CN112491985A

CN112491985A - Remote meter reading data processing method, gas meter system and gas cloud platform

Info

Publication number: CN112491985A
Application number: CN202011276298.0A
Authority: CN
Inventors: 潘从平
Original assignee: Individual
Current assignee: Individual
Priority date: 2020-03-04
Filing date: 2020-03-04
Publication date: 2021-03-12
Also published as: CN111327706A; CN112398944A; CN111327706B

Abstract

The embodiment of the application provides a remote meter reading data processing method, a gas meter system and a gas cloud platform, gas meter data of a gas user in each marked gas use interval and a preset gas use label corresponding to each gas use behavior node are learned through a machine, the gas control habit of the gas user can be well learned, so that a control strategy mode meeting the habit of the gas user is subsequently provided for the gas user to perform automatic gas control, the operation amount caused by complicated and repeated control operation of the gas user is effectively reduced, and meanwhile, the condition that the use process is unexpected due to the fact that certain lost operation is difficult to avoid is reduced.

Description

Remote meter reading data processing method, gas meter system and gas cloud platform

Technical Field

The application relates to the technical field of Internet of things and machine learning, in particular to a remote meter reading data processing method, a gas meter system and a gas cloud platform.

Background

With the rapid development of the internet of things technology, the traditional gas meter is gradually replaced by the internet of things gas meter, and the gas internet of things system adopting the internet of things technology can provide additional internet of things services besides providing basic gas data record and gas supply for users. In the conventional scheme, a gas meter system is usually manually operated by a user to control the flow, on-off, duration and the like of gas. However, in the actual use process, the gas user often needs to frequently perform control operation, but in practice, for a single gas user, the gas use habit is usually relatively stable, the tedious and repeated control operation brings a relatively large operation amount to the gas user, and an accident may occur in the use process due to a certain time of operation failure, which affects the daily use effect.

Disclosure of Invention

In view of this, an object of the present application is to provide a remote meter reading data processing method, a gas meter system, and a gas cloud platform, which can well learn a gas control habit of a gas user by machine learning gas meter data of the gas user in each marked gas use interval and a preset gas use label corresponding to each gas use behavior node, so as to subsequently provide a control strategy mode conforming to the habit of the user for automatic control, thereby effectively reducing an operation amount caused by a tedious and repeated control operation of the gas user, and reducing a situation that an accident occurs in the use process due to an accidental operation at a certain time.

In a first aspect, the application provides a remote meter reading data processing method, which is applied to a gas cloud platform, wherein the gas cloud platform is in communication connection with gas internet of things systems of a plurality of different gas users, each gas internet of things system comprises a gas meter and a gas control internet of things device in communication connection with the gas meter, and the method comprises the following steps:

acquiring gas meter data of a gas user in each marked gas use interval, wherein the gas meter data is obtained by acquiring real-time data of the gas meter through the gas control Internet of things device in the gas Internet of things system of the gas user, the gas meter data comprises gas use behavior nodes and a gas use data sequence corresponding to each gas use behavior node, the gas use behavior nodes are used for representing gas control behaviors generated each time in the gas use process, and the gas use data sequence is used for recording gas use data under the corresponding gas use behavior nodes;

training to obtain a corresponding gas meter data analysis model according to the gas meter data of the gas user in each marked gas use interval and a preset gas use label corresponding to each gas use behavior node;

performing data analysis on the gas meter data of the gas user under each gas use behavior node in a preset time period according to the gas meter data analysis model to obtain a gas prediction label of a gas use data sequence corresponding to each gas use behavior node in the preset time period;

and generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction label of the gas use data sequence corresponding to each gas use behavior node, wherein the gas control instruction sequence comprises at least one control node and an instruction set corresponding to each control node.

In a possible design of the first aspect, the step of training to obtain a corresponding gas meter data analysis model according to the gas meter data of the gas user in each marked gas use interval and the preset gas use label corresponding to each gas use behavior node includes:

extracting gas data characteristics of the gas use data sequence corresponding to each gas use behavior node;

the gas data characteristics are used as input characteristics of a gas meter data analysis model to be trained, the gas data characteristics are input into the gas meter data analysis model to be trained, the gas meter data analysis model to be trained is used for analyzing characteristics to be trained of the gas data characteristics in a marked data item, and the characteristics to be trained comprise a characteristic section set to be trained;

dividing the set of the characteristic interval sections to be trained according to preset identifiers to obtain a plurality of training mark nodes;

determining a plurality of first model parameters according to the feature vectors corresponding to the features to be trained, wherein the plurality of first model parameters are respectively model parameters of the plurality of training mark nodes trained in the gas meter data analysis model to be trained, the gas meter data analysis model to be trained is used for learning training mark nodes after a plurality of characteristic segment sets to be trained are segmented, and model parameters mapped by each training mark node after the segmentation processing in the gas meter data analysis model to be trained, the feature block section sets to be trained are feature block section sets to be trained which are included in the features to be trained acquired in the marked data items, the first model parameter is obtained according to the characteristic parameter type represented by the characteristic vector and preset model parameters corresponding to different characteristic parameter types;

sequencing the plurality of first model parameters according to the sequence of each first model parameter in the plurality of first model parameters from high convergence to low convergence to obtain a model parameter sequence;

determining model parameters mapped by training mark nodes in the gas meter data analysis model to be trained in the plurality of training mark nodes based on a preset similarity ratio threshold and the model parameter sequence, wherein the preset similarity ratio threshold is used for indicating the proportion of the characteristic section set to be trained and the similar part of the characteristic section set to be trained acquired in the marked data item in the characteristic section set to be trained;

when the model parameters mapped by the training mark nodes in the gas meter data analysis model to be trained are matched with preset model parameters, determining that the features to be trained are target features to be trained, when the features to be trained are determined to be target features to be trained, controlling the training mark nodes obtained by segmenting a plurality of feature segment sets to be trained obtained in the mark data items by the gas meter data analysis model to be trained according to the first model parameters and the model parameters mapped by each segmented training mark node in the gas meter data analysis model to be trained according to the first model parameters for each first model parameter in the plurality of first model parameters, and generating corresponding prediction labels after training;

and updating the model parameters of the gas meter data analysis model to be trained according to the prediction label of each gas use behavior node and the preset gas use label corresponding to each gas use behavior node.

