CN-122001924-A - Equipment control method, system, storage medium and electronic device

CN122001924ACN 122001924 ACN122001924 ACN 122001924ACN-122001924-A

Abstract

The application discloses a device control method, a system, a storage medium and an electronic device, and relates to the technical field of device control, wherein the method comprises the steps of constructing a plurality of data uploading interfaces according to prompt word requirements of a cloud large model to obtain a data uploading interface library, wherein the plurality of data uploading interfaces comprise data uploading interfaces corresponding to different functions of intelligent devices; the method comprises the steps of obtaining target function data associated with target functions of intelligent equipment from equipment data, determining a target data uploading interface corresponding to the target functions from a data uploading interface library, transmitting the target function data to a cloud large model through the target data uploading interface, receiving a control instruction sent by the cloud large model, and controlling the intelligent equipment according to the control instruction, wherein the control instruction is generated after the cloud large model infers target control data. By adopting the technical scheme, the problem that the large language model cannot accurately understand and intelligently control the data reported by the equipment is solved.

Inventors

ZHAO SHIJUN
ZHANG YUNHAO
YIN DESHUAI
HU BAICHUN

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
青岛海尔智能家电科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251226

Claims (10)

1. The device control method is characterized by being applied to intelligent devices and comprising the following steps: Constructing a plurality of data uploading interfaces according to the prompt word requirements of the cloud large model to obtain a data uploading interface library, wherein the plurality of data uploading interfaces comprise data uploading interfaces corresponding to different functions of the intelligent equipment; Acquiring target function data associated with a target function of the intelligent device from device data, and determining a target data uploading interface corresponding to the target function from the data uploading interface library; transmitting the target function data to a cloud large model through the target data uploading interface; And receiving a control instruction sent by the cloud large model, and controlling the intelligent equipment according to the control instruction, wherein the control instruction is generated after the cloud large model infers the target control data.
2. The apparatus control method according to claim 1, wherein determining a target data upload interface corresponding to the target function from the data upload interface library includes: determining a first data uploading interface matched with the target function from the data uploading interface library, wherein the interface function of the first data uploading interface is the same as the target function; Acquiring interface parameters of the interface of the first data and a parameter value range corresponding to the interface parameters; And determining the first data uploading interface as the target data uploading interface under the condition that the data type of the target function data is consistent with the data type of the interface parameter and the target function data accords with the parameter value range.
3. The device control method according to claim 1, wherein uploading the target function data to a cloud large model through the target data uploading interface includes: Determining an interface parameter format corresponding to the target data uploading interface; Encapsulating the target equipment data and the target function according to the interface parameter format to obtain encapsulated data; and transmitting the encapsulated data to the cloud large model through a preset network transmission protocol.
4. The equipment control method is characterized by being applied to a cloud large model and comprising the following steps of: Receiving target function data which is uploaded by intelligent equipment and is associated with a target function of the intelligent equipment; Reasoning the target function data based on preset prompt words to obtain a reasoning result; And generating a control instruction according to the reasoning result, and sending the control instruction to the intelligent equipment so as to control the intelligent equipment.
5. The device control method according to claim 4, wherein the reasoning about the target function data based on the preset prompt word, to obtain a reasoning result, includes: Judging whether the target function data meets preset conditions according to knowledge of a knowledge base and preset rules; Determining expected functional data corresponding to the preset condition under the condition that the target functional data does not meet the preset condition; And determining the expected functional data as the reasoning result.
6. The device control method according to claim 5, wherein generating a control instruction according to the inference result and transmitting the control instruction to the smart device, comprises: Determining a target working state corresponding to the target function of the intelligent device under the condition that the intelligent device accords with the expected function data; generating the control instruction according to the target working state, wherein the control instruction is used for adjusting the working state of the target function of the intelligent equipment; And transmitting the control instruction to the intelligent equipment through a preset network transmission protocol so as to control the intelligent equipment to adjust the working state of the target function to the target working state.
7. The apparatus control method according to claim 5, characterized in that the method further comprises: generating a response message under the condition that the target function data meets the preset condition, wherein the response message is used for notifying the intelligent equipment that the cloud large model successfully receives the target function data; and transmitting the response message to the intelligent equipment through a preset network transmission protocol.
8. A device control system, comprising: intelligent equipment, cloud large model; The intelligent equipment is used for constructing a plurality of data uploading interfaces according to the prompt word requirement of the cloud large model to obtain a data uploading interface library, wherein the plurality of data uploading interfaces comprise data uploading interfaces corresponding to different functions of the intelligent equipment, acquiring target function data associated with target functions of the intelligent equipment from equipment data, determining the target data uploading interfaces corresponding to the target functions from the data uploading interface library, transmitting the target function data to the cloud large model through the target data uploading interfaces, receiving a control instruction sent by the cloud large model, and controlling the intelligent equipment according to the control instruction, wherein the control instruction is generated after the cloud large model infers the target control data; the cloud large model is used for receiving target function data which are uploaded by the intelligent equipment and are associated with target functions of the intelligent equipment, reasoning the target function data based on preset prompt words to obtain reasoning results, generating control instructions according to the reasoning results, and sending the control instructions to the intelligent equipment to control the intelligent 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 of the preceding 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

