CN109343481B - Method and device for controlling device - Google Patents
Method and device for controlling device Download PDFInfo
- Publication number
- CN109343481B CN109343481B CN201811125949.9A CN201811125949A CN109343481B CN 109343481 B CN109343481 B CN 109343481B CN 201811125949 A CN201811125949 A CN 201811125949A CN 109343481 B CN109343481 B CN 109343481B
- Authority
- CN
- China
- Prior art keywords
- user
- signal source
- source sample
- noise signal
- intelligent household
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001914 filtration Methods 0.000 claims description 12
- 230000001815 facial effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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] or computer integrated manufacturing [CIM]
-
- 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
- G05B15/00—Systems controlled by a computer
- G05B15/02—Systems controlled by a computer electric
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Selective Calling Equipment (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a method and equipment for controlling equipment, which are used for solving the problem that the accuracy of analyzing and determining a user control voice instruction is not high because a voice recognition model of an intelligent home system in the prior art cannot effectively filter interference signals. In the embodiment of the invention, after the voice control signal of the user for the intelligent household equipment is obtained and the user is determined to be the control user corresponding to the intelligent household equipment, the interference of the voice control signal is filtered according to the noise signal source sample and the control signal source sample in the voice recognition model of the intelligent household equipment; and then the intelligent household equipment is controlled. Therefore, before the voice control instruction of the user is analyzed and recognized, the interference of the voice control signal is filtered according to the operation noise signal source sample, the user noise signal source sample and the user control signal source sample in the voice recognition model of the intelligent household equipment, and the accuracy of analyzing and determining the user control voice instruction is improved.
Description
Technical Field
The present invention relates to the field of wireless communications technologies, and in particular, to a method and a device for controlling a device.
Background
The intelligent home is an ecosystem which takes a house as a platform and connects various devices in the house together through the Internet of things technology to realize intellectualization. The intelligent video interphone has the functions of intelligent light control, intelligent electric appliance control, a security monitoring system, intelligent background music, intelligent video sharing, a visual intercom system, a home theater system and the like.
The intelligent home integrates facilities related to home life by utilizing a comprehensive wiring technology, a network communication technology, a safety precaution technology, an automatic control technology and an audio and video technology, constructs an efficient management system for residential facilities and family schedule affairs, improves home safety, convenience, comfortableness and artistry, and realizes an environment-friendly and energy-saving living environment.
In the existing intelligent home environment, when a target user controls equipment in a functional furniture system through voice, an intelligent home system server directly analyzes and extracts a control voice instruction of the user from collected voice information containing the control voice instruction, and controls corresponding intelligent home equipment according to the determined control voice instruction. However, in daily furniture life, a household is usually configured with multiple smart home devices, and a household usually has multiple users, so that the noise generated by the smart home devices in an operating state and the uncontrolled users can make the voice information collected by the server very complicated, and the voice command extraction is directly controlled, and the accuracy of analyzing and recognizing the voice command controlled by the user is not high due to the interference of the noise.
In summary, the speech recognition model of the existing smart home system cannot effectively filter out the interference signal, so that the accuracy of analyzing and determining the user control speech command is not high.
Disclosure of Invention
The invention provides a method and equipment for controlling equipment, which are used for solving the problem that the accuracy of analyzing and determining a user control voice instruction is not high because a voice recognition model of an intelligent home system in the prior art cannot effectively filter interference signals.
The embodiment of the invention provides a method for controlling equipment, which comprises the following steps:
acquiring a voice control signal of a user for the intelligent household equipment; then, after the user is determined to be the control user corresponding to the intelligent home equipment according to the user information, filtering the interference of the voice control signal according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment; and controlling the intelligent household equipment according to the voice control signal after the interference is filtered.
According to the method, after a voice control signal of a user for the intelligent home equipment is obtained and the user is determined to be a control user corresponding to the intelligent home equipment according to user information, interference of the voice control signal is filtered according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment; and controlling the intelligent household equipment according to the voice control signal after the interference is filtered. Therefore, before the collected voice control signal of the intelligent household equipment is analyzed and recognized, the interference of the voice control signal is filtered according to the operation noise signal source sample, the user noise signal source sample and the user control signal source sample in the voice recognition model of the intelligent household equipment, and the accuracy of analyzing and determining the user control voice command is improved.
