US 11,985,271 B2
Methods, internet of things systems, and media for seat management of smart gas call center
Zehua Shao, Chengdu (CN); Yaqiang Quan, Chengdu (CN); Xiaojun Wei, Chengdu (CN); Bin Liu, Chengdu (CN); and Yuefei Wu, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on May 22, 2023, as Appl. No. 18/321,767.
Claims priority of application No. 202310432156.6 (CN), filed on Apr. 21, 2023.
Prior Publication US 2023/0291838 A1, Sep. 14, 2023
Int. Cl. H04M 3/00 (2006.01); G06Q 10/0631 (2023.01); G06Q 30/015 (2023.01); G06Q 50/06 (2012.01); H04M 3/51 (2006.01); H04M 3/523 (2006.01)
CPC H04M 3/5232 (2013.01) [G06Q 10/06311 (2013.01); G06Q 30/015 (2023.01); G06Q 50/06 (2013.01); H04M 3/5183 (2013.01); H04M 3/5238 (2013.01)] 4 Claims
OG exemplary drawing
 
1. A method for seat management of a smart gas call center, wherein the method is performed by a processor of a smart gas management platform in an Internet of Things system for seat management of a smart gas call center, and the method comprises:
obtaining gas usage data, the gas usage data including at least a historical gas usage rate;
generating, based on the gas usage data, a predicted call feature of a smart gas call center within a target time period;
generating, based on the predicted call feature, a preferred seat feature of the smart gas call center within the target time period, the preferred seat feature including a count of customer services in each of one or more time periods within the target time period; and
transmitting the preferred seat feature to a terminal of the smart gas call center, wherein
the generating, based on the gas usage data, a predicted call feature of a smart gas call center within a target time period includes:
predicting, based on the gas usage data, a predicted gas usage feature within the target time period, wherein the predicted gas usage feature includes gas usage rates at a plurality of time points in the target time period; and
generating the predicted call feature of the smart gas call center within the target time period based on the gas predicted usage feature, the predicted call feature within the target time period being further related to a gas business feature;
the gas usage data includes gas usage data of at least one user type, the predicted gas usage feature includes a predicted gas usage feature of the at least one user type, and the predicted call feature includes a predicted call feature of at least one call type;
the generating the predicted call feature of the smart gas call center within the target time period based on the predicted gas usage feature includes:
inputting the predicted gas usage feature of the at least one user type into a call feature prediction model, analyzing the predicted gas usage feature of the at least one user type through the call feature prediction model, and outputting the predicted call feature of the at least one call type within the target time period, wherein the call feature prediction model is a machine learning model;
the inputting the predicted gas usage feature of the at least one user type into a call feature prediction model, analyzing the predicted gas usage feature of the at least one user type through the call feature prediction model, and outputting the predicted call feature of the at least one call type within the target time period includes:
inputting the predicted gas usage feature of the at least one user type and a gas business feature of the at least one user type into the call feature prediction model, analyzing the predicted gas usage feature of the at least one user type and the gas business feature of the at least one user type through the call feature prediction model, and outputting the predicted call feature of the at least one call type within the target time period and a call tolerance of the at least one call type; and
the generating, based on the predicted call feature, a preferred seat feature of the smart gas call center within the target time period includes:
generating, based on the predicted call feature, at least one group of candidate seat features; and
performing at least one round of iterative optimization on the at least one group of candidate seat features, and determining the preferred seat feature from the at least one group of candidate seat features, wherein
the iterative optimization includes: calculating an evaluation value of the at least one group of candidate seat features; and performing an elimination screening on the evaluation value, wherein the evaluation value is related to a gas business feature of at least one user type, and the gas business feature of the at least one user type includes a gas usage frequency and a gas calorific sensitivity.