CN-121978975-A - Control method and device of household equipment, electronic equipment and medium
Abstract
The embodiment of the invention provides a control method, a device, electronic equipment and a storage medium of household equipment, which comprise the steps of obtaining multi-mode data in a household environment, carrying out desensitization processing on the multi-mode data and carrying out feature extraction to obtain multi-dimensional features, determining a preprocessing strategy matched with the multi-dimensional features in a locally deployed edge rule engine, executing the preprocessing strategy to control the household equipment, sending the multi-dimensional features to a server so as to enable the server to generate an active care decision based on the multi-dimensional features, and receiving and executing the active care decision issued by the server to control the corresponding household equipment. According to the embodiment of the invention, the edge node can immediately generate and execute the local preprocessing strategy after recognizing the multi-mode data to be matched with the edge rule engine, and the feature data after the desensitization processing is uploaded to the server for joint decision, so that the flow of the active care decision of the household equipment is simplified, and the control efficiency is improved and the privacy of a user is ensured.
Inventors
- XIAO HONGWEI
- LI MENGYAO
- LI TAOYU
- Cui Weizhi
Assignees
- 珠海格力电器股份有限公司
- 珠海联云科技有限公司
Dates
- Publication Date
- 20260505
- Application Date
- 20251222
Claims (10)
- 1. A method for controlling home appliances, applied to an edge node, the edge node being communicatively connected to a plurality of home appliances and servers in a home environment, respectively, the method comprising: The method comprises the steps of acquiring multi-modal data in the home environment, wherein the multi-modal data comprises at least one of user physiological data, user behavior data, environment data and home equipment operation data; desensitizing the multi-mode data and extracting features to obtain multi-dimensional features; Determining a preprocessing strategy matched with the multidimensional features in a preset edge rule engine, and controlling corresponding household equipment according to the preprocessing strategy; transmitting the multi-dimensional feature to the server; and receiving the initiative care decision generated by the server according to the multidimensional characteristics, and controlling corresponding household equipment to execute according to the initiative care decision.
- 2. The method for controlling a home appliance according to claim 1, wherein the edge rule engine includes a plurality of rules for describing a preprocessing strategy to be executed when a preset multi-dimensional feature is detected; The determining a preprocessing strategy matched with the multidimensional feature in a preset edge rule engine, and controlling corresponding household equipment according to the preprocessing strategy comprises the following steps: and determining a target rule matched with the multidimensional features in a plurality of rules of a preset edge rule engine, and controlling corresponding household equipment according to a preprocessing strategy in the target rule.
- 3. The control method of a home appliance according to claim 1, wherein after the multi-dimensional feature is transmitted to the server, the method comprises: And receiving the active care decision sent by the server, and updating the edge rule engine according to the active care decision.
- 4. A method of controlling home appliances, characterized by being applied to a server in communication with at least one edge node and a plurality of said home appliances in a home environment, the method comprising: Receiving the multidimensional features uploaded by the edge node when the multidimensional features are in communication connection with the server, wherein the multidimensional features are generated by the edge node according to multi-mode data in a home environment; determining a user risk scene according to the multidimensional features; Generating an active care decision according to the user risk scene; The active care decision is sent to the edge node to cause the edge node to control the home device to perform the active care decision.
- 5. The method according to claim 4, wherein determining a user risk scenario from the multi-dimensional feature comprises: The health state model is constructed according to the historical multidimensional feature vector and the medical knowledge graph; and inputting the multi-dimensional characteristics into the health state model to determine a user risk scene.
- 6. The method for controlling home appliances according to claim 5, further comprising: Performing aggregation processing according to the multidimensional features sent by the plurality of edge nodes to obtain aggregation update information; And updating the health state model according to the aggregation updating information.
- 7. A control device for a home appliance, applied to an edge node, said edge node being communicatively connected to a plurality of home appliances and servers in a home environment, respectively, said device comprising: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring multi-mode data in the home environment, and the multi-mode data comprises at least one of user physiological data, user behavior data, environment data and home equipment operation data; the feature extraction module is used for carrying out desensitization treatment on the multi-mode data and carrying out feature extraction to obtain multi-dimensional features; The equipment preprocessing module is used for determining a preprocessing strategy matched with the multidimensional features in a preset edge rule engine and controlling corresponding household equipment according to the preprocessing strategy; the feature sending module is used for sending the multi-dimensional features to the server; And the decision receiving module is used for receiving the initiative care decision generated by the server according to the multidimensional characteristics and controlling corresponding household equipment to execute according to the initiative care decision.