In a possible implementation manner, whether the user is a control user corresponding to the smart home device is judged by the following manner:
judging whether user information of the user exists in the user information corresponding to the control user of the intelligent household equipment, if so, determining that the user is the control user corresponding to the intelligent household equipment, otherwise, determining that the user is not the control user corresponding to the intelligent household equipment;
according to the method, when whether the user is the control user corresponding to the intelligent home equipment is judged, the acquired user information of the user is matched with the user information corresponding to the control user of the intelligent home equipment, and when the user information corresponding to the control user of the intelligent home equipment contains the user information of the user, the user is determined to be the control user corresponding to the intelligent home equipment; otherwise, determining that the user is not the control user corresponding to the intelligent household equipment. Therefore, after the user sending the instruction is determined to be the control user of the intelligent household equipment, the intelligent household equipment is controlled according to the processed voice control instruction, and the safety is improved to a certain extent.
The user information is voiceprint information and/or a face image of a user.
According to the method, the user sending the voice control instruction is distinguished through the voiceprint information, the face image, the voiceprint information and the face image of the user, so that the user sending the instruction is judged to be the control user of the intelligent home equipment.
In one possible implementation, the speech recognition model of the smart home device is generated by:
determining an operation noise signal source sample of the intelligent home equipment in an operation state, and determining a user noise signal source sample and a user control signal source sample of the intelligent home equipment in a non-operation state;
and generating a voice recognition model corresponding to the smart home based on the operation noise signal source sample, the user noise signal source sample and the user control signal source sample.
According to the method, an operation noise signal source sample of the intelligent household equipment in an operation state is determined when the intelligent household equipment is in the operation state, and a user noise signal source sample and a user control signal source sample are determined when the intelligent equipment is not in the operation state; and generating a voice recognition model corresponding to the smart home based on the operation noise signal source sample, the user noise signal source sample and the user control signal source sample. And then the interference signals in the collected voice control signals are filtered through the established voice recognition model, so that the difficulty of analyzing and recognizing the voice control instruction of the user is reduced, and the accuracy of analyzing and determining the voice control instruction of the user is improved.
In a possible implementation manner, the determining a user noise signal source sample and a user control signal source sample of the smart home device in a non-operating state includes:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
According to the method, a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-operation state are determined from collected signal sources according to a user sample voice source database. Therefore, after the control user is determined, the noise of other users can be filtered according to the user noise signal source sample, so that the difficulty of the voice control instruction is reduced, and the accuracy of analyzing and determining the user control voice instruction is improved.
In a possible implementation manner, the determining an operating noise signal source sample of the smart home device in an operating state includes:
if a plurality of intelligent household devices exist, respectively determining an operation noise signal source sample of each intelligent household device in an independent operation state, combining the plurality of intelligent household devices, and respectively determining an operation noise signal source sample of each intelligent household device combination in an operation state;
and taking the set containing each determined running noise signal source sample as a running noise signal source sample of the intelligent household equipment in a running state.
According to the method, firstly, running noise signal source samples of the intelligent household equipment in the independent running state are determined, meanwhile, running noise signal source samples of the intelligent household equipment in the combined backward running state are determined, and a set containing each determined running noise signal source sample is used as a running noise signal source sample of the intelligent household equipment in the running state. So can determine the running noise signal source sample under the running state of intelligent home equipment under all combinations, and then when the user passes through speech control intelligent equipment, can eliminate the noise that the intelligent equipment operation produced in the signal source of gathering according to the running noise signal source sample of intelligent home equipment under the running state of confirming for the composition in the signal source of gathering becomes simple, thereby reduce the degree of difficulty that the analysis acquireed the control speech information of gathering, and then improve the accuracy that the analysis confirmed user control speech instruction.
In a second aspect, an embodiment of the present invention further provides an apparatus for controlling an apparatus, where the apparatus includes: at least one processor and at least one memory, the apparatus having functionality to implement the embodiments of the first aspect described above.
In a third aspect, an embodiment of the present invention further provides an apparatus for controlling an apparatus, where the apparatus includes an obtaining module, a filtering module, and a control module, and the apparatus has functions of implementing the embodiments of the first aspect.
