponding to the voice signal according to the collected voice signal and the pre-stored password set, the offline recognition of the voice signal can be realized, the accuracy of the voice signal recognition is improved, and the solution is solved.
  • FIG. 1 is a schematic structural block diagram of a smart refrigerator according to an embodiment of the present invention.
  • FIG. 2 is a schematic structural block diagram of a server according to an embodiment of the present invention.
  • FIG. 3 is a schematic structural block diagram of a voice control system according to an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of a voice control method according to an embodiment of the present invention.
  • FIG. 5 is a schematic flowchart of a voice control method according to another embodiment of the present invention.
  • FIG. 1 is a schematic structural block diagram of a smart refrigerator 100 according to an embodiment of the present invention.
  • the smart refrigerator 100 shown in FIG. 1 includes a main control module 110 and a voice module 120.
  • the voice module 120 is configured to collect voice signals, and transmit the collected voice signals to the main control module 110;
  • the main control module 110 is configured to determine whether to control the smart refrigerator 100 to perform an operation corresponding to the voice signal according to the voice signal transmitted by the voice module 120 and the pre-stored password set.
  • the voice module 120 can employ a microphone array.
  • the voice module 120 has the functions of collecting voice signals and pre-processing the voice signals, and the voice module 120 performs pre-processing on the voice signals, including but not limited to noise reduction processing, echo cancellation processing, reduced reverberation processing, and sound source localization processing. Separation from blind sources.
  • the set of passwords pre-stored in the master module 110 comes from a server connected to the smart refrigerator.
  • the password set includes a plurality of password sub-sets, each of which consists of a different voice but the same semantic password. For example: “open the door” and “please open the door” are two passwords with different voices but the same semantics, they belong to a subset of passwords, and “mediation temperature” and “please adjust temperature” are passwords with different voices but the same semantics, belonging to another A collection of passwords.
  • the intelligent refrigerator provided by the foregoing embodiment determines, by the main control module, whether to control the smart refrigerator to perform the operation corresponding to the voice signal according to the voice signal transmitted by the voice module and the pre-stored password set.
  • the offline recognition of the speech signal can be realized, the accuracy of the speech signal recognition can be improved, and the real-time problem of the speech signal recognition can be solved.
  • the main control module 110 is specifically configured to: match the voice signal transmitted by the voice module 120 and the password in the password set to obtain a matching result, and determine whether to control the smart refrigerator according to the matching result. 100 performs an operation corresponding to the voice signal.
  • the voice signal is an "open door” password.
  • the smart refrigerator 100 is controlled to open the refrigerator door. Otherwise, the smart refrigerator does not perform the operation of opening the refrigerator door.
  • the voice signal transmitted by the voice module and the password in the password set are matched by the main control module to obtain a matching result, and according to the matching result, it is determined whether to control the smart refrigerator to perform the corresponding voice signal.
  • the operation can realize off-line recognition of the voice signal, improve the accuracy of the voice signal recognition, and solve the real-time problem of the voice signal recognition.
  • the main control module 110 is further configured to send a voice signal and a matching result to a server connected thereto, so that the server updates the password set according to the voice signal and the matching result.
  • the password corresponding to the voice signal is “open door”, and when the “open door” password matches the password in the password set, the smart refrigerator 100 is controlled to open the refrigerator door.
  • the voice signal and the matching matching result are sent to the server, and the server receives the voice signal and the matching matching result, and updates the password set. That is: the "open door” password in the original password set is updated.
  • the smart refrigerator does not perform the operation of opening the refrigerator door.
  • the voice signal and the matching result of the mismatch are sent to the server, and the server receives the voice signal and the matching result that does not match, and updates the password set. That is, the "open door” password is added to the existing password sub-collection, which contains the same but the same semantics as the "open door” password voice. make.
  • a password sub-collection can be added according to the "open door” password.
  • the main control module 110 is further configured to receive an updated password set sent by the server, and replace the previously pre-stored password set according to the updated password set.
  • the voice signal transmitted by the voice module and the password in the password set are matched by the main control module to obtain a matching result, and the voice signal and the matching result are sent to the server connected thereto, and received.
  • the updated password set sent by the server replaces the previously pre-stored password set according to the updated password set, thereby realizing online update of the password set, and continuously improving the ability of the main control module to recognize the password in the password set.
  • the main control module 110 after power-on, the main control module 110 is in a sleep state, and the voice module 120 is in an active state.
  • the main control module 110 is further configured to match the voice signal and the wake-up password in the password set, and determine whether to enter the scanning state according to the matching result.
  • the main control module 110 if they match, it is determined that the main control module 110 enters a scanning state; otherwise, the main control module 110 continues to be in a dormant state.
  • the main control module 110 is further configured to provide confirmation voice information to the user, and determine whether to enter according to whether the feedback voice signal of the user collected by the voice module can be received within the first preset time period. Activation status.
  • the main control module 110 if the feedback voice signal is received within the first preset time period, it is determined that the main control module 110 enters an active state; otherwise, the main control module 110 continues to be in a sleep state.
  • the main control module 110 After the main control module 110 enters the active state, the main control module 110 is further configured to detect whether the voice signal collected by the voice module 120 can be received in the second preset time period; if the voice signal is received in the second preset time period, Then, according to the voice signal and the password set, it is determined whether the smart refrigerator is controlled to perform an operation corresponding to the voice signal; otherwise, the main control module 110 continues to be in a sleep state.
  • the main control module 110 is in a sleep state.
  • the voice module 120 is in an active state.
  • the voice signal is transmitted to the main control module 110, and the main control module 110 matches the password corresponding to the voice signal, such as “I love my home”, with the wake-up password in the password set. If the matches, the main control module 110 enters the scanning state; otherwise, it continues to be in the sleep state.
  • the main control module 110 After the main control module 110 enters the scanning state, the user is provided with confirmation voice information, such as: "Hello", if a feedback voice signal is received within the first preset time period, such as: “Hello, hello”, then it is determined to enter Active state; otherwise, continue to sleep.
  • confirmation voice information such as: "Hello”
