CN112786040A - Voice control method, device and equipment applied to intelligent household electrical appliance - Google Patents
Voice control method, device and equipment applied to intelligent household electrical appliance Download PDFInfo
- Publication number
- CN112786040A CN112786040A CN202011138266.4A CN202011138266A CN112786040A CN 112786040 A CN112786040 A CN 112786040A CN 202011138266 A CN202011138266 A CN 202011138266A CN 112786040 A CN112786040 A CN 112786040A
- Authority
- CN
- China
- Prior art keywords
- voice
- semantic
- intelligent household
- 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 62
- 230000006870 function Effects 0.000 claims description 75
- 238000012790 confirmation Methods 0.000 claims description 22
- 238000012795 verification Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 230000003993 interaction Effects 0.000 abstract description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 23
- 238000010586 diagram Methods 0.000 description 10
- 238000013507 mapping Methods 0.000 description 10
- 238000010438 heat treatment Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000003863 physical function Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Abstract
The invention belongs to the technical field of intelligent household appliances, and particularly relates to a voice control method, a voice control device and voice control equipment applied to intelligent household appliances, wherein first voice information input by a user is acquired, wherein the first voice information comprises a trigger keyword; determining a semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category; according to the semantic type, the equipment function corresponding to the semantic type is determined and executed, and the semantic type corresponding to the voice information input by the user can be determined according to the instruction model information, so that the intelligent household appliance can determine and execute the corresponding function according to the semantic type, the limitation that the user can only use a fixed voice instruction when performing voice control is avoided, and the voice control flexibility and the human-computer interaction efficiency of the intelligent household appliance are improved.
Description
Technical Field
The invention belongs to the technical field of intelligent household appliances, and particularly relates to a voice control method, a voice control device and voice control equipment applied to intelligent household appliances.
Background
At present, with the increasingly mature voice control technology, more and more intelligent household appliances with voice control function enter the life of a user, and through voice remote control of the intelligent household appliances, the operation efficiency of the intelligent household appliances is improved, and the user experience is also improved.
However, in the prior art, after receiving a voice command of a user, an intelligent household electrical appliance needs to analyze the voice command, determine and execute a function corresponding to the voice command, but the intelligent household electrical appliance of different manufacturers and different product models has a preset function and the voice command corresponding to the preset function is different, and the user needs to know the exact voice command to perform voice control, so that the learning cost of the user is increased, and the problems of poor flexibility and low efficiency when the intelligent household electrical appliance performs voice control are caused.
Accordingly, there is a need in the art for a new voice control method, apparatus and device for intelligent home appliances to solve the above problems.
Disclosure of Invention
In order to solve the problems in the prior art, namely, the problems of poor flexibility and low efficiency when the existing intelligent household electrical appliance performs voice control, the invention provides a voice control method, a voice control device and voice control equipment applied to the intelligent household electrical appliance.
According to a first aspect of embodiments of the present invention, the present invention provides a voice control method applied to an intelligent home appliance, including: acquiring first voice information input by a user, wherein the first voice information comprises a trigger keyword; determining a semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category; and determining and executing equipment functions corresponding to the semantic categories according to the semantic categories.
In the above preferred technical solution of the voice control method applied to the intelligent household electrical appliance, determining the semantic category corresponding to the first voice information according to a preset device instruction model includes: performing semantic recognition on the first voice information to obtain a triggering keyword; and determining semantic categories corresponding to the triggering keywords according to the equipment instruction model.
In the above preferred technical solution of the voice control method applied to the intelligent household electrical appliance, determining a semantic category corresponding to the first voice information according to a preset device instruction model, further includes: determining user identification information according to the first voice information; performing semantic recognition on the first voice information to obtain a triggering keyword, including: according to a preset semantic recognition model, performing semantic recognition on first voice information corresponding to the user identification information to obtain a trigger keyword; the semantic recognition model is used for converting voice information corresponding to different user identification information into the triggering keyword.
In the above preferred technical solution of the voice control method applied to the intelligent household electrical appliance, after determining the semantic category corresponding to the first voice information, the method further includes: broadcasting a confirmation voice to a user, wherein the confirmation voice comprises a device function name corresponding to the semantic category; and after receiving the confirmation of the user, executing the equipment function corresponding to the semantic category.
In a preferred technical solution of the above voice control method applied to an intelligent home appliance, the method further includes: and acquiring a device instruction model of the intelligent household appliance from a cloud server according to the identification information of the intelligent household appliance.
In a preferred technical solution of the above voice control method applied to an intelligent home appliance, the method further includes: and acquiring a semantic recognition model corresponding to the equipment instruction model from a cloud service according to the identification information of the intelligent household electrical appliance.
In a preferred technical solution of the above voice control method applied to an intelligent home appliance, the method further includes: generating instruction identification verification information according to the first voice information and the execution result of the equipment function; uploading the instruction identification verification information to the cloud server, wherein the instruction identification verification information is used for correcting the equipment instruction model.