In addition, for technical effects brought by any one implementation manner of the second aspect to the third aspect, reference may be made to technical effects brought by different implementation manners of the first aspect, and details are not described here.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a method for controlling a device according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a first control device provided in an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a second control device provided in the embodiment of the present invention.
Detailed Description
The invention provides a method for controlling equipment, which relates to a voice recognition template, wherein the voice recognition template divides collected voice signal sources into three categories, and comprises the following steps: a running noisy signal source sample, a user noisy signal source sample, and a user control signal source sample.
In specific implementation, the intelligent equipment server acquires a voice control signal of a user for the intelligent household equipment; then, after the user is determined to be the control user corresponding to the intelligent home equipment according to the user information, filtering the interference of the voice control signal according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment; and controlling the intelligent household equipment according to the voice control signal after the interference is filtered. Therefore, the interference signals in the voice control signals can be filtered to a certain extent, and the accuracy of analyzing and determining the voice command controlled by the user is improved.
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a method for generating a speech recognition model, where the method includes:
and step 102, controlling the intelligent household equipment according to the voice control signal after the interference is filtered.
According to the method, after a voice control signal of a user for the intelligent home equipment is obtained and the user is determined to be a control user corresponding to the intelligent home equipment according to user information, interference of the voice control signal is filtered according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment; and controlling the intelligent household equipment according to the voice control signal after the interference is filtered. Therefore, before the collected voice control signal of the intelligent household equipment is analyzed and recognized, the interference of the voice control signal is filtered according to the operation noise signal source sample, the user noise signal source sample and the user control signal source sample in the voice recognition model of the intelligent household equipment, and the accuracy of analyzing and determining the user control voice command is improved.
The following will describe in detail embodiments of the present invention.
According to the scheme provided by the embodiment of the invention, the intelligent household equipment is controlled, and then a voice recognition template for filtering interference noise needs to be constructed firstly.
When the voice recognition template is established, the running noise of the intelligent household equipment and the noise of an uncontrolled user need to be collected respectively.
Firstly, determining an operation noise signal source sample of the intelligent household equipment in an operation state.
Before specific operation, all the intelligent home devices need to be configured in a networking manner, so that the intelligent home system server can regulate and control each intelligent home device.
And then, obtaining an operation noise signal source sample of the intelligent household equipment in the operation state in the current household environment.
If only one intelligent household device exists in the current household environment, only the running noise signal source sample of the intelligent household device in the independent running state needs to be collected and used as the running noise signal source sample of the intelligent household device in the running state.
However, nowadays, a plurality of smart home devices are generally available in home life, rather than only one smart home device.
In this way, the following method is adopted to determine the operating noise signal source sample of the smart home device in the operating state.
Optionally, if there are multiple pieces of smart home equipment, respectively determining an operating noise signal source sample of each piece of smart home equipment in an independent operating state, combining the multiple pieces of smart home equipment, and respectively determining an operating noise signal source sample of each piece of smart home equipment combination in an operating state; and taking the set containing each determined running noise signal source sample as a running noise signal source sample of the intelligent household equipment in a running state.
According to the method, firstly, running noise signal source samples of the intelligent household equipment in the independent running state are determined, meanwhile, running noise signal source samples of the intelligent household equipment in the combined backward running state are determined, and a set containing each determined running noise signal source sample is used as a running noise signal source sample of the intelligent household equipment in the running state. So can determine the running noise signal source sample under the running state of intelligent home equipment under all combinations, and then when the user passes through speech control intelligent equipment, can eliminate the noise that the intelligent equipment operation produced in the signal source of gathering according to the running noise signal source sample of intelligent home equipment under the running state of confirming for the composition in the signal source of gathering becomes simple, thereby reduce the degree of difficulty that the analysis acquireed the control speech information of gathering, and then improve the accuracy that the analysis confirmed user control speech instruction.
The following will illustrate how to determine the operating noise signal source sample of the smart home device in the operating state.
