CN113900383A - Intelligent household equipment control method, router, intelligent household system and medium - Google Patents
Intelligent household equipment control method, router, intelligent household system and medium Download PDFInfo
- Publication number
- CN113900383A CN113900383A CN202111179669.8A CN202111179669A CN113900383A CN 113900383 A CN113900383 A CN 113900383A CN 202111179669 A CN202111179669 A CN 202111179669A CN 113900383 A CN113900383 A CN 113900383A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- router
- input information
- terminal control
- training
- 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 61
- 238000004891 communication Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims description 79
- 230000015654 memory Effects 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 description 62
- 238000005516 engineering process Methods 0.000 description 12
- 230000009471 action Effects 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 9
- 241000282414 Homo sapiens Species 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010408 sweeping Methods 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003930 cognitive ability Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- 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
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2642—Domotique, domestic, home control, automation, smart house
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)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an intelligent household equipment control method, a router, an intelligent household system and a medium, and belongs to the field of intelligent household. The router is in communication connection with at least one intelligent household device, and the method comprises the following steps: acquiring an interface calling request sent by the intelligent home equipment, wherein the interface calling request comprises input information acquired by the intelligent home equipment; calling a pre-trained terminal control model, and inputting the input information into the terminal control model to obtain a control instruction output by the terminal control model; determining target intelligent household equipment corresponding to the control instruction from at least one intelligent household equipment; and sending the control instruction to target intelligent household equipment so that the intelligent household equipment executes the operation corresponding to the control instruction. The invention provides the low-delay AI service for the intelligent household equipment, improves the intelligent level of the intelligent terminal equipment and further improves the user experience.
Description
Technical Field
The invention relates to the technical field of intelligent home, in particular to an intelligent home equipment control method, a router, an intelligent home system and a medium.
Background
In the related art, terminal equipment of the smart home system can remotely acquire an AI service from a cloud server to improve the intelligence level of the terminal equipment.
However, the delay of remotely calling the AI service from the cloud server is high, and the response to the demand of the user is not timely.
Disclosure of Invention
The invention mainly aims to provide an intelligent home device control method, a router, an intelligent home system and a medium, and aims to solve the technical problems that the delay of remotely calling an AI (Internet access) service from a cloud server is high and the response to the demand of a user is not timely in the prior art.
In order to achieve the above object, in a first aspect, the present invention provides a method for controlling smart home devices, where the method is used for a router, and the router is in communication connection with at least one smart home device, and the method includes:
acquiring an interface calling request sent by the intelligent home equipment, wherein the interface calling request comprises input information acquired by the intelligent home equipment;
calling a pre-trained terminal control model, and inputting the input information into the terminal control model to obtain a control instruction output by the terminal control model;
determining target intelligent household equipment corresponding to the control instruction from at least one intelligent household equipment;
and sending the control instruction to target intelligent household equipment so that the target intelligent household equipment executes the operation corresponding to the control instruction.
In an embodiment, before the invoking the pre-trained terminal control model, the method further includes:
and determining a terminal control model corresponding to the interface calling request from at least one terminal control model to be selected according to the interface calling request.
In an embodiment, before the obtaining of the interface call request sent by the smart home device, the method further includes:
when the intelligent home equipment is registered to the router, feeding back interface information corresponding to at least one terminal control model to be selected to the intelligent home equipment, so that when the intelligent home equipment collects the input information, target interface information is determined from the at least one interface information, and the interface calling request is generated based on the target interface information.
In an embodiment, before the inputting the input information into the terminal control model and obtaining the control instruction output by the terminal control model, the method further includes:
judging whether the current moment is within a preset training time period;
and if the input information is not in the preset training time period, executing the input information to the terminal control model to obtain a control instruction output by the terminal control model.
In an embodiment, the determining whether the current time is after a preset training time period further includes:
and if so, training the terminal control model by using the input information and/or the historical input information as training samples to obtain a new terminal control model.
In an embodiment, the training the terminal control model using the input information and/or the historical input information as training samples to obtain a new terminal control model includes:
training the terminal control model by taking the input information and/or historical input information as training samples to obtain new model parameters and a training result instruction;
determining target intelligent home equipment corresponding to the training result instruction from at least one piece of intelligent home equipment, and sending the control instruction to the target intelligent home equipment so that the intelligent home equipment executes operation corresponding to the training result instruction;
when user feedback information sent by at least one intelligent home terminal is received, the user feedback information is used as a verification set to verify the model parameters;
and if the verification result is positive feedback, updating the terminal control model according to the model parameters.
