Smart home appliance monitoring system for carbon footprint recording and method thereof

Abstract

This invention primarily utilizes home appliances to receive operational data from the external environment. A monitoring module receives this data and records usage time and power consumption for each appliance model. A carbon footprint calculation module then calculates carbon emissions based on this data. This allows for monitoring of the carbon emissions of home appliances and subsequent calculations using this data to provide energy-saving recommendations.

Claims

1. A smart home appliance monitoring system for carbon footprint, comprising: A plurality of home appliances generate appliance operation data during operation; a monitoring module connected to the home appliances to receive the appliance operation data, the monitoring module recording a usage time and a power consumption data for the appliance operation data corresponding to a model number of the appliance; a carbon footprint calculation module connected to the monitoring module to receive the usage time and the power consumption data, and calculating a carbon emission data based on the usage time and the power consumption data; A sensing device is connected to the monitoring module. The sensing device senses whether a human body is present in the current environment. When the sensing device senses a human body, it generates human body data and transmits it to the monitoring module. When the monitoring module receives the human body data, it marks the operation data of the home appliances to generate marked operation data. The monitoring module records the presence time when it receives the human body data where a human body is present, and the departure time when it receives the human body data where a human body is not present, based on the presence time and departure time. It also generates time data based on the presence time and departure time, and generates a user behavior model based on the marked operation data and the time data. A neural network model is connected to the monitoring module. The monitoring module generates multiple state vectors based on the user behavior model and carbon emission data, and sets multiple reward values ​​corresponding to a carbon emission standard in a sustainability report. These state vectors, multiple action parameters corresponding to the home appliances, and the reward values ​​are input into the neural network model for computation to generate an energy-saving suggestion that meets the carbon emission standard. A feedback module is connected to the home appliances and the monitoring module. When the feedback module receives a feedback signal, it receives the current operating data of the home appliance corresponding to the feedback signal and transmits the first interval of the feedback signal and the current operating data of the home appliance to the monitoring module. The carbon footprint calculation module calculates the electricity consumption of the home appliance based on the usage time and the power data, and converts the electricity consumption into carbon emission data based on a fixed carbon conversion factor. The carbon footprint calculation module checks the carbon emission data according to the carbon emission standard. When the carbon emission data does not meet the standard, the carbon footprint calculation module provides energy-saving suggestions that comply with the carbon emission standard based on the carbon emission data of each home appliance. The neural network model includes an input layer, multiple hidden layers, and an output layer. The input layer receives state vectors and action parameters, and identifies the corresponding model data in the state vectors and action parameters. The input layer outputs the state vectors, action parameters, and model data to multiple nodes in the hidden layers. The hidden layers assign a reward value to each node according to the carbon emission standard. The output layer receives various types of calculation data from the configuration output of the hidden layers and generates the energy-saving suggestions based on the calculation data.

2. A smart home appliance monitoring system for carbon footprint as described in claim 1, wherein, The monitoring module confirms the reward value corresponding to the carbon emission standard and the current operating data of the home appliance, and modifies the reward value according to the level in the feedback signal.

3. A smart home appliance monitoring system for carbon footprint as described in claim 1, comprising: A display module is connected to the monitoring module and the carbon footprint calculation module. The display module displays the appliance's operating data, usage time, power data, carbon emission data, energy-saving suggestions, or a combination of any two or more of these.

4. A method for monitoring the carbon footprint of a smart home appliance applied to a carbon footprint monitoring system as described in any one of claims 1 to 3, comprising: The operation data of a single home appliance is generated by multiple home appliances operating simultaneously. The system utilizes a monitoring module to receive operational data from home appliances and records usage time and power data corresponding to the model data of each appliance. It also uses a carbon footprint calculation module to receive the usage time and power data and calculate carbon emission data based on these data. A sensing device connected to the monitoring module detects the presence of a human body in the environment. When the sensing device detects a human body, it generates human body data and transmits it to the monitoring module. When the monitoring module receives the human body data, it marks the operational data of the home appliances to generate marked operational data. The monitoring module records the presence time when it receives data indicating the presence of a human body and the departure time when it receives data indicating the absence of a human body. It generates time data based on the presence time and departure time, and generates a user behavior model based on the marked operational data and the time data. Using a neural network model connected to the monitoring module, a plurality of state vectors are generated based on the user behavior model and the carbon emission data. A plurality of corresponding reward values ​​are set based on a carbon emission standard in a sustainability report. These state vectors, a plurality of action parameters corresponding to the home appliances, and the reward values ​​are input into the neural network model for computation to generate an energy-saving suggestion that meets the carbon emission standard. Furthermore, using a feedback module connected to the home appliances and the monitoring module, when the feedback module receives a feedback signal, it receives the current time's operating data of the home appliance corresponding to the feedback signal and transmits the first-order distance from the feedback signal and the current time's operating data of the home appliance to the monitoring module. The carbon footprint calculation module calculates the electricity consumption of the home appliance based on the usage time and power data, and converts the electricity consumption into carbon emission data based on a fixed carbon conversion factor. The carbon footprint calculation module checks the carbon emission data according to the carbon emission standard. When the carbon emission data does not meet the standard, the carbon footprint calculation module provides energy-saving suggestions that comply with the carbon emission standard based on the carbon emission data of each home appliance. The neural network model includes an input layer, multiple hidden layers, and an output layer. The input layer receives state vectors and action parameters, and identifies the corresponding model data in the state vectors and action parameters. The input layer outputs the state vectors, action parameters, and model data to multiple nodes in the hidden layers. The hidden layers assign a reward value to each node according to the carbon emission standard. The output layer receives various types of calculation data from the configuration output of the hidden layers and generates the energy-saving suggestions based on the calculation data.

Images