For example:
the current intelligent home system comprises three intelligent home devices, namely a television, an air conditioner and a refrigerator; when determining an operating noise signal source sample of the intelligent household equipment in an operating state, firstly, controlling three intelligent household equipment such as a television, an air conditioner and a refrigerator in a network, then obtaining the operating states of the television, the air conditioner and the refrigerator, and arranging and combining the television, the air conditioner and the refrigerator to obtain a set A1 ═ television }, A2 ═ air conditioner }, A3 ═ refrigerator }, A4 ═ television, air conditioner }, A5 ═ television, refrigerator }, A6 ═ air conditioner, refrigerator }, A7 ═ television, air conditioner and refrigerator }, wherein the 7 combinations are obtained; and then, sequentially collecting the operation noise signals of each intelligent household equipment combination in the operation state, and taking the set containing each determined operation noise signal source sample as the operation noise signal source sample of the intelligent household equipment in the operation state.
And after the operating noise signal source sample of the intelligent household equipment in the operating state is determined, acquiring a user noise signal source sample and a user control signal source sample.
And secondly, determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-operation state.
Based on various data that can be used to distinguish information for controlling users, only two of them will be described as examples in the embodiments of the present invention. One is the user's voiceprint type, and the other is the user's face image.
When the relevant data of the user are collected, all the intelligent household equipment are in a non-running state.
And (I) taking the voiceprint type of the user as the user information of the user.
In a specific implementation, when a sample voice database of a user is established, a control user and a non-control user need to be distinguished.
Optionally, the determining the user noise signal source sample and the user control signal source sample of the smart home device in the non-operating state includes:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
According to the method, a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-operation state are determined from collected signal sources according to a user sample voice source database. Therefore, after the control user is determined, the noise of other users can be filtered according to the user noise signal source sample, so that the difficulty of the voice control instruction is reduced, and the accuracy of analyzing and determining the user control voice instruction is improved.
In specific implementation, when it is determined that the user noise signal source sample and the user control signal source sample of the intelligent home equipment are in a non-operation state, a control user needs to be designated, so that the non-control user is determined, and the voiceprint types of the users are collected respectively.
For example: the existing users have three people: a, B and C;
when a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-operation state are determined, firstly, an A is designated as a control user, voice information of the A is collected and analyzed, and a voiceprint type of the A is determined; at the moment, a voice B and a voice C are non-control users, then voice B and voice C are respectively collected and analyzed, respective voiceprint types of the voice B and the voice C are determined, the voiceprint type of the voice A is used as the voiceprint type of the control user, the voiceprint types of the voice B and the voice C are used as the voiceprint type of the non-control user, and a binding relationship is formed;
secondly, appointing a user B as a control user, collecting and analyzing voice information of the user B, and determining the voiceprint type of the user B; at the moment, a and C are non-control users, and respectively collect and analyze voice of A and C, determine respective voiceprint types of A, B and C, use the voiceprint type of B as the voiceprint type of a control user, use the voiceprint types of A and C as the voiceprint type of the non-control users, and form a binding relationship;
finally, designating the third party as a control user, collecting and analyzing voice information of the third party, and determining the voiceprint type of the third party; at the moment, the first voice and the second voice are respectively collected and analyzed by the first user and the second user as non-control users, the respective voiceprint types of the first voice and the second voice are determined, the voiceprint type of the third user is used as the voiceprint type of the control user, the voiceprint types of the first user and the second user are used as the voiceprint type of the non-control users, and a binding relationship is formed.
Therefore, according to the user sample voice source database, a user noise signal source sample and a user control signal source sample of the intelligent household equipment in the non-operation state are determined from the collected signal sources.
And secondly, taking the face image of the user as the user information of the user.
In a specific implementation, when a sample voice database of a user is established, a control user and a non-control user need to be distinguished.
Optionally, the determining the user noise signal source sample and the user control signal source sample of the smart home device in the non-operating state includes:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
According to the method, a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-operation state are determined from collected signal sources according to a user sample voice source database. Therefore, after the control user is determined, the noise of other users can be filtered according to the user noise signal source sample, so that the difficulty of the voice control instruction is reduced, and the accuracy of analyzing and determining the user control voice instruction is improved.
In specific implementation, when it is determined that the user noise signal source sample and the user control signal source sample of the intelligent home equipment are in a non-operation state, a control user needs to be designated, so that the non-control user is determined, and the voiceprint types of the users are collected respectively.
