CN-121993894-A - Intelligent control method and device for air conditioner, electronic equipment and storage medium

CN121993894ACN 121993894 ACN121993894 ACN 121993894ACN-121993894-A

Abstract

The application relates to the technical field of intelligent control of air conditioners, and discloses an intelligent control method, an intelligent control device, electronic equipment and a storage medium of an air conditioner, wherein the method comprises the following steps: the radar data is analyzed through the first offline AI model, the perception of the gesture is realized, the Bluetooth dynamic characteristics are analyzed through the second offline AI model, the identification of the authorized identity and the active intention is realized, the identification results of the two are fused and calculated through the confidence score model, double evidence of physical existence and identity signals is synthesized, and the control instruction of the air conditioner is generated. The application has the beneficial technical effects of reducing false triggering rate caused by pets, mobile interference or equipment carry-over, guaranteeing user privacy safety, eliminating network delay and providing personalized strategies which are more in line with user habits.

Inventors

LI GUOJUN
ZHANG JIAHU
ZHOU YUDONG
ZHOU YI
ZHANG CHUANJIAN
HE XIANGANG
HUANG YONG

Assignees

深圳唯创知音电子有限公司

Dates

Publication Date: 20260508
Application Date: 20260409

Claims (10)

1. An intelligent control method of an air conditioner is characterized by comprising the following steps: Periodically acquiring target characteristic data of a target sensing area through a preset human body interaction detection module, and acquiring Bluetooth signal intensity data through a Bluetooth module; based on the target feature data, performing human body recognition through a preset first offline AI model to obtain a first recognition result comprising human body presence judgment and gesture classification; Based on the Bluetooth signal intensity data, carrying out dynamic feature analysis through a preset second offline AI model to obtain a second identification result representing the approaching intention of the authorized terminal; fusing the first recognition result and the second recognition result to obtain a fused recognition result; Inputting the fusion recognition result into a preset confidence score model for calculation to obtain comprehensive confidence, and comparing the comprehensive confidence with a preset threshold value to obtain a comparison result; and generating a control instruction for the air conditioner according to the first identification result, the second identification result and the comparison result.
2. The intelligent control method of an air conditioner according to claim 1, wherein the step of performing human body recognition through a preset first offline AI model based on the target feature data to obtain a first recognition result including human body presence determination and gesture classification includes: based on the target feature data, identifying whether a human body target exists in the target sensing area through a preset first offline AI model; If a human body target exists in the target sensing area, extracting human body target data in the target characteristic data; And carrying out gesture recognition on the human body target data through a preset first offline AI model to obtain a gesture classification result, thereby obtaining a first recognition result.
3. The intelligent control method of an air conditioner according to claim 1, wherein the step of obtaining a second recognition result representing the approaching intention of the authorized terminal by performing dynamic feature analysis through a preset second offline AI model based on the bluetooth signal intensity data comprises: judging whether the Bluetooth signal strength data is derived from a bound authorized terminal or not; If the Bluetooth signal is from the bound authorized terminal, extracting dynamic change characteristics of the Bluetooth signal intensity in a preset time window; based on the dynamic change characteristics, analyzing the approaching behavior mode of the authorized terminal through a preset second offline AI model; And outputting the confidence degree representing the active approaching intention of the user as the second recognition result according to the approaching behavior mode.
4. The intelligent control method of an air conditioner according to claim 1, wherein the step of generating the control command for the air conditioner according to the first recognition result, the second recognition result, and the comparison result comprises: Judging whether a human body target exists in the first identification result or not, and identifying whether the Bluetooth signal strength data belongs to a bound authorized terminal or not in the second identification result; When the first recognition result judges that a human body target exists and the second recognition result confirms that a Bluetooth signal is derived from a bound authorized terminal, combining the gesture feature in the first recognition result, the dynamic feature confidence coefficient in the second recognition result and the environmental context feature to form a multidimensional feature vector as the fusion recognition result.
5. The intelligent control method of an air conditioner according to claim 1, wherein the step of generating the control command for the air conditioner according to the first recognition result, the second recognition result, and the comparison result comprises: when the comprehensive confidence coefficient is lower than a first preset threshold value, generating an instruction for controlling the air conditioner to be closed; When the comprehensive confidence coefficient reaches or is higher than a second preset threshold value, generating an instruction for controlling the air conditioner to be started, wherein the second preset threshold value is larger than the first preset threshold value; And when the first identification result judges that the human body target leaves but the Bluetooth signal strength data indicate that the authorized terminal is still in the preset range, generating an instruction for controlling the air conditioner to enter a delay closing process.
6. The intelligent control method of an air conditioner according to claim 1, wherein the step of generating the control command for the air conditioner according to the first recognition result, the second recognition result, and the comparison result comprises: If the first recognition result judges that the human body target does not exist and the second recognition result judges that the terminal signal is not authorized, a first instruction for controlling the air conditioner to be closed or kept closed is generated; If the first recognition result judges that a human body target exists and the comprehensive confidence coefficient is lower than a first threshold value, generating a second instruction for controlling the air conditioner to be closed or kept closed; If the first identification result judges that a human body target exists, the second identification result judges that the Bluetooth signal strength data is derived from an authorized terminal, and the comprehensive confidence reaches a second threshold, a third instruction for controlling the air conditioner to be started or switched to a preset mode is generated, wherein the second threshold is larger than the first threshold; and if the first identification result judges that the human body target does not exist, and the second identification result judges that the authorization terminal signal exists, generating a fourth instruction for controlling the air conditioner to enter a delay closing process.
7. The intelligent control method of an air conditioner according to claim 1, wherein after the step of generating the control command for the air conditioner according to the first recognition result, the second recognition result, and the comparison result, further comprising: receiving operation data of a user on an air conditioner, and forming a positive sample according to the Bluetooth signal intensity data corresponding to the operation data during regulation and control; And optimizing parameters of the confidence score model by using the positive sample through an online learning algorithm to obtain an optimized confidence score model.
8. An intelligent control device of an air conditioner, the device comprising: The acquisition module is used for periodically acquiring target characteristic data of a target sensing area through a preset human body interaction detection module and acquiring Bluetooth signal intensity data through a Bluetooth module; the identification module is used for carrying out human body identification through a preset first offline AI model based on the target characteristic data to obtain a first identification result comprising human body existence judgment and gesture classification; the analysis module is used for carrying out dynamic characteristic analysis through a preset second offline AI model based on the Bluetooth signal intensity data to obtain a second identification result representing the approaching intention of the authorized terminal; The fusion module is used for fusing the first identification result and the second identification result to obtain a fusion identification result; The calculation module is used for inputting the fusion recognition result into a preset confidence score model for calculation to obtain comprehensive confidence, and comparing the comprehensive confidence with a preset threshold value to obtain a comparison result; and the generation module is used for generating a control instruction for the air conditioner according to the first identification result, the second identification result and the comparison result.
9. A computer-readable storage medium, characterized in that a computer program is stored, which, when being executed by a processor, causes the processor to perform the steps of the intelligent control method of an air conditioner according to any one of claims 1 to 7.
10. An electronic device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps of the intelligent control method of an air conditioner according to any one of claims 1 to 7.