Equipment control method, system, storage medium and electronic device Technical Field The present application relates to the field of device control technologies, and in particular, to a device control method, a system, a storage medium, and an electronic apparatus. Background With the rapid development of the internet of things technology, mass intelligent devices realize interconnection and data reporting, and the existing device data reporting scheme mainly focuses on simple data serialization and transmission, and although reporting data can be used in some data processing scenes based on clear rules, how to utilize a large model for deeper analysis and intelligent reasoning is not considered. Therefore, the related art has the problem that the large language model cannot accurately understand and intelligently control the data reported by the equipment. Aiming at the problem that a large language model cannot accurately understand and intelligently control the data reported by equipment in the related technology, an effective solution is not proposed yet. Disclosure of Invention The embodiment of the application provides a device control method, a system, a storage medium and an electronic device, which at least solve the problem that a large language model cannot accurately understand and intelligently control data reported by a device in the related technology. According to one embodiment of the application, the device control method is applied to intelligent devices and comprises the steps of constructing a plurality of data uploading interfaces according to prompt word requirements of a cloud large model to obtain a data uploading interface library, wherein the data uploading interfaces comprise data uploading interfaces corresponding to different functions of the intelligent devices, acquiring target function data associated with target functions of the intelligent devices from device data, determining the target data uploading interfaces corresponding to the target functions from the data uploading interface library, transmitting the target function data to the cloud large model through the target data uploading interfaces, receiving control instructions sent by the cloud large model, and controlling the intelligent devices according to the control instructions, wherein the control instructions are generated after the cloud large model infers the target control data. In an exemplary embodiment, determining a target data uploading interface corresponding to the target function from the data uploading interface library includes determining a first data uploading interface matched with the target function from the data uploading interface library, wherein an interface function of the first data uploading interface is the same as the target function, acquiring an interface parameter of the first data uploading interface and a parameter value range corresponding to the interface parameter, and determining the first data uploading interface as the target data uploading interface when determining that a data type of the target function data is consistent with a data type of the interface parameter and the target function data is consistent with the parameter value range. In an exemplary embodiment, uploading the target function data to a cloud big model through the target data uploading interface comprises determining an interface parameter format corresponding to the target data uploading interface, packaging the target device data and the target function according to the interface parameter format to obtain packaged data, and transmitting the packaged data to the cloud big model through a preset network transmission protocol. According to another aspect of the embodiment of the application, the device control method is applied to a cloud large model and comprises the steps of receiving target function data which is uploaded by intelligent devices and is associated with target functions of the intelligent devices, reasoning the target function data based on preset prompt words to obtain reasoning results, generating control instructions according to the reasoning results, and sending the control instructions to the intelligent devices to control the intelligent devices. In an exemplary embodiment, the inference is performed on the target function data based on preset prompt words to obtain an inference result, and the inference method comprises the steps of judging whether the target function data meets preset conditions according to knowledge of a knowledge base and preset rules, determining expected function data corresponding to the preset conditions when the target function data does not meet the preset conditions, and determining the expected function data as the inference result. In an exemplary embodiment, generating a control instruction according to the reasoning result and sending the control instruction to the intelligent device includes determining a target working state corresponding to t