Air conditioner, data transmission method, and air conditioning system
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing air conditioning systems face challenges in reducing data traffic for artificial intelligence (AI) learning while maintaining learning accuracy, as transmitting all operation history data results in high communication traffic, and simply deleting data can lead to insufficient information for accurate AI learning.
Innovation Solution
An air conditioning system with an adapter that acquires operation history data, determines the amount of change between continuous data points, and thins the data by deleting entries with insignificant changes, thereby reducing the data transmitted to the server while maintaining learning accuracy by preserving critical data points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all operation history data are transmitted to the server device, then learning accuracy of AI is maintained, but communication traffic between air conditioner and server device becomes large
Solution Approach 1:
The patent extracts only the essential features from operation history data by calculating feature quantities that represent characteristic patterns, rather than transmitting all raw data. This extraction process isolates the most important information for AI learning while removing redundant data, thereby reducing communication traffic while preserving learning accuracy.
Solution Approach 2:
The patent transforms raw operation history data into derived parameters (feature quantities) that capture the essential characteristics of the data. By changing the representation from raw data to extracted features, the system reduces data volume for transmission while maintaining the information necessary for accurate AI learning.
2Quantity of substance
If some operation history data are deleted to reduce communication traffic, then data transmission is reduced, but learning accuracy of AI may be lowered due to insufficient data
Solution Approach 1:
Instead of randomly deleting data, the patent extracts essential features from the data, ensuring that the most important information is retained. This selective extraction maintains learning accuracy by preserving characteristic patterns while reducing overall data volume for transmission.
Solution Approach 2:
The patent transforms raw data into meaningful parameters that capture essential information. This parameter transformation ensures that reduced data sets still contain the critical information needed for accurate AI learning, preventing degradation of learning accuracy.
3Quantity of substance
If operation history data are compressed and converted to minimum data, then communication traffic is reduced, but data processing time and complexity increase
Solution Approach 1:
The patent performs preliminary extraction of feature quantities at the air conditioner side before transmission. By pre-processing the data to extract essential features locally, the system reduces the burden on the server and minimizes overall processing time, as the server receives already-processed essential information rather than raw data requiring extensive processing.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An air conditioner (2) comprises: a control unit (2B,14) that controls the air conditioner using a learning model, and an adapter (3) including a communication unit (12) that communicates with a server device (5) that generates the learning model on the basis of operation history data of the air conditioner. The adapter (3) includes an acquisition unit (14A), a determination unit (14B), an erasing unit (14C), and a transmission unit (14D). The acquisition unit (14A) acquires the operation history data every predetermined cycle from the air conditioner. The determination unit (14B) determines whether an amount of change between pieces of temporally continuous data out of the operation history data acquired by the acquisition unit is within a predetermined range. The erasing unit (14C) leaves at least one of the pieces of continuous data and deletes the other pieces of continuous data in a case where the amount of change between the pieces of the continuous data is within the predetermined range. The transmission unit (14D) transmits the operation history data after the other pieces of continuous data is deleted by the erasing unit to the server device. Also, time stamps are added to the operation history data acquired every predetermined cycle.