CN113285978B

CN113285978B - Fault identification method based on block chain and big data and general computing node

Info

Publication number: CN113285978B
Application number: CN202110397270.0A
Authority: CN
Inventors: 詹能勇
Original assignee: Block Beijing Data Technology Co ltd
Current assignee: Block Beijing Data Technology Co ltd
Priority date: 2020-08-08
Filing date: 2020-08-08
Publication date: 2022-08-12
Anticipated expiration: 2040-08-08
Also published as: CN111935279B; CN111935279A; CN113285977A; CN113285978A; CN113285977B

Abstract

The application provides a fault identification method based on a block chain and big data and a cloud computing platform, relates to the technical field of the Internet of things, and aims to accurately and quickly determine a target fault data sequence from fault information data by extracting a fault type of a first fault data sequence and a fault type of a second fault data sequence from fault information data and determining the second fault data sequence as the target fault sequence of the fault information data when the fault in the first fault data sequence is different from the fault in the second fault data sequence, and broadcast a state maintenance message containing the target fault sequence in an information verification block network to which a target computing node belongs, so that a maintainer can obtain the target fault data sequence from the information verification block network, and the maintainer can obtain the target fault data sequence according to the target fault data sequence, and analyzing the fault condition of the target data acquisition equipment.

Description

Fault identification method based on block chain and big data and general computing node

Technical Field

The application relates to the technical field of Internet of things, in particular to a fault identification method based on a block chain and big data and a general computing node.

Background

With the development and application of the information technology in the industrial field, all production equipment is constructed in the same Internet of things by adopting a large-scale network structure, centralized management can be carried out on all the production equipment in the industrial application in a centralized manner without dispersedly adopting a plurality of sets of information management systems, and therefore the information management efficiency of an industrial factory is improved.

However, the existing management method generally stores each network node separately, and uses the traditional method to encrypt, so that the reliability is low.

Disclosure of Invention

The object of the application is to provide a block chain and big data-based internet of things maintenance method and a general computing node, which can effectively calculate respective data statistical efficiency for each data acquisition device managed by an internet of things platform, and store the data in a block network, thereby improving the reliability of the data.

In order to achieve the purpose, the technical scheme adopted by the application is as follows:

in a first aspect, the present application provides a method for maintaining an internet of things based on a block chain and big data, where the method includes:

responding to a received state maintenance request, and acquiring first to-be-processed data corresponding to a target computing node in a target message field, wherein target data acquisition equipment corresponding to the first to-be-processed data is configured to be in a maximum data acquisition state, a data collection mode is downtime collection, the target message field is a field corresponding to the target computing node in a received message, and the target computing node is one of all computing nodes contained in an internet of things platform;

acquiring second data to be processed and a data collection efficiency statistical strategy corresponding to the target computing node in the target message field, and determining target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical strategy and the first data to be processed;

storing the target data statistical efficiency into a state record file corresponding to the target computing node, and broadcasting a state maintenance message containing the target data statistical efficiency in an information verification block network to which the target computing node belongs; the state maintenance message is used for indicating the received block node to record the data statistical efficiency recorded in the state maintenance message.

Optionally, the acquiring first to-be-processed data corresponding to the target computing node in the target packet field includes:

acquiring all collected data of which the corresponding data collection mode in the target message field is downtime collection, and recording the collected data as first initial collected data;

according to a node data statistical rule corresponding to the target computing node, performing data cleaning on the first initial acquisition data so as to acquire all acquisition data of which the data acquisition mode corresponding to the target computing node is down and record the acquisition data as second initial acquisition data;

dividing the number of the acquired data in the second initial acquired data by the acquisition time range of the data to obtain the unit data acquisition rate in the unit acquisition time range;

comparing a preset data acquisition rate threshold with the unit data acquisition rate;

if the preset data acquisition rate threshold is equal to the unit data acquisition rate, the target data acquisition equipment corresponding to the second initial acquisition data is currently in a maximum data acquisition state;

if the preset data acquisition rate threshold is greater than the unit data acquisition rate, the target data acquisition equipment corresponding to the second initial acquisition data is not in the maximum data acquisition state currently;

and performing data cleaning on the initial acquisition data which is not in the maximum data acquisition state at present to acquire the initial acquisition data which is not in the maximum data acquisition state at present as the first to-be-processed data.

Optionally, the second to-be-processed data includes a second total received data amount of the second collected data of the target computing node and a total amount of normally collected data of all collected data that are normally collected in a corresponding data collection mode; the data collection efficiency statistical strategy comprises a set minimum expected data collection amount and a data collection time range;

the determining the target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical strategy and the first data to be processed includes:

subtracting the minimum expected data acquisition amount from the total amount of the normally collected data to generate a surplus collection amount in a normal collection state, wherein the surplus collection amount in the normal collection state is greater than or equal to zero;

multiplying the surplus collection amount in the normal collection state by the collection time range of the data to obtain the surplus data collection upper limit amount;

subtracting the total receiving quantity of the second acquired data from the surplus data collection upper limit quantity to acquire a target surplus collecting quantity;

determining the quantity of target collected data according to the total receiving quantity of first collected data in the first to-be-processed data, the minimum expected data collecting quantity and the collecting time range of the data;

and dividing the smaller of the target surplus collection amount and the target collection data quantity with the collection time range of the data to generate the target data statistical efficiency.