  • a feedback voice signal is received within the first preset time period, such as: “Hello, hello”
  • the main control module 110 After the main control module 110 enters the active state, it is detected whether the voice signal collected by the voice module 120 can be received in the second preset time period. If the voice signal is received within the second preset time period, the password corresponding to the voice signal, such as “adjust temperature”, is matched with the password in the password set, and if matched, the smart refrigerator is controlled to perform “adjust temperature”. Operation; otherwise, continue to sleep.
  • the voice signal collected by the voice module 120 If the voice signal is received within the second preset time period, the password corresponding to the voice signal, such as “adjust temperature”, is matched with the password in the password set, and if matched, the smart refrigerator is controlled to perform “adjust temperature”. Operation; otherwise, continue to sleep.
  • the main control module wakes up and works only when the preset condition is met, and can achieve low power consumption and achieve power saving effect.
  • the wake-up password by setting the wake-up password, the false wake-up can be eliminated, and the voice recognition performance can be effectively improved.
  • a smart refrigerator according to an embodiment of the present invention is described in detail above with reference to FIG. 1, and a server according to an embodiment of the present invention is described in detail below with reference to FIG.
  • FIG. 2 is a schematic structural block diagram of a server 200 according to an embodiment of the present invention.
  • the server 200 shown in FIG. 2 includes a receiving module 210, an updating module 220, and a receiving module 230. among them,
  • the receiving module 210 is configured to receive a voice signal sent by a main control module of the smart refrigerator, and a matching result corresponding to the voice signal.
  • the update module 220 is configured to update the pre-stored password set according to the voice signal received by the receiving module 210 and the matching result.
  • the sending module 230 is configured to send the updated password set of the update module 220 to the smart refrigerator.
  • a server provided in the foregoing embodiment by receiving a language sent by a main control module of the smart refrigerator The sound signal, and the matching result corresponding to the voice signal, and updating the pre-stored password set according to the voice signal and the matching result, can realize the online update of the password set, and improve the ability of the main control module to recognize the password in the password set.
  • the update module 220 may update the language signal received by the receiving module 210 when the preset condition is met.
  • the preset condition is that the number of language signals received by the receiving module 210 reaches default value.
  • the server 200 further includes an identification module 240.
  • the identification module 240 is configured to perform automatic speech recognition on the speech signal and obtain a recognition result.
  • the sending module 230 is further configured to send the result identified by the identification module 240 to the smart refrigerator.
  • the identification module 240 may convert the voice signal into a corresponding semantic text, and then match the semantic text with the pre-stored password set to obtain a matching result, that is, the recognized result.
  • a server provided in the above embodiment performs automatic speech recognition on a voice signal through an identification module, and obtains a recognition result.
  • the sending module sends the recognized result to the smart refrigerator, and online recognition of the language signal can be realized.
  • FIG. 3 is a schematic structural block diagram of a voice control system 300 according to an embodiment of the present invention.
  • the voice control system shown in FIG. 3 includes a smart refrigerator 310, a server 320, and a communication module 330.
  • the smart refrigerator 310 adopts the smart refrigerator 100 shown in FIG. 1 described above, and can realize all functions of the smart refrigerator 100.
  • the server 320 is the server 200 shown in FIG. 2 described above, and can implement all the functions of the server 200.
  • the voice module 311 included in the smart refrigerator 310 can collect the language signal and transmit the voice signal to the main control module 312.
  • the main control module 312 can and pre-stored passwords The set performs matching, and it is determined according to the matching result whether to control the smart refrigerator 310 to perform an operation corresponding to the voice signal.
  • the smart refrigerator 310 is controlled to perform an operation corresponding to the voice signal; otherwise, the smart refrigerator does not perform the operation.
  • the main control module 312 also transmits the voice signal and the matching result to the receiving module 321 included in the server 320 through the communication module 330.
  • the receiving module 321 receives the language signal and the matching result sent by the main control module 312 through the communication module 330.
  • the update module 322 updates the pre-stored password set according to the voice signal and the matching result received by the receiving module 321.
  • the sending module 323 sends the updated password set to the main control module 312 via the communication module 330.
  • the password corresponding to the voice signal is “Please open the door”, and when the “Please open the door” password matches the password in the password set, the smart refrigerator 310 is controlled to open the refrigerator door.
  • the voice signal and the matching matching result are sent to the server 320 through the communication module 330.
  • the server 320 receives the voice signal and the matching matching result, and updates the "please open the door” password in the password set.
  • the smart refrigerator 310 does not perform the operation of opening the refrigerator door.
  • the voice signal is sent to the server 320 and the matching result is not matched.
  • the server receives the voice signal and the matching result of the mismatch, and determines to update the password set, that is, the password of “please open the door” is added to the existing password subset.
  • the password sub-collection contains a password that is different from the "Please open the door” password voice but has the same semantics.
  • a password sub-collection can be added according to the "please open the door” password.
  • the updated password set is sent to the smart refrigerator 310 through the communication module 330.
  • the smart refrigerator 310 receives the updated password set sent by the server 320, and can perform the replacement upgrade on the previously pre-stored password set according to the updated password set.
  • the voice signal transmitted by the voice module and the password in the password set are matched by the main control module of the smart refrigerator to obtain a matching result, and the voice is obtained.
  • the signal and the matching result are sent to the server through the communication module, the server updates the pre-stored password set according to the voice signal and the matching result, and sends the updated password set to the smart refrigerator, and the smart refrigerator receives and stores the previously pre-stored according to the updated password set.
  • the replacement of the password set can realize online update of the password set, and continuously improve the ability of the main control module to recognize the password in the password set.
  • the server 320 further includes an identification module 324.
  • the recognition module 324 performs automatic speech recognition on the speech signal and obtains the recognition result.
  • the sending module 323 sends the result identified by the identification module 324 to the smart refrigerator.
  • the identification module 324 can convert the voice signal into a corresponding semantic text, and then match the semantic text with the pre-stored password set to obtain a matching result, that is, the recognized result.