In a possible design of the first aspect, the step of extracting the gas data feature of the gas usage data sequence corresponding to each of the gas usage behavior nodes includes:

determining a tag characteristic associated with a gas usage tag corresponding to the gas usage behavior node in the gas usage data of each data item of the gas usage data sequence;

determining the label feature association degree of each gas use data according to the type information of each label node on the label feature in each gas use data, and determining the confidence label feature association degree of each gas use data according to the label feature association degree of each gas use data, wherein the type information of each label node comprises at least one of the number, sequence position and feature value of the label node;

sequencing the gas use data according to the sequence of the confidence label feature association degree from high to low, and selecting the gas use data with the feature quantity in the front sequence as the gas data feature of the gas use data sequence according to the preset feature quantity;

wherein, if the type information of the tag nodes includes the number of the tag nodes, the step of determining the tag feature association degree of each gas usage data according to the type information of each tag node aiming at the type information of each tag node on the tag feature in each gas usage data includes:

for each gas use data, determining a first tag feature association degree corresponding to each associated tag feature according to the sum of the number of tag nodes on each associated tag feature in the gas use data, and determining a tag feature association degree of the gas use data according to the sum of the first tag feature association degrees corresponding to each associated tag feature, wherein the greater the number sum, the greater the first tag feature association degree;

or, if the type information of the tag node includes a sequence bit of the tag node, the step of determining the tag feature association degree of each gas usage data according to the type information of each tag node with respect to the type information of each tag node on the tag feature in each gas usage data includes:

for each piece of gas use data, determining a maximum label range and a minimum label range determined by two adjacent label nodes on each label feature according to the sequence position of the label node on each label feature in the gas use data, determining a second label feature association degree corresponding to each label feature according to whether the ratio of the maximum label range to the minimum label range on each label feature is smaller than a preset threshold, and determining the label feature association degree of the gas use data according to the sum of the second label feature association degrees corresponding to each label feature, wherein when the ratio is smaller than the preset threshold, the second label feature association degree is larger than that when the ratio is larger than the preset threshold;

determining an average sequence position of the label nodes on each label feature according to the sequence position of the label nodes on the label feature aiming at each label feature in each gas use data;

determining a site formation sequence corresponding to each associated tag feature according to the relation of average sequence sites on each associated tag feature, determining a third tag feature association degree corresponding to each associated tag feature according to the sequence association degree of the site formation sequence and a sequence of time corresponding to the data of the gas usage data, and determining a tag feature association degree of the gas usage data according to the sum of the third tag feature association degrees corresponding to each associated tag feature, wherein the sequence association degree is larger, the third tag feature association degree is larger, and the sequence of time corresponding to the data of the gas usage data is a sequence formed by the gas usage data along a forward time axis;

for each tag feature in each gas use data, determining an average sequence position of the tag nodes on the tag feature according to the sequence positions of the tag nodes on the tag feature, determining a middle sequence position of the average sequence positions on any two of every three adjacent tag features, and simultaneously determining the matching degree of the average sequence position on the remaining tag feature and the middle sequence position;

determining the contact degree of every two adjacent three label features according to the matching degree, wherein the contact degree is higher when the matching degree is higher, or determining the middle sequence site of the average sequence site on two adjacent label features in every two adjacent three label features, and determining the contact degree of every two adjacent three label features according to the sequence contact degree of the two middle sequence sites to determine the fourth label feature contact degree corresponding to every two adjacent three label features, wherein the contact degree is higher when the sequence contact degree is higher;

determining the tag feature association degree of the gas use data according to the sum of fourth tag feature association degrees corresponding to every three adjacent tag features, wherein the higher the coincidence degree is, the larger the fourth tag feature association degree is;

or, if the type information of the tag node includes a feature value of the tag node, the step of determining the tag feature association degree of each gas usage data according to the type information of each tag node with respect to the type information of each tag node on the tag feature in each gas usage data includes:

for each piece of gas use data, determining feature value change features of a first tag node and a last tag node on each tag feature according to a feature value of the tag node on each tag feature in the gas use data, determining a fifth tag feature association degree corresponding to each tag feature according to whether the feature value change features meet a preset feature change rule, and determining a tag feature association degree of the gas use data according to the sum of the fifth tag feature association degrees corresponding to each tag feature, wherein the fifth tag feature association degree corresponding to the gas use data when the preset feature change rule is met is greater than the fifth tag feature association degree corresponding to the gas use data when the preset feature change rule is not met;

for each piece of gas use data, determining a gradient value of a label node on each label feature according to a feature value of the label node on each label feature in the gas use data, determining a sixth label feature relevance degree corresponding to each label feature according to an average value of absolute values of the gradient values of the label nodes on each label feature, and determining the label feature relevance degree of the gas use data according to a sum of the sixth label feature relevance degrees corresponding to each label feature, wherein the larger the average value is, the larger the sixth label feature relevance degree is.

In a possible design of the first aspect, the step of generating at least one control strategy pattern and a gas control instruction sequence corresponding to each control strategy pattern according to the gas prediction label of the gas usage data sequence corresponding to each gas usage behavior node includes:

dividing the gas use data sequence corresponding to each gas use behavior node into gas use data sequences according to a preset gas use mode, and respectively generating gas use mode gas prediction tag information of each gas use mode;

and generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction label information of each gas use mode.

In a possible design of the first aspect, the step of dividing the gas prediction labels of the gas usage data sequence corresponding to each gas usage behavior node according to a predetermined gas usage pattern and generating gas prediction label information of each gas usage pattern includes:

acquiring preset label nodes corresponding to each preset gas use mode, forming a label node sequence of each preset gas use mode, and selecting target label nodes with the top sequence from the label node sequence according to a preset node quantity threshold corresponding to each gas use mode to obtain target label nodes corresponding to each preset gas use mode;

and matching the gas forecasting label of the gas use data sequence corresponding to each gas use behavior node with the target label node corresponding to each preset gas use mode, and determining the gas forecasting label matched with each preset gas use mode according to the matching result to generate gas forecasting label information of each gas use mode.