For example: the existing users have three people: a, B and C;
when a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-operation state are determined, firstly, an A is designated as a control user, a face image of the A is shot by a camera and analyzed, and the face image feature of the A is determined; at the moment, a second user and a third user are non-control users, then the face images of the second user and the face images of the third user are shot by a camera and are analyzed, the face image characteristics of the second user and the face image characteristics of the third user are determined, the face image of the first user is used as the face image of the control user, and the voiceprint types of the second user and the third user are used as the face images of the non-control users to form a binding relationship;
secondly, a second user is designated as a control user, a face image of the second user is shot by a camera and analyzed, and the face image characteristics of the second user are determined; at the moment, a and C are non-control users, then the facial images of the A and C are shot by a camera and analyzed respectively, the facial image characteristics of the A and C are determined, the facial image of the B is used as the facial image of the control user, the voiceprint types of the A and C are used as the facial images of the non-control users, and a binding relationship is formed;
finally, designating the third user as a control user, shooting a face image of the third user through a camera, analyzing, and determining the face image characteristics of the third user; at the moment, the first and second users are non-control users, then the facial images of the first and second users are shot by a camera and are analyzed respectively, the facial image characteristics of the first and second users are determined, the facial image of the third user is used as the facial image of the control user, the facial images of the first and second users are used as the facial images of the non-control users, and a binding relationship is formed;
therefore, according to the user sample voice source database, a user noise signal source sample and a user control signal source sample of the intelligent household equipment in the non-operation state are determined from the collected signal sources.
After the speech recognition template is established, the method is applied to a speech control recognition process of the intelligent device, and the following is briefly described by way of example.
Optionally, whether the user is the control user corresponding to the smart home device is judged in the following manner:
judging whether user information of the user exists in the user information corresponding to the control user of the intelligent household equipment, if so, determining that the user is the control user corresponding to the intelligent household equipment, otherwise, determining that the user is not the control user corresponding to the intelligent household equipment;
according to the method, when whether the user is the control user corresponding to the intelligent home equipment is judged, the acquired user information of the user is matched with the user information corresponding to the control user of the intelligent home equipment, and when the user information corresponding to the control user of the intelligent home equipment contains the user information of the user, the user is determined to be the control user corresponding to the intelligent home equipment; otherwise, determining that the user is not the control user corresponding to the intelligent household equipment. Therefore, whether the user sending the instruction is the control user of the intelligent home equipment or not can be determined, and meanwhile, after the user sending the instruction is determined to be the control user of the intelligent home equipment, the intelligent home equipment is controlled according to the processed voice control instruction, so that the safety is improved to a certain extent.
When the voiceprint information of a user is used as the user information of the user, when a plurality of users send out voice control instructions, the weight evaluation can be carried out according to the collected volume of the voice control instructions of the user, the use frequency, the distance from the intelligent furniture server and the like, and then the control user is determined.
Example (c):
1. in a family with an intelligent home system, the user voiceprint type is used as user information of a user. Total three people, A, B, C respectively;
and equipped with 4 pieces of smart homes, D, E, F, G each;
at a certain moment, the equipment D and the equipment E are working, the A sends an instruction to the equipment D, the B, C does not send any instruction, the server of the intelligent home system determines the A to be a control user, the server of the intelligent home system collects the current signal source at the moment, analyzes the voiceprint type in the signal source, comparing the voice print type with the voice print type in the sample voice source database of the intelligent home device A, finding an operating noise signal source sample of the intelligent home device associated with the voice print type A in the operating state and other user noise signal source samples, then filtering the noise of the device D and the device E in the operating state according to the operating noise signal source sample of the intelligent home device in the operating state, wherein other voice print types are not found in the server analysis process of the intelligent home system, that is, in the current state, there is no other user noise signal source, so the filtering process is not performed according to the user noise signal source sample.