According to a second aspect of the embodiments of the present invention, the present invention provides a voice control apparatus for an intelligent home appliance, including:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first voice information input by a user, and the first voice information comprises a trigger keyword;
the determining module is used for determining the semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category;
and the execution module is used for determining and executing the equipment function corresponding to the semantic category according to the semantic category.
In the foregoing preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the determining module is specifically configured to: performing semantic recognition on the first voice information to obtain a triggering keyword; and determining semantic categories corresponding to the triggering keywords according to the equipment instruction model.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the determining module is further configured to: determining user identification information according to the first voice information; the obtaining module is specifically configured to, when performing semantic recognition on the first voice information and obtaining a trigger keyword: according to a preset semantic recognition model, performing semantic recognition on first voice information corresponding to the user identification information to obtain a trigger keyword; the semantic recognition model is used for converting voice information corresponding to different user identification information into the triggering keyword.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, after determining the semantic type corresponding to the first voice information, the execution module is further configured to: broadcasting a confirmation voice to a user, wherein the confirmation voice comprises a device function name corresponding to the semantic category; and after receiving the confirmation of the user, executing the equipment function corresponding to the semantic category.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the apparatus further includes a transceiver module, configured to: and acquiring a device instruction model of the intelligent household appliance from a cloud server according to the identification information of the intelligent household appliance.
In the foregoing preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the transceiver module is further configured to: and acquiring a semantic recognition model corresponding to the equipment instruction model from a cloud service according to the identification information of the intelligent household electrical appliance.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the transceiver module is further configured to: generating instruction identification verification information according to the first voice information and the execution result of the equipment function; uploading the instruction identification verification information to the cloud server, wherein the instruction identification verification information is used for correcting the equipment instruction model.
According to a third aspect of embodiments of the present invention, there is provided an electronic apparatus including: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor according to any one of the first aspect of the embodiments of the present invention, where the method is applied to an intelligent home appliance.
According to a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is configured to implement the voice control method applied to the intelligent home appliance according to any one of the first aspect of the embodiments of the present invention.
The technical personnel in the field can understand that the voice control method, the voice control device and the voice control equipment applied to the intelligent household appliance, provided by the invention, have the advantages that the first voice information input by a user is obtained, wherein the first voice information comprises a trigger keyword; determining a semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category; according to the semantic type, determining and executing equipment functions corresponding to the semantic type, and because the semantic type corresponding to the voice information input by the user can be determined according to the instruction model information, the intelligent household appliance can determine and execute the corresponding functions according to the semantic type, the limitation that the user can only use fixed voice instructions during voice control is avoided, and the voice control flexibility and the human-computer interaction efficiency of the intelligent household appliance are improved.
Drawings
The following describes preferred embodiments of a voice control method, apparatus and device applied to an intelligent home appliance according to the present invention with reference to the accompanying drawings. The attached drawings are as follows:
fig. 1 is an application scene diagram of a voice control method applied to an intelligent household electrical appliance according to an embodiment of the present application;
fig. 2 is a flowchart of a voice control method applied to an intelligent home appliance according to an embodiment of the present application;
fig. 3 is a schematic diagram of an apparatus instruction model according to an embodiment of the present application;
fig. 4 is a flowchart of a voice control method applied to an intelligent home appliance according to another embodiment of the present application;
fig. 5 is a flowchart of a voice control method applied to an intelligent home appliance according to still another embodiment of the present application;
fig. 6 is a schematic structural diagram of a voice control apparatus applied to an intelligent home appliance according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a voice control apparatus applied to an intelligent home appliance according to another embodiment of the present application;
fig. 8 is a schematic diagram of an intelligent home appliance according to an embodiment of the present application.
Detailed Description
First, it should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention. And can be adjusted as needed by those skilled in the art to suit particular applications. For example, although the voice control method applied to the intelligent household electrical appliance is described in conjunction with the intelligent water heater, this is not limiting, and other devices with voice control and voice interaction requirements may be configured with the voice control method applied to the intelligent household electrical appliance, such as the intelligent air conditioning device.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "connected" and "connected" should be interpreted broadly, e.g., as being fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; the two components can be directly connected or indirectly connected through an intermediate medium, and the two components can be communicated with each other. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The terms referred to in this application are explained first:
1) the intelligent household appliance equipment is a household appliance product formed by introducing a microprocessor, a sensor technology and a network communication technology into the household appliance equipment, has the characteristics of intelligent control, intelligent perception and intelligent application, and the operation process of the intelligent household appliance equipment usually depends on the application and processing of modern technologies such as the Internet of things, the Internet and an electronic chip, for example, the intelligent household appliance equipment can realize the remote control and management of a user on the intelligent household appliance equipment by connecting a cloud server.