In a possible design of the first aspect, the step of generating at least one control strategy mode and a gas control command sequence corresponding to each control strategy mode according to the gas forecast label information of each gas usage mode includes:

respectively acquiring preset instruction information matched with the gas forecasting tags for each gas forecasting tag of the gas forecasting tag information of each gas using mode, acquiring a target instruction set associated with the preset instruction information and the gas using mode, and determining the gas using mode as a control strategy mode when the number of target instructions in the target instruction set is larger than a set number;

on the basis of determining the gas use mode as a control strategy mode, calculating the target instruction set to acquire control feature information corresponding to the target instruction set, and performing instruction feature extraction on each target instruction of the gas prediction tag in the target instruction set to acquire instruction feature information of each target instruction in the target instruction set;

determining a target instruction with historical instruction use times larger than a preset threshold value in the control characteristic information corresponding to the target instruction set as a key target instruction;

calculating a first instruction feature vector mean value of the whole instruction set according to the instruction feature information of each target instruction in the target instruction set, and calculating a second instruction feature vector mean value of the key target instruction according to the instruction feature information of each target instruction in the key target instruction;

calculating preset weight coefficients corresponding to the first instruction feature vector mean value, the second instruction feature vector mean value, the first instruction feature vector mean value and the second instruction feature vector mean value respectively to obtain feature coefficients of the key target instructions, calculating instruction feature information of each target instruction in the target instruction set and calculation results of the feature coefficients, and obtaining a first instruction feature reference degree of each target instruction in the target instruction set according to the calculation results;

calculating the first instruction characteristic reference degree of each target instruction in the target instruction set and the control characteristic information to obtain the instruction characteristic reference degree of each target instruction in the target instruction set;

or acquiring a first instruction characteristic reference degree of each target instruction in the target instruction set according to the instruction characteristic information of each target instruction in the target instruction set and the calculation result of the characteristic coefficient, and calculating the first instruction characteristic reference degree of each target instruction in the target instruction set according to a preset reference degree range to acquire a second instruction characteristic reference degree of each target instruction in the target instruction set, wherein the difference between the second instruction characteristic reference degree and the first instruction characteristic reference degree is smaller than the reference degree range;

calculating the second instruction characteristic reference degree of each target instruction in the target instruction set and the control characteristic information to obtain the instruction characteristic reference degree of each target instruction in the target instruction set;

determining a target coefficient of each target instruction in the target instruction set according to the instruction feature reference degree and the control feature information, and calculating a ratio of the instruction feature reference degree of each target instruction in the target instruction set to a preset constant, wherein the target coefficient is a value obtained by dividing the instruction feature reference degree by a feature vector value of the control feature information;

calculating the product of the ratio of the instruction characteristic reference degree of each target instruction to a preset constant and a corresponding target coefficient, and acquiring the gas mode screening degree of each target instruction in the target instruction set;

and arranging the target instructions with the gas mode screening degrees larger than the set screening degree according to the gas mode screening degree of each target instruction, and determining the target instructions with the same instruction type as one control node to determine the gas control instruction sequence corresponding to the control strategy mode.

In a possible design of the first aspect, after the step of generating at least one control strategy pattern and a gas control instruction sequence corresponding to each control strategy pattern according to the gas prediction label of the gas usage data sequence corresponding to each gas usage behavior node, the method further includes:

and sending the at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode to a gas control Internet of things device in a gas Internet of things system of the gas user, so that the gas control Internet of things device controls a gas channel corresponding to the gas meter according to the gas control instruction sequence corresponding to the control strategy mode according to the control strategy mode selected by the gas user.

In a second aspect, an embodiment of the present application further provides a remote meter reading data processing device, which is applied to a gas cloud platform, the gas cloud platform is in communication connection with a gas internet of things system of a plurality of different gas users, the gas internet of things system includes a gas meter and a gas control internet of things device in communication connection with the gas meter, and the device includes:

the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring gas meter data of a gas user in each marked gas use interval, the gas meter data is obtained by acquiring real-time data of the gas meter through a gas control Internet of things device in a gas Internet of things system of the gas user, the gas meter data comprises gas use behavior nodes and a gas use data sequence corresponding to each gas use behavior node, the gas use behavior nodes are used for representing gas control behaviors generated each time in the gas use process, and the gas use data sequence is used for recording gas use data under the corresponding gas use behavior nodes;

the training module is used for training to obtain a corresponding gas meter data analysis model according to the gas meter data of the gas user in each marked gas use interval and the preset gas use label corresponding to each gas use behavior node;

the data analysis module is used for carrying out data analysis on the gas meter data of the gas user under each gas use behavior node in a preset time period according to the gas meter data analysis model to obtain a gas prediction label of a gas use data sequence corresponding to each gas use behavior node in the preset time period;

and the generating module is used for generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas forecasting label of the gas use data sequence corresponding to each gas use behavior node, and the gas control instruction sequence comprises at least one control node and an instruction set corresponding to each control node.

In a third aspect, an embodiment of the present application further provides a gas meter system, where the gas meter system includes a gas cloud platform and gas internet of things systems of multiple different gas users communicatively connected to the gas cloud platform, and the gas internet of things system includes a gas meter and a gas control internet of things device communicatively connected to the gas meter;

the gas control Internet of things device acquires real-time data of the gas meter to obtain gas meter data of a gas user in each marked gas use interval;

the gas cloud platform is used for acquiring gas meter data of a gas user in each marked gas use interval, the gas meter data comprises gas use behavior nodes and a gas use data sequence corresponding to each gas use behavior node, the gas use behavior nodes are used for representing gas control behaviors generated each time in the gas use process, and the gas use data sequences are used for recording gas use data under the corresponding gas use behavior nodes;

the gas cloud platform is used for training to obtain a corresponding gas meter data analysis model according to gas meter data of the gas user in each marked gas use interval and a preset gas use label corresponding to each gas use behavior node;

the gas cloud platform is used for performing data analysis on the gas meter data of the gas user under each gas use behavior node in a preset time period according to the gas meter data analysis model to obtain a gas prediction label of a gas use data sequence corresponding to each gas use behavior node in the preset time period;

the gas cloud platform is used for generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction labels of the gas use data sequences corresponding to the gas use behavior nodes, and the gas control instruction sequence comprises at least one control node and an instruction set corresponding to each control node.