Optionally, the storing the target data statistical efficiency into a state record file corresponding to the target computing node, and broadcasting a state maintenance packet including the target data statistical efficiency in an information verification block network to which the target computing node belongs includes:

after the target data statistical efficiency is stored in a corresponding state record file of the target computing node, filling the target data statistical efficiency in a field corresponding to the statistical efficiency in an initial maintenance message to generate a state maintenance message;

and determining an information verification block network corresponding to the target computing node according to the block network indication identifier of the target computing node, and broadcasting the state maintenance message in the information verification block network.

Optionally, the method further comprises:

acquiring fault information data recorded in the target message field;

dividing the fault information data into a plurality of fault data sequences according to a time sequence;

extracting the fault type of a first fault data sequence in the plurality of fault data sequences to obtain the fault type of the first fault data sequence, and extracting the fault type of a second fault data sequence behind the first fault data sequence to obtain the fault type of the second fault data sequence;

comparing the fault type of the first fault data sequence with the fault type of the second fault data sequence;

and when the fault in the first fault data sequence is different from the fault in the second fault data sequence, determining the second fault data sequence as a target fault sequence of the fault information data, and broadcasting a state maintenance message containing the target fault sequence in an information verification block network to which the target computing node belongs.

Optionally, when the priority corresponding to the fault is a first priority, the extracting the fault type of a first fault data sequence in the plurality of fault data sequences to obtain the fault type of the first fault data sequence includes:

carrying out fault information identification on the first fault data sequence to obtain a fault equipment identifier and a fault content abstract of the first fault data sequence;

performing information splicing on the fault equipment identifier and the fault content abstract of the first fault data sequence to obtain the fault type of the first fault data sequence;

correspondingly, the extracting the fault type of the second fault data sequence after the first fault data sequence to obtain the fault type of the second fault data sequence includes:

carrying out fault information identification on the second fault data sequence to obtain a fault equipment identifier and a fault content abstract of the second fault data sequence;

and carrying out information splicing on the fault equipment identification and the fault content abstract of the second fault data sequence to obtain the fault type of the second fault data sequence.

Optionally, when the priority corresponding to the fault is a second priority, the extracting the fault type of a first fault data sequence in the plurality of fault data sequences to obtain the fault type of the first fault data sequence includes:

performing information identification of a fault content abstract on the first fault data sequence to obtain a fault content abstract containing the first fault data sequence, wherein the fault content abstract is used for describing the content of a fault;

performing information identification of a fault equipment identifier on the first fault data sequence to obtain a fault equipment identifier containing the first fault data sequence, wherein the fault equipment identifier is used for indicating fault occurrence equipment;

according to the fault grade identification of the first fault data sequence, carrying out information splicing on the fault equipment identification and the fault content abstract of the first fault data sequence to obtain the fault type of the first fault data sequence;

and according to the fault grade identification of the second fault data sequence, carrying out information splicing on the fault equipment identification and the fault content abstract of the second fault data sequence to obtain the fault type of the second fault data sequence.

Optionally, before performing information splicing on the faulty device identifier and the faulty content summary of the first faulty data sequence, the method further includes:

carrying out equipment type search on the fault equipment identifier of the first fault data sequence to obtain a target equipment type identifier;

performing fault class level search on the target equipment class identifier to obtain a fault class identifier of the first fault data sequence;

the fault grade identification is used for representing the fault grade corresponding to the fault in the first fault data sequence;

correspondingly, the information splicing is performed on the fault equipment identifier and the fault content summary of the first fault data sequence according to the fault level identifier of the first fault data sequence to obtain the fault type of the first fault data sequence, and the method includes:

executing the following processing aiming at the identification value of each bit segment in the faulty equipment identification of the first faulty data sequence:

multiplying the identification value corresponding to the bit segment in the fault level identification of the first fault data sequence by the identification value of the bit segment to obtain an equipment fault degree identification value of the bit segment;

performing information splicing on the equipment fault degree identification values of all the segments of the first fault data sequence to obtain a first equipment fault degree identification value of the first fault data sequence;

performing information splicing on the fault level identification of the first fault data sequence and the fault content abstract of the first fault data sequence to obtain the fault level content abstract of the first fault data sequence;

and carrying out information splicing on the first equipment fault degree identification value of the first fault data sequence and the fault level content abstract of the first fault data sequence to obtain the fault type of the first fault data sequence.

Optionally, the comparing the fault type of the first fault data sequence with the fault type of the second fault data sequence includes:

performing the following processing for the identifier of each bit segment in the fault type of the first fault data sequence:

performing character splicing on the identifier corresponding to the bit segment in the fault type of the second fault data sequence and the identifier of the bit segment to obtain a combined character item of the bit segment;

performing information splicing on the combined character items of each bit segment to obtain a type identification character string;

performing similarity operation on the type identification character string to obtain a similarity matrix corresponding to the first fault data sequence and the second fault data sequence;

performing fault category grade matching on the similarity matrix to obtain corresponding similarity of the fault in the first fault data sequence and the fault in the second fault data sequence;

and when the corresponding similarity is smaller than a set similarity threshold value, determining that the fault in the first fault data sequence is different from the fault in the second fault data sequence.

