CN-121996841-A - Recommendation scene determining method and device, storage medium and electronic equipment

CN121996841ACN 121996841 ACN121996841 ACN 121996841ACN-121996841-A

Abstract

The application discloses a method and a device for determining a recommended scene, a storage medium and electronic equipment, and relates to the technical field of smart families, wherein the method comprises the steps of obtaining first metadata of household equipment in a first time period, wherein the first time period is positioned before the current time, and the first metadata are used for representing the space where the household equipment is positioned and the use data of the household equipment; the method comprises the steps of inputting first metadata into a scene recommendation model to be processed, determining a first recommendation scene corresponding to the household equipment according to a first output result of the scene recommendation model, sending the first recommendation scene to a target object, obtaining first feedback returned by the target object based on the first recommendation scene, and determining a second recommendation scene according to the first feedback and the first recommendation scene, wherein the second recommendation scene is applied to the household equipment. By adopting the technical scheme, the problem that the intelligent degree of the household electrical appliance is low due to the fact that the automatic control of the intelligent household electrical appliance depends on manual setting parameters of a user in the related technology is solved.

Inventors

ZHANG SHIYAN

Assignees

青岛海尔科技有限公司
海尔优家智能科技（北京）有限公司
海尔智家股份有限公司

Dates

Publication Date: 20260508
Application Date: 20251229

Claims (10)

1. A method for determining a recommended scene, comprising: Acquiring first metadata of household equipment in a first time period, wherein the first time period is positioned before the current time, and the first metadata are used for representing the space where the household equipment is positioned and the use data of the household equipment; Inputting the first metadata into a scene recommendation model for processing, and determining a first recommendation scene corresponding to the household equipment according to a first output result of the scene recommendation model; the first recommended scene is sent to a target object, and first feedback returned by the target object based on the first recommended scene is obtained; And determining a second recommended scene according to the first feedback and the first recommended scene, wherein the second recommended scene is applied to the household equipment.
2. The method for determining a recommended scene according to claim 1, wherein before determining a first recommended scene corresponding to the home device according to a first output result of the scene recommendation model, the method further comprises: Performing feature extraction on the first metadata through a convolutional neural network to obtain a plurality of data features; Determining a plurality of association relations among the plurality of data features through a cyclic neural network, inputting the plurality of association relations into the scene recommendation model for processing, and obtaining a plurality of using habits of the target object on the household equipment and confidence degrees of the plurality of using habits, wherein the plurality of association relations are used for indicating the relation among any N data features in the plurality of data features, the plurality of using habits are in one-to-one correspondence with the plurality of association relations, and N is a positive integer; And determining a first usage habit with highest confidence in the plurality of usage habits as the first output result.
3. The method for determining a recommended scene according to claim 1, wherein determining a first recommended scene corresponding to the home device according to a first output result of the scene recommendation model includes: Determining a plurality of recommended scenes matched with the first output result in a household appliance function rule base, wherein the plurality of recommended scenes comprise the first recommended scene, and the household appliance function rule base comprises a plurality of scenes corresponding to the household equipment; And determining scores of the plurality of recommended scenes, and determining the recommended scene with the highest score in the plurality of recommended scenes as the first recommended scene, wherein the scores are used for representing the use frequency of the plurality of recommended scenes.
4. The method of claim 3, wherein determining a second recommended scene from the first feedback and the first recommended scene comprises: Determining the first recommended scene as the second recommended scene in the case that the first feedback indicates acceptance of the first recommended scene; Modifying the first recommended scene according to the first feedback when the first feedback indicates modification of the first recommended scene, and determining the modified first recommended scene as the second recommended scene; And determining a third recommended scene in a plurality of recommended scenes as the second recommended scene under the condition that the first feedback indicates refusing the first recommended scene, wherein the third recommended scene is the highest-scoring recommended scene in other recommended scenes, and the other recommended scenes are scenes except the first recommended scene in the plurality of recommended scenes.
5. The method of claim 1, wherein after determining a second recommended scene from the first feedback and the first recommended scene, the method further comprises: Acquiring second metadata of the household equipment in a second time period, wherein the second time period is a time period when the second recommended scene is applied to the household equipment, and the second metadata are the same as the first metadata in type; And under the condition that a first parameter in the second metadata changes relative to a second parameter in the first metadata, inputting the second metadata into the scene recommendation model for processing, and determining a fourth recommendation scene of the household equipment according to a second output result of the scene recommendation model, wherein the first parameter and the second parameter are the same in type.
6. The method for determining a recommended scenario of claim 1, wherein obtaining first metadata of a home device in a first period of time comprises: encrypting fourth metadata of the household equipment in a third time period to obtain fifth metadata, wherein the starting time of the third time period is located before the starting time of the first time period, and the ending time of the third time period is the current time; respectively storing the fifth data to a local server and a cloud server, and determining encrypted first metadata from the fifth data according to the first time period; and decrypting the encrypted first metadata to obtain the first metadata.
7. The method for determining a recommended scenario of claim 1, wherein after obtaining the first metadata of the home device in the first period of time, the method further comprises: acquiring a working mode determined by the target object for the scene recommendation model, wherein the working mode comprises a local mode and a cloud mode; under the condition that the working mode is the local mode, determining the category of the scene recommendation model as a local scene recommendation model; And under the condition that the working mode is the cloud mode, determining the category of the scene recommendation model as a cloud scene recommendation model.
8. A recommended scene determining apparatus, characterized by comprising: The first acquisition module is used for acquiring first metadata of the household equipment in a first time period, wherein the first time period is positioned before the current time, and the first metadata are used for representing the space where the household equipment is positioned and the use data of the household equipment; The first determining module is used for inputting the first metadata into a scene recommending model for processing, and determining a first recommending scene corresponding to the household equipment according to a first output result of the scene recommending model; The second acquisition module is used for sending the first recommended scene to a target object and acquiring first feedback returned by the target object based on the first recommended scene; and the second determining module is used for determining a second recommended scene according to the first feedback and the first recommended scene, wherein the second recommended scene is applied to the household equipment.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program, when run, performs the method of any one of claims 1 to 7.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method according to any of the claims 1 to 7 by means of the computer program.

Description

Recommendation scene determining method and device, storage medium and electronic equipment Technical Field The application relates to the technical field of smart families, in particular to a method and a device for determining recommended scenes, a storage medium and electronic equipment. Background In the related art, the automation control of most intelligent home appliances still depends on the user manually setting parameters such as preset time, operation mode, etc. While this provides the user with basic customization functionality, the lack of in-depth understanding and adaptation of user behavior results in the home devices not being able to make corresponding adjustments in the face of changes in user habits. For example, there may be significant differences in the usage patterns of home appliances in different seasons, workdays and rest days, but manually set parameters are often fixed and cannot flexibly match these changes, so that the level of intelligence and user experience of the home appliances are reduced. Aiming at the problem that in the related art, the automatic control of intelligent household appliances depends on manual parameter setting of users, and the intelligent degree of the household appliances is low, no effective solution has been proposed yet. Disclosure of Invention The embodiment of the application provides a method and a device for determining a recommended scene, a storage medium and electronic equipment, and aims to at least solve the problems that in the related technology, the automatic control of intelligent household appliances depends on manual setting parameters of users and the intelligent degree of the household appliances is low. According to one embodiment of the application, a method for determining a recommended scene is provided, which comprises the steps of obtaining first metadata of household equipment in a first time period, wherein the first time period is located before the current time, the first metadata are used for representing space where the household equipment is located and using data of the household equipment, processing the first metadata input scene recommended model, determining a first recommended scene corresponding to the household equipment according to a first output result of the scene recommended model, sending the first recommended scene to a target object, obtaining first feedback returned by the target object based on the first recommended scene, and determining a second recommended scene according to the first feedback and the first recommended scene, wherein the second recommended scene is applied to the household equipment. In an alternative embodiment, before determining a first recommended scene corresponding to the home equipment according to a first output result of the scene recommendation model, the method further comprises performing feature extraction on the first metadata through a convolutional neural network to obtain a plurality of data features, determining a plurality of association relations among the plurality of data features through a cyclic neural network, inputting the plurality of association relations into the scene recommendation model to process, and obtaining a plurality of using habits of the target object on the home equipment and confidence degrees of the plurality of using habits, wherein the plurality of association relations are used for indicating relations among any N data features in a one-to-one correspondence, N is a positive integer, and determining a first using habit with the highest confidence degree among the plurality of using habits as the first output result. In an alternative embodiment, determining a first recommended scene corresponding to the home equipment according to a first output result of the scene recommendation model includes determining a plurality of recommended scenes matched with the first output result in a home appliance function rule base, wherein the plurality of recommended scenes include the first recommended scene, the home appliance function rule base includes a plurality of scenes corresponding to the home equipment, determining scores of the plurality of recommended scenes, and determining a recommended scene with the highest score in the plurality of recommended scenes as the first recommended scene, wherein the scores are used for representing use frequencies of the plurality of recommended scenes. In an alternative embodiment, determining a second recommended scene according to the first feedback and the first recommended scene includes determining the first recommended scene as the second recommended scene when the first feedback indicates that the first recommended scene is accepted, modifying the first recommended scene according to the first feedback when the first feedback indicates that the first recommended scene is modified, determining the modified first recommended scene as the second recommended scene when the first feedback indicates that