2. In a family with an intelligent home system, a user face image is used as user information of a user. Total three people, A, B, C respectively;
and equipped with 4 pieces of smart homes, D, E, F, G each;
at a certain moment, equipment D and equipment E are working, a camera connected with an intelligent home system server shoots a face image of the equipment B and simultaneously collects a control voice signal, the server of the intelligent home system determines that the equipment B is a control user, the server of the intelligent home system analyzes the face image in the collected signal source and compares the face image with a face image in a user sample voice source database to determine that the shot face image Y is matched with the face image of the equipment B in a user sample voice source database, then an operating noise signal source sample and other user noise signal source samples of the intelligent home equipment in an operating state related to the face image of the equipment B are searched, then noise of the equipment D and the equipment E in the operating state is filtered according to the operating noise signal source sample of the intelligent home equipment in the operating state, and other voiceprint types are not found in the server analysis process of the intelligent home system, that is, in the current state, there is no other user noise signal source, so the filtering process is not performed according to the user noise signal source sample.
Based on the same inventive concept, the embodiment of the present invention further provides a device for controlling a device, and since the device is a device for controlling the smart home device in the method in the embodiment of the present invention, and the principle of the device for solving the problem is similar to that of the method, the implementation of the device may refer to the implementation of the method, and repeated details are omitted.
As shown in fig. 2, an apparatus for controlling an apparatus according to an embodiment of the present invention includes:
at least one processor 900 and at least one memory 901, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the following:
acquiring a voice control signal of a user for the intelligent household equipment; after the user is determined to be the control user corresponding to the intelligent home equipment according to the user information, filtering the interference of the voice control signal according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment; and controlling the intelligent household equipment according to the voice control signal after the interference is filtered.
Optionally, the processor 200 is specifically configured to:
whether the user is a control user corresponding to the intelligent household equipment is judged in the following mode:
judging whether user information of the user exists in the user information corresponding to the control user of the intelligent household equipment, if so, determining that the user is the control user corresponding to the intelligent household equipment, otherwise, determining that the user is not the control user corresponding to the intelligent household equipment;
the user information is voiceprint information and/or a face image of a user.
Optionally, the processor 200 is specifically configured to:
generating a voice recognition model of the intelligent household equipment in the following way:
determining an operation noise signal source sample of the intelligent home equipment in an operation state, and determining a user noise signal source sample and a user control signal source sample of the intelligent home equipment in a non-operation state;
and generating a voice recognition model corresponding to the smart home based on the operation noise signal source sample, the user noise signal source sample and the user control signal source sample.
Optionally, the processor 200 is specifically configured to:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
Optionally, the processor 200 is specifically configured to:
if a plurality of intelligent household devices exist, respectively determining an operation noise signal source sample of each intelligent household device in an independent operation state, combining the plurality of intelligent household devices, and respectively determining an operation noise signal source sample of each intelligent household device combination in an operation state;
and taking the set containing each determined running noise signal source sample as a running noise signal source sample of the intelligent household equipment in a running state.
As shown in fig. 3, an apparatus for controlling an apparatus according to an embodiment of the present invention includes:
the acquiring module 300 is configured to acquire a voice control signal of a user for the smart home device;
the filtering module 301 is configured to, after determining that the user is a control user corresponding to the smart home device according to user information, filter interference of the voice control signal according to an operating noise signal source sample, a user noise signal source sample, and a user control signal source sample in a voice recognition model of the smart home device;
and the control module 302 is configured to control the smart home device according to the voice control signal after the interference is filtered.
Optionally, the obtaining module 300 is specifically configured to: whether the user is a control user corresponding to the intelligent household equipment is judged in the following mode:
judging whether user information of the user exists in the user information corresponding to the control user of the intelligent household equipment, if so, determining that the user is the control user corresponding to the intelligent household equipment, otherwise, determining that the user is not the control user corresponding to the intelligent household equipment;
the user information is voiceprint information and/or a face image of a user.
Optionally, the obtaining module 300 is specifically configured to: generating a voice recognition model of the intelligent household equipment in the following way:
determining an operation noise signal source sample of the intelligent home equipment in an operation state, and determining a user noise signal source sample and a user control signal source sample of the intelligent home equipment in a non-operation state;
and generating a voice recognition model corresponding to the smart home based on the operation noise signal source sample, the user noise signal source sample and the user control signal source sample.