Optionally, the dividing the fault information data into fault data according to a time sequence to obtain a plurality of fault data sequences includes:

dividing the fault information data into fault data by any one of the following modes to obtain a plurality of fault data sequences:

dividing the fault information data according to a first time gradient to obtain a first initial fault data sequence, and dividing the fault information data according to a second time gradient to obtain a second initial fault data sequence, wherein the first time gradient is greater than the second time gradient;

performing first time gradient fault data division on the fault information data to obtain a first initial fault data sequence, and performing second time gradient fault data division on the first initial fault data sequence to obtain a second initial fault data sequence, wherein the first time gradient is greater than the second time gradient;

correspondingly, when the fault in the first fault data sequence is different from the fault in the second fault data sequence, determining the second fault data sequence as a target fault sequence of the fault information data includes:

determining the second failure data sequence in the first initial failure data sequence as a target failure sequence in the first initial failure data sequence when the failure in the first failure data sequence is different from the failure in the second failure data sequence;

determining the second failure data sequence in the second initial failure data sequence as a target failure sequence in the second initial failure data sequence when the failure in the first failure data sequence in the second initial failure data sequence is different from the failure in the second failure data sequence;

the method further comprises the following steps:

performing sequence splicing on a target fault sequence in the plurality of first initial fault data sequences and a target fault sequence in the plurality of second initial fault data sequences to obtain a spliced target fault sequence, and

and carrying out same element filtering on the spliced target fault sequence to obtain a plurality of target fault sequences of the fault information data.

Optionally, the method further comprises:

carrying out fault type recognition on a first fault data sequence sample in a fault data sequence sample pair through a pre-constructed fault type recognition network to obtain a training fault type of the first fault data sequence sample, and carrying out fault type recognition on a second fault data sequence sample in the fault data sequence sample pair to obtain a training fault type of the second fault data sequence sample;

predicting the training fault type of the first fault data sequence sample and the training fault type of the second fault data sequence sample to obtain a fault prediction result of the fault data sequence sample pair; wherein the fault prediction result characterizes whether the fault in the first fault data sequence sample is the same as the fault in the second fault data sequence sample;

constructing a corresponding loss function of the first fault data sequence sample according to the obtained fault level identification of the first fault data sequence sample and the fault level identification label of the first fault data sequence sample;

constructing a corresponding loss function of the second fault data sequence sample according to the obtained fault level identification of the second fault data sequence sample and the fault level identification label of the second fault data sequence sample;

constructing a loss function corresponding to the corresponding priority fault data sequence sample pair according to the fault prediction result of the fault data sequence sample pair and an expected fault result labeled for the fault data sequence sample pair in advance;

weighting and summing the loss functions corresponding to the first fault data sequence sample, the second fault data sequence sample and the priority fault data sequence sample to obtain the loss function of the fault type identification network;

and updating the parameters of the fault type identification network until the loss function of the fault type identification network is converged, and taking the updated parameters of the fault type identification network when the loss function is converged as the parameters of the trained fault type identification network.

In a second aspect, the present application provides an internet of things network maintenance device based on a block chain and big data, the device includes:

the processing module is used for responding to the received state maintenance request and acquiring first to-be-processed data corresponding to a target computing node in a target message field, wherein the target data acquisition equipment corresponding to the first to-be-processed data is configured to be in a maximum data acquisition state, the data acquisition mode is down collection, the target message field is a field corresponding to the target computing node in the received message, and the target computing node is one of all computing nodes contained in the internet of things platform;

the processing module is further configured to obtain second data to be processed and a data collection efficiency statistical strategy corresponding to the target computing node in the target message field, and determine target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical strategy and the first data to be processed;

the maintenance module is used for storing the target data statistical efficiency into a state record file corresponding to the target computing node and broadcasting a state maintenance message containing the target data statistical efficiency in an information verification block network to which the target computing node belongs; the state maintenance message is used for indicating the received block node to record the data statistical efficiency recorded in the state maintenance message.

In a third aspect, the present application provides an internet of things maintenance system based on a block chain and big data, where the internet of things maintenance system includes a plurality of computing nodes that establish communication through a network, and the plurality of computing nodes include a target computing node;

the target computing node is configured to, in response to the received status maintenance request, obtain first to-be-processed data corresponding to the target computing node in a target message field, where a target data acquisition device corresponding to the first to-be-processed data is configured to be in a maximum data acquisition status and a data collection mode is down collection, and the target message field is a field corresponding to the target computing node in a received message;

the target computing node is further configured to acquire second data to be processed and a data collection efficiency statistical strategy corresponding to the target computing node in the target message field, and determine target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical strategy and the first data to be processed;

the target computing node is further configured to store the target data statistical efficiency into a state record file corresponding to the target computing node, and broadcast a state maintenance packet including the target data statistical efficiency in an information verification block network to which the target computing node belongs; the state maintenance message is used for indicating the received block node to record the data statistical efficiency recorded in the state maintenance message.

In a fourth aspect, the present application provides a general-purpose computing node comprising a memory for storing one or more programs; a processor; when the one or more programs are executed by the processor, the method for maintaining the internet of things based on the block chains and the big data is realized.

In a fifth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the above-mentioned method for maintaining an internet of things based on a blockchain and big data.

