CN117648670A - Rescue data fusion method, electronic equipment, storage medium and rescue fire truck - Google Patents
Rescue data fusion method, electronic equipment, storage medium and rescue fire truck Download PDFInfo
- Publication number
- CN117648670A CN117648670A CN202410094931.6A CN202410094931A CN117648670A CN 117648670 A CN117648670 A CN 117648670A CN 202410094931 A CN202410094931 A CN 202410094931A CN 117648670 A CN117648670 A CN 117648670A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- monitoring
- fusion
- deviation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 22
- 238000012544 monitoring process Methods 0.000 claims abstract description 174
- 230000004927 fusion Effects 0.000 claims abstract description 94
- 238000012795 verification Methods 0.000 claims abstract description 9
- 230000009467 reduction Effects 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 64
- 230000006870 function Effects 0.000 claims description 51
- 230000008569 process Effects 0.000 claims description 31
- 238000003491 array Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 17
- 230000009191 jumping Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 abstract description 16
- 238000012545 processing Methods 0.000 abstract description 7
- 230000005856 abnormality Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013524 data verification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008521 reorganization Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of emergency rescue data processing, in particular to a rescue data fusion method, electronic equipment, a storage medium and a rescue fire truck; then adding the monitoring data set into a sample set library, and determining the deviation degree of the monitoring data set and the sample set library by counting the classification times required by classifying the monitoring data set into independent classes from the sample set library; and finally, when the deviation degree is smaller than the deviation threshold value, inputting the monitoring data set into a fusion model, and fusing the monitoring data set. According to the invention, the fusion model is utilized to generate the fusion data for the monitoring data set, and the efficiency of data transmission is improved when the fusion data is utilized to carry out data transmission. Before fusion, the invention firstly performs deviation verification on the data, ensures the data reduction degree, can adopt other transmission channels when the deviation is larger, and can play a role in warning the information abnormality of the data set.
Description
Technical Field
The invention relates to the technical field of emergency rescue data processing, in particular to a rescue data fusion method, electronic equipment, a storage medium and a rescue fire truck.
Background
Fire engines can be classified into fire extinguishment, elevation, special duty and guarantee according to their use. The rescue fire engine is used as a member of a special service fire engine, along with informatization transformation, not only various fire rescue equipment, special protection equipment for firefighters, fire breaking and dismantling tools and fire source detectors are equipped, but also tasks of communication, data transmission and transfer are carried on shoulder, and the on-site situation is timely sent to a rescue command platform, so that the significance of the rescue command platform in the rescue and the fire fighting process is different.
In order to ensure the reliability and timeliness of rescue data reception and transfer, various methods have been devised, for example, using a wider network bandwidth to classify data according to attributes, and the like.
However, whether a broadband network or a data priority transmission is adopted, the reliability and timeliness of transmission of the data are compromised when the data are subjected to a large amount of multi-source data.
Based on the above, a rescue data fusion method needs to be developed and designed to improve the transmission efficiency of the rescue data.
Disclosure of Invention
The embodiment of the invention provides a rescue data fusion method, electronic equipment, a storage medium and a rescue fire truck, which are used for solving the problem of low transmission efficiency of emergency rescue data in the prior art.
In a first aspect, an embodiment of the present invention provides a rescue data fusion method, including:
acquiring a monitoring data set, wherein the monitoring data set is acquired based on state monitoring points of a rescue scene;
adding the monitoring data set into a sample set library, and determining the deviation degree of the monitoring data set and the sample set library by counting the classification times required for classifying the monitoring data set into independent classes from the sample set library, wherein the deviation degree is inversely related to the classification times, and the sample set library comprises a plurality of sample monitoring data sets;
and when the deviation degree is smaller than a deviation threshold value, inputting the monitoring data set into a fusion model, and fusing the monitoring data set, wherein the fusion model is constructed according to the sample set library, and the fusion model is used for outputting fusion data according to the input data and restoring the monitoring data set according to the fusion data.
In one possible implementation manner, the determining the deviation degree of the monitoring data set from the sample set library by counting the classification times required for classifying the monitoring data set into independent classes includes:
Constructing a plurality of first monitoring arrays according to the sample set library, wherein the plurality of first monitoring arrays correspond to a plurality of state monitoring points;
normalizing the plurality of first monitoring arrays to obtain a plurality of second monitoring arrays;
arranging each second monitoring array in the plurality of second monitoring arrays according to the values in the arrays, so as to obtain a plurality of first queues;
performing multiple independent classification on the sample set library according to the multiple first queues to obtain multiple classification times, wherein the multiple classification times correspond to the multiple independent classification, and the independent classification is a process of classifying the sample set library according to the multiple first queues until the monitoring data set is independently classified;
and determining the deviation degree according to the classification times and the number of data sets in the sample set library.