2) Terminal equipment, indicate the electronic equipment who has wireless connection function, for example, hand-held type terminal equipment, vehicle-mounted terminal equipment etc, terminal equipment can be through connecting the internet, with intelligent household electrical appliances as above carry out communication connection, also can directly carry out communication connection through modes such as bluetooth, wifi and intelligent household electrical appliances as above, terminal equipment is for cell-phone, panel computer, notebook computer, palm computer, mobile internet equipment (mobile internet device, MID), wearable equipment for example, wherein, wearable equipment includes for example: smart watches, smart bracelets, pedometers, and the like.
3) "plurality" means two or more, and other terms are analogous. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
4) "correspond" may refer to an association or binding relationship, and a corresponds to B refers to an association or binding relationship between a and B.
The following explains an application scenario of the embodiment of the present application:
fig. 1 is an application scenario diagram of the voice control method applied to the intelligent household electrical appliance according to the embodiment of the present application, as shown in fig. 1, the intelligent household electrical appliance in the scenario of this embodiment is an intelligent water heater, and a user controls the intelligent water heater by sending a voice instruction to the intelligent water heater, so that the intelligent water heater executes a corresponding function.
The process that a user carries out man-machine interaction with the intelligent household appliance needs two main steps of 'recognition' and 'execution', and is different from voice assistants of other software layers, and because the intelligent household appliance needs to execute specific physical functions such as 'heater on' and 'temperature rise' after receiving an instruction, compared with the voice control of a voice assistant of a software type (such as inquiring weather, inquiring date, playing music and the like), the 'execution' step of the intelligent household appliance has higher safety requirements, therefore, the voice control and voice interaction of the intelligent household appliance have higher requirements for the accuracy of a voice instruction, and the safety problem caused by inaccurate voice instruction recognition is avoided.
Based on the above consideration, in the prior art, after receiving a voice instruction of a user, an intelligent household appliance needs to analyze the voice instruction to determine and execute a function corresponding to the voice instruction, but intelligent household appliances of different manufacturers and different product models have different preset functions and voice instructions corresponding to the preset functions, for example, a start instruction of an intelligent household appliance of a brand a is "on"; the starting instruction of the brand B intelligent household appliance is 'starting'. Only after the user inputs a correct voice command, the device can execute the corresponding function, so that in the scene shown in fig. 1, the user a inputs an accurate execution password of "on", and thus the intelligent household appliance is successfully started; and the user b inputs a similar but inaccurate execution password and cannot start the intelligent household appliance. Therefore, in consideration of the use safety of the intelligent household electrical appliance, in the prior art, the user is required to know the exact voice command to perform voice control, so that the learning cost of the user is increased, and the problems of poor flexibility and low efficiency of the intelligent household electrical appliance during voice control are caused.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 2 is a flowchart of a voice control method applied to an intelligent household electrical appliance according to an embodiment of the present application, exemplarily, an intelligent household electrical appliance in the embodiment is an intelligent water heater, and as shown in fig. 2, the voice control method applied to the intelligent household electrical appliance according to the present embodiment includes the following steps:
step S101, first voice information input by a user is obtained, wherein the first voice information comprises a trigger keyword.
Illustratively, the first voice message is descriptive information of a voice command issued by a user for realizing control of the intelligent household appliance. Illustratively, the intelligent household electrical appliance is provided with a sound collection unit which collects sound in the environment where the intelligent household electrical appliance is located and generates digitized sound information. The voice information comprises voice irrelevant to the control command, information corresponding to background noise and first voice information relevant to the control command.
Further, the first voice message includes a trigger keyword, which may be one or more words or one or more phrases, where the trigger keyword corresponds to a specific device function, for example, the trigger keyword a corresponds to a heating starting function of the intelligent water heater; the triggering keyword B corresponds to the heating-off function of the intelligent water heater, and according to the triggering keyword in the first voice message, the equipment function corresponding to the triggering keyword can be realized.
Step S102, determining a semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category.
Illustratively, the device instruction model is a software functional unit preset in the intelligent home appliance, and the device instruction model is capable of determining a semantic category corresponding to the voice information by accepting the voice information. Further, the semantic category refers to category information for describing functions of the smart home device, for example. Specifically, in one possible implementation, the semantic category may be identification information, such as "# 001", "# 002", etc., each identification information corresponding to one of the device functions, such as "# 001" corresponding to turning on the heating function and "# 002" corresponding to turning off the heating function. Of course, it is understood that the semantic categories may also have other implementations, such as words, numbers, letters, symbols, and combinations thereof, and the representation of the semantic categories is not specifically limited herein.
Further, the device command model characterizes different semantic categories, each semantic type corresponding to a device function. Fig. 3 is a schematic diagram of an apparatus instruction model provided in an embodiment of the present application, and as shown in fig. 3, each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category, so that each apparatus function corresponds to a plurality of trigger keywords, and a one-to-many relationship exists between the apparatus function and the trigger keywords. The device instruction model can characterize a mapping relationship between the device function and the plurality of trigger keywords. The first voice information comprises trigger keywords, and after the first voice information is input into the equipment instruction model, semantic categories corresponding to the trigger keywords can be determined according to the mapping relation between the equipment functions represented by the equipment instruction model and the trigger keywords.
And step S103, determining and executing the device function corresponding to the semantic category according to the semantic category.
Specifically, the semantic category corresponds to a specific device function, and the device function corresponding to the semantic category may be determined and executed according to a function mapping table preset in the intelligent household appliance and used for representing a mapping relationship between the semantic category and the device function, where, for example, the function mapping table corresponds to device identification information, and intelligent household appliances with different identification information have different function mapping tables, and the identification information may be, for example, a product model, a product brand, and the like, and is not described here any more.
In the embodiment, first voice information input by a user is acquired, wherein the first voice information comprises a trigger keyword; determining a semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category; according to the semantic type, the equipment function corresponding to the semantic type is determined and executed, and the semantic type corresponding to the voice information input by the user can be determined according to the instruction model information, so that the intelligent household appliance can determine and execute the corresponding function according to the semantic type, the limitation that the user can only use a fixed voice instruction when performing voice control is avoided, and the voice control flexibility and the human-computer interaction efficiency of the intelligent household appliance are improved.
Fig. 4 is a flowchart of a voice control method applied to an intelligent home appliance according to another embodiment of the present application, and as shown in fig. 4, the voice control method applied to the intelligent home appliance according to the present embodiment further details step S102 on the basis of the voice control method applied to the intelligent home appliance according to the embodiment shown in fig. 2, and then the voice control method applied to the intelligent home appliance according to the present embodiment includes the following steps:
step S201, acquiring first voice information input by a user, where the first voice information includes a trigger keyword.
Step S202, according to the first voice information, determining user identification information.
Illustratively, the first voice information includes voiceprint information. Specifically, different users have different vocalization characteristics, and therefore, different users send first voice messages with different voiceprint information. Further, through the voiceprint information, different users who uttered the first voice information can be identified. Specifically, in a possible implementation manner, a voice recognition model is preset locally in the intelligent water heater, and the voice recognition model can perform voiceprint recognition on the first voice information and determine a voiceprint feature of the first voice information. The voiceprint feature can be a feature matrix output by the speech recognition model for characterizing a difference between the first speech information. The voiceprint feature and the user identification information have a specific mapping relationship, and the mapping relationship can be determined through a preset user voice mapping relationship table, which is not described herein again.
Further, the speech recognition model may be a neural network model for speech recognition obtained by training, for example. In one possible implementation manner, the intelligent water heater is further communicated with the cloud server, and the intelligent water heater performs speech recognition model training by accepting a speech sample input by a user and uploading the speech sample to the cloud server, wherein the speech sample is, for example, first speech information. After the cloud server trains the voice recognition model according to the voice sample uploaded by the intelligent water heater to be convergent, the voice recognition model is issued to the intelligent water heater, and the intelligent water heater conducts voiceprint recognition by using the voice recognition model to obtain voiceprint characteristics of the first voice information.
Step S203, according to a preset semantic recognition model, performing semantic recognition on first voice information corresponding to user identification information to obtain a trigger keyword; the semantic recognition model is used for converting voice information corresponding to different user identification information into trigger keywords.
Exemplarily, in the process of controlling the intelligent household electrical appliance through the voice instruction, due to the language habits of different users and the difference of voice characteristics, the difficulty is high, the accuracy is low, or the time consumption of the recognition process is long because the obtained voice information is used for recognizing the trigger keywords. As described above, the voice control process of the intelligent home appliance is different from that of a common software-based voice assistant, and has higher accuracy requirement and real-time requirement. For example, when a smart home appliance having a heating function is controlled by voice, inaccurate instructions and time delay may cause a safety problem for a user.
Therefore, exemplarily, the semantic recognition model includes a plurality of submodels, each submodel corresponds to a method for converting voice information into a trigger keyword, the semantic recognition model has two input parameters, which are user identification information and first voice information, the corresponding submodel is determined according to the user identification information, and the trigger keyword corresponding to the user identification information is obtained by recognizing the first voice information according to the submodel. In this embodiment, the first voice information is processed by different sub-models through different user identification information, so that the problem of a wrong recognition of the triggering keyword caused by the accent problem can be solved, and the recognition accuracy of the voice instruction sent by the user is improved.
And step S204, determining semantic categories corresponding to the triggering keywords according to the equipment instruction model.