According to the method for maintaining the internet of things based on the block chains and the big data and the general computing node, first to-be-processed data, second to-be-processed data and a data collection efficiency statistical strategy which correspond to the target computing node in a target message field are obtained; then, the target data statistical efficiency can be determined according to the first data to be processed, the second data to be processed and the data collection efficiency statistical strategy; and finally, storing the target data statistical efficiency to a state recording file corresponding to the target computing node, and broadcasting a state maintenance message containing the target data statistical efficiency in an information verification block network to which the target computing node belongs. According to the technical scheme, the data statistical efficiency of each data acquisition device managed by the Internet of things platform can be effectively calculated and counted, the data are stored in the block network, and the reliability of the data is improved.

In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solution of the present application, the drawings required for 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 those skilled in the art can also derive other related drawings based on these drawings without inventive effort.

Fig. 1 is a schematic diagram of an internet of things network maintenance platform provided by the present application.

FIG. 2 is a schematic diagram of a general purpose computing node provided herein.

Fig. 3 is a flowchart of an internet of things network maintenance method based on artificial intelligence and big data provided by the present application.

Fig. 4 is a structural diagram of an internet of things network maintenance device based on artificial intelligence and big data provided by the present application.

In the figure: 100-a general purpose computing node; 101-a memory; 102-a processor; 103-a communication interface; 400-an internet of things network maintenance device; 410-a processing module; 420-maintenance module.

Detailed Description

To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in some embodiments of the present application, and it is obvious that the described embodiments are some, but not all embodiments of the present application. The components of the present application, as generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations.

Thus, the following detailed description of the embodiments of the present application, as presented in the figures, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments obtained by a person of ordinary skill in the art based on a part of the embodiments in the present application without any creative effort belong to the protection scope of the present application.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.

With reference to fig. 1, the present application provides an internet of things maintenance platform, where the internet of things maintenance platform includes a plurality of computing nodes, each computing node is configured to process all data of a corresponding data acquisition group, and each data acquisition group may include a plurality of data acquisition devices; for example, a data collection group may be a collection of all production devices of a production department, and the corresponding compute node of the production department may be responsible for processing data generated by all production devices of the production department.

It can be understood that, the above-mentioned industrial plant is only used as an example to describe an application scenario of the internet of things platform, and based on the inventive concept of the technical solution provided by the present application, the internet of things platform provided by the present application may also be applied to a scenario where a big data technology may be applied, such as smart medical, smart city management, general service monitoring management, and the like.

Referring to fig. 2, fig. 2 is a schematic diagram of a general-purpose computing node 100 provided in the present application, in this embodiment, the general-purpose computing node 100 includes a memory 101, a processor 102, and a communication interface 103, and the memory 101, the processor 102, and the communication interface 103 are electrically connected to each other directly or indirectly to implement data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.

The memory 101 may be configured to store software programs and modules, such as program instructions/modules corresponding to the internet of things maintenance device based on artificial intelligence and big data provided in the present application, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101, so as to execute the steps of the internet of things maintenance method based on artificial intelligence and big data provided in the present application. The communication interface 103 may be used for communicating signaling or data with other node devices.

The Memory 101 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Programmable Read-Only Memory (EEPROM), and the like.

The processor 102 may be an integrated circuit chip having signal processing capabilities. The Processor 102 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

It will be appreciated that the configuration shown in FIG. 2 is merely illustrative and that the general purpose computing node 100 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.

Referring to fig. 3, fig. 3 is a flowchart of an internet of things network maintenance method based on artificial intelligence and big data provided in the present application, where the internet of things network maintenance method includes the following steps:

step S310, in response to the received status maintenance request, obtaining first to-be-processed data corresponding to a target computing node in a target message field, where a target data collection device corresponding to the first to-be-processed data is configured to be in a maximum data collection status and a data collection mode is down collection, the target message field is a field corresponding to the target computing node in the received message, and the target computing node is one of all computing nodes included in the internet of things platform.

In this embodiment of the application, taking one of all the computing nodes included in the internet of things platform as a target computing node as an example, the target computing node may obtain a state maintenance request by receiving an input from a user or an input from another control device, and execute step S310 based on the state maintenance request.

In all data acquisition devices which are responsible for maintenance of the internet of things platform, the data collection mode of each data acquisition device comprises downtime collection and normal collection, the downtime collection means that the corresponding data acquisition device is in a fault working state, and the normal collection means that the corresponding data acquisition device is in a stable and normal working state; in addition, the maintenance personnel can also configure a data acquisition state for each data acquisition device, that is, the efficiency of each data acquisition device for data acquisition, for example, the data acquisition state may include a maximum data acquisition state when the acquisition efficiency is 100%, a normal data acquisition state when the acquisition efficiency is 70%, and an energy-saving data acquisition state when the acquisition efficiency is 30%.

Step S320, obtaining second data to be processed and a data collection efficiency statistical strategy corresponding to the target computing node in the target packet field, and determining target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical strategy, and the first data to be processed.

In this embodiment, when the target data acquisition device generates each piece of data, a data type identifier may be added to each piece of data to indicate that the corresponding piece of data is the first piece of data to be processed or the second piece of data to be processed, so that the target computing node can identify the first piece of data to be processed and the second piece of data to be processed according to the data type identifier of each piece of data.

Step S330, storing the target data statistical efficiency into a state record file corresponding to the target computing node, and broadcasting a state maintenance message containing the target data statistical efficiency in an information verification block network to which the target computing node belongs; the state maintenance message is used for indicating the received block node to record the data statistical efficiency recorded in the state maintenance message.

