Methods for regulating flow meters of industrial and commercial units of smart gas, internet of things (IOT) systems and media thereof

1 . A method for regulating a flow meter of an industrial and commercial unit of a smart gas, wherein the method is implemented by a smart gas management platform of an Internet of Things (IoT) system comprising:

regulating the flow meter of the industrial and commercial unit of the smart gas, wherein the IoT system further comprises a smart gas user platform, a smart gas service platform, the smart gas management platform, a smart gas sensor network platform, and a smart gas object platform, wherein the smart gas user platform is configured to upload user feedback data to the smart gas management platform via the smart gas service platform based on a gas user sub-platform, and the smart gas service platform is configured to obtain continuous gas supply parameters from the smart gas management platform and send the continuous gas supply parameters to the smart gas user platform, the smart gas object platform comprises a gas pipeline network equipment object sub-platform, the smart gas object platform includes a valve control equipment;

obtaining operation data, a time feature, and the user feedback data, the operation data including gas usage data and gas outage feedback data of the industrial and commercial unit;

determining, based on the operation data, the time feature, and the user feedback data, a gas flow trend of a low balance user; and

determining, based on the gas flow trend, the time feature, and the gas outage feedback data, the continuous gas supply parameters of the low balance user, the continuous gas supply parameters including continuous gas supply quota and a continuous gas supply time, wherein the continuous gas supply quota includes gas supply quotas for a plurality of time periods;

predicting, based on the gas flow trend and the time feature, a planned gas outage time;

determining, based on the planned gas outage time, the time feature, and the gas outage feedback data, the continuous gas supply parameters;

determining, based on a candidate continuous gas supply time, the planned gas outage time, the time feature, and the gas outage feedback data, a gas outage influence value, the gas outage influence value refers to a value for assessing how a gas outage affects an user;

determining, based on the candidate continuous gas supply time, the planned gas outage time, the time feature, the gas outage feedback data, and the gas flow trend, the gas flow trend refers to a gas flow value reflecting a future gas usage trend, the gas outage influence value through a first model, wherein the first model is a neural network model, wherein the first model is obtained by a training process using a plurality of training samples with labels, wherein the training samples include sample historical continuous gas supply times, sample historical planned gas outage times, sample historical time features, sample historical gas flow trends, and sample historical gas outage feedback data of a sample historical moment, wherein the historical gas outage feedback data refers to the gas outage feedback data prior to the historical moment, wherein the labels are labeled based on the gas outage influence value corresponding to the historical continuous gas supply times, wherein the gas outage influence value is determined based on subsequent user feedback, wherein the subsequent user feedback includes a user gas application time and a user attitude feedback score after an actual gas outage;

determining, based on the gas outage influence value, the continuous gas supply time; and

controlling the smart gas object platform, based on the continuous gas supply parameters, to utilize the valve control equipment to continue supplying gas to the low balance user based on the continuous gas supply quota and the continuous gas supply time;

after a paid gas quota of the low balance user is used up, continuing to supply the gas to the low balance user for a period of time, and allocating different gas supply quotas for the low balance user for different time periods in a time-gas supply distribution,

wherein the determining based on the gas flow trend of the low balance user based on the operation data, the time feature, and the user feedback data includes:

determining, based on the operation data, the time feature, and the user feedback data, a customer flow feature of a future time period; and

determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend; and

wherein the determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend includes:

determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend through a second model, the second model being a machine learning model; and

wherein the determining, based on the operation data, the time feature, and the user feedback data, the customer flow feature of the future time period includes:

determining, based on the operation data and the time feature, a first candidate customer flow feature;

determining, based on the user feedback data, a second candidate customer flow feature; and

determining, based on the first candidate customer flow feature and the second candidate customer flow feature, the customer flow feature of the future time period; and

wherein the determining, based on the first candidate customer flow feature and the second candidate customer flow feature, the customer flow feature of the future time period includes:

determining the customer flow feature of the future time period by performing a weighted summation on the first candidate customer flow feature and the second candidate customer flow feature.

2 . The method of claim 1 , wherein the determining, based on the operation data and the time feature, the first candidate customer flow feature includes:

determining, based on the operation data and the time feature, a plurality of customer flow feature centers of the future time period by clustering; and

determining, based on the plurality of customer flow feature centers of the future time period, the first candidate customer flow feature.

3 . The method of claim 2 , wherein the determining, based on the operation data and the time feature, the plurality of customer flow feature centers of the future time period by the clustering comprises:

constructing, based on actual operation data and actual customer flow features of a plurality of surrounding industrial and commercial units within a first preset time period, clustering feature vectors corresponding to the plurality of surrounding industrial and commercial units, and performing the clustering on the clustering feature vectors to form a plurality of clusters,

wherein each of the plurality of clusters corresponds to a clustering center, and each of the clustering centers corresponds to one of the customer flow feature centers of the future time period;

calculating, based on the actual operation data and the actual customer flow features of a current industrial and commercial unit within a second preset time period, a target distance between the current industrial and commercial unit and each of the plurality of clusters, and determining a target cluster to which the current industrial and commercial unit belongs;

determining, based on a customer flow feature center of the target cluster, a target industrial and commercial unit corresponding to the customer flow feature center, and determining the actual customer flow features of the target industrial and commercial unit in a subsequent continuous time period of a target time period as the first candidate customer flow feature of the current industrial and commercial unit, wherein a duration of the first preset time period is longer than a duration of the second preset time period, and both the first preset time period and the second preset time period are historical time periods.