Illustratively, the device instruction model includes a many-to-one mapping relationship between trigger keywords and semantic categories, for example, according to the device instruction model, three keywords, namely "turn on", "start up", and "turn on", correspond to a semantic category "# 001", which indicates that the heating function of the intelligent water heater is turned on; the three keywords of 'temperature rise', 'one hot spot' and 'too cold' correspond to a semantic category '# 002', and the semantic category represents that the heating power of the intelligent water heater is improved. Each semantic category corresponds to one equipment function, after the semantic category to which the trigger keyword belongs is determined, the corresponding equipment function can be determined, and each semantic category corresponds to a plurality of trigger keywords, so that the corresponding equipment function can be triggered no matter which trigger keyword is used by a user, and the efficiency of man-machine interaction is improved.
Step S205, a confirmation voice is broadcasted to the user, and the confirmation voice comprises the device function name corresponding to the semantic category.
Step S206, after receiving the confirmation of the user, executing the device function corresponding to the semantic category.
After the semantic category is determined, which corresponds to the determined corresponding device function, as described above, in order to further improve the use safety of the intelligent home appliance, after the semantic category is obtained, the device function name corresponding to the semantic category is played to the user, for example, through a sound generating unit arranged on the intelligent home appliance or a sound generating device connected to the intelligent home appliance, so as to confirm whether the operation is performed or not to the user, and avoid that the voice command is recognized incorrectly to cause misoperation.
The method provided in this embodiment is described below with a more specific embodiment:
in the application scene of controlling the intelligent water heater through voice by a user, the user sends a voice instruction to the intelligent water heater to turn on the water heater, after receiving first voice information corresponding to the voice instruction, the intelligent water heater recognizes the identity of the user through a voice recognition model, determines that user identification information is ' user _01 ', inputs the ' user _01 ' and the first voice information into a semantic recognition model, recognizes that a trigger keyword corresponding to the first voice information is ' on ', determines that a corresponding semantic category is ' 001 ' through an equipment instruction model, and then determines and broadcasts confirmation information corresponding to the semantic category ' 001 ' to the user, such as ' do you want to start the intelligent water heater to heat water? ". The user confirms this voice broadcast, and intelligent water heater carries out this equipment function according to user's response result, or cancels and carries out this equipment function.
In this embodiment, the implementation manner of step 201 is the same as the implementation manner of step S101 in the embodiment shown in fig. 2 of this application, and is not described in detail here.
In the embodiment, the user identification information corresponding to the first voice information is determined, the trigger keywords in the first voice information are identified according to the user identification information, the identification accuracy is improved, the man-machine interaction efficiency is improved, the confirmation voice is broadcasted to the user after the semantic category is determined according to the trigger keywords, the accuracy of voice control of the user on the intelligent household appliance is improved, and the use safety of the device is improved.
Fig. 5 is a flowchart of a voice control method applied to an intelligent household electrical appliance according to still another embodiment of the present application, and as shown in fig. 5, the voice control method applied to an intelligent household electrical appliance according to this embodiment adds a step of acquiring a device instruction model semantic recognition model by an intelligent household electrical appliance on the basis of the voice control method applied to an intelligent household electrical appliance according to the embodiment shown in fig. 4, so that the voice control method applied to an intelligent household electrical appliance according to this embodiment includes the following steps:
step S301, according to the identification information of the intelligent household appliance, acquiring an appliance instruction model of the intelligent household appliance from the cloud server, and acquiring a semantic recognition model corresponding to the appliance instruction model.
The identification information of the smart home device is, for example, an identification capable of distinguishing smart home devices having different device functions, such as a model identification of the smart home device, a software version number of the smart home device, a serial number of the smart home device, and the like. Because different intelligent household electrical appliances have different functions, for example, the device a has three functions a, B and c, and the device B has only two functions a and B, the semantic type corresponding to the function c is not included in the device instruction model corresponding to the device B. The device instruction model of the intelligent household appliance is generated, set and modified in the cloud server, and is configured in the intelligent household appliance according to the identification information of the intelligent household appliance through a network, and the intelligent household appliance performs off-line recognition of semantic types by using the device instruction model matched with the intelligent household appliance, so that the recognition precision and the recognition speed can be improved.
On the basis, the intelligent household appliance obtains the semantic recognition model corresponding to the equipment instruction model from the cloud server, the applicable range of the model is further limited, the semantic recognition model can recognize the voice instruction sent by the user only in the instruction set range covered by the equipment instruction model, the misjudgment rate is further reduced, and the recognition precision and the recognition speed are improved.
In the embodiment, the intelligent household appliance acquires the device instruction model and the corresponding semantic recognition model from the cloud server, and performs recognition of the voice control instruction of the user on a local off-line basis, so that the recognition precision and recognition speed of the voice instruction are improved, and the use safety of the device is improved.
Step S302, first voice information input by a user is obtained, wherein the first voice information comprises a trigger keyword.
Step S303, determining user identification information according to the first voice information.
Step S304, according to the semantic recognition model, performing semantic recognition on the first voice information corresponding to the user identification information to obtain a trigger keyword.
Step S305, determining semantic categories corresponding to the triggering keywords according to the equipment instruction model.
And step S306, broadcasting confirmation voice to the user, wherein the confirmation voice comprises the equipment function name corresponding to the semantic category.
