| CPC H04L 67/1097 (2013.01) [G16Y 10/35 (2020.01); G16Y 40/35 (2020.01); H04L 67/1004 (2013.01); H04L 67/1095 (2013.01); H04L 67/568 (2022.05)] | 13 Claims |
|
1. A method for managing gas data, implemented by at least one processor of an Internet of Things (IoT) system for managing the gas data, wherein the IoT system includes 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 includes a terminal device;
the smart gas service platform includes a first server;
the smart gas management platform includes a gas business management sub-platform, a non-gas business management sub-platform, and a smart gas data center, the gas business management sub-platform includes a second server, the non-gas business management sub-platform includes a third server, the smart gas data center includes at least one sub-data center, wherein the at least one sub-data center is configured to store data blocks and redundant data blocks corresponding to to-be-stored-data, and each of the at least one sub-data center includes at least one storage node;
the smart gas sensor network platform includes a communication network and a gateway; and
the smart gas object platform includes various types of gas pipeline network devices and monitoring devices;
the method comprising:
obtaining to-be-stored-gas data and downstream user features corresponding to the to-be-stored-gas data, wherein the to-be-stored-gas data refers to gas-related data that needs to be stored in the smart gas data center, and the downstream user features refer to features related to gas users;
determining a user importance level based on the downstream user features;
determining accessing frequency distribution features of the to-be-stored-gas data, wherein the accessing frequency distribution features refer to a probability distribution of accessing frequencies of different data types of the to-be-stored-gas data;
determining a risk degree of data through a second prediction model based on the accessing frequency distribution features, the second prediction model being a machine learning model, wherein the risk degree of data refers to a probability of data abnormalities, wherein the second prediction model is obtained by training based on second training samples with second labels, the second training samples include sample to-be-stored-gas data and sample accessing frequency distribution features corresponding to the sample to-be-stored-gas data, the second labels refer to a frequency of abnormity of the sample to-be-stored-gas data, and the second labels are obtained based on historical abnormal data in the smart gas data center;
constructing query feature vectors based on pipeline data obtained from the gas pipeline network devices and monitor devices, determining a risk degree of a gas pipeline by performing vector matching in a vector database based on the query feature vectors, wherein the pipeline data includes information related to the gas pipeline;
determining a gas data level based on the user importance level, the risk degree of data, and the risk degree of the gas pipeline;
determining a data redundancy level through a preset algorithm based on the gas data level, an estimated retention time of the to-be-stored-gas data, and an estimated accessing frequency of the to-be-stored-gas data, wherein estimated retention time refers to an estimated time period for which the to-be-stored-gas data needs to be retained in the smart gas data center, and the estimated accessing frequency refers to an estimated frequency at which the to-be-stored-gas data is accessed;
generating redundant data blocks of the to-be-stored-gas data based on a data redundancy ratio corresponding to the data redundancy level; and
storing the to-be-stored gas data and the redundant data blocks in the at least one storage node of the at least one sub-data center based on loading distribution features, wherein the loading distribution features refer to criteria of the at least one sub-data center for receiving data in a gas data processing task.
|