4 . The method of claim 1 , wherein the predicting, based on the gas flow trend and the time feature, the planned gas outage time includes:

determining, based on a current gas amount, the gas flow trend, and the time feature, the planned gas outage time through a third model, the third model being the machine learning model.

5 . The method of claim 1 , wherein the determining, based on the planned gas outage time, the time feature, and the gas outage feedback data, the continuous gas supply parameters includes:

determining, based on the planned gas outage time, the time feature, the gas outage feedback data, and the customer flow feature of the future time period, the continuous gas supply quota through a fourth model, the fourth model being the machine learning model.

6 . The method of claim 5 , wherein the fourth model is obtained by a training process, and the training process includes:

obtaining the plurality of training samples with the labels, the plurality of training samples including the sample historical planned gas outage times, the sample historical time features, the sample historical gas outage feedback data, and sample historical customer flow features of future time periods, the labels being gas consumption of users at various time periods within a first time threshold after the planned gas outage time of the historical gas outage feedback data, the first time threshold being related to the continuous gas supply time; and

obtaining the fourth model by training an initial fourth model based on the plurality of the training samples and the labels thereof.

7 . An Internet of Things (IoT) system for regulating a flow meter of an industrial and commercial unit of a smart gas, comprising:

a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, and a smart gas object platform which interact in sequence, wherein the smart gas user platform is configured to upload user feedback data to the smart gas management platform via the smart gas service platform based on a gas user sub-platform, and the smart gas service platform is configured to obtain continuous gas supply parameters from the smart gas management platform and send the continuous gas supply parameters to the smart gas user platform, the smart gas object platform comprises a gas pipeline network equipment object sub-platform, the smart gas object platform includes a valve control equipment, wherein the smart gas management platform is configured to:

obtain operation data, a time feature, and the user feedback data, the operation data including gas usage data and gas outage feedback data of the industrial and commercial unit;

determine, based on the operation data, the time feature, and the user feedback data, a gas flow trend of a low balance user; and

determine, based on the gas flow trend, the time feature, and the gas outage feedback data, the continuous gas supply parameters of the low balance user, the continuous gas supply parameters including continuous gas supply quota and a continuous gas supply time, wherein the continuous gas supply quota includes gas supply quotas for a plurality of time periods;

predicting, based on the gas flow trend and the time feature, a planned gas outage time;

determining, based on the planned gas outage time, the time feature, and the gas outage feedback data, the continuous gas supply parameters;

determining, based on a candidate continuous gas supply time, the planned gas outage time, the time feature, and the gas outage feedback data, a gas outage influence value, the gas outage influence value refers to a value for assessing how a gas outage affects an user;

determining, based on the candidate continuous gas supply time, the planned gas outage time, the time feature, the gas outage feedback data, and the gas flow trend, the gas flow trend refers to a gas flow value reflecting a future gas usage trend, the gas outage influence value through a first model, wherein the first model is a neural network model, wherein the first model is obtained by a training process using a plurality of training samples with labels, wherein the training samples include sample historical continuous gas supply times, sample historical planned gas outage times, sample historical time features, sample historical gas flow trends, and sample historical gas outage feedback data of a sample historical moment, wherein the historical gas outage feedback data refers to the gas outage feedback data prior to the historical moment, wherein the labels are labeled based on the gas outage influence value corresponding to the historical continuous gas supply times, wherein the gas outage influence value is determined based on subsequent user feedback, wherein the subsequent user feedback includes a user gas application time and a user attitude feedback score after an actual gas outage;

determining, based on the gas outage influence value, the continuous gas supply time; and

controlling the smart gas object platform, based on the continuous gas supply parameters, to utilize the valve control equipment to continue supplying gas to the low balance user based on the continuous gas supply quota and the continuous gas supply time;

after a paid gas quota of the low balance user is used up, continuing to supply the gas to the low balance user for a period of time, and allocating different gas supply quotas for the low balance user for different time periods in a time-gas supply distribution,

wherein the determining based on the gas flow trend of the low balance user based on the operation data, the time feature, and the user feedback data includes:

determining, based on the operation data, the time feature, and the user feedback data, a customer flow feature of a future time period; and

determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend; and

wherein the determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend includes:

determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend through a second model, the second model being a machine learning model; and

wherein the determining, based on the operation data, the time feature, and the user feedback data, the customer flow feature of the future time period includes:

determining, based on the operation data and the time feature, a first candidate customer flow feature;

determining, based on the user feedback data, a second candidate customer flow feature; and

determining, based on the first candidate customer flow feature and the second candidate customer flow feature, the customer flow feature of the future time period; and

wherein the determining, based on the first candidate customer flow feature and the second candidate customer flow feature, the customer flow feature of the future time period includes:

determining the customer flow feature of the future time period by performing a weighted summation on the first candidate customer flow feature and the second candidate customer flow feature.

8 . The IoT system of claim 7 , wherein the smart gas management platform includes a smart customer service management sub-platform, a smart operation management sub-platform, and a smart gas data center; and

the smart customer service management sub-platform performs two-way interaction with the smart gas data center, the smart operation management sub-platform performs two-way interaction with the smart gas data center, and the smart customer service management sub-platform and the smart operation management sub-platform obtain data from the smart gas data center and feedback corresponding operation information.

9 . The IoT system of claim 7 , wherein the smart gas management platform is further configured to:

determine, based on the operation data and the time feature, a plurality of customer flow feature centers of the future time period by clustering; and

determine, based on the plurality of customer flow feature centers of the future time period, the first candidate customer flow feature.

10 . A non-transitory computer-readable storage medium storing computer instructions that, when executed by a processor, direct the processor to perform operations comprising:

regulating a flow meter of an industrial and commercial unit of a smart gas, wherein an Internet of Things (IoT) system further comprises a smart gas user platform, a smart gas service platform, a smart gas management platform, a smart gas sensor network platform, and a smart gas object platform, wherein the smart gas user platform is configured to upload user feedback data to the smart gas management platform via the smart gas service platform based on a gas user sub-platform, and the smart gas service platform is configured to obtain continuous gas supply parameters from the smart gas management platform and send the continuous gas supply parameters to the smart gas user platform, the smart gas object platform comprises a gas pipeline network equipment object sub-platform, the smart gas object platform includes a valve control equipment;

obtaining operation data, a time feature, and the user feedback data, the operation data including gas usage data and gas outage feedback data of the industrial and commercial unit;

determining, based on the operation data, the time feature, and the user feedback data, a gas flow trend of a low balance user; and

determining, based on the gas flow trend, the time feature, and the gas outage feedback data, the continuous gas supply parameters of the low balance user, the continuous gas supply parameters including continuous gas supply quota and a continuous gas supply time, wherein the continuous gas supply quota includes gas supply quotas for a plurality of time periods;

predicting, based on the gas flow trend and the time feature, a planned gas outage time;

determining, based on the planned gas outage time, the time feature, and the gas outage feedback data, the continuous gas supply parameters;

determining, based on a candidate continuous gas supply time, the planned gas outage time, the time feature, and the gas outage feedback data, a gas outage influence value, the gas outage influence value refers to a value for assessing how a gas outage affects an user;

determining, based on the candidate continuous gas supply time, the planned gas outage time, the time feature, the gas outage feedback data, and the gas flow trend, the gas flow trend refers to a gas flow value reflecting a future gas usage trend, the gas outage influence value through a first model, wherein the first model is a neural network model, wherein the first model is obtained by a training process using a plurality of training samples with labels, wherein the training samples include sample historical continuous gas supply times, sample historical planned gas outage times, sample historical time features, sample historical gas flow trends, and sample historical gas outage feedback data of a sample historical moment, wherein the historical gas outage feedback data refers to the gas outage feedback data prior to the historical moment, wherein the labels are labeled based on the gas outage influence value corresponding to the historical continuous gas supply times, wherein the gas outage influence value is determined based on subsequent user feedback, wherein the subsequent user feedback includes a user gas application time and a user attitude feedback score after an actual gas outage;

determining, based on the gas outage influence value, the continuous gas supply time; and

controlling the smart gas object platform, based on the continuous gas supply parameters, to utilize the valve control equipment to continue supplying gas to the low balance user based on the continuous gas supply quota and the continuous gas supply time;

after a paid gas quota of the low balance user is used up, continuing to supply the gas to the low balance user for a period of time, and allocating different gas supply quotas for the low balance user for different time periods in a time-gas supply distribution,

wherein the determining based on the gas flow trend of the low balance user based on the operation data, the time feature, and the user feedback data includes:

determining, based on the operation data, the time feature, and the user feedback data, a customer flow feature of a future time period; and

determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend; and

wherein the determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend includes:

determining, based on the customer flow feature of the future time period and the time feature, the gas flow trend through a second model, the second model being a machine learning model; and

wherein the determining, based on the operation data, the time feature, and the user feedback data, the customer flow feature of the future time period includes:

determining, based on the operation data and the time feature, a first candidate customer flow feature;

determining, based on the user feedback data, a second candidate customer flow feature; and

determining, based on the first candidate customer flow feature and the second candidate customer flow feature, the customer flow feature of the future time period; and

wherein the determining, based on the first candidate customer flow feature and the second candidate customer flow feature, the customer flow feature of the future time period includes:

determining the customer flow feature of the future time period by performing a weighted summation on the first candidate customer flow feature and the second candidate customer flow feature.