In this embodiment, each computing node in the internet of things platform also has an information verification block network, where the information verification block network is configured to store some key information generated by the corresponding computing node, such as a state maintenance packet, verification information, and block attributes generated by the corresponding computing node.

In this embodiment, after the target data statistical efficiency is obtained in step S320, a state maintenance packet including the target data statistical efficiency may be broadcast in the information verification block network to which the target computing node belongs, so that each block node in the information verification block network to which the target computing node belongs can store the target data statistical efficiency included in the state maintenance packet, so as to improve the storage reliability of the target data statistical efficiency.

It can be seen that, in the technical solution provided in the embodiment of the present application, first to-be-processed data, second to-be-processed data and a data collection efficiency statistical strategy corresponding to a target computing node in a target message field are obtained; then, the target data statistical efficiency can be determined according to the first data to be processed, the second data to be processed and the data collection efficiency statistical strategy; and finally, storing the target data statistical efficiency to a state recording file corresponding to the target computing node, and broadcasting a state maintenance message containing the target data statistical efficiency in an information verification block network to which the target computing node belongs. The technical scheme provided by the embodiment of the application can effectively calculate the respective data statistical efficiency for each data acquisition device managed by the Internet of things platform to carry out statistics, and the statistics is stored in the block network, so that the reliability of data is improved.

In this embodiment, in order to accurately acquire the first data to be processed, step S210 may be executed in the following manner:

firstly, all the collected data of which the corresponding data collection mode in the target message field is collected in downtime are obtained and recorded as first initial collected data.

In this embodiment, all the collected data collected in the downtime in the corresponding data collection mode may be determined according to the label corresponding to each data in the target message field; for example, assuming that the tag 000 represents an down collection and the tag 001 represents a normal collection, all of the identified collection data corresponding to the tag 000 may be recorded as the first initial collection data.

And then, according to a node data statistical rule corresponding to the target computing node, performing data cleaning on the first initial collected data so as to acquire all collected data in the first initial collected data, wherein a data collection mode corresponding to the target computing node is downtime collection, and recording the data as second initial collected data.

In this embodiment, in order to ensure that data processed by each computing node in the internet of things platform is accurate and reliable, different node data statistical rules may be configured for each computing node, so that each computing node processes data by using different node data statistical data.

Then, the number of the collected data in the second initial collected data is divided by the collection time range of the data to obtain the unit data collection rate in the unit collection time range.

Next, a preset data acquisition rate threshold is compared with the unit data acquisition rate.

In this way, if the preset data acquisition rate threshold is equal to the unit data acquisition rate, the target data acquisition device corresponding to the second initial acquisition data is currently in the maximum data acquisition state; i.e. the data is collected in a normal collection state.

If the preset data acquisition rate threshold is greater than the unit data acquisition rate, the target data acquisition equipment corresponding to the second initial acquisition data is not in the maximum data acquisition state currently; the data is collected while in the down collection state.

And then, performing data cleaning on the initial acquisition data which is not in the maximum data acquisition state currently to acquire the initial acquisition data which is not in the maximum data acquisition state currently as the first to-be-processed data.

In this embodiment, after determining the initial collected data that is not currently in the maximum data collection state, the part of data may be further subjected to data cleaning, for example, information identifiers other than the opening data itself are removed, so that the initial collected data that is not currently in the maximum data collection state after the data cleaning is used as the first data to be processed.

In addition, as an implementation manner, in this embodiment, the second to-be-processed data includes a second total received quantity of the collected data of the target computing node and a total quantity of normally collected data of all collected data that are normally collected in a corresponding data collection mode; the data collection efficiency statistical strategy comprises a set minimum expected data collection amount and a data collection time range.

Therefore, in this embodiment, step S320 may include the following sub-steps:

and a substep S321, subtracting the minimum expected data acquisition amount from the total amount of the normal collected data to generate a surplus collection amount in a normal collection state, wherein the surplus collection amount in the normal collection state is greater than or equal to zero.

And a substep S322, multiplying the surplus collection amount in the normal collection state by the collection time range of the data to obtain a surplus data collection upper limit amount.

Substep S323, subtracting the second collected data total receiving quantity from the surplus data collection upper limit quantity to obtain a target surplus collecting quantity;

and a substep S324, determining the amount of the target collected data according to the total received amount of the first collected data in the first data to be processed, the minimum expected data collection amount and the collection time range of the data.

In this embodiment, the total first collected data receiving amount is a total data amount in the first to-be-processed data, and when step S324 is executed, the total first collected data receiving amount and the minimum expected data collecting amount may be subtracted to obtain an expected surplus collecting amount; and multiplying the minimum collection efficiency under the preset downtime collection by the collection time range of the data to obtain the basic collection amount under the downtime collection, and then superposing and summing the basic collection amount and the expected surplus collection amount to obtain the quantity of the target collection data.

Substep S325, dividing the smaller of the target excess collection amount and the target collected data amount by the collection time range of the data to generate the target data statistical efficiency.

In addition, in the present embodiment, step S330 may be performed by:

firstly, after the statistical efficiency of the target data is stored in a corresponding state record file of the target computing node, filling the statistical efficiency of the target data in a field corresponding to the statistical efficiency in an initial maintenance message to generate a state maintenance message.

Then, according to the block network indication identifier of the target computing node, determining an information verification block network corresponding to the target computing node, and broadcasting the state maintenance message in the information verification block network.