  • the voice recognition system provided in the above embodiment performs automatic voice recognition on the voice signal through the identification module included in the server, and obtains the recognition result, and the sending module sends the recognized result to the smart refrigerator, and the language signal can be realized online. Identification.
  • the main control module 312 After the smart refrigerator 310 is powered on, the main control module 312 is in a sleep state, and the voice module 311 is in an active state. The main control module 312 matches the voice signal with the wake-up password in the password set, and determines whether to enter the scan state according to the matching result. If they match, the main control module 312 enters the scanning state; otherwise, it continues to be in the sleep state.
  • the main control module 312 After the main control module 312 enters the scanning state, the user is provided with the confirmation voice information, and determines whether to enter the activation state according to whether the feedback voice signal of the user collected by the voice module can be received within the first preset time period. If the feedback voice signal is received within the first preset time period, the main control module 312 enters an active state; otherwise, continues to be in a sleep state.
  • the main control module 312 After the main control module 312 enters the active state, it is detected whether the voice signal collected by the voice module 311 can be received in the second preset time period. If the voice signal is received within the second preset time period, the language is based on the language The tone signal and the password in the password set determine whether to control the smart refrigerator 310 to perform an operation corresponding to the voice signal; otherwise, continue to be in a sleep state.
  • the main control module of the smart refrigerator wakes up and works only when the preset condition is met, and can achieve low power consumption and achieve power saving effect.
  • the wake-up password by setting the wake-up password, the false wake-up can be eliminated, and the voice recognition performance can be effectively improved.
  • FIG. 4 is a schematic flowchart of a voice control method 400 according to an embodiment of the present invention.
  • the execution body of the method 400 shown in FIG. 4 may be the smart refrigerator shown in FIG. 1 described above.
  • Method 400 includes:
  • step 420 Determine, according to the voice signal collected in step 410 and the pre-stored password set, whether to control the smart refrigerator to perform an operation corresponding to the voice signal.
  • the execution body of the voice control method 400 according to the embodiment of the present invention may correspond to the smart refrigerator 100 according to the embodiment of the present invention, and the foregoing operations of the modules in the smart refrigerator 100.
  • the functions and/or functions are respectively implemented in order to implement the corresponding processes of the respective methods in FIG. 4 and FIG. 5, and are not described herein again for brevity.
  • the voice control method provided by the foregoing embodiment determines whether to control the smart refrigerator to perform the operation corresponding to the voice signal according to the collected voice signal and the pre-stored password set, thereby performing off-line recognition of the voice signal and improving the accuracy of the voice signal recognition. Rate and solve real-time problems with speech signal recognition.
  • the method 500 shown in FIG. 5 includes:
  • the voice control method provided by the foregoing embodiment converts the collected voice signal into corresponding semantic text, matches the semantic text with the password in the password set, obtains a matching result, and determines whether to control the smart refrigerator according to the matching result.
  • Performing the operation corresponding to the voice signal can realize the offline recognition of the voice signal, improve the accuracy of the voice signal recognition, and solve the real-time problem of the voice signal recognition.
  • the method 500 shown in FIG. 5 further includes:
  • the voice control method provided by the foregoing embodiment obtains a matching result by matching the collected voice signal with the password in the password set, and sends the voice signal and the matching result to the server connected to the smart refrigerator, and receives the sending by the server.
  • the updated password set replaces the previously pre-stored password set according to the updated password set, thereby realizing online update of the password set, and continuously improving the ability of the main control module to recognize the password in the password set.
  • a further embodiment of the present invention provides a computer device comprising: a processor, when the processor is configured to execute a computer program stored in the memory, implementing the following steps:
  • determining whether to control the operation of the smart phone to perform the voice signal according to the voice signal and the pre-stored password set specifically includes:
  • the voice signal is a “open door” password
  • the smart refrigerator is controlled to open the refrigerator door; otherwise, the smart refrigerator does not perform the operation of opening the refrigerator door.
  • the method further includes: transmitting a voice signal and a matching result to a server connected to the refrigerator, so that the server updates the password set according to the voice signal and the matching result.
  • the pre-stored password set is replaced according to the updated password set.
  • the matching result is obtained by matching the voice signal with the password in the password set
  • the voice signal and the matching result are sent to the server connected thereto, and the updated password set sent by the server is received, according to the update.
  • the subsequent password set replaces the previously pre-stored password set, which can implement online update of the password set, and continuously improve the ability of the main control module to recognize the password in the password set.
  • a further embodiment of the present invention provides a computer readable storage medium having stored thereon a computer program.
  • the computer program is executed by the processor, the following steps are implemented:
  • determining whether to control the operation of the smart phone to perform the voice signal according to the voice signal and the pre-stored password set specifically includes:
  • the voice signal is a “open door” password
  • the smart refrigerator is controlled to open the refrigerator door; otherwise, the smart refrigerator does not perform the operation of opening the refrigerator door.
  • the method further includes: transmitting a voice signal and a matching result to a server connected to the refrigerator, so that the server updates the password set according to the voice signal and the matching result.
  • the pre-stored password set is replaced according to the updated password set.
  • the matching result is obtained by matching the voice signal with the password in the password set
  • the voice signal and the matching result are sent to the server connected thereto, and the updated password set sent by the server is received, according to the update.
  • the subsequent password set replaces the previously pre-stored password set, which can implement online update of the password set, and continuously improve the ability of the main control module to recognize the password in the password set.
  • the size of the sequence numbers of the foregoing processes does not mean the order of execution sequence, and the execution order of each process should be determined by its function and internal logic, and should not be implemented in the embodiments of the present invention.
  • the process constitutes any limitation.
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of cells is only a logical function division.
  • multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.
  • the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • An integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, can be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention contributes in essence or to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), and a random A variety of media that can store program code, such as a memory (RAM, Random Access Memory), a disk, or an optical disk.
  • ROM Read-Only Memory
  • RAM Random Access Memory

Abstract

一种智能冰箱（100）、服务器（200）及语言控制系统和方法，该智能冰箱（100）包括：主控模块（110）和语音模块（120），其中，语音模块（120）用于采集语音信号，并将语音信号传输至主控模块（110）；主控模块（110）用于根据语音信号和预存的口令集合，确定是否控制智能冰箱（100）执行语音信号对应的操作，提高语音信号识别的准确率并解决语音信号识别的实时性问题。

Description

一种智能冰箱、服务器及语言控制系统和方法
本申请要求2016年05月30日在中国国家知识产权局提交的申请号为201610384412.9、发明名称为“一种智能冰箱、服务器及语言控制系统和方法”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及智能冰箱技术领域，尤其涉及一种智能冰箱、服务器及语言控制系统和方法。
背景技术
随着集成电路，人工智能，互联网技术的空前发展，冰箱不仅仅只需具备保存食物的功能，也成为家庭网络的一部分，可以为家庭成员提供更多的智能化服务。但是传统冰箱的控制方式不能满足智能冰箱更便捷的人机交互的需求，且语音控制技术在家电行业中因为实时性差，识别率低，可靠性低等问题一直得不到广泛的应用。
发明内容
本发明所要解决的技术问题是针对现有技术的不足，提供一种智能冰箱、服务器及语言控制系统和方法。
本发明解决上述技术问题的技术方案如下：一种智能冰箱，包括：主控模块和语音模块，其中，所述语音模块用于采集语音信号，并将所述语音信号传输至所述主控模块；所述主控模块用于根据所述语音模块传输的所述语音信号和预存的口令集合，确定是否控制所述智能冰箱执行所述语音信号对应的操作。
本发明的有益效果是：通过主控模块根据语音模块传输来的语音信号和预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
在上述技术方案的基础上，本发明还可以做如下改进。
进一步地，所述主控模块具体用于：将所述语音信号和所述口令集合中的口令进行匹配，得到匹配结果；根据匹配结果，确定是否控制所述智能冰箱执行所述语音信号对应的操作。
进一步地，所述主控模块还用于向与其连接的服务器发送所述语音信号和所述匹配结果，以便所述服务器根据所述语音信号和所述匹配结果更新所述口令集合。
采用上述进一步方案的有益效果是：可以实现口令集合的在线更新。
进一步地，所述主控模块还用于接收所述服务器发送的更新后的口令集合，并根据更新后的口令集合对预存的口令集合进行替换。
采用上述进一步方案的有益效果是：可以不断提高主控模块对口令集合中的口令的识别能力。
进一步地，所述口令集合包括多个口令子集合，每个所述口令子集合由语音不同但语义相同的口令构成。
本发明解决上述技术问题的另一种技术方案如下：一种服务器，包括：接收模块，用于接收智能冰箱的主控模块发送的语音信号，以及所述语音信号对应的匹配结果；更新模块，用于根据所述接收模块接收的所述语音信号和所述匹配结果更新预存的口令集合；发送模块，用于向智能冰箱发送所述更新模块更新后的口令集合。
本发明的有益效果是：通过接收智能冰箱的主控模块发送的语音信号，以及语音信号对应的匹配结果，并根据语音信号和匹配结果更新预存的口令集 合，可以实现口令集合的在线更新，提高主控模块对口令集合中的口令的识别能力。
在上述技术方案的基础上，本发明还可以做如下改进。
进一步地，所述服务器还包括：识别模块，用于对所述语音信号进行自动语音识别，并得到识别结果；所述发送模块还用于向所述智能冰箱发送所述识别模块识别出的结果。
采用上述进一步方案的有益效果是：可以实现在线语音识别。
本发明解决上述技术问题的另一种技术方案如下：一种语音控制系统，包括：通讯模块、上述实施例中的智能冰箱，以及上述实施例中的服务器，其中，所述智能冰箱与所述服务器通过所述通讯模块连接。
本发明的有益效果是：通过智能冰箱的主控模块将语音模块传输来的语音信号和口令集合中的口令进行匹配，得到匹配结果，将语音信号和匹配结果通过通信模块发送给服务器，服务器根据语音信号和匹配结果更新预存的口令集合，并向智能冰箱发送更新后的口令集合，智能冰箱接收并根据该更新后的口令集合对原先预存的口令集合进行替换，可以实现口令集合的在线更新，并不断提高主控模块对口令集合中的口令的识别能力。
本发明解决上述技术问题的另一种技术方案如下：一种语音控制方法，其特征在于，包括以下步骤：步骤1、采集语音信号；步骤2、根据所述语音信号和预存的口令集合，确定是否控制智能冰箱执行所述语音信号对应的操作。
本发明的有益效果是：通过根据采集的语音信号和预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
本发明附加的方面的优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明实践了解到。
附图说明
图1为本发明实施例提供的一种智能冰箱的示意性结构框图；
图2为本发明实施例提供的一种服务器的示意性结构框图；
图3为本发明实施例提供的一种语音控制系统的示意性结构框图；
图4为本发明实施例提供的一种语音控制方法的示意性流程图；
图5为本发明另一实施例提供的一种语音控制方法的示意性流程图。
具体实施方式
以下结合附图对本发明的原理和特征进行描述，所举实例只用于解释本发明，并非用于限定本发明的范围。
图1给出了本发明实施例提供的一种智能冰箱100的示意性结构框图。如图1所示的智能冰箱100包括：主控模块110和语音模块120。其中，语音模块120用于采集语音信号，并将采集的语音信号传输至主控模块110；
主控模块110用于根据语音模块120传输来的语音信号和预存的口令集合，确定是否控制智能冰箱100执行该语音信号对应的操作。
具体的，在该实施例中，语音模块120可以采用麦克风阵列。且该语音模块120具有采集语音信号和对语音信号进行预处理的功能，语音模块120对语音信号进行预处理包括但不局限于降噪处理、回声消除处理、降低混响处理、声源定位处理和盲源分离处理。
主控模块110中预存的口令集合来自与智能冰箱连接的服务器。口令集合包括多个口令子集合，每个口令子集合由语音不同但语义相同的口令构成。例如：“开门”和“请开门”是语音不同但语义相同的两个口令，它们属于一个口令子集合，而“调解温度”和“请调温”也是语音不同但语义相同的口令，属于另一个口令子集合。
上述实施例提供的一种智能冰箱，通过主控模块根据语音模块传输来的语音信号和预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操 作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
可选地，作为本发明的一个实施例，主控模块110具体用于：将语音模块120传输来的语音信号和口令集合中口令进行匹配，得到匹配结果，根据匹配结果，确定是否控制智能冰箱100执行语音信号对应的操作。
例如：语音信号为“开门”口令，当“开门”的口令与口令集合中的口令相匹配时，控制智能冰箱100打开冰箱门，否则，智能冰箱不执行打开冰箱门的操作。
上述实施例提供的一种智能冰箱，通过主控模块将语音模块传输来的语音信号和口令集合中的口令进行匹配，得到匹配结果，并根据匹配结果，确定是否控制智能冰箱执行语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
可选地，作为本发明的另一个实施例，主控模块110还用于向与其连接的服务器发送语音信号和匹配结果，以便服务器根据语音信号和匹配结果更新口令集合。