Step S307, after receiving the confirmation of the user, executes the device function corresponding to the semantic category.
Step S308, according to the first voice information and the execution result of the equipment function, generating instruction identification verification information.
Step S309, uploading instruction identification verification information to the cloud server, wherein the instruction identification verification information is used for correcting the equipment instruction model.
After the confirmation voice is played to the user, according to the confirmation information of the user, the intelligent household appliance may execute or not execute the function of the appliance, where the execution result is equivalent to the mark of the recognition result of the first voice information in the above step, that is, if the first voice information is recognized accurately, the corresponding function is executed; and if the first voice information is not accurately identified, the corresponding function is not executed. Therefore, according to the first voice information and the execution result of the equipment function, verification information for correcting the model, namely instruction identification verification information is generated and uploaded to the cloud server, so that the cloud server can correct the equipment instruction model and/or the semantic identification model according to the instruction identification verification information, and the recognition rate of the voice instruction is improved.
In this embodiment, the implementation manners of steps S302 to S307 are the same as the implementation manners of steps S201 to S206 in the embodiment shown in fig. 4 of this application, and are not described again.
It should be noted that the voice control method applied to the intelligent household electrical appliance provided in this embodiment may also be applied to the voice control method applied to the intelligent household electrical appliance provided in the embodiment shown in fig. 2, that is, a step of acquiring the device instruction model by the intelligent household electrical appliance is added, a specific implementation manner of this step is the same as the step of acquiring the device instruction model in step S301 in this embodiment, and details of the implementation manner are not described here.
Fig. 6 is a schematic structural diagram of a voice control apparatus applied to an intelligent home appliance according to an embodiment of the present application, and as shown in fig. 6, the voice control apparatus 4 applied to an intelligent home appliance according to the present embodiment includes:
the obtaining module 41 is configured to obtain first voice information input by a user, where the first voice information includes a trigger keyword.
The determining module 42 is configured to determine a semantic category corresponding to the first voice information according to a preset device instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category.
And the execution module 43 is used for determining and executing the device function corresponding to the semantic category according to the semantic category.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the determining module 42 is specifically configured to: performing semantic recognition on the first voice information to obtain a triggering keyword; and determining semantic categories corresponding to the triggering keywords according to the equipment instruction model.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the determining module 42 is further configured to: determining user identification information according to the first voice information; when performing semantic recognition on the first voice information and obtaining the trigger keyword, the determining module 42 is specifically configured to:
according to a preset semantic recognition model, performing semantic recognition on first voice information corresponding to user identification information to obtain a trigger keyword; the semantic recognition model is used for converting voice information corresponding to different user identification information into trigger keywords.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, after determining the semantic category corresponding to the first voice information, the executing module 43 is further configured to:
broadcasting a confirmation voice to a user, wherein the confirmation voice comprises a device function name corresponding to the semantic category;
and after receiving the confirmation of the user, executing the equipment function corresponding to the semantic category.
The obtaining module 41, the determining module 42 and the executing module 43 are connected in sequence. The voice control apparatus 4 applied to the intelligent home appliance provided in this embodiment may execute the technical solutions of the method embodiments shown in fig. 2 and fig. 4, and the implementation principles and technical effects are similar, and are not described herein again.
Fig. 7 is a schematic structural diagram of a voice control apparatus applied to an intelligent home appliance according to another embodiment of the present application, and as shown in fig. 7, a transceiver module 51 is added to the voice control apparatus 5 applied to an intelligent home appliance, based on the voice control apparatus 4 applied to an intelligent home appliance shown in fig. 6, for:
and acquiring a device instruction model of the intelligent household appliance from the cloud server according to the identification information of the intelligent household appliance.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the transceiver module 51 is further configured to:
and acquiring a semantic recognition model corresponding to the equipment instruction model from the cloud service according to the identification information of the intelligent household appliance.
In the above preferred technical solution applied to the voice control apparatus of the intelligent household electrical appliance, the transceiver module 51 is further configured to:
generating instruction identification verification information according to the first voice information and the execution result of the equipment function; and uploading the instruction identification verification information to the cloud server, wherein the instruction identification verification information is used for correcting the equipment instruction model.
The transceiver module 51 is connected to the determination module 42. The voice control apparatus 5 applied to the intelligent home appliance provided in this embodiment may implement the technical solution of the method embodiment shown in fig. 5, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 8 is a schematic diagram of an intelligent home device according to an embodiment of the present application, and as shown in fig. 8, an intelligent home device 6 according to this embodiment includes: memory 61, processor 62 and computer programs.
The computer program is stored in the memory 61 and configured to be executed by the processor 62 to implement the voice control method applied to the intelligent home appliance according to any one of the embodiments corresponding to fig. 2 to 5 of the present application.
Wherein the memory 61 and the processor 62 are connected by a bus 63.