In a fourth aspect, an embodiment of the present application further provides a gas cloud platform, where the gas cloud platform includes a processor, a machine-readable storage medium, and a network interface, the machine-readable storage medium, the network interface, and the processor are connected by a bus system, the network interface is used for being in communication connection with at least one gas meter system, the machine-readable storage medium is used for storing a program, an instruction, or a code, and the processor is used for executing the program, the instruction, or the code in the machine-readable storage medium to execute the remote meter reading data processing method in the first aspect or any one of possible designs in the first aspect.

In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are detected on a computer, the computer is enabled to execute the remote meter reading data processing method in the first aspect or any one of the possible designs of the first aspect.

According to any one of the aspects, the gas meter data of the gas user in each marked gas use interval and the preset gas use label corresponding to each gas use behavior node are learned through the machine, the gas control habit of the gas user can be well learned, so that the gas user is conveniently and subsequently provided with a control strategy mode according with the habit to perform automatic gas control, the operation amount caused by the complicated and repeated control operation of the gas user is effectively reduced, and meanwhile, the condition that the use process is unexpected due to the fact that the operation is lost for a certain time is unavoidable is reduced.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

Fig. 1 is a schematic view of an application scenario of a gas meter system provided in an embodiment of the present application;

fig. 2 is a schematic flow chart of a remote meter reading data processing method according to an embodiment of the present application;

fig. 3 is a functional module schematic diagram of a remote meter reading data processing device according to an embodiment of the present application;

fig. 4 is a schematic block diagram of a structure of a gas cloud platform for implementing the remote meter reading data processing method provided in the embodiment of the present application.

Detailed Description

The present application will now be described in detail with reference to the drawings, and the specific operations in the method embodiments may also be applied to the apparatus embodiments or the system embodiments. In the description of the present application, "at least one" includes one or more unless otherwise specified. "plurality" means two or more. For example, at least one of A, B and C, comprising: a alone, B alone, a and B in combination, a and C in combination, B and C in combination, and A, B and C in combination. In this application, "/" means "or, for example, A/B may mean A or B; "and/or" herein is merely an association describing an associated object, and means that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone.

Fig. 1 is an interaction schematic diagram of a gas meter system 10 according to an embodiment of the present application. The gas meter system 10 may include a gas cloud platform 100 and a gas internet of things system 200 communicatively connected to the gas cloud platform 100, and a processor executing instruction operations may be included in the gas cloud platform 100. The gas meter system 10 shown in fig. 1 is only one possible example, and in other possible embodiments, the gas meter system 10 may include only one of the components shown in fig. 1 or may also include other components.

In some embodiments, the gas cloud platform 100 may be a single server or a group of servers. The server group may be centralized or distributed (e.g., the gas cloud platform 100 may be a distributed system). In some embodiments, the gas cloud platform 100 may be local or remote to the gas internet of things system 200. For example, the gas cloud platform 100 may access information stored in the gas internet of things system 200 and databases, or any combination thereof, via a network. As another example, the gas cloud platform 100 may be directly connected to at least one of the gas internet of things system 200 and a database to access information and/or data stored therein. In some embodiments, the gas cloud platform 100 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (community cloud), a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof.

In some embodiments, the gas cloud platform 100 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. A processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a Reduced Instruction Set computer (Reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

The network may be used for the exchange of information and/or data. In some embodiments, one or more components (e.g., the gas cloud platform 100, the gas internet of things system 200, and the database) in the gas meter system 10 may send information and/or data to other components. In some embodiments, the network may be any type of wired or wireless network, or combination thereof. Merely by way of example, Network 130 may include a wired Network, a Wireless Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a WLAN, a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a ZigBee Network, a Near Field Communication (NFC) Network, or the like, or any combination thereof. In some embodiments, the network may include one or more network access points. For example, the network may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of the gas meter system 10 may connect to the network to exchange data and/or information.

The aforementioned database may store data and/or instructions. In some embodiments, the database may store data distributed to the gas internet of things system 200. In some embodiments, the database may store data and/or instructions for the exemplary methods described herein. In some embodiments, the database may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, and the like; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write Memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double data Rate Synchronous Dynamic RAM (DDR SDRAM); static RAM (SRAM), Thyristor-Based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like. In some embodiments, the database may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, across clouds, multiple clouds, or the like, or any combination thereof.

In some embodiments, a database may be connected to the network to communicate with one or more components in the gas meter system 10 (e.g., the gas cloud platform 100, the gas internet of things system 200, etc.). One or more components in the gas meter system 10 may access data or instructions stored in a database via a network. In some embodiments, the database may be directly connected to one or more components in the gas meter system 10 (e.g., the gas cloud platform 100, the gas Internet of things system 200, etc.; or, in some embodiments, the database may be part of the gas cloud platform 100.

In this embodiment, the gas internet of things system 200 may specifically include a gas meter and a gas control internet of things device in communication connection with the gas meter, the gas meter may be used to record gas meter data in a gas control process, and the gas control internet of things device may be used to collect gas meter data recorded by the gas meter and may control a gas channel, which is not specifically limited in this embodiment.

In order to solve the technical problem in the foregoing background art, fig. 2 is a schematic flow chart of a remote meter reading data processing method provided in an embodiment of the present application, and the remote meter reading data processing method provided in this embodiment may be executed by the gas cloud platform 100 shown in fig. 1, and the remote meter reading data processing method is described in detail below.