例如：语音信号对应的口令为“开门”，当“开门”口令与口令集合中的口令相匹配时，控制智能冰箱100打开冰箱门。同时向服务器发送该语音信号和相匹配的匹配结果，服务器接收该语音信号和相匹配的匹配结果，并更新口令集合。即：将原口令集合中的“开门”口令进行更新。
若“开门”口令与口令集合中的口令不匹配，智能冰箱不执行打开冰箱门的操作。同时向服务器发送该语音信号和不匹配的匹配结果，服务器接收该语音信号和不匹配的匹配结果，并更新口令集合。即：将“开门”口令增加至已有的口令子集合中，该口令子集合中包含与“开门”口令语音不同但语义相同的口 令。或者，口令集合中没有与“开门”口令语音不同但语义相同的口令组成的口令子集合时，可以根据“开门”口令新增一个口令子集合。
具体的，在该实施例中，主控模块110还用于接收服务器发送的更新后的口令集合，并根据该更新后的口令集合对原先预存的口令集合进行替换。
上述实施例提供的一种智能冰箱，通过主控模块将语音模块传输来的语音信号和口令集合中的口令进行匹配，得到匹配结果，将语音信号和匹配结果发送给与其连接的服务器，并接收服务器发送的更新后的口令集合，根据该更新后的口令集合对原先预存的口令集合进行替换，可以实现口令集合的在线更新，并不断提高主控模块对口令集合中的口令的识别能力。
可选地，作为本发明的一个实施例，上电后，主控模块110处于休眠状态，语音模块120处于工作状态。主控模块110还用于将语音信号和口令集合中的唤醒口令进行匹配，并根据匹配结果，确定是否进入扫描状态。
具体的，在该实施例，若相匹配，则确定主控模块110进入扫描状态；否则，主控模块110继续处于休眠状态。
当主控模块110进入扫描状态后，主控模块110还用于向用户提供确认语音信息，并根据是否能在第一预设时段内接收到语音模块采集的用户的反馈语音信号，确定是否进入激活状态。
具体的，在该实施例，若在第一预设时段内接收到反馈语音信号，则确定主控模块110进入激活状态；否则，主控模块110继续处于休眠状态。
当主控模块110进入激活状态后，主控模块110还用于检测在第二预设时段内是否能接收到语音模块120采集的语音信号；若在第二预设时段内接收到语音信号，则根据语音信号和口令集合，确定是否控制智能冰箱执行语音信号对应的操作；否则，主控模块110继续处于休眠状态。
例如：在该实施例中，智能冰箱100上电后，主控模块110处于休眠状态， 语音模块120处于工作状态。当语言模块120采集到语言信号后，将该语音信号传输至主控模块110，主控模块110将该语音信号对应的口令，如：“我爱我家”，与口令集合中的唤醒口令进行匹配，如果相匹配，则主控模块110进入扫描状态；否则，继续处于休眠状态。
当主控模块110进入扫描状态后，向用户提供确认语音信息，如：“您好”，若在第一预设时段内接收到反馈语音信号，如：“嗯，您好”，则确定进入激活状态；否则，继续处于休眠状态。
当主控模块110进入激活状态后，检测在第二预设时段内是否能接收到语音模块120采集的语音信号。若在第二预设时段内接收到语音信号，将该语音信号对应的口令，如：“调节温度”，与口令集合中的口令进行匹配，如果相匹配，则控制智能冰箱执行“调节温度”的操作；否则，继续处于休眠状态。
上述实施例提供的智能冰箱，主控模块只有在满足预设条件时，才唤醒并进行工作，可以实现低功耗、达到省电的效果。同时，通过设置唤醒口令，可以排除误唤醒，可以有效的提升语音识别性能。
上文结合图1，详细描述了根据本发明实施例提供的智能冰箱，下面结合图2，详细描述根据本发明实施例提供的服务器。
图2给出了本发明实施例提供的一种服务器200的示意性结构框图。如图2所示的服务器200包括：接收模块210、更新模块220和接收模块230。其中，
接收模块210用于接收智能冰箱的主控模块发送的语音信号，以及语音信号对应的匹配结果。更新模块220用于根据接收模块210接收的语音信号和匹配结果更新预存的口令集合。发送模块230用于向智能冰箱发送更新模块220更新后的口令集合。
上述实施例中提供的一种服务器，通过接收智能冰箱的主控模块发送的语 音信号，以及语音信号对应的匹配结果，并根据语音信号和匹配结果更新预存的口令集合，可以实现口令集合的在线更新，提高主控模块对口令集合中的口令的识别能力。
需要说明的是，在该实施例中，更新模块220可以在满足预设条件时，再对接收模块210接收的语言信号进行更新，例如：预设条件为接收模块210接收的语言信号的数量达到预设值。
可选地，作为本发明的一个实施例，如图2所示，服务器200还包括识别模块240。识别模块240，用于对语音信号进行自动语音识别，并得到识别结果。发送模块230还用于向智能冰箱发送识别模块240识别出的结果。
具体的，在该实施例中，识别模块240可以将语音信号转换成对应的语义文本，再将语义文本与预存的口令集合进行匹配，得到匹配结果，即为识别出的结果。
上述实施例中提供的一种服务器，通过识别模块对语音信号进行自动语音识别，并得到识别结果。发送模块向智能冰箱发送识别出的结果，可以实现语言信号的在线识别。
本发明还提供一种语音控制系统。图3给出了本发明实施例提供的一种语音控制系统300的示意性结构框图。
如图3所示的语音控制系统包括：智能冰箱310、服务器320和通信模块330。其中，智能冰箱310采用上述图1所示的智能冰箱100，可以实现智能冰箱100的全部功能。服务器320为上述图2所示的服务器200，可以实现服务器200的全部功能。
具体的，在该实施例中，智能冰箱310包括的语音模块311可以采集语言信号，并将语音信号传输至主控模块312。主控模块312可以将和预存的口令 集合进行匹配，根据匹配结果确定是否控制智能冰箱310执行语音信号对应的操作。
例如，语音信号对应的口令和预存的口令集合中的口令相匹配时，控制智能冰箱310执行语音信号对应的操作，否则，智能冰箱不执行该操作。
主控模块312还通过通信模块330向服务器320包括的接收模块321发送该语音信号和匹配结果。接收模块321通过通信模块330接收主控模块312发送的语言信号和匹配结果。更新模块322根据接收模块321接收的该语音信号和匹配结果更新预存的口令集合。发送模块323通过通信模块330向主控模块312发送更新后的口令集合。
例如：语音信号对应的口令为“请把门打开”，当“请把门打开”口令与口令集合中的口令相匹配时，控制智能冰箱310打开冰箱门。同时通过通信模块330向服务器320发送该语音信号和相匹配的匹配结果，服务器320接收该语音信号和相匹配的匹配结果，并更新口令集合中的“请把门打开”口令。
若“请把门打开”口令与口令集合中的口令不匹配，智能冰箱310不执行打开冰箱门的操作。同时向服务器320发送该语音信号和不匹配的匹配结果，服务器接收该语音信号和不匹配的匹配结果，并确定更新口令集合，即：将“请把门打开”口令增加至已有的口令子集合中，该口令子集合中包含与“请把门打开”口令语音不同但语义相同的口令。或者，口令集合中没有与“请把门打开”口令语音不同但语义相同的口令组成的口令子集合时，可以根据“请把门打开”口令新增一个口令子集合。
当服务器320完成口令集合的更新后，将更新后的口令集合通过通信模块330发送给智能冰箱310。智能冰箱310接收服务器320发送的更新后的口令集合，可以根据该更新后的口令集合对原先预存的口令集合进行替换升级。