The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 2 to fig. 5 can be understood, and are not described in detail herein.
An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the voice control method for an intelligent home appliance provided in any one of the embodiments corresponding to fig. 2 to fig. 5 of the present application.
The computer readable storage medium may be, among others, ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (10)
1. A voice control method applied to intelligent household appliances is characterized by comprising the following steps:
acquiring first voice information input by a user, wherein the first voice information comprises a trigger keyword;
determining a semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category;
and determining and executing equipment functions corresponding to the semantic categories according to the semantic categories.
2. The method according to claim 1, wherein determining the semantic category corresponding to the first speech information according to a preset device instruction model comprises:
performing semantic recognition on the first voice information to obtain a triggering keyword;
and determining semantic categories corresponding to the triggering keywords according to the equipment instruction model.
3. The method according to claim 2, wherein determining the semantic category corresponding to the first speech information according to a preset device instruction model, further comprises:
determining user identification information according to the first voice information;
performing semantic recognition on the first voice information to obtain a triggering keyword, including:
according to a preset semantic recognition model, performing semantic recognition on first voice information corresponding to the user identification information to obtain a trigger keyword; the semantic recognition model is used for converting voice information corresponding to different user identification information into the triggering keyword.
4. The method according to claim 1, further comprising, after determining the semantic category corresponding to the first speech information:
broadcasting a confirmation voice to a user, wherein the confirmation voice comprises a device function name corresponding to the semantic category;
and after receiving the confirmation of the user, executing the equipment function corresponding to the semantic category.
5. The method according to any one of claims 1-4, further comprising:
and acquiring a device instruction model of the intelligent household appliance from a cloud server according to the identification information of the intelligent household appliance.
6. The method of claim 5, further comprising:
and acquiring a semantic recognition model corresponding to the equipment instruction model from a cloud service according to the identification information of the intelligent household electrical appliance.
7. The method of claim 5, further comprising:
generating instruction identification verification information according to the first voice information and the execution result of the equipment function;
uploading the instruction identification verification information to the cloud server, wherein the instruction identification verification information is used for correcting the equipment instruction model.
8. The utility model provides a be applied to intelligent household electrical appliances's voice control device which characterized in that, the device includes:
the device comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring first voice information input by a user, and the first voice information comprises a trigger keyword;
the determining module is used for determining the semantic category corresponding to the first voice information according to a preset equipment instruction model; the device instruction model is used for representing different semantic categories, and each semantic category corresponds to a plurality of trigger keywords belonging to the semantic category;
and the execution module is used for determining and executing the equipment function corresponding to the semantic category according to the semantic category.
9. An intelligent home appliance device, comprising: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the voice control method applied to the intelligent home appliance according to any one of claims 1 to 7.
10. A computer-readable storage medium, wherein computer-executable instructions are stored in the computer-readable storage medium, and when executed by a processor, the computer-executable instructions are used for implementing the voice control method applied to an intelligent home appliance according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011138266.4A CN112786040A (en) | 2020-10-22 | 2020-10-22 | Voice control method, device and equipment applied to intelligent household electrical appliance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011138266.4A CN112786040A (en) | 2020-10-22 | 2020-10-22 | Voice control method, device and equipment applied to intelligent household electrical appliance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112786040A true CN112786040A (en) | 2021-05-11 |
Family
ID=75750464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011138266.4A Pending CN112786040A (en) | 2020-10-22 | 2020-10-22 | Voice control method, device and equipment applied to intelligent household electrical appliance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112786040A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581959A (en) * | 2020-12-15 | 2021-03-30 | 四川虹美智能科技有限公司 | Intelligent device control method and system and voice server |
| CN113506565A (en) * | 2021-07-12 | 2021-10-15 | 北京捷通华声科技股份有限公司 | Speech recognition method, speech recognition device, computer-readable storage medium and processor |
| CN113593582A (en) * | 2021-06-24 | 2021-11-02 | 青岛海尔科技有限公司 | Control method and device of intelligent device, storage medium and electronic device |