And step S110, acquiring gas meter data of the gas user in each marked gas use interval.

And step S120, training to obtain a corresponding gas meter data analysis model according to the gas meter data of the gas user in each marked gas use interval and the preset gas use label corresponding to each gas use behavior node.

Step S130, performing data analysis on the gas meter data of the gas user under each gas use behavior node in a preset time period according to the gas meter data analysis model to obtain a gas forecast label of the gas use data sequence corresponding to each gas use behavior node in the preset time period.

And step S140, generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction label of the gas use data sequence corresponding to each gas use behavior node.

In this embodiment, the gas cloud platform 100 may provide gas meter data of the gas user in different gas use intervals for the gas user, and the gas user may flexibly select, through the terminal, gas meter data in a part of or all of the gas use intervals to mark according to the self condition, so that the gas cloud platform 100 may obtain the gas meter data of the gas user in each marked gas use interval.

In this embodiment, the gas meter data may be obtained by performing real-time data acquisition on the gas meter through a gas control internet of things device in the gas internet of things system 200 of the gas user. As a possible example, the gas meter data may include gas usage behavior nodes and a gas usage data sequence corresponding to each gas usage behavior node, where the gas usage behavior nodes are used to represent gas control behaviors (e.g., behaviors such as switching on and off of gas each time, and controlling magnitude of gas flow) generated each time during a gas usage process, and the gas usage data sequence may be used to record gas usage data under the corresponding gas usage behavior nodes, for example, each gas usage behavior node usually lasts for a certain time, and in this time period, gas usage data under the corresponding gas usage behavior node may be recorded with each unit time (e.g., one second) as one recording point, and the gas usage data sequence is obtained after summarizing.

In this embodiment, the preset gas usage label may be used to represent usage or an effect of gas usage corresponding to each gas usage behavior node, for example, the preset gas usage label may be used to cook (or may be used in multiple cooking modes), boil water, steam, stew, or the like, and the gas user may set the preset gas usage label corresponding to each gas usage behavior node according to the historical usage condition of the user, and upload the preset gas usage label to the gas cloud platform 100 for recording.

In this embodiment, the gas control instruction sequence may include at least one control node and an instruction set corresponding to each control node, and a control instruction may be formed in the instruction sets by taking the time axis as the direction and taking the unit time as a control unit for subsequently controlling the gas process.

Based on the above design, this embodiment can use the label through the preset gas that machine learning gas user's gas table data and every gas in every gas use interval that has marked use the behavior node to correspond, can learn gas user's gas control custom well to thereby follow-up for gas user provides the control strategy mode that accords with self custom and carry out automatic gas control, effectively reduce the operation volume that the loaded down with trivial details repetitive control operation of gas user brought from this, reduce simultaneously because the situation that this use process of certain mistake operation unavoidably leads to the accident appears.

In a possible design, for step S120, in order to improve the training effect and avoid introducing a noise training feature, the embodiment may extract a gas data feature (e.g., a gas variation feature, a gas data type feature, etc.) of the gas usage data sequence corresponding to each gas usage behavior node. And then, taking the gas data characteristics as input characteristics of a gas meter data analysis model to be trained, inputting the gas data characteristics into the gas meter data analysis model to be trained, analyzing the characteristics to be trained of the gas data characteristics in the marked data items through the gas meter data analysis model to be trained, wherein the characteristics to be trained comprise a characteristic section set to be trained.

On the basis, considering that the feature segment set to be trained is usually separated by some identifiers, the feature segment set to be trained can be segmented according to preset identifiers (such as a mark, a pause mark and the like) to obtain a plurality of training mark nodes, and a plurality of first model parameters are determined according to the feature vector corresponding to the feature to be trained.

It should be noted that the plurality of first model parameters are model parameters of a plurality of training mark nodes trained in a to-be-trained gas meter data analysis model, the to-be-trained gas meter data analysis model is used for learning training mark nodes obtained by segmenting a plurality of to-be-trained feature segment sets, and model parameters mapped by each segmented training mark node in the to-be-trained gas meter data analysis model, and the plurality of to-be-trained feature segment sets are to-be-trained feature segment sets included in a plurality of to-be-trained features acquired in a marked data item. In addition, it should be noted that the first model parameter is obtained according to the feature parameter type represented by the feature vector and the preset model parameters corresponding to different feature parameter types.

Next, the plurality of first model parameters may be ranked according to the order from high convergence to low convergence of each of the plurality of first model parameters to obtain a model parameter sequence, and a model parameter mapped by a training label node of the plurality of training label nodes in the gas meter data analysis model to be trained is determined based on a preset similarity ratio threshold and the model parameter sequence.

It should be noted that the preset similarity ratio threshold is used to indicate the proportion of the to-be-trained feature interval set and the similar part of the to-be-trained feature interval set acquired in the labeled data item in the to-be-trained feature interval set.

On the basis, when model parameters mapped by the training mark nodes in the gas meter data analysis model to be trained are matched with preset model parameters, determining the feature to be trained as a target feature to be trained, when determining the feature to be trained as the target feature to be trained, for each first model parameter in the multiple first model parameters, controlling a training marking node after a gas meter data analysis model to be trained learns the multiple characteristic segment sets to be trained obtained in the marking data item and is subjected to segmentation processing according to the first model parameter, and model parameters of each training mark node after the segmentation processing are mapped in the gas meter data analysis model to be trained, and corresponding prediction labels are generated after the training, therefore, the model parameters of the gas meter data analysis model to be trained can be updated according to the prediction label of each gas use behavior node and the preset gas use label corresponding to each gas use behavior node.

It should be noted that the number of update iterations may be set, and when the number of update iterations reaches the set number, it indicates that the gas meter data analysis model to be trained is trained, and thus the trained gas meter data analysis model is output.

In a possible design, in the process of extracting the gas data characteristics of the gas use data sequence corresponding to each gas use behavior node, in order to enable the extracted gas data characteristics to effectively relate to the relevance of different data characteristics, to improve the subsequent training effect, the present embodiment may, in the gas usage data of each data item of the gas usage data sequence, determining a tag characteristic associated with a gas usage tag corresponding to the gas usage activity node, then for each tag node type information on the tag characteristics in each gas usage data, determining the label characteristic association degree of each gas use data according to the type information of each label node, and determining the confidence tag feature relevance of each gas use data according to the tag feature relevance of each gas use data.

Then, the gas use data can be sorted according to the sequence of the confidence label feature relevance degree from high to low, and the gas use data with the feature quantity arranged in the front is selected as the gas data feature of the gas use data sequence according to the preset feature quantity.

Wherein the type information of the tag node may include at least one of the number, sequence bits, and characteristic values of the tag node. Next, the present embodiment will give several possible examples to determine the tag feature association degree of each gas usage data.

For example, if the type information of the tag nodes includes the number of the tag nodes, for each gas usage data, according to the sum of the number of the tag nodes on the associated respective tag features in the gas usage data, determining the first tag feature association degree corresponding to the associated respective tag features, and according to the sum of the first tag feature association degrees corresponding to the associated respective tag features, determining the tag feature association degree of the gas usage data, wherein the greater the sum of the number, the greater the first tag feature association degree.

Or, if the type information of the tag node includes the sequential bit of the tag node, for each gas usage data, according to the sequential bit of the tag node on each tag feature in the gas usage data, determining a maximum tag range and a minimum tag range determined by two adjacent tag nodes on each tag feature, according to whether a ratio of the maximum tag range to the minimum tag range on each tag feature is smaller than a preset threshold, determining a second tag feature association degree corresponding to each tag feature, and according to a sum of the second tag feature association degrees corresponding to each tag feature, determining a tag feature association degree of the gas usage data, where when the ratio is smaller than the preset threshold, the second tag feature association degree is greater than when the ratio is greater than the set threshold.

For another example, for each tag feature in each gas usage data, from the ordinal number of the tag node on that tag feature, an average ordinal position of the tag node on that tag feature can be determined, determining the site forming sequence corresponding to each associated tag feature according to the relation of the average sequence sites on each associated tag feature, determining a third tag feature association degree corresponding to each associated tag feature according to the sequence association degree of the time sequence corresponding to the data of the site formation sequence and the gas usage data, and determining the tag feature association degree of the gas usage data according to the sum of the third tag feature association degrees corresponding to the associated tag features, the sequence relevance degree is larger, the third label characteristic relevance degree is larger, and the sequence of the time corresponding to the data of the gas use data is a sequence formed by the gas use data along a forward time axis.

For another example, for each tag feature in each gas usage data, according to the sequence position of the tag node on the tag feature, an average sequence position of the tag node on the tag feature is determined, an intermediate sequence position of the average sequence positions on any two of every three adjacent tag features is determined, and meanwhile, the matching degree between the average sequence position on the remaining one tag feature and the intermediate sequence position is determined.

And then, according to the matching degree, determining the contact degree of every two adjacent three label features, wherein the contact degree is higher if the matching degree is higher, or determining the middle sequence position of the average sequence position on two adjacent label features in every two adjacent three label features, and according to the sequence contact degree of the two middle sequence positions, determining the contact degree of every two adjacent three label features to determine the fourth label feature contact degree corresponding to every two adjacent three label features, wherein the contact degree is higher if the sequence contact degree is higher.

Therefore, the label characteristic association degree of the gas use data is determined according to the sum of the fourth label characteristic association degrees corresponding to every three adjacent label characteristics, wherein the higher the coincidence degree is, the larger the fourth label characteristic association degree is.

Or in another case, if the type information of the tag node includes a feature value of the tag node, for each gas usage data, determining feature value change features of a first tag node and a last tag node on each tag feature according to the feature value of the tag node on each tag feature in the gas usage data, determining a fifth tag feature association degree corresponding to each tag feature according to whether the feature value change features satisfy a preset feature change rule, and determining the tag feature association degree of the gas usage data according to the sum of the fifth tag feature association degrees corresponding to each tag feature, wherein the fifth tag feature association degree corresponding to the case that the preset feature change rule is satisfied is greater than the fifth tag feature association degree corresponding to the case that the preset feature change rule is not satisfied.

For another example, for each gas usage data, the gradient value of the label node on each label feature in the gas usage data is determined according to the feature value of the label node on each label feature, the sixth label feature relevance degree corresponding to each label feature is determined according to the average value of the absolute values of the gradient values of the label nodes on each label feature, and the label feature relevance degree of the gas usage data is determined according to the sum of the sixth label feature relevance degrees corresponding to each label feature, wherein the larger the average value is, the larger the sixth label feature relevance degree is.

In a possible design, further referring to step S140, in this embodiment, the gas prediction labels of the gas usage data sequences corresponding to the gas usage behavior nodes are divided according to a predetermined gas usage mode, so as to generate gas prediction label information of each gas usage mode, and then at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode are generated according to the gas prediction label information of each gas usage mode.

For example, preset tag nodes corresponding to each preset gas usage mode may be obtained, a tag node sequence of each preset gas usage mode is formed, and according to a preset node quantity threshold corresponding to each gas usage mode, a target tag node ranked in the top is selected from the tag node sequence, so as to obtain a target tag node corresponding to each preset gas usage mode. On the basis, matching the gas prediction labels of the gas use data sequence corresponding to the gas use behavior nodes with the target label nodes corresponding to each preset gas use mode, and determining the gas prediction labels matched with each preset gas use mode according to the matching result to generate gas prediction label information of each gas use mode.

For another example, for each gas prediction tag of the gas prediction tag information of each gas usage mode, preset instruction information matched with the gas prediction tag may be acquired, a target instruction set in which the preset instruction information is associated with the gas usage mode may be acquired, and when the number of target instructions in the target instruction set is greater than a set number, the gas usage mode may be determined as a control strategy mode.

On the basis of determining the gas use mode as a control strategy mode, calculating a target instruction set, acquiring control characteristic information corresponding to the target instruction set, performing instruction characteristic extraction on each target instruction of a gas prediction tag in the target instruction set, acquiring instruction characteristic information of each target instruction in the target instruction set, and determining a target instruction with historical instruction use times larger than a preset threshold value in the control characteristic information corresponding to the target instruction set as a key target instruction.

Then, according to the instruction feature information of each target instruction in the target instruction set, calculating a first instruction feature vector mean value of the whole instruction set, and according to the instruction feature information of each target instruction in the key target instruction, calculating a second instruction feature vector mean value of the key target instruction, thereby calculating preset weight coefficients corresponding to the first instruction feature vector mean value, the second instruction feature vector mean value, the first instruction feature vector mean value and the second instruction feature vector mean value, obtaining feature coefficients of the key target instruction, calculating the instruction feature information and the feature coefficients of each target instruction in the target instruction set, and obtaining a first instruction feature reference degree of each target instruction in the target instruction set according to the calculation results.

And finally, calculating the first instruction characteristic reference degree and the control characteristic information of each target instruction in the target instruction set to obtain the instruction characteristic reference degree of each target instruction in the target instruction set.

Or, in another possible design, the embodiment may also obtain the first instruction feature reference degree of each target instruction in the target instruction set according to the instruction feature information and the calculation result of the feature coefficient of each target instruction in the target instruction set, and calculate the first instruction feature reference degree of each target instruction in the target instruction set according to a preset reference degree range, to obtain the second instruction feature reference degree of each target instruction in the target instruction set, where a difference between the second instruction feature reference degree and the first instruction feature reference degree is smaller than the reference degree range.

And then, calculating a second instruction characteristic reference degree and control characteristic information of each target instruction in the target instruction set to obtain an instruction characteristic reference degree of each target instruction in the target instruction set, determining a target coefficient of each target instruction in the target instruction set according to the instruction characteristic reference degree and the control characteristic information, and calculating a ratio of the instruction characteristic reference degree of each target instruction in the target instruction set to a preset constant, wherein the target coefficient is a value obtained by dividing the instruction characteristic reference degree by a characteristic vector value of the control characteristic information.

On the basis, the product of the ratio of the instruction characteristic reference degree of each target instruction to the preset constant and the corresponding target coefficient can be calculated, the gas mode screening degree of each target instruction in the target instruction set is obtained, the target instructions with the gas mode screening degrees larger than the set screening degree are arranged according to the gas mode screening degree of each target instruction according to the time sequence, and the target instructions of the same instruction type are determined as a control node to determine the gas control instruction sequence corresponding to the control strategy mode.

Based on the above description, in this embodiment, at least one control strategy mode and the gas control instruction sequence corresponding to each control strategy mode may be sent to the gas control internet of things device in the gas internet of things system 200 of the gas user, so that the gas control internet of things device controls the gas channel corresponding to the gas meter according to the gas control instruction sequence corresponding to the control strategy mode, according to the control strategy mode selected by the gas user. In other words, in the future use process of the gas user, a control strategy mode obtained by machine learning the daily gas use habit of the gas user can be flexibly selected for automatic control, and then the collected gas meter data is more and more, so that the gas meter data analysis model can be continuously trained, and the precision of the gas meter data analysis model is continuously improved.

Fig. 3 is a schematic functional module diagram of a remote meter reading data processing device 300 according to an embodiment of the present application, where the present embodiment may perform functional module division on the remote meter reading data processing device 300 according to the foregoing method embodiment. For example, the functional blocks may be divided for the respective functions, or two or more functions may be integrated into one processing block. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, the division of the modules in the present application is schematic, and is only a logical function division, and there may be another division manner in actual implementation. For example, in the case of dividing each function module according to each function, the remote meter reading data processing device 300 shown in fig. 3 is only a schematic device diagram. The remote meter reading data processing apparatus 300 may include an obtaining module 310, a training module 320, a data analyzing module 330, and a generating module 340, and the functions of the functional modules of the remote meter reading data processing apparatus 300 are described in detail below.

The obtaining module 310 is configured to obtain gas meter data of the gas user in each marked gas use interval, where the gas meter data is obtained by performing real-time data acquisition on the gas meter through a gas control internet of things device in the gas internet of things system 200 of the gas user, the gas meter data includes gas use behavior nodes and a gas use data sequence corresponding to each gas use behavior node, the gas use behavior nodes are used to represent gas control behaviors generated each time in a gas use process, and the gas use data sequence is used to record gas use data under the corresponding gas use behavior nodes.

And the training module 320 is configured to train to obtain a corresponding gas meter data analysis model according to the gas meter data of the gas user in each marked gas use interval and the preset gas use label corresponding to each gas use behavior node.

The data analysis module 330 is configured to perform data analysis on the gas meter data of the gas user at each gas usage behavior node within a preset time period according to the gas meter data analysis model, so as to obtain a gas prediction tag of a gas usage data sequence corresponding to each gas usage behavior node within the preset time period.

The generating module 340 is configured to generate at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction tag of the gas usage data sequence corresponding to each gas usage behavior node, where the gas control instruction sequence includes at least one control node and an instruction set corresponding to each control node.

Further, fig. 4 is a schematic structural diagram of a gas cloud platform 100 for executing the remote meter reading data processing method according to the embodiment of the present application. As shown in fig. 4, the gas cloud platform 100 may include a network interface 110, a machine-readable storage medium 120, a processor 130, and a bus 140. The processor 130 may be one or more, and one processor 130 is illustrated in fig. 4 as an example. The network interface 110, the machine-readable storage medium 120, and the processor 130 may be connected by a bus 140 or otherwise, as exemplified by the connection by the bus 140 in fig. 4.

The machine-readable storage medium 120 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the remote meter reading data processing method in the embodiment of the present application (for example, the obtaining module 310, the training module 320, the data analysis module 330, and the generation module 340 of the remote meter reading data processing apparatus 300 shown in fig. 3). The processor 130 executes various functional applications and data processing of the terminal device by detecting the software programs, instructions and modules stored in the machine-readable storage medium 120, that is, the above-mentioned remote meter reading data processing method is implemented, and details are not described herein.

The machine-readable storage medium 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the machine-readable storage medium 120 may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM). It should be noted that the memories of the systems and methods described herein are intended to comprise, without being limited to, these and any other suitable memory of a publishing node. In some examples, machine-readable storage medium 120 may further include memory located remotely from processor 130, which may be connected to gas cloud platform 100 via a network. Examples of such networks include, but are not limited to, the internet, an intranet of items to be compiled, a local area network, a mobile communications network, and combinations thereof.

The processor 130 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 130. The processor 130 may be a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor.

The gas cloud platform 100 may perform information interaction with other devices (e.g., the gas internet of things system 200) through the network interface 110. Network interface 110 may be a circuit, bus, transceiver, or any other device that may be used to exchange information. Processor 130 may send and receive information using network interface 110.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the embodiments of the present application without departing from the spirit and scope of the application. Thus, to the extent that such expressions and modifications of the embodiments of the application fall within the scope of the claims and their equivalents, the application is intended to embrace such alterations and modifications.

Claims

1. A remote meter reading data processing method is applied to a gas cloud platform, the gas cloud platform is in communication connection with gas Internet of things systems of a plurality of different gas users, each gas Internet of things system comprises a gas meter and a gas control Internet of things device in communication connection with the gas meter, and the method comprises the following steps:

acquiring gas meter data of a gas user in each marked gas use interval, wherein the gas meter data is obtained by acquiring real-time data of the gas meter through a gas control Internet of things device in a gas Internet of things system of the gas user, the gas meter data comprises gas use behavior nodes and a gas use data sequence corresponding to each gas use behavior node, the gas use behavior nodes are used for representing gas control behaviors generated each time in the gas use process, the gas use data sequence is used for recording gas use data under the corresponding gas use behavior nodes, the gas use data under the corresponding gas use behavior nodes are recorded by taking each unit time as a recording point and are summarized to obtain the gas use data sequence, and the gas control behaviors comprise switching, switching and switching of each gas, Behavior of magnitude control of gas flow;

according to the gas meter data of the gas user in each marked gas use interval and a preset gas use label corresponding to each gas use behavior node, training to obtain a corresponding gas meter data analysis model, wherein the preset gas use label is used for representing the use or the effect of the gas corresponding to each gas use behavior node;

and generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction label of the gas use data sequence corresponding to each gas use behavior node, wherein the gas control instruction sequence comprises at least one control node and an instruction set corresponding to each control node, and a control instruction is formed in the instruction set by taking a time axis as a direction and taking unit time as a control unit for subsequently controlling the gas process.

2. The remote meter reading data processing method according to claim 1, wherein the step of training to obtain a corresponding gas meter data analysis model according to the gas meter data of the gas user in each marked gas use interval and the preset gas use label corresponding to each gas use behavior node comprises:

extracting gas data characteristics of the gas use data sequence corresponding to each gas use behavior node, wherein the gas data characteristics comprise gas change characteristics and gas data type characteristics;

3. The remote meter reading data processing method according to claim 2, wherein the step of extracting the gas data characteristics of the gas usage data sequence corresponding to each of the gas usage behavior nodes includes:

4. The remote meter reading data processing method according to any one of claims 1 to 3, wherein the step of generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction label of the gas use data sequence corresponding to each gas use behavior node comprises:

5. The remote meter reading data processing method according to claim 4, wherein the step of dividing the gas prediction labels of the gas usage data sequence corresponding to each gas usage behavior node according to a predetermined gas usage pattern and generating gas prediction label information of each gas usage pattern respectively comprises:

6. The remote meter reading data processing method according to claim 4, wherein the step of generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas forecast label information of each gas usage mode includes:

7. The remote meter reading data processing method according to any one of claims 1 to 6, wherein after the step of generating at least one control strategy pattern and a gas control instruction sequence corresponding to each control strategy pattern according to the gas prediction label of the gas usage data sequence corresponding to each gas usage behavior node, the method further comprises:

8. A gas meter system is characterized by comprising a gas cloud platform and gas Internet of things systems of a plurality of different gas users, wherein the gas Internet of things systems are in communication connection with the gas cloud platform and comprise a gas meter and a gas control Internet of things device in communication connection with the gas meter;

the gas cloud platform is used for acquiring gas meter data of a gas user in each marked gas use interval, wherein the gas meter data comprises gas use behavior nodes and a gas use data sequence corresponding to each gas use behavior node, the gas use behavior nodes are used for representing gas control behaviors generated each time in the gas use process, the gas use data sequences are used for recording the gas use data under the corresponding gas use behavior nodes, the gas use data under the corresponding gas use behavior nodes are recorded by taking each unit time as a recording point, the gas use data sequences are obtained after the data are summarized, and the gas control behaviors comprise the behaviors of opening and closing of each time of gas and control over the gas flow;

the gas cloud platform is used for training to obtain a corresponding gas meter data analysis model according to gas meter data of the gas user in each marked gas use interval and a preset gas use label corresponding to each gas use behavior node, wherein the preset gas use label is used for representing the use or the effect of the gas corresponding to each gas use behavior node;

the gas cloud platform is used for generating at least one control strategy mode and a gas control instruction sequence corresponding to each control strategy mode according to the gas prediction labels of the gas use data sequences corresponding to the gas use behavior nodes, the gas control instruction sequence comprises at least one control node and an instruction set corresponding to each control node, and a control instruction is formed in the instruction set by taking a time axis as a direction and taking unit time as a control unit and is used for controlling a gas process subsequently.

9. A gas cloud platform, comprising a processor, a machine-readable storage medium, and a network interface, wherein the machine-readable storage medium, the network interface, and the processor are connected through a bus system, the network interface is configured to be communicatively connected to at least one gas meter system, the machine-readable storage medium is configured to store a program, an instruction, or a code, and the processor is configured to execute the program, the instruction, or the code in the machine-readable storage medium to perform the remote meter reading data processing method according to any one of claims 1 to 7.