上述实施例中提供的一种语音控制系统，通过智能冰箱的主控模块将语音模块传输来的语音信号和口令集合中的口令进行匹配，得到匹配结果，将语音 信号和匹配结果通过通信模块发送给服务器，服务器根据语音信号和匹配结果更新预存的口令集合，并向智能冰箱发送更新后的口令集合，智能冰箱接收并根据该更新后的口令集合对原先预存的口令集合进行替换，可以实现口令集合的在线更新，并不断提高主控模块对口令集合中的口令的识别能力。
可选地，作为本发明的一个实施例，服务器320还包括识别模块324。识别模块324对语音信号进行自动语音识别，并得到识别结果。发送模块323向智能冰箱发送识别模块324识别出的结果。
具体的，在该实施例中，识别模块324可以将语音信号转换成对应的语义文本，再将语义文本与预存的口令集合进行匹配，得到匹配结果，即为识别出的结果。
上述实施例中提供的一种语音识别系统，通过服务器包括的识别模块对语音信号进行自动语音识别，并得到识别结果，并由发送模块向智能冰箱发送识别出的结果，可以实现语言信号的在线识别。
智能冰箱310在上电后，主控模块312处于休眠状态，语音模块311处于工作状态。主控模块312将语音信号和口令集合中的唤醒口令进行匹配，并根据匹配结果，确定是否进入扫描状态。若相匹配，则主控模块312进入扫描状态；否则，继续处于休眠状态。
当主控模块312进入扫描状态后，向用户提供确认语音信息，并根据是否能在第一预设时段内接收到语音模块采集的用户的反馈语音信号，确定是否进入激活状态。若在第一预设时段内接收到反馈语音信号，则主控模块312进入激活状态；否则，继续处于休眠状态。
当主控模块312进入激活状态后，检测在第二预设时段内是否能接收到语音模块311采集的语音信号。若在第二预设时段内接收到语音信号，则根据语 音信号和口令集合中的口令，确定是否控制智能冰箱310执行语音信号对应的操作；否则，继续处于休眠状态。
上述实施例提供的语音控制系统，智能冰箱的主控模块只有在满足预设条件时，才唤醒并进行工作，可以实现低功耗、达到省电的效果。同时，通过设置唤醒口令，可以排除误唤醒，可以有效的提升语音识别性能。
本发明还提供一种语音控制方法。图4给出了本发明实施例提供的一种语音控制方法400的示意性流程图。如图4所示的方法400的执行主体可以为上述图1所示的智能冰箱。方法400包括：
410、采集语音信号。
420、根据步骤410中采集的语音信号和预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操作。
应理解，在本发明实施例中，根据本发明实施例的语音控制方法400的执行主体，可对应于根据本发明实施例的智能冰箱100，该智能冰箱100中的各个模块的上述和其它操作和/或功能分别为了实现图4和图5中的各个方法的相应流程，为了简洁，在此不再赘述。
上述实施例提供的一种语音控制方法，通过根据采集的语音信号和预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
可选地，作为本发明的一个实施例，如图5所示的方法500包括：
510、采集语言信号。
521、将语音信号和口令集合中的口令进行匹配，得到匹配结果。
522、根据匹配结果，确定是否控制智能冰箱执行语音信号对应的操作。
上述实施例提供的一种语音控制方法，通过将采集的语音信号转换成对应的语义文本，将语义文本和口令集合中的口令进行匹配，得到匹配结果，并根据匹配结果，确定是否控制智能冰箱执行语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
可选地，作为本发明的一个实施例，如图5所示的方法500还包括：
530、向与智能冰箱连接的服务器发送语音信号和匹配结果，以便服务器根据所述语音信号和匹配结果更新口令集合。
540、接收服务器发送的更新后的口令集合。
550、根据更新后的口令集合对预存的口令集合进行替换。
上述实施例提供的一种语音控制方法，通过将采集的语音信号和口令集合中的口令进行匹配，得到匹配结果，将语音信号和匹配结果发送给与智能冰箱连接的服务器，并接收服务器发送的更新后的口令集合，根据该更新后的口令集合对原先预存的口令集合进行替换，可以实现口令集合的在线更新，并不断提高主控模块对口令集合中的口令的识别能力。
本发明的又一实施例提供一种计算机设备，包括：处理器，处理器用于执行存储器中存储的计算机程序时，实现如下步骤：
采集语音信号；
根据语音信号和预存的口令集合，确定是否控制智能冰箱执行语音信号对应的操作。
在执行上述步骤时，通过采集到的语音信号以及预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
在上述实施例中，具体地，根据语音信号和预存的口令集合，确定是否控制智能冰箱执行语音信号对应的操作具体包括：
将语音信号和口令集合中的口令进行匹配，得到匹配结果；
根据匹配结果，确定是否控制智能冰箱执行语音信号对应的操作。
具体地，例如：语音信号为“开门”口令，当“开门”的口令与口令集合中的口令相匹配时，控制智能冰箱打开冰箱门，否则，智能冰箱不执行打开冰箱门的操作。
在上述实施例中，具体地，还包括：向与冰箱连接的服务器发送语音信号和匹配结果，以便服务器根据语音信号和匹配结果更新口令集合。
接收服务器发送的更新后的口令集合；
根据更新后的口令集合对预存的口令集合进行替换。
在执行上述步骤时，通过将语音信号和口令集合中的口令进行匹配，得到匹配结果，将语音信号和匹配结果发送给与其连接的服务器，并接收服务器发送的更新后的口令集合，根据该更新后的口令集合对原先预存的口令集合进行替换，可以实现口令集合的在线更新，并不断提高主控模块对口令集合中的口令的识别能力。
本发明的又一实施例提供一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时，实现如下步骤：
采集语音信号；
根据语音信号和预存的口令集合，确定是否控制智能冰箱执行语音信号对应的操作。
在执行上述步骤时，通过采集到的语音信号以及预存的口令集合，确定是否控制智能冰箱执行该语音信号对应的操作，可以实现语音信号的离线识别，提高语音信号识别的准确率，并解决语音信号识别的实时性问题。
在上述实施例中，具体地，根据语音信号和预存的口令集合，确定是否控制智能冰箱执行语音信号对应的操作具体包括：
将语音信号和口令集合中的口令进行匹配，得到匹配结果；
根据匹配结果，确定是否控制智能冰箱执行语音信号对应的操作。
具体地，例如：语音信号为“开门”口令，当“开门”的口令与口令集合中的口令相匹配时，控制智能冰箱打开冰箱门，否则，智能冰箱不执行打开冰箱门的操作。
在上述实施例中，具体地，还包括：向与冰箱连接的服务器发送语音信号和匹配结果，以便服务器根据语音信号和匹配结果更新口令集合。
接收服务器发送的更新后的口令集合；
根据更新后的口令集合对预存的口令集合进行替换。
在执行上述步骤时，通过将语音信号和口令集合中的口令进行匹配，得到匹配结果，将语音信号和匹配结果发送给与其连接的服务器，并接收服务器发送的更新后的口令集合，根据该更新后的口令集合对原先预存的口令集合进行替换，可以实现口令集合的在线更新，并不断提高主控模块对口令集合中的口令的识别能力。
应理解，在本发明各实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用 来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本发明实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机 存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (22)