- 8. A control device for a home appliance, applied to a server in communication with at least one edge node and a plurality of said home appliances in a home environment, said device comprising: The device comprises a feature receiving module, a feature processing module and a feature processing module, wherein the feature receiving module is used for receiving multidimensional features uploaded by the edge node when the feature receiving module is in communication connection with the server, and the multidimensional features are generated by the edge node according to multi-mode data in a home environment; The scene determining module is used for determining a user risk scene according to the multidimensional features; The decision generation module is used for generating an active care decision according to the user risk scene; and the decision sending module is used for sending the active care decision to the edge node so that the edge node controls the household equipment to execute the active care decision.
- 9. An electronic device comprising a processor, a memory and a program or instructions stored on the memory, which when executed by the processor, implement the steps of the method of controlling a home device as claimed in claims 1-3 or 4-6.
- 10. A readable storage medium, wherein a program or instructions is stored on the readable storage medium, which when executed by a processor, implement the steps of the method for controlling a home appliance according to claims 1-3 or 4-6.
Description
Control method and device of household equipment, electronic equipment and medium Technical Field The present invention relates to the field of home devices, and in particular, to a method and apparatus for controlling a home device, an electronic device, and a readable storage medium. Background With the rapid development of the internet of things and artificial intelligence technology, the demands of home health management are increasingly refined, and intelligent home systems are gradually upgraded from equipment networking control to active health care services, so that intelligent health care systems are generated. In the running process of the system, the local edge node processes the multi-mode data in real time and executes the instant control strategy, and meanwhile, the characteristic data is uploaded to the cloud for deep analysis and model training. In the related technology, local decisions are often based on simple rules or depend on cloud completely, so that response delay is high, network disconnection is failure, and personalized continuous optimization cannot be realized. When a user encounters an emergency health event or the dynamic change of the health requirement, the response timeliness of the existing scheme is insufficient, the pertinence of care measures is lacking, and the real and dynamic health management requirement of the user is difficult to be effectively met. Disclosure of Invention In view of the foregoing, embodiments of the present invention are provided to provide a method, an apparatus, an electronic device, and a readable storage medium for controlling a home device, which overcome or at least partially solve the foregoing problems. In a first aspect, an embodiment of the present invention provides a method for controlling a home device, which is applied to an edge node, where the edge node is respectively in communication connection with a plurality of home devices and servers in a home environment, and the method includes: The method comprises the steps of acquiring multi-modal data in the home environment, wherein the multi-modal data comprises at least one of user physiological data, user behavior data, environment data and home equipment operation data; desensitizing the multi-mode data and extracting features to obtain multi-dimensional features; Determining a preprocessing strategy matched with the multidimensional features in a preset edge rule engine, and controlling corresponding household equipment according to the preprocessing strategy; transmitting the multi-dimensional feature to the server; and receiving the initiative care decision generated by the server according to the multidimensional characteristics, and controlling corresponding household equipment to execute according to the initiative care decision. Optionally, the edge rule engine includes a plurality of rules, where the rules are used to describe a preprocessing policy that needs to be executed when a preset multidimensional feature is detected; The determining a preprocessing strategy matched with the multidimensional feature in a preset edge rule engine, and controlling corresponding household equipment according to the preprocessing strategy comprises the following steps: and determining a target rule matched with the multidimensional features in a plurality of rules of a preset edge rule engine, and controlling corresponding household equipment according to a preprocessing strategy in the target rule. Optionally, after the sending the multidimensional feature to the server, the method includes: And receiving the active care decision sent by the server, and updating the edge rule engine according to the active care decision. In a second aspect, an embodiment of the present invention provides a control method of a home device, applied to a server, where the server is in communication connection with at least one edge node and communicates with a plurality of home devices in a home environment, and the method includes: Receiving the multidimensional features uploaded by the edge node when the multidimensional features are in communication connection with the server, wherein the multidimensional features are generated by the edge node according to multi-mode data in a home environment; determining a user risk scene according to the multidimensional features; Generating an active care decision according to the user risk scene; The active care decision is sent to the edge node to cause the edge node to control the home device to perform the active care decision. Optionally, the determining the user risk scene according to the multidimensional feature includes: The health state model is constructed according to the historical multidimensional feature vector and the medical knowledge graph; and inputting the multi-dimensional characteristics into the health state model to determine a user risk scene. Optionally, the method further comprises: Performing aggregation processing according to the mul