In an embodiment, if the terminal control model is trained within the preset training time period, training the terminal control model using the input information and/or the historical input information as training samples to obtain a new terminal control model, including:
if the training time is within the preset training time period, sequencing the input information and/or the historical sequencing information according to a preset data priority sequencing rule to obtain at least one sequenced training sample;
and sequentially training the corresponding terminal control models through the sequenced at least one training sample to obtain a new terminal control model.
In a second aspect, the present invention further provides a router, including: the intelligent home equipment control method comprises a memory, a processor and an intelligent home equipment control program which is stored on the memory and can run on the processor, wherein the intelligent home equipment control method program is configured to realize the intelligent home equipment control method.
In a third aspect, the present invention further provides an intelligent home system, including:
at least one smart home device; and
the router is in communication connection with at least one intelligent household device.
In a fourth aspect, the present invention further provides a computer-readable storage medium, where the computer-readable storage medium stores an intelligent home device control program, and the intelligent home device control program, when executed by a processor, implements the intelligent home device control method as described above.
The embodiment of the invention provides an intelligent household equipment control method, a router, an intelligent household system and a medium. According to the method, the abundant hardware resources such as calculation and storage on the router are fully utilized, and the AI service deployed on the router is remotely called by the intelligent household equipment, so that the low-delay AI service is provided for the intelligent household equipment. The intelligent level of the intelligent terminal equipment is improved, and further the user experience is improved.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent home system according to the present invention;
FIG. 2 is a schematic block diagram of a router of the smart home system according to the present invention;
fig. 3 is a schematic flow chart of a first embodiment of a smart home device control method according to the present invention;
fig. 4 is a flowchart illustrating a second embodiment of a method for controlling smart home devices according to the present invention;
fig. 5 is a flowchart illustrating a third embodiment of a method for controlling smart home devices according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Smart home devices such as air conditioners, washing machines or sound boxes are often limited in hardware resources such as calculation and storage, and do not have high intelligent capability. In order to improve the user experience, in the related art, the intelligent home device remotely acquires the AI service from the cloud server to improve the intelligent level of the intelligent home device. However, the delay of the AI service is long-distance acquired from the cloud server, and potential safety hazards of easy leakage of personal data of a user exist.
Therefore, the intelligent home equipment control method makes full use of hardware resources such as computation and storage on the router, provides low-delay AI service for the intelligent home equipment by remotely calling the AI service deployed on the router, improves the intelligence level of the intelligent terminal equipment, and further improves user experience.
The techniques involved in the implementation of the technique of the present invention will be separately described below.
Artificial Intelligence (AI), which refers to the subject of computer systems that can simulate human intelligence based on computer science and by integrating knowledge such as information theory, psychology, physiology, linguistics, logics and mathematics. At present, artificial intelligence is widely concerned by academia and industry, AI is more and more widely applied, and the AI is beyond the level of common human beings in many application fields. For example: the application of the AI technology in the field of machine vision (human recognition, image classification, object detection and the like) enables the accuracy of machine vision to be higher than that of human, and the AI technology also has good application in the fields of natural language processing, recommendation systems and the like.
Machine learning is a core means for realizing AI, a computer constructs an AI model according to the existing data aiming at the technical problem to be solved, and then the result is predicted by using the AI model, so that the computer can simulate the learning ability (such as cognitive ability, discrimination ability and classification ability) of human to solve the technical problem, and the method is called machine learning.
An AI model is a mathematical model (e.g., a neural network (neural network) model) used in implementing various applications of AI by machine learning, and is essentially an algorithm including a large number of parameters and calculation formulas (or calculation rules). The AI model may employ learning of the intrinsic laws and representation hierarchies of the input data to obtain a non-linear function for the mapping relationship between the input and output, and process and analyze the new input data according to the non-linear function. The AI model can be used in a number of application scenarios such as speech recognition, visual recognition, security, etc., for example: when voice data such as 'please open the air conditioner' input by a user is collected, the AI model can recognize a 'please open the air conditioner' text according to the input voice data.
The AI models are various, and different AI models can be adopted for different application scenes and target events. Such as artificial neural network (ans) models, also known as Neural Network (NNs) models or connection models (connection models), which are a typical representation of AI models. The neural network model is a mathematical computation model which simulates the behavior characteristics of a human brain neural network and performs distributed parallel information processing. The main task of the artificial neural network is to construct a practical artificial neural network according to application requirements by using the principle of the human brain neural network as a reference, realize the learning algorithm design suitable for the application requirements, simulate the intelligent activities of the human brain, and solve the practical problems technically. The neural network is designed by adjusting the interconnection relationship among a large number of internal nodes according to the complexity of the network structure, so that a corresponding learning algorithm is realized.
Rpc (remote Procedure Call protocol) remote Procedure Call protocol, a protocol that requests services from a remote computer program over a network without knowledge of the underlying network technology. Briefly, RPC enables a program to access remote system resources as well as local system resources.
Fig. 1 is a schematic structural diagram of an intelligent home system according to an embodiment of the present invention.
Fig. 1 is a schematic diagram of an intelligent home system according to an exemplary embodiment of the present invention. As shown in fig. 1, the smart home system includes: server 11, router 12, communication network 13, smart home devices 14 and terminal 15. The server 11 is configured to receive the information of the smart home devices 14 sent by the router 12, and send the received information of the smart home devices 14 to the terminal 15, optionally, the server 11 may be a physical server, or may also be a cloud server, that is, a virtual server set in a cloud, and the server 11 may be one server, or may also be a set of servers composed of multiple servers.
The server 11 and the router 12 are connected through a communication network 13, the communication network 13 may be a wired network or a wireless network, and optionally, the communication network 13 may be at least one of a local area network, a metropolitan area network, and a wide area network.
The router 12 is a device for controlling the smart home devices 14, and optionally, the router 12 controls the smart home devices 14 through a communication technology, where the communication technology may be a wireless communication technology or a wired communication technology, and the wireless communication technology may also be a short-range wireless communication technology (NFC), a ZigBee (violet protocol) technology, a Bluetooth technology, a WiFi (wireless local area network) technology, or the like.
It should be noted that the router 12 may include a master router and a slave router, and in some embodiments, the router 12 includes a master router and at least one slave router. Wherein, the main router is used for controlling the smart home devices 14 corresponding thereto, optionally, the smart home devices 14 may also be a smart home device group, the main router is used for controlling the smart home device group corresponding thereto, wherein, the smart home device group includes smart home devices and smart home devices again, if: the main router is used for controlling the intelligent household equipment group corresponding to the main router, and the intelligent household equipment group comprises an air conditioner and a television. Optionally, the main router is further configured to manage devices in the smart home multi-gateway system, such as: the corresponding relationship between the router 12 and the smart home devices 14 in the smart home multi-gateway system is stored, and illustratively, the corresponding relationship between the slave router and the smart home devices and the corresponding relationship between the router and the smart home devices are also stored in the master router.
The slave router is used for controlling the corresponding smart home devices 14. It can be understood that the number of the smart home devices 14 controlled by each router 12 is within a preset number range, and one smart home device 14 can only be controlled by one router 12, that is, one smart home device 14 can only be bound with one router 12.
The smart home devices 14 are devices that can be registered in the router 12, and optionally, the smart home devices 14 may include one or more devices. Optionally, the smart home device 14 may be at least one of an air conditioner, a television, a water heater, an air purifier, a sweeping robot, or a monitoring device.
The terminal 15 is a terminal device for interacting with a user. Optionally, the terminal 15 is configured to display the state of the smart home device 14 on a user interface, and control the smart home device 14 through the user interface, such as: the method includes the steps of starting the intelligent household equipment 14, closing the intelligent household equipment 14, changing parameters of the intelligent household equipment 14 and the like. Optionally, when the smart home device 14 is a smart home device group, the smart home device group includes a plurality of smart home devices, and the smart home devices in the smart home device group may be respectively displayed or controlled through the user interface. Optionally, the terminal 15 is a terminal device associated with the router 12, that is, the terminal 15 and the router 12 establish a binding relationship. Alternatively, the terminal 15 may be a mobile terminal, such as: at least one of a cell phone, tablet or laptop.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a router in a hardware operating environment according to an embodiment of the present application.
As shown in fig. 2, the router may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the architecture shown in fig. 2 does not constitute a limitation of a router, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 2, the memory 1005, which is a storage medium, may include an operating system, a data storage module, a bluetooth communication module, a user interface module, and a smart home device control program therein.
In the playback terminal shown in fig. 2, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the router of the present invention may be disposed in the router, and the router invokes the smart home device control program stored in the memory 1005 through the processor 1001, and executes the smart home device control method provided in the embodiment of the present invention.
Based on the above hardware device but not limited to the above hardware device, a first embodiment of a method for controlling smart home devices according to the present application is provided. Referring to fig. 3, fig. 3 is a schematic flowchart of a first embodiment of a control method for smart home devices according to the present application.
In this embodiment, the method includes:
step S101, an interface calling request sent by the intelligent household equipment is obtained, and the interface calling request comprises input information collected by the intelligent household equipment.
The intelligent household equipment can acquire voice data input by a user or acquire current environment information of the intelligent household equipment through a sensor or acquisition equipment carried by the intelligent household equipment during operation. The input information may include at least one of voice data or current environment information terminal.
After the input information is collected, the smart home system needs to respond to the input information. In order to improve the intelligence level, the intelligent home device can send an interface call request to the router through an RPC protocol between the intelligent home device and the router or a RESTFUL architecture, so that an AI model deployed in the router is remotely called to utilize an AI service of the router.
After receiving the interface calling request sent by the intelligent home terminal, the router can analyze the interface calling request to obtain data such as a service interface address, input information, an input information type and the like carried in the interface calling request.
And S102, calling the pre-trained terminal control model, and inputting input information into the terminal control model to obtain a control instruction output by the terminal control model.
The pre-trained terminal control model is an AI model deployed in the router in advance. After the router acquires the interface calling request and analyzes the interface calling request, the pre-trained terminal control model deployed in the router can be called, input information is input into the terminal control model, and a control instruction output by the terminal control model is obtained. The terminal control model may be a convolutional neural network model. The pre-trained terminal control model can output a corresponding control instruction according to input information.
And S103, determining target household equipment corresponding to the control instruction from at least one piece of intelligent household equipment.
And step S104, feeding back the control instruction to the target intelligent household equipment so that the target intelligent household equipment executes the operation corresponding to the control instruction.
It can be understood that, for the smart home system, the information input end and the action execution end may be different or the same. If the intelligent air conditioner collects voice data input by a user, the voice recognition AI service needs to be called, then the action corresponding to the voice data is executed, and at the moment, the information input end is consistent with the action execution end. When the information input end is consistent with the action execution end, the router can directly feed back the control instruction to the intelligent household equipment so that the intelligent household equipment can execute the control instruction.
In other embodiments, kitchen smog alarm signal is gathered to the camera, calls domestic security protection AI model, then the router sends control command to smart window, carries out the window instruction of opening of domestic security protection AI model output to and the router sends control command to user's mobile terminal, and this mobile terminal disposes intelligent house APP, thereby sends alarm signal, takes place accident in order to remind user's kitchen.
After the AI model such as the terminal control model in the router outputs the control instruction according to the input information, the router returns the control instruction to the intelligent household equipment or sends the control instruction to the target intelligent household equipment, and the target intelligent household equipment executes the operation corresponding to the control instruction, so that the intelligent service is provided intelligently and with low delay in response to the input information.
In still other embodiments, step S104 may further specifically be:
(1) feeding back the control instruction to the intelligent household equipment so that the intelligent household equipment returns the control instruction to the router;
(2) and after the router receives the control instruction, controlling the target intelligent household equipment to execute the operation corresponding to the control instruction.
At this time, after the router calls an AI model such as an internal terminal control model to output a control instruction according to input information, the router returns an output result, that is, the control instruction to the smart home device, that is, an information input end. After the intelligent home equipment receives the control instruction, the intelligent home equipment recognizes that the object of the control instruction is not the intelligent home equipment, but the target intelligent home equipment, namely the action execution end, at the moment, the intelligent home equipment feeds the control instruction back to the router, the router sends the control instruction to the target intelligent home equipment (the action execution end) to control the corresponding operation executed by the target intelligent home equipment, and therefore the embodiment can respond to the input information and provide intelligent service intelligently and with low delay.
For ease of understanding, some specific scenarios are shown below.
When the intelligent air conditioner collects voice data 'close wind sweeping' input by a user through a microphone arranged in a shell of the indoor unit, the intelligent air conditioner packs the voice data into a voice recognition interface calling request through a communication module in the intelligent air conditioner, and sends the voice data into a router connected with the intelligent air conditioner. And after receiving the voice recognition interface calling request, the router analyzes the voice recognition interface calling request to obtain voice data 'wind sweeping closing'. The router calls the pre-trained voice recognition model, recognizes a corresponding 'wind sweeping closing' instruction, and sends the instruction to the intelligent air conditioner. And after receiving the wind-sweeping-off command, the intelligent air conditioner executes a wind-sweeping-off mode command.
When the intelligent desk lamp detects that the user stands up through the built-in infrared sensor, the infrared sensing information triggered by the user can be packaged into the control calling request, and the control calling request is sent to the router connected with the intelligent desk lamp. And after receiving the control calling request, the router analyzes the control calling request to obtain the infrared sensing information. The router calls the pre-trained control model, obtains a window opening instruction and an intelligent wardrobe opening instruction output by the control model, and sends the window opening instruction and the intelligent wardrobe opening instruction to the intelligent curtain and the intelligent wardrobe, the window opening action is executed after the window opening instruction is received by the intelligent curtain, and the lamp in the wardrobe is opened and opened after the opening instruction is received by the intelligent wardrobe.
When the intelligent desk lamp detects that the user stands up through the built-in infrared sensor, the infrared sensing information triggered by the user can be packaged into the control calling request, and the control calling request is sent to the router connected with the intelligent desk lamp. And after receiving the control calling request, the router analyzes the control calling request to obtain the infrared sensing information. The router calls the pre-trained control model, a window opening instruction and an intelligent wardrobe opening instruction which are output by the control model are obtained, the window opening instruction and the intelligent wardrobe opening instruction are fed back to the intelligent desk lamp, the intelligent desk lamp returns to the router after obtaining the control instruction, the window opening instruction and the intelligent wardrobe opening instruction are sent to the intelligent curtain and the intelligent wardrobe respectively by the router, the window opening action is executed after the window opening instruction is received by the intelligent curtain, and the wardrobe door is opened and the lamp in the wardrobe is opened after the opening instruction is received by the intelligent wardrobe.
In this embodiment, by fully utilizing the abundant hardware resources such as computation and storage on the router, and by remotely calling the intelligent home device to the AI services such as the AI model deployed on the router, the low-latency AI service is provided for the intelligent home device. The intelligent level of the intelligent terminal equipment is improved, and further the user experience is improved.
In addition, in this embodiment, the intelligent home device remotely calls the AI services such as the AI model deployed on the router, so that the input information collected by the intelligent home device, such as the user instruction, the current environment information and the like, is not sent to the cloud server through the router, and thus the data security of the user can be guaranteed.
Based on the first embodiment of the intelligent household equipment control method, a second embodiment of the intelligent household equipment control method is provided. Referring to fig. 4, fig. 4 is a schematic flowchart of a second embodiment of the smart home device control method according to the present application.
In this embodiment, the method includes the steps of:
step S201, an interface calling request sent by the intelligent household equipment is obtained, and the interface calling request comprises input information collected by the intelligent household equipment.
Step S202, according to the interface calling request, determining a terminal control model corresponding to the interface calling request from at least one terminal control model to be selected.
It is understood that a variety of AI models, such as a voice recognition model, an image recognition model, an infrared information recognition model, etc., may be disposed within the router. When an interface calling request sent by an intelligent home terminal is received, a router can analyze the interface calling request to obtain a service interface address corresponding to the interface calling request, and therefore a terminal control model corresponding to the interface calling request is determined from at least one terminal control model to be selected.
In other embodiments, when the smart home device registers in the router, interface information corresponding to the at least one terminal control model to be selected is fed back to the smart home device, so that when the smart home device collects input information, target interface information is determined from the at least one interface information to generate an interface calling request.
When any intelligent household equipment is registered in the intelligent household system and corresponds to a corresponding router, the router sends interface information of all AI models deployed in a local deployment mode to the intelligent household equipment, and therefore the intelligent household equipment can know AI services provided by the router. The intelligent home equipment can store the interface information of all AI models in the local database, and when the AI service is needed, the intelligent home equipment determines the target interface information according to the collected data type and generates an interface calling service based on the target interface information.
Specifically, when a user registers an AI home robot to a router, the router sends interface information of both a locally deployed voice recognition model and an image recognition model to the AI home robot. When the household robot collects image data and voice data, a first interface calling request is generated according to the image data and interface information of the image recognition model, and a second interface calling request is generated according to the voice data and the interface information of the voice recognition model.
Step S203, calling the pre-trained terminal control model, inputting the input information into the pre-trained terminal control model, and obtaining the control instruction output by the terminal control model.
And S204, determining target household equipment corresponding to the control instruction from the at least one intelligent household equipment.
And S205, feeding back the control instruction to the target intelligent household equipment so that the target intelligent household equipment executes the operation corresponding to the control instruction.
In this embodiment, when the smart home device registers in the router, the AI service capabilities in the router, that is, the interface addresses of the AI models, are sent to the smart home device, so that the smart home device can generate corresponding interface call requests according to corresponding data types during subsequent use, and the smart home device can call the corresponding AI models conveniently, thereby being beneficial to the router to provide AI services for the smart home device better.
Based on the above embodiment, referring to fig. 5, a third embodiment of the intelligent home device control method according to the present application is provided, in which an AI model deployed by a router is trained by the following method.
Step S301, judging whether the current time is within a preset training time period;
step S302, if the input information is not in the preset training time period, the input information is input into the terminal control model, and a control instruction output by the terminal control model is obtained.
And S303, if the terminal control model is within the preset training time period, training the terminal control model by using the input information and/or the historical input information as training samples to obtain a new terminal control model.
Specifically, in this embodiment, the user may configure a preset training time period in the router according to personal habits, so as to train the AI model on the basis of not affecting the implementation of the data transmission function of the router itself, so that the AI model is more adaptive to the user, thereby providing more intelligent services and improving user experience. Wherein the historical input information may be input information that has not been trained.
The preset training time period may be at night, and at this time, the router may perform training using the input information or the historical input information to update the model parameters of the internal AI model.
In some embodiments, to make training more efficient, training may be performed according to the priority of the input information. At this time, step S303 includes:
and A10, if the input information and/or the historical input information are in the preset training time period, sorting the input information and/or the historical input information according to a preset data priority sorting rule to obtain at least one sorted training sample.
And in the preset time period, the router sorts the input information and/or the historical input information received at the time according to a preset priority ranking rule, so as to obtain at least one training sample after sorting.
If the router has the voice data a and the sensor data B, the priority of the voice data in the preset data priority arrangement rule is the highest, and at this time, the voice data a is ranked at the front and the sensor data B is ranked at the back.
And A20, sequentially training the corresponding terminal control models through the sequenced at least one training sample to obtain a new terminal control model.
The router may identify the data type of each input message so that the prioritized previous data is input first into the corresponding AI model. After the training of the data with the prior priority is finished, the subsequent data with the later priority is sent to the corresponding AI model for training.
For example, the router trains the speech recognition model by taking the speech data A as a training sample, and updates the model parameters of the speech recognition model. And after training, training the sensor signal recognition model by taking the sensor data B as a training sample.
In this embodiment, the AI models are trained in sequence according to the data priority, so that the training effectiveness is higher, and especially, the training is more focused on training the AI models with higher association with the user experience, such as a voice recognition model.
In some embodiments, modifications may be made based on user feedback in order to make training more efficient.
At this time, step S303 includes:
step B10, training the terminal control model by taking the input information and/or the historical input information as training samples to obtain new model parameters and training result instructions;
and step B20, determining target intelligent household equipment corresponding to the training result instruction from the at least one intelligent household equipment, and sending the control instruction to the target intelligent household equipment so that the intelligent household equipment can execute the operation corresponding to the training result instruction.
And step B30, when user feedback information sent by at least one intelligent home terminal is received, the user feedback information is used as a verification set to verify the model parameters.
And step B30, if the verification result is positive feedback, updating the terminal control model according to the model parameters.
Specifically, the router can output a training result instruction in the training process, so that a user can observe or experience the action executed by the target smart home device and evaluate the action to obtain user feedback information. The user feedback information can be input through an intelligent home APP on the mobile terminal and also can be input through the voice of the AI robot. And are not limiting herein. When the router receives user feedback information sent by at least one intelligent home terminal, the user feedback information is used as a verification set to verify the model parameters, and therefore whether the training is effective or not is determined. If the verification result is positive feedback, the training is effective, the AI model can be updated, and if the verification result is negative feedback, the training is ineffective.
It should be noted that, in some other embodiments, the data type of some input information may be identified as a supervision event, and the router recognizes the supervision event identification when training the input information as a training sample, so as to perform the above steps to improve the training effect. And when the supervision event identification is not identified, the verification is carried out without user feedback information.
In this embodiment, the AI model deployed on the router may be efficiently trained within a preset time period, so as to satisfy the training and growth of the AI model, and not hinder the normal use of the router function.
In addition, an embodiment of the present invention further provides a computer storage medium, where an intelligent home device control program is stored on the storage medium, and the steps of the intelligent home device control method are implemented when the intelligent home device control program is executed by a processor. Therefore, a detailed description thereof will be omitted. In addition, the beneficial effects of the same method are not described in detail. For technical details not disclosed in embodiments of the computer-readable storage medium referred to in the present application, reference is made to the description of embodiments of the method of the present application. It is determined that, by way of example, the program instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It should be noted that the above-described embodiments of the apparatus are merely schematic, where units illustrated as separate components may or may not be physically separate, and components illustrated as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention may be implemented by software plus necessary general hardware, and may also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components and the like. Generally, functions performed by computer programs can be easily implemented by corresponding hardware, and specific hardware structures for implementing the same functions may be various, such as analog circuits, digital circuits, or dedicated circuits. However, the implementation of a software program is a more preferable embodiment for the present invention. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, where the computer software product is stored in a readable storage medium, such as a floppy disk, a usb disk, a removable hard disk, a Read-only memory (ROM), a random-access memory (RAM), a magnetic disk or an optical disk of a computer, and includes instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. The intelligent household equipment control method is used for a router, the router is in communication connection with at least one intelligent household equipment, and the method comprises the following steps:
acquiring an interface calling request sent by the intelligent home equipment, wherein the interface calling request comprises input information acquired by the intelligent home equipment;
calling a pre-trained terminal control model, and inputting the input information into the terminal control model to obtain a control instruction output by the terminal control model;
determining target intelligent household equipment corresponding to the control instruction from at least one intelligent household equipment;
and sending the control instruction to target intelligent household equipment so that the target intelligent household equipment executes the operation corresponding to the control instruction.
2. The smart home device control method according to claim 1, wherein before the invoking of the pre-trained terminal control model, the method further comprises:
and determining a terminal control model corresponding to the interface calling request from at least one terminal control model to be selected according to the interface calling request.
3. The intelligent home device control method according to claim 2, wherein before the obtaining of the interface call request sent by the intelligent home device, the method further comprises:
when the intelligent home equipment is registered to the router, feeding back interface information corresponding to at least one terminal control model to be selected to the intelligent home equipment, so that when the intelligent home equipment collects the input information, target interface information is determined from the at least one interface information, and the interface calling request is generated based on the target interface information.
4. The smart home device control method according to claim 1, wherein before the inputting the input information into the terminal control model and obtaining the control command output by the terminal control model, the method further comprises:
judging whether the current moment is within a preset training time period;
and if the input information is not in the preset training time period, executing the input information to the terminal control model to obtain a control instruction output by the terminal control model.
5. The smart home device control method according to claim 4, wherein the determining whether the current time is after a preset training time period further includes:
and if so, training the terminal control model by using the input information and/or the historical input information as training samples to obtain a new terminal control model.
6. The smart home device control method according to claim 5, wherein training the terminal control model by using the input information and/or historical input information as training samples to obtain a new terminal control model comprises:
training the terminal control model by taking the input information and/or historical input information as training samples to obtain new model parameters and a training result instruction;
determining target intelligent home equipment corresponding to the training result instruction from at least one piece of intelligent home equipment, and sending the control instruction to the target intelligent home equipment so that the target intelligent home equipment executes operation corresponding to the training result instruction;
when user feedback information sent by at least one intelligent home terminal is received, the user feedback information is used as a verification set to verify the model parameters;
and if the verification result is positive feedback, updating the terminal control model according to the model parameters.
7. The smart home device control method according to claim 5, wherein if the input information and/or the historical input information is within the preset training time period, training the terminal control model by using the input information and/or the historical input information as training samples to obtain a new terminal control model, including:
if the training time is within the preset training time period, sequencing the input information and/or the historical sequencing information according to a preset data priority sequencing rule to obtain at least one sequenced training sample;
and sequentially training the corresponding terminal control models through the sequenced at least one training sample to obtain a new terminal control model.
8. A router, comprising: a memory, a processor and a smart home device control program stored on the memory and executable on the processor, the smart home device control program being configured to implement the steps of the smart home device control method according to any one of claims 1 to 7.
9. The utility model provides an intelligent home systems which characterized in that includes:
at least one smart home device; and
the router of claim 8, the router communicatively coupled to at least one of the smart home devices.
10. A computer-readable storage medium, wherein the computer-readable storage medium has a smart home device control program stored thereon, and when the smart home device control program is executed by a processor, the steps of the smart home device control method according to any one of claims 1 to 7 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111179669.8A CN113900383A (en) | 2021-10-08 | 2021-10-08 | Intelligent household equipment control method, router, intelligent household system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111179669.8A CN113900383A (en) | 2021-10-08 | 2021-10-08 | Intelligent household equipment control method, router, intelligent household system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113900383A true CN113900383A (en) | 2022-01-07 |
Family
ID=79190938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111179669.8A Pending CN113900383A (en) | 2021-10-08 | 2021-10-08 | Intelligent household equipment control method, router, intelligent household system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113900383A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111090243A (en) * | 2018-10-23 | 2020-05-01 | 宁波方太厨具有限公司 | Method for realizing intelligent interconnection of kitchen appliances |
| CN114815707A (en) * | 2022-05-17 | 2022-07-29 | 重庆伏特猫科技有限公司 | Intelligent device control method and system based on Netty network framework |
| CN115576215A (en) * | 2022-10-14 | 2023-01-06 | 清华大学 | Intelligent home system and linkage control method based on intelligent home system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106782559A (en) * | 2016-12-31 | 2017-05-31 | 广东博意建筑设计院有限公司 | Smart home house keeper central control system and its control method with telecommunication control |