  1. 一种智能冰箱，包括：主控模块，其特征在于，还包括：语音模块，其中，
    所述语音模块用于采集语音信号，并将所述语音信号传输至所述主控模块；
    所述主控模块用于根据所述语音模块传输的所述语音信号和预存的口令集合，确定是否控制所述智能冰箱执行所述语音信号对应的操作。
  2. 根据权利要求1所述的智能冰箱，其特征在于，所述主控模块具体用于：
    将所述语音信号和所述口令集合中的口令进行匹配，得到匹配结果；
    根据匹配结果，确定是否控制所述智能冰箱执行所述语音信号对应的操作。
  3. 根据权利要求2所述的智能冰箱，其特征在于，所述主控模块还用于向与其连接的服务器发送所述语音信号和所述匹配结果，以便所述服务器根据所述语音信号和所述匹配结果更新所述口令集合。
  4. 根据权利要求3所述的智能冰箱，其特征在于，所述主控模块还用于接收所述服务器发送的更新后的口令集合，并根据更新后的口令集合对预存的口令集合进行替换。
  5. 根据权利要求1至4中任一项所述的智能冰箱，其特征在于，所述口令集合包括多个口令子集合，每个所述口令子集合由语音不同但语义相同的口 令构成。
  6. 根据权利要求2所述的智能冰箱，其特征在于，上电后，所述主控模块处于休眠状态，所述主控模块还用于将所述语音信号和所述口令集合中的唤醒口令进行匹配，确定是否进入扫描状态。
  7. 根据权利要求6所述的智能冰箱，其特征在于，所述主控模块具体用于：若相匹配，则确定进入扫描状态；否则，继续处于休眠状态。
  8. 根据权利要求7所述的智能冰箱，其特征在于，当所述主控模块进入扫描状态后，所述主控模块还用于向用户提供确认语音信息，并根据是否能在第一预设时段内接收到所述语音模块采集的用户的反馈语音信号，确定是否进入激活状态。
  9. 根据权利要求8所述的智能冰箱，其特征在于，所述主控模块具体用于：若在所述第一预设时段内接收到所述反馈语音信号，则确定进入激活状态；否则，继续处于休眠状态。
  10. 根据权利要求9所述的智能冰箱，其特征在于，当所述主控模块进入激活状态后，所述主控模块还用于检测在第二预设时段内是否能接收到所述语音模块采集的所述语音信号；若在所述第二预设时段内接收到所述语音信号，则根据所述语音信号和所述口令集合，确定是否控制所述智能冰箱执行所述语音信号对应的操作；否则，继续处于休眠状态。
  11. 根据权利要求1所述的智能冰箱，其特征在于，所述语音模块采用麦 克风阵列。
  12. 一种服务器，其特征在于，包括：
    接收模块，用于接收智能冰箱的主控模块发送的语音信号，以及所述语音信号对应的匹配结果；
    更新模块，用于根据所述接收模块接收的所述语音信号和所述匹配结果更新预存的口令集合；
    发送模块，用于向智能冰箱发送所述更新模块更新后的口令集合。
  13. 根据权利要求12所述的服务器，其特征在于，所述服务器还包括：
    识别模块，用于对所述语音信号进行自动语音识别，并得到识别结果；
    所述发送模块还用于向所述智能冰箱发送所述识别模块识别出的结果。
  14. 根据权利要求12或13所述的服务器，其特征在于，所述口令集合包括多个口令子集合，每个所述口令子集合由语音不同但语义相同的口令构成。
  15. 一种语音控制系统，其特征在于，包括：通讯模块、如权利要求1至11中任一项所述的智能冰箱，以及如权利要求12至14中任一项所述的服务器，其中，所述智能冰箱与所述服务器通过所述通讯模块连接。
  16. 一种语音控制方法，其特征在于，包括以下步骤：
    步骤1、采集语音信号；
    步骤2、根据所述语音信号和预存的口令集合，确定是否控制智能冰箱执行所述语音信号对应的操作。
  17. 根据权利要求16所述的方法，其特征在于，步骤2具体包括：
    步骤2.1、将所述语音信号和所述口令集合中的口令进行匹配，得到匹配结果；
    步骤2.2、根据匹配结果，确定是否控制所述智能冰箱执行所述语音信号对应的操作。
  18. 根据权利要求17所述的方法，其特征在于，所述方法还包括：
    步骤3、向与所述冰箱连接的服务器发送所述语音信号和所述匹配结果，以便所述服务器根据所述语音信号和所述匹配结果更新所述口令集合。
  19. 根据权利要求18所述的方法，其特征在于，所述方法还包括：
    步骤4、接收所述服务器发送的更新后的口令集合；
    步骤5、根据更新后的口令集合对预存的口令集合进行替换。
  20. 根据权利要求16至19中任一项所述的方法，其特征在于，所述口令集合包括多个口令子集合，每个所述口令子集合由语音不同但语义相同的口令构成。
  21. 一种计算机设备，其特征在于，包括处理器，所述处理器用于执行存储器中存储的计算机程序时实现如权利要求16至20中任一项所述语音控制方法的步骤。
  22. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求16至20中任一项所述语音控制方法的步骤。
PCT/CN2017/084959 2016-05-30 2017-05-18 一种智能冰箱、服务器及语言控制系统和方法 WO2017206725A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610384412.9A CN105913839A (zh) 2016-05-30 2016-05-30 一种智能冰箱、服务器及语音控制系统和方法
CN201610384412.9 2016-05-30