Therefore, according to the above embodiment provided by the embodiment, the data statistical efficiency of each data acquisition device managed by the internet of things platform can be effectively calculated.

In addition, in this embodiment, the internet of things platform not only can count the statistical efficiency of each data acquisition device, so that maintenance personnel can utilize the statistical efficiency of each data acquisition device to perform downtime analysis, but also can process and store fault data reported by each data acquisition device, so that the maintenance personnel can perform fault analysis.

Therefore, in this embodiment, the method for maintaining the internet of things based on the block chains and the big data may further include the following steps:

step 340, obtaining the fault information data recorded in the target message field.

And 350, dividing the fault information data into fault data according to the time sequence to obtain a plurality of fault data sequences.

Step 360, extracting the fault type of a first fault data sequence in the plurality of fault data sequences to obtain the fault type of the first fault data sequence, and extracting the fault type of a second fault data sequence after the first fault data sequence to obtain the fault type of the second fault data sequence.

Step 370, comparing the failure type of the first failure data sequence with the failure type of the second failure data sequence.

Step 380, when the fault in the first fault data sequence is different from the fault in the second fault data sequence, determining the second fault data sequence as a target fault sequence of the fault information data, and broadcasting a state maintenance packet containing the target fault sequence in an information verification block network to which the target computing node belongs.

It can be seen that, based on the above scheme, by extracting the fault type of the first fault data sequence and the fault type of the second fault data sequence in the fault information data, and when the fault in the first fault data sequence is different from the fault in the second fault data sequence, determining the second fault data sequence as a target fault sequence of the fault information data, therefore, the target fault data sequence can be accurately and quickly determined from the fault information data, and the state maintenance message containing the target fault sequence is broadcasted in the information verification block network to which the target computing node belongs, thereby enabling maintenance personnel to obtain the target fault data sequence from the information verification block network, so that maintenance personnel can analyze the fault condition of the target data acquisition equipment according to the target fault data sequence.

In addition, in this embodiment, the fault conditions of the target data acquisition device may be divided into two types, and different priorities may be configured for the two types of faults, for example, a first priority and a second priority are configured, respectively, and the first priority is higher than the second priority.

When the priority corresponding to the fault of the target data acquisition device is the first priority, step S360 may be executed in the following manner to extract the fault type of the first fault data sequence:

firstly, fault information identification is carried out on the first fault data sequence to obtain a fault equipment identifier and a fault content abstract of the first fault data sequence.

In this embodiment, the faulty device identifier is used to indicate a device corresponding to a fault, and the summary of the fault content is a brief description of the fault occurring in the target data acquisition device.

And then, carrying out information splicing on the fault equipment identification and the fault content abstract of the first fault data sequence to obtain the fault type of the first fault data sequence.

Accordingly, step S360 may also be performed in the following manner to extract the fault type of the second fault data sequence:

firstly, carrying out fault information identification on the second fault data sequence to obtain a fault equipment identifier and a fault content abstract of the second fault data sequence.

And then, carrying out information splicing on the fault equipment identification and the fault content abstract of the second fault data sequence to obtain the fault type of the second fault data sequence.

On the other hand, when the priority corresponding to the fault of the target data acquisition device is the second priority, step S360 may be executed in the following manner to extract the fault type of the first fault data sequence:

firstly, performing information identification of a fault content abstract on the first fault data sequence to obtain a fault content abstract containing the first fault data sequence, wherein the fault content abstract is used for describing the content of a fault.

Then, performing information identification of a fault equipment identifier on the first fault data sequence to obtain a fault equipment identifier containing the first fault data sequence, wherein the fault equipment identifier is used for indicating fault occurrence equipment.

And then, according to the fault grade identification of the first fault data sequence, performing information splicing on the fault equipment identification and the fault content abstract of the first fault data sequence to obtain the fault type of the first fault data sequence.

In this embodiment, when information splicing is performed on the failure device identifier and the failure content abstract, characters of the failure device identifier and the failure content abstract may be directly spliced, so as to obtain the failure type of the first failure data sequence.

firstly, fault information identification is carried out on the second fault data sequence to obtain a fault equipment identifier and a fault content abstract of the second fault data sequence.

And then, according to the fault grade identification of the second fault data sequence, carrying out information splicing on the fault equipment identification and the fault content abstract of the second fault data sequence to obtain the fault type of the second fault data sequence.

In addition, in some embodiments, before performing the step of information splicing the faulty device identification and the faulty content summary of the first faulty data sequence, the method may further include the steps of:

firstly, the device type search may be performed on the faulty device identifier of the first faulty data sequence to obtain a target device type identifier.

In this embodiment, the target device class identifier may be used to indicate a device class to which the faulty device identifier of the first faulty data sequence belongs.

Then, the class identifier of the target device may be subjected to a fault class level search, so as to obtain a fault class identifier of the first fault data sequence.

In this embodiment, the failure level identifier is used to characterize a failure level corresponding to a failure in the first failure data sequence.

Thus, when the step of performing information splicing on the fault equipment identifier and the fault content summary of the first fault data sequence according to the fault level identifier of the first fault data sequence to obtain the fault type of the first fault data sequence is executed, the following method may be adopted:

firstly, the identification value of the bit segment corresponding to the identification value of the fault level identification of the first fault data sequence is multiplied by the identification value of the bit segment to obtain the equipment fault degree identification value of the bit segment.

