US 11,928,623 B2
Methods and smart gas internet of things systems for maintenance scheduling and management based gas safety
Zehua Shao, Chengdu (CN); Yong Li, Chengdu (CN); Yongzeng Liang, Chengdu (CN); Xiaojun Wei, Chengdu (CN); and Junyan Zhou, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on Nov. 2, 2022, as Appl. No. 18/052,195.
Claims priority of application No. 202211256360.9 (CN), filed on Oct. 14, 2022.
Prior Publication US 2023/0125033 A1, Apr. 20, 2023
Int. Cl. G06Q 10/0631 (2023.01); G16Y 10/35 (2020.01); G16Y 20/20 (2020.01)
CPC G06Q 10/06312 (2013.01) [G16Y 10/35 (2020.01); G16Y 20/20 (2020.01)] 6 Claims
OG exemplary drawing
 
1. A method for maintenance scheduling and management based on gas safety, wherein the method is implemented by a smart gas Internet of Things system for maintenance scheduling and management based on gas safety, and the smart gas Internet of Things system includes a smart gas user platform, a smart gas service platform, a smart gas safety management platform, a smart gas sensor network platform and a smart gas object platform, and the method is executed by at least one processor of the smart gas safety management platform, the method comprising:
obtaining gas-related features of at least one area, wherein the gas-related features include gas consumption features;
determining alert vectors of the at least one area based on the gas-related features by methods for feature extraction, which include multilayer perceptrons, convolutional neural networks, and residual networks, the alert vectors including a leakage alert value;
determining a count of on-call maintenance personnel in the at least one area based on the alert vectors;
determining whether the count of on-call maintenance personnel meets a preset threshold; and
in response to a determination that there is at least one area where the count of on-call maintenance personnel meets the preset threshold, determining a real-time scheduling policy based on a scheduling capability value of the at least one area where the count of on-call maintenance personnel meets the preset threshold, wherein the real-time scheduling policy includes a scheduling quantity and a scheduling location when on-call maintenance personnel is scheduled, and determining the scheduling capability value includes:
performing multiple rounds of iterative update on the scheduling capability value, wherein when an updated scheduling capability value meets a preset condition, the update ends; and
determining the real-time scheduling policy based on the updated scheduling capability value, wherein the multiple rounds of iterative update includes:
in a first round: determining an initial scheduling capability value of each node of an area map, and using the initial scheduling capability value as a scheduling capability value to be updated, wherein the area map includes a plurality of nodes and a plurality of edges, each node denoting each area, each edge denoting a relationship between two connected nodes, a feature of the node includes a count of current on-call maintenance personnel in the area, a feature of the edge includes a distance between the two nodes and a weight value, the weight value being related to household features of the two nodes connected by the edge;
in a tth round (t larger than 1): updating the scheduling capability value to be updated of each node based on a preset algorithm, using an updated scheduling capability value of each node in the tth round as a scheduling capability value to be updated of each node in (t+1) round, wherein the updated scheduling capability value of node i in the tth round is determined based on the updated scheduling capability value of the node i in the (t−1)th round, a change value between an updated scheduling capability value of a node connected to the node i and a scheduling capability value before update of the node connected to the node i, and a feature of an edge connected the node i.