Description

Intelligent control method and device for air conditioner, electronic equipment and storage medium Technical Field The present invention relates to the field of intelligent control technologies of air conditioners, and in particular, to an intelligent control method and apparatus for an air conditioner, an electronic device, and a storage medium. Background Currently, intelligent control of an air conditioner mainly depends on a single sensor technology or a scheme requiring cloud cooperation, and a scheme based on a single sensor, such as a scheme of human infrared (PIR) or simple radar, can only sense movement, cannot distinguish interference of a user and a pet, and is easy to cause false triggering. In addition, solutions that rely on networks and cloud have the risk of response delay and privacy disclosure. Therefore, in the prior art, accurate judgment is difficult to realize in an offline environment, so that the air conditioner is inaccurate to control, and the user experience is poor. Disclosure of Invention Based on this, it is necessary to provide an intelligent control method, an intelligent control device, an electronic device and a storage medium for an air conditioner, aiming at the intelligent control problem of the existing air conditioner. An intelligent control method of an air conditioner, the method comprising: Periodically acquiring target characteristic data of a target sensing area through a preset human body interaction detection module, and acquiring Bluetooth signal intensity data through a Bluetooth module; based on the target feature data, performing human body recognition through a preset first offline AI model to obtain a first recognition result comprising human body presence judgment and gesture classification; Based on the Bluetooth signal intensity data, carrying out dynamic feature analysis through a preset second offline AI model to obtain a second identification result representing the approaching intention of the authorized terminal; fusing the first recognition result and the second recognition result to obtain a fused recognition result; Inputting the fusion recognition result into a preset confidence score model for calculation to obtain comprehensive confidence, and comparing the comprehensive confidence with a preset threshold value to obtain a comparison result; and generating a control instruction for the air conditioner according to the first identification result, the second identification result and the comparison result. Further, the step of performing human body recognition through a preset first offline AI model based on the target feature data to obtain a first recognition result including human body presence determination and gesture classification includes: based on the target feature data, identifying whether a human body target exists in the target sensing area through a preset first offline AI model; If a human body target exists in the target sensing area, extracting human body target data in the target characteristic data; And carrying out gesture recognition on the human body target data through a preset first offline AI model to obtain a gesture classification result, thereby obtaining a first recognition result. Further, the step of obtaining a second recognition result representing the approach intention of the authorized terminal by performing dynamic feature analysis through a preset second offline AI model based on the bluetooth signal intensity data includes: judging whether the Bluetooth signal strength data is derived from a bound authorized terminal or not; If the Bluetooth signal is from the bound authorized terminal, extracting dynamic change characteristics of the Bluetooth signal intensity in a preset time window; based on the dynamic change characteristics, analyzing the approaching behavior mode of the authorized terminal through a preset second offline AI model; And outputting the confidence degree representing the active approaching intention of the user as the second recognition result according to the approaching behavior mode. Further, the step of generating a control command for the air conditioner according to the first identification result, the second identification result and the comparison result includes: Judging whether a human body target exists in the first identification result or not, and identifying whether the Bluetooth signal strength data belongs to a bound authorized terminal or not in the second identification result; When the first recognition result judges that a human body target exists and the second recognition result confirms that a Bluetooth signal is derived from a bound authorized terminal, combining the gesture feature in the first recognition result, the dynamic feature confidence coefficient in the second recognition result and the environmental context feature to form a multidimensional feature vector as the fusion recognition result. Further, the step of generating a control command for the air