| CN114489437A (en) * | 2022-01-14 | 2022-05-13 | 深圳优美创新科技有限公司 | Smart watch, control method thereof and computer-readable storage medium |
| CN114882883A (en) * | 2022-05-31 | 2022-08-09 | 四川虹美智能科技有限公司 | Intelligent equipment control method, device and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106571140A (en) * | 2016-11-14 | 2017-04-19 | Tcl集团股份有限公司 | Electrical appliance intelligent control method based on voice meaning and electrical appliance intelligent control system thereof |
| US20170186427A1 (en) * | 2015-04-22 | 2017-06-29 | Google Inc. | Developer voice actions system |
| CN107610702A (en) * | 2017-09-22 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Terminal device standby wakeup method, apparatus and computer equipment |
| CN108133707A (en) * | 2017-11-30 | 2018-06-08 | 百度在线网络技术（北京）有限公司 | A kind of content share method and system |
| CN110286599A (en) * | 2019-06-28 | 2019-09-27 | 成都驰通数码系统有限公司 | A kind of intelligent appliance remote control method and system based on speech recognition |
| CN110634472A (en) * | 2018-06-21 | 2019-12-31 | 中兴通讯股份有限公司 | Voice recognition method, server and computer readable storage medium |
| CN110808037A (en) * | 2019-11-14 | 2020-02-18 | 广东美的制冷设备有限公司 | Voice control method and device, household appliance and storage medium |
-
2020
- 2020-10-22 CN CN202011138266.4A patent/CN112786040A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170186427A1 (en) * | 2015-04-22 | 2017-06-29 | Google Inc. | Developer voice actions system |
| CN106571140A (en) * | 2016-11-14 | 2017-04-19 | Tcl集团股份有限公司 | Electrical appliance intelligent control method based on voice meaning and electrical appliance intelligent control system thereof |
| CN107610702A (en) * | 2017-09-22 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Terminal device standby wakeup method, apparatus and computer equipment |
| CN108133707A (en) * | 2017-11-30 | 2018-06-08 | 百度在线网络技术（北京）有限公司 | A kind of content share method and system |
| CN110634472A (en) * | 2018-06-21 | 2019-12-31 | 中兴通讯股份有限公司 | Voice recognition method, server and computer readable storage medium |
| CN110286599A (en) * | 2019-06-28 | 2019-09-27 | 成都驰通数码系统有限公司 | A kind of intelligent appliance remote control method and system based on speech recognition |
| CN110808037A (en) * | 2019-11-14 | 2020-02-18 | 广东美的制冷设备有限公司 | Voice control method and device, household appliance and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112581959A (en) * | 2020-12-15 | 2021-03-30 | 四川虹美智能科技有限公司 | Intelligent device control method and system and voice server |
| CN113593582A (en) * | 2021-06-24 | 2021-11-02 | 青岛海尔科技有限公司 | Control method and device of intelligent device, storage medium and electronic device |
| CN113506565A (en) * | 2021-07-12 | 2021-10-15 | 北京捷通华声科技股份有限公司 | Speech recognition method, speech recognition device, computer-readable storage medium and processor |
| CN114489437A (en) * | 2022-01-14 | 2022-05-13 | 深圳优美创新科技有限公司 | Smart watch, control method thereof and computer-readable storage medium |
| CN114489437B (en) * | 2022-01-14 | 2024-03-19 | 深圳优美创新科技有限公司 | Smart watch, control method thereof and computer readable storage medium |
| CN114882883A (en) * | 2022-05-31 | 2022-08-09 | 四川虹美智能科技有限公司 | Intelligent equipment control method, device and system |
| CN114882883B (en) * | 2022-05-31 | 2023-07-25 | 合肥长虹美菱生活电器有限公司 | Intelligent device control method, device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112786040A (en) | Voice control method, device and equipment applied to intelligent household electrical appliance | |
| CN106558310B (en) | Virtual reality voice control method and device | |
| CN107544272B (en) | Terminal control method, device and storage medium | |
| CN108665897B (en) | Electric appliance control method and device, storage medium and server | |
| CN107220532B (en) | Method and apparatus for recognizing user identity through voice | |
| CN107199971A (en) | Vehicle-mounted voice exchange method, terminal and computer-readable recording medium | |
| CN103578472A (en) | Method and device for controlling electrical equipment | |
| CN105446159A (en) | Intelligent household system and data processing method thereof | |
| CN111197841A (en) | Control method, control device, remote control terminal, air conditioner, server and storage medium | |
| CN109346069A (en) | A kind of interactive system and device based on artificial intelligence | |
| CN110942773A (en) | Method and device for controlling intelligent household equipment through voice | |
| CN107479400A (en) | Control method, device, home appliance and the readable storage medium storing program for executing of home appliance | |
| WO2021082131A1 (en) | Air conditioning device, and temperature control method and apparatus | |
| US20090018818A1 (en) | Operating device for natural language input | |
| CN104978959A (en) | Voice control method and system | |
| CN112270926B (en) | After-sales service method of environment adjusting equipment and after-sales service equipment | |
| CN107274899B (en) | Air conditioner voice control method and device, air conditioner and readable storage medium | |
| CN113506568B (en) | Central control and intelligent equipment control method | |
| CN112912955B (en) | Electronic device and system for providing speech recognition based services | |
| CN205620724U (en) | Intelligence pronunciation remote control system | |
| CN111583921A (en) | Voice control method, device, computer equipment and storage medium | |
| CN107449109B (en) | Air conditioner voice control method and device, air conditioner and readable storage medium | |
| CN106843882B (en) | Information processing method and device and information processing system | |
| CN112634897A (en) | Equipment awakening method and device, storage medium and electronic device | |
| CN110754948B (en) | Intention identification method in cooking process and intelligent cooking equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210511 |