In one possible implementation manner, the classifying the sample set library according to the plurality of first queues until the monitoring data sets are independently classified includes:
randomly selecting a first queue from a plurality of first queues as a first target queue;
Generating a classification random number between 0 and 1;
performing two classifications on the data in the first target queue according to the classification random number;
taking a sub-queue containing target monitoring data as a second target queue, wherein the target monitoring data is data from the monitoring data set in the first target queue;
and if the number of the data in the second target queue is greater than one, randomly selecting a first queue from a plurality of first queues as a third target queue, performing data removal operation on the third target queue according to the source data set of the second target queue so that the source data set of the third target queue is consistent with the source data set of the second target queue, taking the third target queue after the removal operation as the second target queue, and jumping to the step of generating a classified random number between 0 and 1.
In one possible implementation manner, the determining the deviation degree according to the multiple classification times and the number of data sets in the sample set library includes:
calculating an average value of the plurality of classification times;
determining the deviation degree according to a first formula, the average value and the number of data sets in the sample set library, wherein the first formula is as follows:
In the method, in the process of the invention,for the degree of deviation->Is a positive number less than 1, +.>For a round-up function->For the number of data sets in the sample set library, +.>Is the average value.
In one possible implementation manner, the fusion model is constructed according to the sample set library, and includes:
obtaining a fusion basic model, wherein the fusion basic model comprises a first model and a second model, the first model is provided with a plurality of inputs and a fusion output, the second model is provided with a fusion input and a plurality of outputs, the fusion input of the second model receives the output of the first model, and the number of the plurality of inputs of the first model is the same as the number of the plurality of outputs of the second model;
dividing a plurality of sample monitoring data sets in the sample set library into a first portion and a second portion, wherein the first portion and the second portion respectively comprise a plurality of sample monitoring data sets;
first partial input: sequentially inputting a plurality of sample monitoring data sets of the first part into a plurality of inputs of the first model, and adjusting parameters of the first model and parameters of the second model according to deviation between a plurality of restoring outputs and the input sample monitoring data sets after each input until the deviation between the plurality of restoring outputs and the input sample monitoring data sets is smaller than a threshold value, wherein the input sample monitoring data sets are data sets input into the first model, and the plurality of restoring outputs are a plurality of outputs of the second model;
Sequentially inputting a plurality of sample monitoring datasets of the second portion to a plurality of inputs of the first model;
determining a total deviation according to a plurality of verification deviations, wherein the verification deviation is a deviation between the input sample monitoring data set and a plurality of reduction outputs after each input sample monitoring data set of the second part, and the total deviation represents the deviation of the first model and the second model;
and if the total deviation is greater than a total deviation threshold, reducing the number of the first model parameters and the number of the second model parameters and jumping to the step of inputting the first part.
In one possible implementation, the first model is:
in the method, in the process of the invention,for the output of the first model, +.>The +.f. of the output function for the first model>Personal weight(s)>Is the +.>Line->Output of column intermediate function, +.>Is a first bias constant of the first model, < ->Is the +.>Line->Output of intermediate function of column, +.>Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>Total number of rows of intermediate function for the first model, < > >For the propagation function +.>Is the +.>The output of the individual input nodes,/>Is the +.>Weight parameters of the individual input nodes,/>Is->Input data->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->A number of weight parameters;
the second model is:
in the method, in the process of the invention,is the +.>Output(s)>The +.f. of the output function for the second model>The weight of the weight is calculated,is the +.>Line->Output of column intermediate function, +.>Is the first bias constant of the second model, +.>Is the +.>Line->Output of intermediate function->Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>For the output of the input node of the second model, +.>Weight parameter for input node of the second model, < ->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->And a weight parameter.
In one possible implementation, the propagation function is:
in the method, in the process of the invention,for input quantity, < >>Is a prepositive constant, < > >Is a natural constant.
In a second aspect, an embodiment of the present invention provides a rescue data fusion device, configured to implement the rescue data fusion method according to the first aspect or any one of the possible implementation manners of the first aspect, where the rescue data fusion device includes:
the data acquisition module is used for acquiring a monitoring data set, wherein the monitoring data set is acquired based on state monitoring points of a rescue scene;
the data verification module is used for adding the monitoring data set into a sample set library, and determining the deviation degree of the monitoring data set and the sample set library in a mode of counting the classification times required for classifying the monitoring data set into independent classes from the sample set library, wherein the deviation degree is inversely related to the classification times, and the sample set library comprises a plurality of sample monitoring data sets;
the method comprises the steps of,
and the data fusion module is used for inputting the monitoring data set into a fusion model to fuse the monitoring data set when the deviation degree is smaller than a deviation threshold value, wherein the fusion model is constructed according to the sample set library, and is used for outputting fusion data according to the input data and restoring the monitoring data set according to the fusion data.
In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor implementing the steps of the method according to the first aspect or any one of the possible implementations of the first aspect when the computer program is executed.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
In a fifth aspect, an embodiment of the present invention provides a rescue fire truck, where the rescue fire truck is provided with the electronic device according to the third aspect and a data receiving device, and the data receiving device is in signal connection with the electronic device;
when the data receiving device receives a monitoring data set, the monitoring data set is sent to the electronic device and processed by the electronic device to generate fusion data.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
The embodiment of the invention discloses a rescue data fusion method, which comprises the steps of firstly, acquiring a monitoring data set, wherein the monitoring data set is acquired based on state monitoring points of a rescue site; then adding the monitoring data set into a sample set library, and determining the deviation degree of the monitoring data set and the sample set library by counting the classification times required for classifying the monitoring data set into independent types from the sample set library, wherein the deviation degree is inversely related to the classification times, and the sample set library comprises a plurality of sample monitoring data sets; and finally, when the deviation degree is smaller than a deviation threshold value, inputting the monitoring data set into a fusion model, and fusing the monitoring data set, wherein the fusion model is constructed according to the sample set library, and the fusion model is used for outputting fusion data according to the input data and restoring the monitoring data set according to the fusion data. According to the embodiment of the invention, the fusion model is utilized to generate the fusion data for the monitoring data set, the data volume of the fused data set is greatly reduced, and the data transmission efficiency is improved when the data transmission is carried out. Before fusion, the embodiment of the invention firstly carries out deviation verification on the data, ensures the data reduction degree, can adopt other transmission channels when the deviation is larger, and can play a role in warning the information abnormality of the data set.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a rescue data fusion method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a process for constructing a queue from a sample set library according to an embodiment of the present invention;
FIG. 3 is a functional block diagram of a rescue data fusion device according to an embodiment of the present invention;
fig. 4 is a functional block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made with reference to the accompanying drawings.
The following describes in detail the embodiments of the present invention, and the present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation procedure are given, but the protection scope of the present invention is not limited to the following embodiments.
Fig. 1 is a flowchart of a rescue data fusion method according to an embodiment of the present invention.
As shown in fig. 1, a flowchart for implementing the rescue data fusion method provided by the embodiment of the present invention is shown, and the details are as follows:
in step 101, a monitoring dataset is acquired, wherein the monitoring dataset is acquired based on status monitoring points of a rescue scene.
In step 102, the monitoring dataset is added to a sample set library, and the degree of deviation of the monitoring dataset from the sample set library is determined by counting the number of classification times required for classifying the monitoring dataset into independent classes from the sample set library, wherein the degree of deviation is inversely related to the number of classification times, and the sample set library comprises a plurality of sample monitoring datasets.
In some embodiments, the step 102 includes:
constructing a plurality of first monitoring arrays according to the sample set library, wherein the plurality of first monitoring arrays correspond to a plurality of state monitoring points;
normalizing the plurality of first monitoring arrays to obtain a plurality of second monitoring arrays;
arranging each second monitoring array in the plurality of second monitoring arrays according to the values in the arrays, so as to obtain a plurality of first queues;
performing multiple independent classification on the sample set library according to the multiple first queues to obtain multiple classification times, wherein the multiple classification times correspond to the multiple independent classification, and the independent classification is a process of classifying the sample set library according to the multiple first queues until the monitoring data set is independently classified;
and determining the deviation degree according to the classification times and the number of data sets in the sample set library.
In some embodiments, the classifying the sample set library according to the plurality of first queues until the monitoring data sets are independently classified comprises:
randomly selecting a first queue from a plurality of first queues as a first target queue;
Generating a classification random number between 0 and 1;
performing two classifications on the data in the first target queue according to the classification random number;
taking a sub-queue containing target monitoring data as a second target queue, wherein the target monitoring data is data from the monitoring data set in the first target queue;
and if the number of the data in the second target queue is greater than one, randomly selecting a first queue from a plurality of first queues as a third target queue, performing data removal operation on the third target queue according to the source data set of the second target queue so that the source data set of the third target queue is consistent with the source data set of the second target queue, taking the third target queue after the removal operation as the second target queue, and jumping to the step of generating a classified random number between 0 and 1.
In some embodiments, the determining the degree of deviation according to the number of classifications and the number of data sets in the sample set library includes:
calculating an average value of the plurality of classification times;
determining the deviation degree according to a first formula, the average value and the number of data sets in the sample set library, wherein the first formula is as follows:
In the method, in the process of the invention,for the degree of deviation->Is a positive number less than 1, +.>For a round-up function->For the number of data sets in the sample set library, +.>Is the average value.
For example, in the fire rescue process, good combat command strategies are indistinguishable from timely field data and field state analysis, and the field data may include: images, videos, gas monitoring data, temperature monitoring data and the like of the rescue scene. In order to reliably and timely transmit the data to the command platform, the embodiment of the invention fuses the data so as to improve the efficiency of data transmission.
To achieve the above object, data acquired in the same period is first aggregated into a data set. Before fusion, the embodiment of the invention firstly verifies the data set, and aims to determine whether fusion conditions exist or not, and whether data are abnormal or not.
In terms of classification method, the embodiment of the present invention reorganizes the data in the sample set library added to the monitoring dataset, as shown in fig. 2, which shows the reorganization process, and the plurality of datasets 201 respectively extract the data from the predetermined time to reorganize the data into arrays, so as to obtain a plurality of arrays, and the arrays respectively perform normalization processing to form normalized arrays, and the normalized arrays are arranged according to the sizes of the elements in the arrays, so as to construct a plurality of queues 202.
It is contemplated that each queue 202 includes a data element derived from the monitoring dataset. For example, monitoring the data set 201 includes: data1, data2 … … DataN, forming a queue 202 by combining, normalizing and ordering as described above: q1, Q2 … … QM, each queue has one element corresponding to the monitored dataset and its location becomes unfixed due to reordering, for a Q1 queue the data corresponding to the monitored dataset may be located at a position a and for a Q2 queue the data corresponding to the monitored dataset may be located at a position b, but for each queue there is always one element corresponding to the monitored dataset, and similarly for other sample datasets in the plurality of datasets 201 there is the same corresponding element in each queue 202.
In terms of classification, the embodiment of the invention randomly extracts one queue from the queues each time, randomly generates a random number between 0 and 1, takes the random number as a classification interval, divides the extracted queue into two sections of sub-queues, finds the sub-queues containing corresponding monitoring data sets, checks the number of elements in the sub-queues, and if the number of elements is larger than 1, the monitoring data sets are not independent and successful. At this time, a queue is randomly extracted from the queues again, data deletion operation is carried out on the re-extracted queue, elements contained in the deleted queue are identical to data sets corresponding to elements containing sub-queues corresponding to the monitoring data sets, at this time, random number generation, segmentation and independent analysis are carried out on the deleted queue again, the above-mentioned processes are repeated until the elements corresponding to the monitoring data sets are independent, and the times of extracting the queue are counted and used as classification times.
It can be seen that the above classification process has a certain uncertainty, so that the embodiment of the invention executes the classification process for a plurality of times, counts the classification times required for separating the monitoring data set for a plurality of times, calculates the average value of the classification times, and calculates the deviation degree of the monitoring data set and the data set in the sample set library by using the first formula:
In the method, in the process of the invention,for the degree of deviation->Is a positive number less than 1, +.>For a round-up function->For the number of data sets in the sample set library, +.>Is an average of a plurality of classification times.
From the above equation, it can be seen that the degree of deviation is inversely related to the number of classification times, and the smaller the average value of the number of classification times is, the larger the deviation is.
In one embodiment, a plurality of monitoring data sets are obtained before fusion, and the monitoring data sets which are easy to repeatedly appear are selected to be added into the sample set library, so that the sample set library is obtained.
In step 103, when the deviation degree is smaller than a deviation threshold, the monitoring data set is input into a fusion model, and the monitoring data set is fused, wherein the fusion model is constructed according to the sample set library, and the fusion model is used for outputting fusion data according to the input data and restoring the monitoring data set according to the fusion data.
In some embodiments, the fusion model is constructed from the sample set library, comprising:
obtaining a fusion basic model, wherein the fusion basic model comprises a first model and a second model, the first model is provided with a plurality of inputs and a fusion output, the second model is provided with a fusion input and a plurality of outputs, the fusion input of the second model receives the output of the first model, and the number of the plurality of inputs of the first model is the same as the number of the plurality of outputs of the second model;
Dividing a plurality of sample monitoring data sets in the sample set library into a first portion and a second portion, wherein the first portion and the second portion respectively comprise a plurality of sample monitoring data sets;
first partial input: sequentially inputting a plurality of sample monitoring data sets of the first part into a plurality of inputs of the first model, and adjusting parameters of the first model and parameters of the second model according to deviation between a plurality of restoring outputs and the input sample monitoring data sets after each input until the deviation between the plurality of restoring outputs and the input sample monitoring data sets is smaller than a threshold value, wherein the input sample monitoring data sets are data sets input into the first model, and the plurality of restoring outputs are a plurality of outputs of the second model;
sequentially inputting a plurality of sample monitoring datasets of the second portion to a plurality of inputs of the first model;
determining a total deviation according to a plurality of verification deviations, wherein the verification deviation is a deviation between the input sample monitoring data set and a plurality of reduction outputs after each input sample monitoring data set of the second part, and the total deviation represents the deviation of the first model and the second model;
And if the total deviation is greater than a total deviation threshold, reducing the number of the first model parameters and the number of the second model parameters and jumping to the step of inputting the first part.
In some embodiments, the first model is:
in the method, in the process of the invention,for the output of the first model, +.>The +.f. of the output function for the first model>Personal weight(s)>Is the +.>Line->Output of column intermediate function, +.>Is a first bias constant of the first model, < ->Is the +.>Line->Output of intermediate function of column, +.>Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>Total number of rows of intermediate function for the first model, < >>For the propagation function +.>Is the +.>The output of the individual input nodes,/>Is the +.>Weight parameters of the individual input nodes,/>Is->Input data->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->A number of weight parameters;
the second model is:
in the method, in the process of the invention,is the +.>Output(s)>The +.f. of the output function for the second model >The weight of the weight is calculated,is the +.>Line->Output of column intermediate function, +.>Is the first bias constant of the second model, +.>Is the +.>Line->Output of intermediate function->Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>For the output of the input node of the second model, +.>Weight parameter for input node of the second model, < ->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->And a weight parameter.
In some embodiments, the propagation function is:
in the method, in the process of the invention,for input quantity, < >>Is a prepositive constant, < >>Is a natural constant.
By way of example, the embodiment of the invention determines the deviation degree of the monitoring data set and the sample set library according to the steps, and when the deviation is smaller, the data sets can be fused to generate fused data.
In the aspect of fusion, the embodiment of the invention only needs to input the monitoring data set into the fusion model, and the fusion model outputs one fused data. And for the receiving end, the data after the fusion is received is restored by the fusion model.
The fusion model provided by the embodiment of the invention comprises a first model and a second model, wherein the first model inputs data of a data set, outputs fused data, and the second model inputs fused data and outputs a restored data set, and in some application scenes, the formula of the first model is as follows:
in the method, in the process of the invention,for the output of the first model, +.>The +.f. of the output function for the first model>Personal weight(s)>Is the +.>Line->Output of column intermediate function, +.>Is a first bias constant of the first model, < ->Is the +.>Line->Output of intermediate function of column, +.>Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>Total number of rows of intermediate function for the first model, < >>For the propagation function +.>Is the +.>The output of the individual input nodes,/>Is the +.>Individual transportWeight parameter of incoming node->Is->Input data->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->A number of weight parameters;
the second model is:
in the method, in the process of the invention, Is the +.>Output(s)>The +.f. of the output function for the second model>The weight of the weight is calculated,is the +.>Line->Output of column intermediate function, +.>Is the first bias constant of the second model, +.>Is the +.>Line->Output of intermediate function->Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>For the output of the input node of the second model, +.>Weight parameter for input node of the second model, < ->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->And a weight parameter.
In the above equation, the propagation function is:
in the method, in the process of the invention,for input quantity, < >>Is a prepositive constant, < >>Is a natural constant.
From the two formulas above, it can be seen that the two models have the same model respectively. When the method is applied to data fusion, the fused data can be obtained by only inputting the data into the first model. If the fused data is sent to the remote end, the remote end receives the fused data, and the data can be restored through the second model.
The two formulas are basic models, and for the determination aspect of parameter values, the invention solves through a sample monitoring data set in a sample set library.
In terms of solving parameter values, firstly, a sample monitoring dataset in a sample dataset library is divided into two parts, the sample monitoring dataset of the first part is sequentially input into a first model, after each part is input, a restored dataset is output in a second model, a deviation is calculated according to the restored dataset and the input dataset, a back propagation algorithm is adopted according to the deviation to adjust parameters until the deviation between the restored dataset output by the second model and the input dataset is smaller than a threshold value, at the moment, the sample monitoring dataset of the second part is sequentially input into the first model, a plurality of restored datasets are obtained in the second model, the total deviation is determined according to the obtained restored datasets and the input datasets, and if the total deviation is larger than the total deviation threshold value, the number of parameters in the first model and the second model is reduced, for example, the total number of columns is reduced, so that the total number of parameters is reduced. And after the reduction, the parameter determination operation is carried out again.
In application, the rescue data fusion method of the invention firstly acquires a preset number of data sets, counts the data sets with higher occurrence frequency in the data sets, adds the data sets as initial sample monitoring data sets into a sample set library, and utilizes the sample set library to construct a fusion model, namely, determines parameters of the fusion model. And transmitting the parameters to a receiving end of the fusion data, and restoring the fusion data into a fusion data set by the receiving end through a fusion model.
For example, a rescue fire engine and a command platform are respectively arranged on a rescue site, the rescue fire engine is responsible for collecting data sets and fusing the data, and the command platform is responsible for receiving the fused data and restoring the fused data sets according to the fused data.
The rescue fire engine receives a part of monitoring data set firstly, based on statistics, a part of monitoring data set is determined to be used as a sample monitoring data set, parameters of the first model and the second model are determined according to the sample monitoring data set, after the parameters are determined, the parameters are transmitted to the command platform, and the command platform builds the second model, namely a data set restoring model, according to the parameters. After the monitoring data set is acquired, the rescue fire truck firstly determines deviation according to the sample set library, when the deviation is smaller than a threshold value, the data set is sent into the first model to obtain fusion data, the fusion data are sent to the command platform through a network, and the command platform carries out data reduction through the second model after receiving the fusion data.
The rescue data fusion method comprises the steps of firstly, acquiring a monitoring data set, wherein the monitoring data set is acquired based on state monitoring points of a rescue site; then adding the monitoring data set into a sample set library, and determining the deviation degree of the monitoring data set and the sample set library by counting the classification times required for classifying the monitoring data set into independent types from the sample set library, wherein the deviation degree is inversely related to the classification times, and the sample set library comprises a plurality of sample monitoring data sets; and finally, when the deviation degree is smaller than a deviation threshold value, inputting the monitoring data set into a fusion model, and fusing the monitoring data set, wherein the fusion model is constructed according to the sample set library, and the fusion model is used for outputting fusion data according to the input data and restoring the monitoring data set according to the fusion data. According to the embodiment of the invention, the fusion model is utilized to generate the fusion data for the monitoring data set, the data volume of the fused data set is greatly reduced, and the data transmission efficiency is improved when the data transmission is carried out. Before fusion, the embodiment of the invention firstly carries out deviation verification on the data, ensures the data reduction degree, can adopt other transmission channels when the deviation is larger, and can play a role in warning the information abnormality of the data set.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 3 is a functional block diagram of a rescue data fusion device according to an embodiment of the present invention, and referring to fig. 3, the rescue data fusion device includes: a data acquisition module 301, a data verification module 302, and a data fusion module 303, wherein:
the data acquisition module 301 is configured to acquire a monitoring dataset, where the monitoring dataset is acquired based on a status monitoring point of a rescue scene;
a data verification module 302, configured to add the monitoring dataset to a sample set library, and determine a degree of deviation between the monitoring dataset and the sample set library by counting a number of classification times required to classify the monitoring dataset into independent classes from the sample set library, where the degree of deviation is inversely related to the number of classification times, and the sample set library includes a plurality of sample monitoring datasets;
And the data fusion module 303 is configured to input the monitoring dataset into a fusion model to fuse the monitoring dataset when the deviation degree is smaller than a deviation threshold, wherein the fusion model is constructed according to the sample set library, and the fusion model is configured to output fusion data according to the input data and to restore the monitoring dataset according to the fusion data.
Fig. 4 is a functional block diagram of an electronic device provided by an embodiment of the present invention. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a processor 400 and a memory 401, said memory 401 having stored therein a computer program 402 executable on said processor 400. The processor 400 implements the steps of the above-described respective rescue data fusion method and embodiment when executing the computer program 402, for example, steps 101 to 103 shown in fig. 1.
By way of example, the computer program 402 may be partitioned into one or more modules/units that are stored in the memory 401 and executed by the processor 400 to accomplish the present invention.
The electronic device 4 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The electronic device 4 may include, but is not limited to, a processor 400, a memory 401. It will be appreciated by those skilled in the art that fig. 4 is merely an example of the electronic device 4 and is not meant to be limiting of the electronic device 4, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the electronic device 4 may further include input-output devices, network access devices, buses, etc.
The processor 400 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 401 may be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 401 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 4. Further, the memory 401 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 401 is used for storing the computer program 402 and other programs and data required by the electronic device 4. The memory 401 may also be used to temporarily store data that has been output or is to be output.
In addition, in some application scenes, the rescue fire truck is provided with the electronic equipment and the data receiving equipment, data received by the receiving equipment are summarized into a data set, and the data set is fused on the electronic equipment to generate fusion data, so that the effects of data fusion and data transmission efficiency improvement are achieved.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, and will not be described herein again.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and the details or descriptions of other embodiments may be referred to for those parts of an embodiment that are not described in detail or are described in detail.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on this understanding, the present invention may also be implemented by implementing all or part of the procedures in the methods of the above embodiments, or by instructing the relevant hardware by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may be implemented by implementing the steps of the embodiments of the methods and apparatuses described above when executed by a processor. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limited thereto; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and they should be included in the protection scope of the present invention.
Claims (10)
1. The rescue data fusion method is characterized by comprising the following steps of:
acquiring a monitoring data set, wherein the monitoring data set is acquired based on state monitoring points of a rescue scene;
adding the monitoring data set into a sample set library, and determining the deviation degree of the monitoring data set and the sample set library by counting the classification times required for classifying the monitoring data set into independent classes from the sample set library, wherein the deviation degree is inversely related to the classification times, and the sample set library comprises a plurality of sample monitoring data sets;
and when the deviation degree is smaller than a deviation threshold value, inputting the monitoring data set into a fusion model, and fusing the monitoring data set, wherein the fusion model is constructed according to the sample set library, and the fusion model is used for outputting fusion data according to the input data and restoring the monitoring data set according to the fusion data.
2. Rescue data fusion method according to claim 1, characterized in that the determining the degree of deviation of the monitoring dataset from the sample set library by counting the number of classification times required to classify the monitoring dataset into independent classes from the sample set library comprises:
constructing a plurality of first monitoring arrays according to the sample set library, wherein the plurality of first monitoring arrays correspond to a plurality of state monitoring points;
normalizing the plurality of first monitoring arrays to obtain a plurality of second monitoring arrays;
arranging each second monitoring array in the plurality of second monitoring arrays according to the values in the arrays, so as to obtain a plurality of first queues;
performing multiple independent classification on the sample set library according to the multiple first queues to obtain multiple classification times, wherein the multiple classification times correspond to the multiple independent classification, and the independent classification is a process of classifying the sample set library according to the multiple first queues until the monitoring data set is independently classified;
and determining the deviation degree according to the classification times and the number of data sets in the sample set library.
3. Rescue data fusion method according to claim 2, characterized in that the classifying the sample set library according to the plurality of first queues until the monitoring data sets are independently classified comprises:
randomly selecting a first queue from a plurality of first queues as a first target queue;
generating a classification random number between 0 and 1;
performing two classifications on the data in the first target queue according to the classification random number;
taking a sub-queue containing target monitoring data as a second target queue, wherein the target monitoring data is data from the monitoring data set in the first target queue;
and if the number of the data in the second target queue is greater than one, randomly selecting a first queue from a plurality of first queues as a third target queue, performing data removal operation on the third target queue according to the source data set of the second target queue so that the source data set of the third target queue is consistent with the source data set of the second target queue, taking the third target queue after the removal operation as the second target queue, and jumping to the step of generating a classified random number between 0 and 1.
4. Rescue data fusion method according to claim 2, characterized in that the determining the degree of deviation from the number of classification times and the number of data sets in the sample set library comprises:
calculating an average value of the plurality of classification times;
determining the deviation degree according to a first formula, the average value and the number of data sets in the sample set library, wherein the first formula is as follows:
in the method, in the process of the invention,for the degree of deviation->Is a positive number less than 1, +.>For a round-up function->For the number of data sets in the sample set library, +.>Is the average value.
5. Rescue data fusion method according to any one of claims 1-4, characterized in that the fusion model is constructed from the sample set library, comprising:
obtaining a fusion basic model, wherein the fusion basic model comprises a first model and a second model, the first model is provided with a plurality of inputs and a fusion output, the second model is provided with a fusion input and a plurality of outputs, the fusion input of the second model receives the output of the first model, and the number of the plurality of inputs of the first model is the same as the number of the plurality of outputs of the second model;
Dividing a plurality of sample monitoring data sets in the sample set library into a first portion and a second portion, wherein the first portion and the second portion respectively comprise a plurality of sample monitoring data sets;
first partial input: sequentially inputting a plurality of sample monitoring data sets of the first part into a plurality of inputs of the first model, and adjusting parameters of the first model and parameters of the second model according to deviation between a plurality of restoring outputs and the input sample monitoring data sets after each input until the deviation between the plurality of restoring outputs and the input sample monitoring data sets is smaller than a threshold value, wherein the input sample monitoring data sets are data sets input into the first model, and the plurality of restoring outputs are a plurality of outputs of the second model;
sequentially inputting a plurality of sample monitoring datasets of the second portion to a plurality of inputs of the first model;
determining a total deviation according to a plurality of verification deviations, wherein the verification deviation is a deviation between the input sample monitoring data set and a plurality of reduction outputs after each input sample monitoring data set of the second part, and the total deviation represents the deviation of the first model and the second model;
And if the total deviation is greater than a total deviation threshold, reducing the number of the first model parameters and the number of the second model parameters and jumping to the step of inputting the first part.
6. The rescue data fusion method according to claim 5, wherein the first model is:
in the method, in the process of the invention,for the output of the first model, +.>The +.f. of the output function for the first model>Personal weight(s)>Is the +.>Line->Output of column intermediate function, +.>Is a first bias constant of the first model, < ->Is the +.>Line->Output of intermediate function of column, +.>Is the +.>Line->Column intermediate function->The number of weight parameters to be used in the process,is the +.>Line->Output of column intermediate function, +.>The total number of rows being an intermediate function of the first model,for the propagation function +.>Is the +.>The output of the individual input nodes,/>Is the +.>Weight parameters of the individual input nodes,/>Is->Input data->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->A number of weight parameters;
the second model is:
in the method, in the process of the invention, Is the +.>Output(s)>The +.f. of the output function for the second model>Personal weight(s)>Is the +.>Line->Output of column intermediate function, +.>Is the first bias constant of the second model, +.>Is the +.>Line->Output of intermediate function->Is the +.>Line->Column intermediate function->Weight parameters->Is the +.>Line->Output of column intermediate function, +.>For the output of the input node of the second model, +.>Weight parameter for input node of the second model, < ->Is the +.>Line->Output of column intermediate function, +.>Is the +.>Line->Column intermediate function->And a weight parameter.
7. Rescue data fusion method according to claim 6, characterized in that the propagation function is:
in the method, in the process of the invention,for input quantity, < >>Is a prepositive constant, < >>Is a natural constant.
8. An electronic device comprising a memory and a processor, the memory having stored therein a computer program executable on the processor, characterized in that the processor implements the steps of the method according to any of the preceding claims 1 to 7 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 7.
10. A rescue fire truck, characterized in that the rescue fire truck is provided with the electronic device as claimed in claim 8 and a data receiving device, wherein the data receiving device is in signal connection with the electronic device;
when the data receiving device receives a monitoring data set, the monitoring data set is sent to the electronic device and processed by the electronic device to generate fusion data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410094931.6A CN117648670B (en) | 2024-01-24 | 2024-01-24 | Rescue data fusion method, electronic equipment, storage medium and rescue fire truck |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410094931.6A CN117648670B (en) | 2024-01-24 | 2024-01-24 | Rescue data fusion method, electronic equipment, storage medium and rescue fire truck |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117648670A true CN117648670A (en) | 2024-03-05 |
| CN117648670B CN117648670B (en) | 2024-04-12 |
Family
ID=90049747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410094931.6A Active CN117648670B (en) | 2024-01-24 | 2024-01-24 | Rescue data fusion method, electronic equipment, storage medium and rescue fire truck |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117648670B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228728A (en) * | 2017-12-11 | 2018-06-29 | 北京航空航天大学 | A kind of paper network node of parametrization represents learning method |
| WO2021135474A1 (en) * | 2020-01-02 | 2021-07-08 | 平安科技（深圳）有限公司 | Method and apparatus for fusing data from multiple data sources, electronic device, and storage medium |
| CN114091360A (en) * | 2022-01-21 | 2022-02-25 | 武汉格蓝若智能技术有限公司 | Multi-model fused voltage transformer error state evaluation method |
| CN115221982A (en) * | 2022-09-21 | 2022-10-21 | 石家庄铁道大学 | Traction power supply operation and maintenance method and device, terminal and storage medium |
| CN116226114A (en) * | 2023-05-09 | 2023-06-06 | 荣耀终端有限公司 | Data processing method, system and storage medium |
| CN116385239A (en) * | 2023-04-07 | 2023-07-04 | 应急管理部上海消防研究所 | Emergency management method based on dynamic perception fusion of disaster site information |
| CN117436017A (en) * | 2023-10-27 | 2024-01-23 | 国网河北省电力有限公司超高压分公司 | Abnormality early warning method and device for electric energy quality monitoring device |
-
2024
- 2024-01-24 CN CN202410094931.6A patent/CN117648670B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108228728A (en) * | 2017-12-11 | 2018-06-29 | 北京航空航天大学 | A kind of paper network node of parametrization represents learning method |
| WO2021135474A1 (en) * | 2020-01-02 | 2021-07-08 | 平安科技（深圳）有限公司 | Method and apparatus for fusing data from multiple data sources, electronic device, and storage medium |
| CN114091360A (en) * | 2022-01-21 | 2022-02-25 | 武汉格蓝若智能技术有限公司 | Multi-model fused voltage transformer error state evaluation method |
| CN115221982A (en) * | 2022-09-21 | 2022-10-21 | 石家庄铁道大学 | Traction power supply operation and maintenance method and device, terminal and storage medium |
| CN116385239A (en) * | 2023-04-07 | 2023-07-04 | 应急管理部上海消防研究所 | Emergency management method based on dynamic perception fusion of disaster site information |
| CN116226114A (en) * | 2023-05-09 | 2023-06-06 | 荣耀终端有限公司 | Data processing method, system and storage medium |
| CN117436017A (en) * | 2023-10-27 | 2024-01-23 | 国网河北省电力有限公司超高压分公司 | Abnormality early warning method and device for electric energy quality monitoring device |
Non-Patent Citations (2)
| Title |
|---|
| 徐成华;宋雨娇;于振铎;庄子尤;: "面向应急救援的多源数据融合技术", 计算机系统应用, no. 12, 15 December 2019 (2019-12-15), pages 9 - 18 * |
| 狄婧;: "云数据融合过程的优化方法研究与仿真", 计算机仿真, no. 12, 15 December 2015 (2015-12-15), pages 396 - 399 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117648670B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084377B (en) | Method and device for constructing decision tree | |
| US20240013098A1 (en) | Data processing system and method | |
| CN110866546B (en) | Method and device for evaluating consensus node | |
| CN116647411B (en) | Game platform network security monitoring and early warning method | |
| CN112087334B (en) | Alarm root cause analysis method, electronic device and storage medium | |
| CN110602034B (en) | Method and system for detecting S7 protocol abnormal communication behavior based on PSO-SVM | |
| CN111343212B (en) | Message processing method, device, equipment and storage medium | |
| CN111507479B (en) | Feature binning method, device, equipment and computer-readable storage medium | |
| CN111276247B (en) | Flight parameter data health assessment method and equipment based on big data processing | |
| CN117648670B (en) | Rescue data fusion method, electronic equipment, storage medium and rescue fire truck | |
| CN113177203B (en) | Method and device for identifying encrypted malicious message flow | |
| CN113011886B (en) | Method and device for determining account type and electronic equipment | |
| CN117294497A (en) | Network traffic abnormality detection method and device, electronic equipment and storage medium | |
| CN117640193A (en) | Industrial control threat detection method based on application layer effective load extraction | |
| US20230412627A1 (en) | Method and apparatus for anomaly detection | |
| CN115455457B (en) | Chain data management method, system and storage medium based on intelligent big data | |
| CN114785805B (en) | Data transmission method, device, electronic equipment and storage medium | |
| CN116070149A (en) | Data analysis method and system based on artificial intelligence and cloud platform | |
| CN110781232A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113553239B (en) | Abnormal data detection method and related device | |
| CN108280224A (en) | Ten thousand grades of dimension data generation methods, device, equipment and storage medium | |
| CN111815442B (en) | Link prediction method and device and electronic equipment | |
| CN113434869A (en) | Data processing method and AI system based on threat perception big data and artificial intelligence | |
| CN114143095A (en) | Power distribution terminal DTU intrusion detection method and system based on isolated forest | |
| WO2022106863A1 (en) | Method and system for accelerating the convergence of an iterative computation code of physical parameters of a multi-parameter system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |