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 PDF

Info

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
smart home
home device
router
terminal control
control model
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
Application number
CN202111179669.8A
Other languages
Chinese (zh)
Inventor
雷鹏
汪铎
张螣英
程宝平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Mobile Communications Group Co Ltd
China Mobile Hangzhou Information Technology Co Ltd
Original Assignee
China Mobile Communications Group Co Ltd
China Mobile Hangzhou Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Mobile Communications Group Co Ltd, China Mobile Hangzhou Information Technology Co Ltd filed Critical China Mobile Communications Group Co Ltd
Priority to CN202111179669.8A priority Critical patent/CN113900383A/en
Publication of CN113900383A publication Critical patent/CN113900383A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B15/00Systems controlled by a computer
    • G05B15/02Systems controlled by a computer electric
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00Programme-control systems
    • G05B19/02Programme-control systems electric
    • G05B19/418Total 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]
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/20Pc systems
    • G05B2219/26Pc applications
    • G05B2219/2642Domotique, 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

本发明公开了一种智能家居设备控制方法、路由器、智能家居系统及介质,属于智能家居领域。路由器与至少一个智能家居设备通信连接,方法包括:获取所述智能家居设备发送的接口调用请求,所述接口调用请求包括所述智能家居设备采集的输入信息;调用预训练的终端控制模型,并将所述输入信息输入终端控制模型,得到所述终端控制模型输出的控制指令;从至少一个智能家居设备中确定所述控制指令对应的目标智能家居设备;将所述控制指令发送至目标智能家居设备,以使所述智能家居设备执行所述控制指令对应的操作。本发明为智能家居设备提供了低延时的AI服务,提升了智能终端设备的智能化水平,进而提高了用户体验。

Figure 202111179669

The invention discloses a smart home equipment control method, a router, a smart home system and a medium, which belong to the field of smart home. The router is communicatively connected to at least one smart home device, and the method includes: acquiring an interface call request sent by the smart home device, where the interface call request includes input information collected by the smart home device; calling a pre-trained terminal control model, and Inputting the input information into a terminal control model to obtain a control command output by the terminal control model; determining a target smart home device corresponding to the control command from at least one smart home device; sending the control command to the target smart home device, so that the smart home device executes the operation corresponding to the control instruction. The present invention provides low-latency AI services for smart home devices, improves the intelligence level of smart terminal devices, and further improves user experience.

Figure 202111179669

Description

Intelligent household equipment control method, router, intelligent household system and medium
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)

1.一种智能家居设备控制方法,其特征在于,用于路由器,所述路由器与至少一个智能家居设备通信连接,所述方法包括:1. a smart home equipment control method, is characterized in that, is used for router, and described router is connected with at least one smart home equipment communication, and described method comprises: 获取所述智能家居设备发送的接口调用请求,所述接口调用请求包括所述智能家居设备采集的输入信息;acquiring an interface call request sent by the smart home device, where the interface call request includes input information collected by the smart home device; 调用预训练的终端控制模型,并将所述输入信息输入所述终端控制模型,得到所述终端控制模型输出的控制指令;Calling the 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; 从至少一个智能家居设备中确定所述控制指令对应的目标智能家居设备;Determine the target smart home device corresponding to the control instruction from at least one smart home device; 将所述控制指令发送至目标智能家居设备,以使所述目标智能家居设备执行所述控制指令对应的操作。The control instruction is sent to the target smart home device, so that the target smart home device executes the operation corresponding to the control instruction. 2.根据权利要求1所述的智能家居设备控制方法,其特征在于,所述调用预训练的终端控制模型之前,所述方法还包括:2. The method for controlling smart home equipment according to claim 1, wherein before calling the pre-trained terminal control model, the method further comprises: 根据所述接口调用请求,从至少一个待选终端控制模型中确定所述接口调用请求对应的终端控制模型。According to the interface invocation request, a terminal control model corresponding to the interface invocation request is determined from at least one candidate terminal control model. 3.根据权利要求2所述的智能家居设备控制方法,其特征在于,所述获取所述智能家居设备发送的接口调用请求之前,所述方法还包括:3. The method for controlling smart home equipment according to claim 2, characterized in that, before acquiring the interface calling request sent by the smart home equipment, the method further comprises: 在所述智能家居设备注册至所述路由器时,将至少一个所述待选终端控制模型对应的接口信息反馈至所述智能家居设备,以使所述智能家居设备在采集到所述输入信息时,从至少一个所述接口信息中确定目标接口信息,基于所述目标接口信息,生成所述接口调用请求。When the smart home device is registered with the router, the interface information corresponding to 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 the input information , determining target interface information from at least one of the interface information, and generating the interface invocation request based on the target interface information. 4.根据权利要求1所述的智能家居设备控制方法,其特征在于,所述将所述输入信息输入所述终端控制模型,得到所述终端控制模型输出的控制指令之前,所述方法还包括:4 . The method for controlling smart home equipment according to claim 1 , wherein, before the input information is input into the terminal control model and the control instructions output by the terminal control model are obtained, the method further comprises: 5 . : 判断当前时刻是否在预设训练时间段内;Determine whether the current moment is within the preset training time period; 若不在所述预设训练时间段内,则执行所述将所述输入信息输入所述终端控制模型,得到所述终端控制模型输出的控制指令。If it is not within the preset training time period, executing the inputting the input information into the terminal control model to obtain a control instruction output by the terminal control model. 5.根据权利要求4所述的智能家居设备控制方法,其特征在于,所述判断当前时刻是否在预设训练时间段内之后,所述方法还包括:5. The method for controlling smart home equipment according to claim 4, wherein after judging whether the current moment is within a preset training time period, the method further comprises: 若在所述预设训练时间段内,则将所述输入信息和/或历史输入信息作为训练样本训练所述终端控制模型,得到新的终端控制模型。If within the preset training time period, the input information and/or historical input information are used as training samples to train the terminal control model to obtain a new terminal control model. 6.根据权利要求5所述的智能家居设备控制方法,其特征在于,所述将所述输入信息和/或历史输入信息作为训练样本训练所述终端控制模型,得到新的终端控制模型,包括:6. The method for controlling smart home equipment according to claim 5, wherein said input information and/or historical input information are used as training samples to train the terminal control model to obtain a new terminal control model, comprising: : 将所述输入信息和/或历史输入信息作为训练样本训练所述终端控制模型,得到新的模型参数和训练结果指令;Using the input information and/or historical input information as training samples to train the terminal control model to obtain new model parameters and training result instructions; 从至少一个智能家居设备中确定所述训练结果指令对应的目标智能家居设备,并将所述控制指令发送至目标智能家居设备,以使所述目标智能家居设备执行所述训练结果指令对应的操作;Determine the target smart home device corresponding to the training result instruction from at least one smart home device, and send the control instruction to the target smart home device, so that the target smart home device executes the operation corresponding to the training result instruction ; 在接收到至少一个智能家居终端发送的用户反馈信息时,将所述用户反馈信息作为验证集对所述模型参数进行验证;When receiving user feedback information sent by at least one smart home terminal, use the user feedback information as a verification set to verify the model parameters; 若验证结果为正反馈,根据所述模型参数更新所述终端控制模型。If the verification result is positive feedback, the terminal control model is updated according to the model parameters. 7.根据权利要求5所述的智能家居设备控制方法,其特征在于,若在所述预设训练时间段内,则将所述输入信息和/或历史输入信息作为训练样本训练所述终端控制模型,得到新的终端控制模型,包括:7. The method for controlling smart home equipment according to claim 5, wherein if within the preset training time period, the input information and/or historical input information are used as training samples to train the terminal control model to get new terminal control models, including: 若在所述预设训练时间段内,则根据预设数据优先级排列规则,将所述输入信息和/历史排序信息排序,得到排序后的至少一个训练样本;If it is within the preset training time period, according to the preset data priority ranking rule, the input information and/or historical ranking information are sorted to obtain at least one sorted training sample; 通过所述排序后的至少一个训练样本依次训练对应的所述终端控制模型,得到新的终端控制模型。A new terminal control model is obtained by sequentially training the corresponding terminal control model through the sorted at least one training sample. 8.一种路由器,其特征在于,包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的智能家居设备控制程序,所述智能家居设备控制程序配置为实现如权利要求1至7中任一项所述的智能家居设备控制方法的步骤。8. A router, characterized in that, comprising: a memory, a processor, and a smart home device control program stored on the memory and running on the processor, the smart home device control program being configured to implement as follows: Steps of the smart home equipment control method according to any one of claims 1 to 7. 9.一种智能家居系统,其特征在于,包括:9. A smart home system, characterized in that, comprising: 至少一个智能家居设备;以及at least one smart home device; and 如权利要求8所述的路由器,所述路由器与至少一个所述智能家居设备通信连接。9. The router of claim 8, communicatively connected to at least one of the smart home devices. 10.一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有智能家居设备控制程序,所述智能家居设备控制程序被处理器执行时实现如权利要求1至7任一项所述的智能家居设备控制方法的步骤。10. A computer-readable storage medium, characterized in that, a smart home device control program is stored on the computer-readable storage medium, and when the smart home device control program is executed by a processor, any one of claims 1 to 7 is implemented. A step of the described smart home equipment control method.
CN202111179669.8A 2021-10-08 2021-10-08 Intelligent household equipment control method, router, intelligent household system and medium Pending CN113900383A (en)

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)

* Cited by examiner, † Cited by third party
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)

* Cited by examiner, † Cited by third party
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

Patent Citations (8)

* Cited by examiner, † Cited by third party
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)

* Cited by examiner, † Cited by third party
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
KR102553299B1 (en) Data learning server and method for generating and using 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
CN113412609B (en) Equipment control method, device, server and storage medium
US20200019887A1 (en) Data-driven activity prediction
CN112286150B (en) Intelligent household equipment management method, device and system and storage medium
US11056114B2 (en) Voice response interfacing with multiple smart devices of different types
CN110578994A (en) operation method and device
US10920356B2 (en) Optimizing processing methods of multiple batched articles having different characteristics
CN106463114A (en) Information processing device, control method, and program
CN109951363A (en) Data processing method, apparatus and system
CN117668763B (en) Digital human all-in-one machine based on multiple modes and multiple mode perception and identification method thereof
CN114821236A (en) Smart home environment sensing method, system, storage medium and electronic device
CN112162492A (en) Control method and device of household equipment, edge computing gateway and storage medium
CN107180090A (en) Reading punch card method, electronic equipment and computer-readable storage medium based on e-book
WO2016147298A1 (en) Recommendation device, recommendation method, and computer program
CN110324216A (en) Automatic configuration method, apparatus, system, server and storage medium
CN112837671A (en) Intelligent voice prompting method, device, device and readable storage medium
CN111583921A (en) Voice control method, device, computer equipment and storage medium
CN113852657B (en) Smart home local control method and system based on edge calculation
WO2019159483A1 (en) Device selection apparatus, data set selection apparatus, device selection method, and program
CN114117023A (en) Interaction method, interaction device, electronic equipment and storage medium
CN116757254B (en) Task processing method, electronic device and storage medium
CN208479659U (en) Behavior prediction voice configuration 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

Application publication date: 20220107

RJ01 Rejection of invention patent application after publication