US 12,190,696 B2
Methods for indoor gas leakage disposal of smart gas and internet of things systems thereof
Zehua Shao, Chengdu (CN); Yaqiang Quan, Chengdu (CN); Bin Liu, Chengdu (CN); Xiaojun Wei, Chengdu (CN); and Lei Zhang, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on Aug. 8, 2023, as Appl. No. 18/446,461.
Application 18/446,461 is a continuation of application No. 18/052,929, filed on Nov. 6, 2022, granted, now 11,854,360.
Claims priority of application No. 202211283273.2 (CN), filed on Oct. 20, 2022.
Prior Publication US 2023/0386314 A1, Nov. 30, 2023
Int. Cl. G08B 17/10 (2006.01); G16Y 20/10 (2020.01)
CPC G08B 17/10 (2013.01) [G16Y 20/10 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method for indoor gas leakage disposal of smart gas, wherein the method is implemented by a smart gas indoor safety management sub platform, including:
obtaining monitoring information and user description information from a smart gas data center, wherein the monitoring information includes alarm information and gas terminal monitoring data, the monitoring information is obtained from a smart gas object platform through a smart gas sensor network platform by the smart gas data center, the user description information includes user-defined alarm information uploaded by a user, and the user description information is obtained from a smart gas user platform through a smart gas service platform by the smart gas data center;
determining a cause of gas leakage based on the monitoring information and the user description information;
determining a plurality of candidate solutions based on the cause of gas leakage, including:
determining a feature vector based on the monitoring information, the user description information, a probability of misreporting, and the cause of gas leakage, wherein the probability of misreporting is determined based on a misreporting probability determination model, and the misreporting probability determination model is a machine learning model; and
determining the plurality of candidate solutions based on a similarity between the feature vector and a reference vector in a database, wherein the database includes a plurality of the reference vectors and candidate solutions corresponding to the plurality of reference vectors; and
determining an effective solution rate of the candidate solutions, and determining a target solution among the candidate solutions according to the effective solution rate.