Publications (1)

Publication Number Publication Date
WO2017206725A1 true WO2017206725A1 (zh) 2017-12-07

Family

ID=56741985

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/084959 WO2017206725A1 (zh) 2016-05-30 2017-05-18 一种智能冰箱、服务器及语言控制系统和方法

Country Status (2)

Country Link
CN (1) CN105913839A (zh)
WO (1) WO2017206725A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108055650A (zh) * 2018-01-31 2018-05-18 四川金互通科技股份有限公司 数据处理设备及方法
CN111696541A (zh) * 2019-03-13 2020-09-22 青岛海尔电冰箱有限公司 向冰箱内添加食材的语音数据交互方法及交互系统

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913839A (zh) * 2016-05-30 2016-08-31 合肥华凌股份有限公司 一种智能冰箱、服务器及语音控制系统和方法
CN106502649A (zh) * 2016-09-27 2017-03-15 北京光年无限科技有限公司 一种机器人服务唤醒方法及装置
CN106782525A (zh) * 2016-11-30 2017-05-31 无锡小天鹅股份有限公司 洗衣机及其的语音控制装置、方法
CN106707788B (zh) * 2017-03-09 2019-05-28 上海电器科学研究院 一种智能家居语音控制识别系统与方法
CN106940119A (zh) * 2017-04-06 2017-07-11 绵阳美菱软件技术有限公司 一种冰箱、食品管理方法及系统
CN107146622B (zh) * 2017-06-16 2021-02-19 合肥美的智能科技有限公司 冰箱、语音交互系统、方法、计算机设备、可读存储介质
CN107403617A (zh) * 2017-06-26 2017-11-28 合肥美的智能科技有限公司 冰箱、语音控制方法、计算机设备、可读存储介质
CN107800572B (zh) * 2017-10-27 2020-10-02 瑞芯微电子股份有限公司 一种基于神经网络升级设备的方法和装置
CN108346207A (zh) * 2018-04-12 2018-07-31 伟创亚洲有限公司 智能酒柜的语音控制系统及方法
CN109247898A (zh) * 2018-09-04 2019-01-22 佛山市顺德区美的洗涤电器制造有限公司 洗碗机及洗碗机的控制装置、方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2429801Y (zh) * 2000-06-13 2001-05-09 广东科龙电器股份有限公司 可语音控制的智能冰箱
CN102855872A (zh) * 2012-09-07 2013-01-02 深圳市信利康电子有限公司 基于终端及互联网语音交互的家电控制方法及系统
US20150235642A1 (en) * 2013-09-03 2015-08-20 Panasonic Intellectual Property Corporation Of America Speech dialogue control method
CN105206275A (zh) * 2015-08-31 2015-12-30 小米科技有限责任公司 一种设备控制方法、装置及终端
CN105913839A (zh) * 2016-05-30 2016-08-31 合肥华凌股份有限公司 一种智能冰箱、服务器及语音控制系统和方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101794126A (zh) * 2009-12-15 2010-08-04 广东工业大学 一种无线智能家电语音控制系统
CN102636171A (zh) * 2012-04-27 2012-08-15 深圳市凯立德科技股份有限公司 一种语音导航方法及装置
CN103578472A (zh) * 2012-08-10 2014-02-12 海尔集团公司 电器设备的控制方法和控制装置
KR101330671B1 (ko) * 2012-09-28 2013-11-15 삼성전자주식회사 전자장치, 서버 및 그 제어방법
CN104505093A (zh) * 2014-12-16 2015-04-08 佛山市顺德区美的电热电器制造有限公司 家用电器及其语音交互方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN2429801Y (zh) * 2000-06-13 2001-05-09 广东科龙电器股份有限公司 可语音控制的智能冰箱
CN102855872A (zh) * 2012-09-07 2013-01-02 深圳市信利康电子有限公司 基于终端及互联网语音交互的家电控制方法及系统
US20150235642A1 (en) * 2013-09-03 2015-08-20 Panasonic Intellectual Property Corporation Of America Speech dialogue control method
CN105206275A (zh) * 2015-08-31 2015-12-30 小米科技有限责任公司 一种设备控制方法、装置及终端
CN105913839A (zh) * 2016-05-30 2016-08-31 合肥华凌股份有限公司 一种智能冰箱、服务器及语音控制系统和方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108055650A (zh) * 2018-01-31 2018-05-18 四川金互通科技股份有限公司 数据处理设备及方法
CN111696541A (zh) * 2019-03-13 2020-09-22 青岛海尔电冰箱有限公司 向冰箱内添加食材的语音数据交互方法及交互系统

Also Published As

Publication number Publication date
CN105913839A (zh) 2016-08-31

Similar Documents

Publication Publication Date Title
WO2017206725A1 (zh) 一种智能冰箱、服务器及语言控制系统和方法
WO2018059405A1 (zh) 语音控制系统及其唤醒方法、唤醒装置和家电、协处理器
US10601599B2 (en) Voice command processing in low power devices
CN107358954A (zh) 一种实时更换唤醒词的设备及方法
CN105009204B (zh) 语音识别功率管理
WO2020042993A1 (zh) 语音控制方法、装置及系统
CN111223497A (zh) 一种终端的就近唤醒方法、装置、计算设备及存储介质
WO2020228270A1 (zh) 语音处理方法、装置、计算机设备及存储介质
CN107112017A (zh) 操作语音识别功能的电子设备和方法
CN107388487B (zh) 控制空调的方法和装置
CN103714815A (zh) 语音控制方法及其设备
WO2016078214A1 (zh) 终端处理方法、装置及计算机存储介质
CN111968644B (zh) 智能设备唤醒方法、装置及电子设备
US20190228773A1 (en) Speech interaction method, apparatus and computer readable storage medium
CN110111789A (zh) 语音交互方法、装置、计算设备和计算机可读介质
CN108899028A (zh) 语音唤醒方法、搜索方法、装置和终端
CN108932942A (zh) 一种实现智能音箱人机对话的系统及其方法
WO2023010861A1 (zh) 一种唤醒处理方法、装置、设备和计算机存储介质
CN111028831B (zh) 一种语音唤醒方法及装置
CN108897517A (zh) 一种信息处理方法及电子设备
CN114402385A (zh) 具有分布式麦克风的声学分区
WO2022222045A1 (zh) 语音信息处理方法及设备
CN207458576U (zh) 一种实时更换唤醒词的设备
CN112634897A (zh) 设备唤醒方法、装置和存储介质及电子装置
WO2018023514A1 (zh) 一种家居背景音乐控制系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17805670

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17805670

Country of ref document: EP

Kind code of ref document: A1