In this embodiment, the faulty device identifier may include a plurality of bit segments, each bit segment having an identifier value; for example, assuming that the faulty device identifier is "56501" or "56501" can be used to indicate the number of the faulty device, the faulty device identifier has 5 bit segments, and the identifier value of each bit segment is 5, 6, 5, 0, 1; accordingly, the fault level identification may be illustrated as "EEEE 2" in which values of some bit segments in the fault level may be replaced with characters for convenience of bit number correspondence; thus, according to this example, the result of the multiplication corresponding to each of the bit segments is then 5E, 6E, 5E, 0E, 2.

And then, carrying out information splicing on the equipment fault degree identification values of all the segments of the first fault data sequence to obtain a first equipment fault degree identification value of the first fault data sequence.

In this embodiment, according to the above example, the obtained first device failure degree identification value is: 5E6E5E0E 2.

And then, performing information splicing on the fault level identification of the first fault data sequence and the fault content abstract of the first fault data sequence to obtain the fault level content abstract of the first fault data sequence.

And then, performing information splicing on the first equipment fault degree identification value of the first fault data sequence and the fault level content abstract of the first fault data sequence to obtain the fault type of the first fault data sequence.

Therefore, according to the implementation manner provided by the embodiment, the accuracy of the fault type of the first fault data sequence can be improved, and the determination of the repeated fault type is avoided.

It can be understood that, the above is exemplified by a manner of generating the fault type of the first fault data sequence, in this embodiment, the fault type of the second fault data sequence may also be generated in the same manner as above, and for brief description, details of this application are not described herein again.

In addition, in the present embodiment, based on the failure type of the first failure data sequence obtained as described above, step S370 may be performed in the following manner:

first, the identifier corresponding to the bit segment in the fault type of the second fault data sequence may be character-spliced with the identifier of the bit segment to obtain a combined character item of the bit segment.

And then, performing information splicing on the combined character items of each bit segment to obtain a type identification character string.

And then, carrying out similarity operation on the type identification character strings to obtain a similarity matrix corresponding to the first fault data sequence and the second fault data sequence.

And then, carrying out fault class grade matching on the similarity matrix to obtain the corresponding similarity of the fault in the first fault data sequence and the fault in the second fault data sequence.

In this way, when the corresponding similarity is smaller than a set similarity threshold, it is determined that the fault in the first fault data sequence is different from the fault in the second fault data sequence.

In addition, in the present embodiment, step S350 may be performed in the following manner:

and performing first time gradient fault data division on the fault information data to obtain a first initial fault data sequence, and performing second time gradient fault data division on the first initial fault data sequence to obtain a second initial fault data sequence, wherein the first time gradient is greater than the second time gradient.

That is, in this embodiment, the failure information data may be divided into a plurality of failure data sequences by selecting any one of the above manners.

Accordingly, step S380 may be performed by:

determining the second failure data sequence in the second initial failure data sequence as a target failure sequence in the second initial failure data sequence when the failure in the first failure data sequence in the second initial failure data sequence is different from the failure in the second failure data sequence.

In addition, on the basis of the obtained target fault sequence, the obtained target fault sequence can be optimized and updated.

For example, in this embodiment, the internet of things maintenance method may further include the following steps:

and performing sequence splicing on a target fault sequence in the plurality of first initial fault data sequences and a target fault sequence in the plurality of second initial fault data sequences to obtain a spliced target fault sequence, and performing same element filtering on the spliced target fault sequence to obtain a plurality of target fault sequences of the fault information data.

Therefore, the implementation mode provided by the embodiment can enable the obtained target fault sequence to be identified more accurately, and the analysis accuracy of maintenance personnel is improved.

In some embodiments, for the accuracy of fault identification, fault identification may be performed by using a trained fault type identification network in an artificial intelligence-based manner.

First, a fault type identification network may be constructed in advance, for example, the fault type identification network may be constructed based on a BilSTM (Bi-Long Short-Term Memory, bidirectional Long Short-Term Memory artificial neural network).

And identifying the fault type of a first fault data sequence sample in a fault data sequence sample pair aiming at the pre-constructed fault type identification network to obtain the training fault type of the first fault data sequence sample, and identifying the fault type of a second fault data sequence sample in the fault data sequence sample pair to obtain the training fault type of the second fault data sequence sample.

Then, the training fault type of the first fault data sequence sample and the training fault type of the second fault data sequence sample can be subjected to prediction processing, so as to obtain a fault prediction result of the fault data sequence sample pair; wherein the fault prediction result characterizes whether the fault in the first fault data sequence sample is the same as the fault in the second fault data sequence sample.

Then, a corresponding loss function of the first fault data sequence sample may be constructed according to the obtained fault level identifier of the first fault data sequence sample and the fault level identifier label of the first fault data sequence sample.

Then, a corresponding loss function of the second fault data sequence sample may be constructed according to the obtained fault level identifier of the second fault data sequence sample and the fault level identifier label of the second fault data sequence sample.

Next, a loss function corresponding to the corresponding priority fault data sequence sample pair may be constructed according to the fault prediction result of the fault data sequence sample pair and an expected fault result labeled for the fault data sequence sample pair in advance.

Then, the loss functions corresponding to the first failure data sequence sample, the second failure data sequence sample, and the priority failure data sequence sample may be subjected to weighted summation to obtain the loss function of the failure type identification network.

Next, the parameters of the fault type identification network may be updated until the loss function of the fault type identification network converges, and the updated parameters of the fault type identification network when the loss function converges are used as the parameters of the trained fault type identification network.

Therefore, the trained fault type identification network obtained by the method is used for identifying the fault information data, so that the accuracy of fault identification can be improved.

In addition, as shown in fig. 4, the present application further provides an internet of things maintenance apparatus based on a block chain and big data, where the internet of things maintenance apparatus 400 includes a processing module 410 and a maintenance module 420.

The processing module 410 is configured to, in response to the received state maintenance request, acquire first to-be-processed data corresponding to a target computing node in a field of a target packet, where a target data acquisition device corresponding to the first to-be-processed data is configured to be in a maximum data acquisition state and a data collection mode is down collection, the field of the target packet is a field corresponding to the target computing node in the received packet, and the target computing node is one of all computing nodes included in the internet of things platform.

The processing module 410 is further configured to obtain second data to be processed and a data collection efficiency statistical policy corresponding to the target computing node in the target packet field, and determine target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical policy, and the first data to be processed.

A maintenance module 420, configured to store the target data statistical efficiency into a state record file corresponding to the target computing node, and broadcast a state maintenance packet including the target data statistical efficiency in an information verification block network to which the target computing node belongs; the state maintenance message is used for indicating the received block node to record the data statistical efficiency recorded in the state maintenance message.

In addition, the present application also provides an internet of things maintenance system based on a block chain and big data, for example, as shown in fig. 1, where the internet of things maintenance system includes a plurality of computing nodes that establish communication through a network, and the plurality of computing nodes includes a target computing node;

It can be understood that the above-mentioned device 400 for maintaining an internet of things based on a block chain and big data and the system for maintaining an internet of things based on a block chain and big data both belong to the same inventive concept as the above-mentioned method for maintaining an internet of things based on a block chain and big data, and the specific implementation manner of the specific functional module and the target computing node thereof please refer to the specific implementation steps of the above-mentioned method for maintaining an internet of things based on a block chain and big data provided in this embodiment, and for convenience of brief description, this embodiment is not repeated herein.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to some embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).

It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, functional modules in some embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to some embodiments of the present application. And the aforementioned storage medium includes: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.

The above description is only a few examples of the present application and is not intended to limit the present application, and those skilled in the art will appreciate that various modifications and variations can be made in the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.

Claims

1. A fault identification method based on a block chain and big data is characterized by comprising the following steps:

acquiring fault information data recorded in a target message field;

dividing the fault information data according to a time sequence to obtain a plurality of fault data sequences;

when the fault in the first fault data sequence is different from the fault in the second fault data sequence, determining the second fault data sequence as a target fault sequence of the fault information data, and broadcasting a state maintenance message containing the target fault sequence in an information verification block network to which a target computing node belongs;

identifying fault information data by using a trained fault type identification network;

the method for training the fault type recognition network comprises the following steps:

2. The method according to claim 1, wherein when the priority corresponding to the fault is a first priority, the extracting the fault type of a first fault data sequence in the plurality of fault data sequences to obtain the fault type of the first fault data sequence comprises:

3. The method of claim 1,

when the priority corresponding to the fault is a second priority, the extracting the fault type of a first fault data sequence in the plurality of fault data sequences to obtain the fault type of the first fault data sequence includes:

4. The method of claim 1, wherein comparing the fault type of the first fault data sequence and the fault type of the second fault data sequence comprises:

character splicing is carried out on the identifier of the bit segment corresponding to the fault type of the second fault data sequence and the identifier of the bit segment to obtain a combined character item of the bit segment;

performing similarity operation on the type identification character strings to obtain a similarity matrix corresponding to the first fault data sequence and the second fault data sequence;

5. The method according to claim 1, wherein the dividing the fault information data into a plurality of fault data sequences according to a time sequence comprises:

the method further comprises the following steps:

6. The method of claim 1, further comprising:

responding to a received state maintenance request, and acquiring first to-be-processed data corresponding to a target computing node in the target message field, wherein the target data acquisition equipment corresponding to the first to-be-processed data is configured to be in a maximum data acquisition state, a data collection mode is downtime collection, the target message field is a field corresponding to the target computing node in a received message, and the target computing node is one of all computing nodes contained in an internet-of-things platform;

7. The method of claim 6, wherein the obtaining the first to-be-processed data corresponding to the target computing node in the target packet field comprises:

8. The method of claim 6, wherein the second pending data comprises a second total received quantity of collected data for the target compute node and a corresponding total quantity of normally collected data for all collected data normally collected for a data collection mode; the data collection efficiency statistical strategy comprises a set minimum expected data collection amount and a data collection time range;

the determining the target data statistical efficiency according to the second data to be processed, the data collection efficiency statistical strategy and the first data to be processed comprises:

determining the quantity of target collected data according to the total receiving quantity of first collected data in the first to-be-processed data, the minimum expected data collecting quantity and the data collecting time range;

9. The method according to claim 6, wherein the saving the target data statistical efficiency into a state record file corresponding to the target computing node and broadcasting a state maintenance packet containing the target data statistical efficiency in an information verification block network to which the target computing node belongs comprises:

10. A general purpose computing node, comprising:

a memory for storing one or more programs;

a processor;

the one or more programs, when executed by the processor, implement the blockchain and big data based fault identification method of any one of claims 1 to 9.