| CN107490977A (en) * | 2017-09-25 | 2017-12-19 | 深圳市斑点猫信息技术有限公司 | Controlling model training method, the control method and device of smart home |
| CN108173722A (en) * | 2017-12-26 | 2018-06-15 | 北京康力优蓝机器人科技有限公司 | A kind of smart home device automatic operation method |
| CN109343359A (en) * | 2018-10-17 | 2019-02-15 | 深圳绿米联创科技有限公司 | Intelligent switch, intelligence control system, method, apparatus and electronic equipment |
| CN109712625A (en) * | 2019-02-18 | 2019-05-03 | 珠海格力电器股份有限公司 | Intelligent equipment control method and system based on gateway and intelligent gateway |
| US20200092125A1 (en) * | 2018-09-18 | 2020-03-19 | Adomi, Inc. | Machine-Learned Smart Home Configuration |
| CN112286150A (en) * | 2020-10-15 | 2021-01-29 | 珠海格力电器股份有限公司 | Intelligent household equipment management method, device and system and storage medium |
| CN112394647A (en) * | 2019-08-19 | 2021-02-23 | 中国移动通信有限公司研究院 | Control method, device and equipment of household equipment and storage medium |
-
2021
- 2021-10-08 CN CN202111179669.8A patent/CN113900383A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106782559A (en) * | 2016-12-31 | 2017-05-31 | 广东博意建筑设计院有限公司 | Smart home house keeper central control system and its control method with telecommunication control |
| CN107490977A (en) * | 2017-09-25 | 2017-12-19 | 深圳市斑点猫信息技术有限公司 | Controlling model training method, the control method and device of smart home |
| CN108173722A (en) * | 2017-12-26 | 2018-06-15 | 北京康力优蓝机器人科技有限公司 | A kind of smart home device automatic operation method |
| US20200092125A1 (en) * | 2018-09-18 | 2020-03-19 | Adomi, Inc. | Machine-Learned Smart Home Configuration |
| CN109343359A (en) * | 2018-10-17 | 2019-02-15 | 深圳绿米联创科技有限公司 | Intelligent switch, intelligence control system, method, apparatus and electronic equipment |
| CN109712625A (en) * | 2019-02-18 | 2019-05-03 | 珠海格力电器股份有限公司 | Intelligent equipment control method and system based on gateway and intelligent gateway |
| CN112394647A (en) * | 2019-08-19 | 2021-02-23 | 中国移动通信有限公司研究院 | Control method, device and equipment of household equipment and storage medium |
| CN112286150A (en) * | 2020-10-15 | 2021-01-29 | 珠海格力电器股份有限公司 | Intelligent household equipment management method, device and system and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111090243A (en) * | 2018-10-23 | 2020-05-01 | 宁波方太厨具有限公司 | Method for realizing intelligent interconnection of kitchen appliances |
| CN111090243B (en) * | 2018-10-23 | 2023-04-14 | 宁波方太厨具有限公司 | Method for realizing intelligent interconnection of kitchen appliances |
| CN114815707A (en) * | 2022-05-17 | 2022-07-29 | 重庆伏特猫科技有限公司 | Intelligent device control method and system based on Netty network framework |
| CN115576215A (en) * | 2022-10-14 | 2023-01-06 | 清华大学 | Intelligent home system and linkage control method based on intelligent home system |
| CN115576215B (en) * | 2022-10-14 | 2024-07-23 | 清华大学 | Intelligent home system and linkage control method based on intelligent home system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113900383A (en) | Intelligent household equipment control method, router, intelligent household system and medium | |
| EP3411634B1 (en) | Data learning server and method for generating and using learning model thereof | |
| CN108919669B (en) | Intelligent home dynamic decision method and device and service terminal | |
| CN110827818B (en) | Control method, device, equipment and storage medium of intelligent voice equipment | |
| CN106406119B (en) | Service robot based on interactive voice, cloud and integrated intelligent Household monitor | |
| CN110578994B (en) | Operation method and device | |
| CN104579873B (en) | The method and system being controlled to intelligent home device | |
| CN108093030B (en) | Artificial intelligence model deployment method based on cloud server | |
| CN108419453B (en) | Lighting lamp control method and device and lighting lamp | |
| CN112286150B (en) | Intelligent household equipment management method, device and system and storage medium | |
| CN104102181A (en) | Intelligent home control method, device and system | |
| CN109951363A (en) | Data processing method, apparatus and system | |
| CN110426962A (en) | A kind of control method and system of smart home device | |
| CN109448721A (en) | Sound control method, system, Cloud Server and speech ciphering equipment | |
| JP6400834B2 (en) | RECOMMENDATION DEVICE, RECOMMENDATION DETERMINING METHOD, AND COMPUTER PROGRAM | |
| CN112162492A (en) | Control method and device of household equipment, edge computing gateway and storage medium | |
| CN111077786A (en) | Intelligent household equipment control method and device based on big data analysis | |
| CN110324216A (en) | Automatic configuration method, apparatus, system, server and storage medium | |
| CN107463096A (en) | A kind of Computer Control Experiment System with cloud controller programing function | |
| CN202771369U (en) | Man-machine interface device based on multiprocessor | |
| CN111431776A (en) | Information configuration method, device and system | |
| CN117668763B (en) | Digital human all-in-one machine based on multiple modes and multiple mode perception and identification method thereof | |
| CN113852657A (en) | Intelligent home local control method and system based on edge calculation | |
| CN112837671A (en) | Intelligent voice prompt method, device and equipment and readable storage medium | |
| CN208479659U (en) | Behavior prediction voice configures smart home system |
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: 20220107 |