Optionally, the obtaining module 300 is specifically configured to:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
Optionally, the obtaining module 300 is specifically configured to:
if a plurality of intelligent household devices exist, respectively determining an operation noise signal source sample of each intelligent household device in an independent operation state, combining the plurality of intelligent household devices, and respectively determining an operation noise signal source sample of each intelligent household device combination in an operation state;
and taking the set containing each determined running noise signal source sample as a running noise signal source sample of the intelligent household equipment in a running state.
The present application is described above with reference to block diagrams and/or flowchart illustrations of methods, apparatus (systems) and/or computer program products according to embodiments of the application. It will be understood that one block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, and/or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer and/or other programmable data processing apparatus, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.
Accordingly, the subject application may also be embodied in hardware and/or in software (including firmware, resident software, micro-code, etc.). Furthermore, the present application may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in connection with an instruction execution system. In the context of this application, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (6)
1. A method of controlling a device, the method comprising:
acquiring a voice control signal of a user for the intelligent household equipment;
after the user is determined to be the control user corresponding to the intelligent home equipment according to the user information, filtering the interference of the voice control signal according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment;
controlling the intelligent household equipment according to the voice control signal after the interference is filtered;
the voice recognition model of the intelligent household equipment is generated in the following mode:
determining an operation noise signal source sample of the intelligent home equipment in an operation state, and determining a user noise signal source sample and a user control signal source sample of the intelligent home equipment in a non-operation state;
generating a voice recognition model corresponding to the smart home based on the operation noise signal source sample, the user noise signal source sample and the user control signal source sample;
wherein, confirm that intelligent household equipment is at the noise signal source sample of operation under the running state, include:
if a plurality of intelligent household devices exist, respectively determining an operation noise signal source sample of each intelligent household device in an independent operation state, combining the plurality of intelligent household devices, and respectively determining an operation noise signal source sample of each intelligent household device combination in an operation state;
and taking the set containing each determined running noise signal source sample as a running noise signal source sample of the intelligent household equipment in a running state.
2. The method according to claim 1, wherein whether the user is a control user corresponding to the smart home device is judged by:
judging whether user information of the user exists in the user information corresponding to the control user of the intelligent household equipment, if so, determining that the user is the control user corresponding to the intelligent household equipment, otherwise, determining that the user is not the control user corresponding to the intelligent household equipment;
the user information is voiceprint information and/or a face image of a user.
3. The method of claim 1, wherein the determining the user noise signal source sample and the user control signal source sample of the smart home device in the non-operating state comprises:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
4. An apparatus for controlling an apparatus, characterized in that the apparatus comprises:
at least one processor and at least one memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform the following:
acquiring a voice control signal of a user for the intelligent household equipment;
after the user is determined to be the control user corresponding to the intelligent home equipment according to the user information, filtering the interference of the voice control signal according to an operation noise signal source sample, a user noise signal source sample and a user control signal source sample in a voice recognition model of the intelligent home equipment;
controlling the intelligent household equipment according to the voice control signal after the interference is filtered;
wherein the processor is specifically configured to:
generating a voice recognition model of the intelligent household equipment in the following way:
determining an operation noise signal source sample of the intelligent home equipment in an operation state, and determining a user noise signal source sample and a user control signal source sample of the intelligent home equipment in a non-operation state;
generating a voice recognition model corresponding to the smart home based on the operation noise signal source sample, the user noise signal source sample and the user control signal source sample;
wherein the processor is specifically configured to:
if a plurality of intelligent household devices exist, respectively determining an operation noise signal source sample of each intelligent household device in an independent operation state, combining the plurality of intelligent household devices, and respectively determining an operation noise signal source sample of each intelligent household device combination in an operation state;
and taking the set containing each determined running noise signal source sample as a running noise signal source sample of the intelligent household equipment in a running state.
5. The device of claim 4, wherein the processor is specifically configured to:
whether the user is a control user corresponding to the intelligent household equipment is judged in the following mode:
judging whether user information of the user exists in the user information corresponding to the control user of the intelligent household equipment, if so, determining that the user is the control user corresponding to the intelligent household equipment, otherwise, determining that the user is not the control user corresponding to the intelligent household equipment;
the user information is voiceprint information and/or a face image of a user.
6. The device of claim 4, wherein the processor is specifically configured to:
and determining a user noise signal source sample and a user control signal source sample of the intelligent household equipment in a non-running state from the collected signal sources according to a user sample voice source database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811125949.9A CN109343481B (en) | 2018-09-26 | 2018-09-26 | Method and device for controlling device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811125949.9A CN109343481B (en) | 2018-09-26 | 2018-09-26 | Method and device for controlling device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109343481A CN109343481A (en) | 2019-02-15 |
| CN109343481B true CN109343481B (en) | 2020-05-26 |
Family
ID=65307057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811125949.9A Active CN109343481B (en) | 2018-09-26 | 2018-09-26 | Method and device for controlling device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109343481B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111028829A (en) * | 2019-11-29 | 2020-04-17 | 浙江想能睡眠科技股份有限公司 | AI sleep-aiding intelligent mattress voice interaction method and system |
| CN113867158B (en) * | 2020-06-12 | 2023-10-24 | 青岛海尔电冰箱有限公司 | Kitchen appliance running state judging method, detecting device, refrigerator and readable storage medium |
| CN113808564B (en) * | 2020-06-12 | 2024-03-19 | 青岛海尔电冰箱有限公司 | Kitchen noise reduction method, refrigerator and computer readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102655006A (en) * | 2011-03-03 | 2012-09-05 | 富泰华工业（深圳）有限公司 | Voice transmission device and voice transmission method |
| CN102945669A (en) * | 2012-11-14 | 2013-02-27 | 四川长虹电器股份有限公司 | Household appliance voice control method |
| WO2016206060A1 (en) * | 2015-06-25 | 2016-12-29 | 宇龙计算机通信科技(深圳)有限公司 | Control method and control system, and smart home control center device |
| CN106412083A (en) * | 2016-10-29 | 2017-02-15 | 深圳智乐信息科技有限公司 | Method and system for visitor to control smart home |
| CN107180632A (en) * | 2017-06-19 | 2017-09-19 | 微鲸科技有限公司 | Sound control method, device and readable storage medium storing program for executing |
| CN108550366B (en) * | 2018-04-24 | 2021-04-06 | 青岛海尔科技有限公司 | Household appliance control method and device, readable storage medium and equipment |
-
2018
- 2018-09-26 CN CN201811125949.9A patent/CN109343481B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109343481A (en) | 2019-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109377995B (en) | Method and device for controlling equipment | |
| CN107135443B (en) | Signal processing method and electronic equipment | |
| CN109343481B (en) | Method and device for controlling device | |
| CN105471705B (en) | Intelligent control method, equipment and system based on instant messaging | |
| CN103529762B (en) | A kind of intelligent home furnishing control method based on sensor technology and system | |
| WO2020014899A1 (en) | Voice control method, central control device, and storage medium | |
| CN112051743A (en) | Device control method, conflict processing method, corresponding devices and electronic device | |
| CN110223690A (en) | The man-machine interaction method and device merged based on image with voice | |
| CN105045140A (en) | Method and device for intelligently controlling controlled equipment | |
| CN109974235A (en) | Control the method, apparatus and household appliance of household appliance | |
| CN104517607A (en) | Speed-controlled appliance and method of filtering noise therein | |
| CN109032039A (en) | A kind of method and device of voice control | |
| CN108917113A (en) | Assistant voice control method, device and air-conditioning | |
| CN106653020A (en) | Multi-business control method and system for smart sound and video equipment based on deep learning | |
| CN112002316A (en) | Electric appliance control method and device, storage medium and terminal | |
| CN114582318B (en) | Intelligent home control method and system based on voice recognition | |
| CN113450792A (en) | Voice control method of terminal equipment, terminal equipment and server | |
| CN108415572B (en) | Module control method and device applied to mobile terminal and storage medium | |
| WO2018023523A1 (en) | Motion and emotion recognizing home control system | |
| CN109976169B (en) | Internet television intelligent control method and system based on self-learning technology | |
| CN106997449A (en) | Robot and face identification method with face identification functions | |
| CN112417923A (en) | System, method and apparatus for controlling smart devices | |
| CN106056063A (en) | Recognition and control system of robot | |
| CN110970019A (en) | Control method and device of intelligent home system | |
| CN114627859A (en) | Method and system for recognizing electronic photo frame in offline semantic manner |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |