CN116665001A - Intelligent park multisource data dynamic monitoring and real-time analysis system and method - Google Patents
Intelligent park multisource data dynamic monitoring and real-time analysis system and method Download PDFInfo
- Publication number
- CN116665001A CN116665001A CN202310636835.5A CN202310636835A CN116665001A CN 116665001 A CN116665001 A CN 116665001A CN 202310636835 A CN202310636835 A CN 202310636835A CN 116665001 A CN116665001 A CN 116665001A
- Authority
- CN
- China
- Prior art keywords
- data
- fusion
- source
- value
- attribute
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000010223 real-time analysis Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 17
- 230000004927 fusion Effects 0.000 claims abstract description 132
- 238000013210 evaluation model Methods 0.000 claims abstract description 40
- 230000007613 environmental effect Effects 0.000 claims abstract description 29
- 238000011156 evaluation Methods 0.000 claims description 36
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 claims description 18
- 238000005259 measurement Methods 0.000 claims description 17
- 238000013507 mapping Methods 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000013441 quality evaluation Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 abstract description 12
- 206010063385 Intellectualisation Diseases 0.000 abstract description 4
- 230000010354 integration Effects 0.000 abstract description 2
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/803—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of input or preprocessed data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a system and a method for dynamically monitoring and analyzing multi-source data in an intelligent park, which are characterized in that the intelligent park aerial image and environmental data acquired by a plurality of sensors are acquired, the aerial image and the environmental data are subjected to self-adaptive weighted fusion, the weight of each sensor is determined to obtain fusion data, the accuracy, the integrity, the timeliness, the consistency, the balance and the relativity of the fusion data are acquired, an evaluation model corresponding to the fusion data is constructed, the multi-source fusion data reconstruction is carried out on the fusion data according to the evaluation model, the multi-source data dynamic monitoring and the real-time analysis are completed, the data quality in a multi-source data fusion scene is quantitatively analyzed, a manager can intuitively know the data quality condition, the integration, the intellectualization and the high efficiency of park management can be greatly improved, the labor cost and the time cost are greatly saved for a park manager, and the management efficiency of the intelligent park is improved.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a system and a method for dynamically monitoring and analyzing multi-source data in an intelligent park in real time.
Background
The intelligent park is the implementation form of the intelligent city in a small area range, and main system characteristics and development characteristics have important reference significance for the intelligent city. Building intelligent parks also creates intelligent service systems for parks, including building intelligent and intelligent information services. The intelligent park adopts the latest information communication technology, uses the Internet or the mobile Internet as an information transmission carrier, adopts the Internet of things technology during data acquisition and transmission, simultaneously utilizes the cloud technology to integrate and intensively calculate information, and has the capabilities of rapidly acquiring various information, rapidly transmitting and accurately processing intelligent transactions. However, for intelligent garden, traditional garden is artificial management, and some management omission can appear in the management process, and artificial management can't carry out fine management to the garden. Because of the lack of a perfect data evaluation process for the multi-source data sources of the intelligent park, the conditions of data attribute conflict, data missing, inconsistent storage structure and the like exist during multi-source data fusion, so that the association relationship among the data is difficult to discover, and the accuracy and the efficiency of dynamic monitoring and real-time analysis of the intelligent park are affected.
Disclosure of Invention
In view of the above, the invention provides an intelligent park multisource data dynamic monitoring and real-time analysis system and method capable of improving the integrity, intellectualization and high efficiency of park management, which can greatly save labor cost and time cost for park managers so as to solve the technical problems, and is realized by adopting the following technical scheme.
In a first aspect, the present invention provides a system for dynamic monitoring and real-time analysis of multi-source data in an intelligent campus, comprising:
the data acquisition module is used for acquiring wisdomThe method comprises the steps of taking aerial images of a park and collecting environmental data through multiple sensors, wherein the aerial images are taken by adopting a rotor unmanned aerial vehicle, and the environmental data comprise temperature, humidity and CO 2 Concentration, formaldehyde concentration, TVOC concentration, and PM2.5 concentration;
the data fusion module is used for carrying out self-adaptive weighted fusion on the aerial image and the environmental data and determining the weight of each sensor so as to obtain fusion data;
the data quality evaluation module is used for acquiring the accuracy, the completeness, the timeliness, the consistency, the balance and the correlation of the fusion data and constructing an evaluation model corresponding to the fusion data;
and the data analysis module is used for carrying out multisource fusion data reconstruction on the fusion data according to the evaluation model so as to complete multisource data dynamic monitoring and real-time analysis.
As a further preferred aspect of the above technical solution, performing multi-source fusion data reconstruction on fusion data according to an evaluation model to complete multi-source data dynamic monitoring and real-time analysis includes:
after the measurement values measured by the same type of detection quantity at different spatial positions are divided into a plurality of batches by adopting a batch estimation algorithm, carrying out batch fusion processing, and presetting a first group of data: t (T) 11 ,T 12 ...T 1m M is N; a second set of data: t (T) 21 ,T 22 ...T 2n Calculating arithmetic mean value and corresponding standard error of two groups of measurement data according to a formula, wherein the standard error measured in the previous time is preset to be sigma - The standard error currently measured is sigma + The previous fusion value was T - The current fusion value is T + According to the current first measurement, no measurement statistics data exist before, sigma + 、σ + The corresponding data is input into the batch estimation to calculate, and the expression of the current variance is calculated as sigma + ＝[(σ - ) -1 +H T R -1 H] -1 Wherein, the method comprises the steps of, wherein,as a coefficient matrix, H T Representing the systemTransposition of the number matrix>Representing covariance +_>Representing the variance of the first set of data, +.>Representing the variance of the second set of data, +.>The data fusion value is derived to obtain a fusion result as T + ＝[σ + +(σ - ) -1 ]T - +[σ + +H T R -1 ]T, will R, H, sigma - 、σ + 、T - And->Inputting the final fusion result into the fusion result to obtain the final fusion result expressed as +.>Wherein->Representing the arithmetic mean of the previous group, +.>Representing the arithmetic mean of the second group.
As a further preferred aspect of the above technical solution, obtaining accuracy, integrity, timeliness, consistency, balance and correlation of the fusion data and constructing an evaluation model corresponding to the fusion data includes:
the accuracy dimension of the accuracy assessment model contains two evaluation indexes of data accuracy and source authority, the specific evaluation indexes are modeled to obtain the accuracy assessment model, and the accuracy of the data reflects whether the data is real and accurate or notDescribing an application scene, presetting the j-th data of the i-th data as D ij The ith data source shares N i Data, an important attribute set attr (D i )＝{A 1 ,A 2 ...A l The reference value standard in this scenario is m= { M 1 ,M 2 ...M l Then there is a mapping function of Wherein->Representing an accuracy judgment function, if D ij In attribute A k The value of the value meets the reference value standard M k Then->1 and vice versa, so data D ij In the attribute set attr (D i ) When the values are correct, the data are true and effective, and mu (x) value is 1;
the data accuracy measurement model is:wherein the DAcc's range of values represents 0,1]When the DAcc takes a value of 0, the data representing the ith data source are inaccurate; when the DAcc takes the value of 1, the data representing the data source are very accurate;
the selection of the evaluation index has flexibility, and the accuracy evaluation model is thatWherein Eval acc Subscript set of accuracy evaluation index representing the accuracy of the selection, k being Eval acc Number of elements in the collection.
As a further preferred aspect of the above technical solution, obtaining the integrity of the fusion data to construct an evaluation model corresponding to the fusion data includes:
the integrity evaluation is based on two evaluation indexes of data non-empty and data normative, the integrity score of the data is measured, when multi-source data are fused, if some attribute values required by fusion are missing, the data are not provided with a fusion function, the usability of the data is directly reduced, and the j-th data of the i-th data source is preset as D ij Its paper-out combination on one important attribute is attrVal ij Then there is a mapping function,therefore, the expression of the data non-empty metric model is +.>Wherein Y (D) ij ) Mapping function for judging whether the jth data of the ith data source is non-empty, and the value range of DComp is [0,1 ]]When the DComp value is 0, the important attribute values of all data of the ith source are null, and when the DComp value is 1, the important attribute values of all data are not null;
data normalization is used for evaluating whether each attribute value description in data is normalized, the normalization degree has a great influence on the mutual identification degree of multi-source data, and the j-th data of the i-th data source is preset as D ij Its value set on the important attribute is attrVal ij Then the expression with mapping function isTherefore, the expression of the data normalization metric model is +.> Wherein Z (D) ij ) A mapping function for judging whether the jth data of the ith data source is standard or not, wherein the value range of DStd is [0,1 ]]If DStd is 0, the values of the important attributes of all the data from the ith source are all specifiedThe expression of the integrity assessment model is +.>Wherein Eval comp Subscript set representing determined integrity assessment index, k represents Eval comp Number of elements in the collection.
As a further preferable mode of the technical scheme, the timeliness evaluation is to reflect the timeliness of data updating, calculate the time difference between the data generation time and the current time, and set the current time as the reference time and r, and then the expression with the data timeliness model isWherein t is i The recording time of the ith data is represented, the range of the DTime is (0, 1), and the expression of the timeliness evaluation model containing the data timeliness evaluation index in the timeliness dimension is timel=dtime (x).
As a further preferable mode of the technical scheme, the consistency assessment model comprises semantic consistency and attribute consistency, and is used for judging whether the attribute value thresholds of the same fusion text contained among data describing the same entity are consistent, and presetting the data logarithm describing the same entity in n source data sets as SN, wherein the i-th fusion text attribute value set representing the data of the same entity as DCont i Then there is Wherein the function SemSim (DCont i ) For determining whether text data is semantically identical, with a value of 1, indicating that the text data in the set is identical, whereas with a value of 0, indicating that the text data is semantically inconsistent, the SConsis has a value range of [0,1 ]]If the SConsis close to 1, the semantic consistency degree of the data is high, otherwise, the SConsis close to 0, the semantic difference between the data is large, and the consistency degree is low;
attribute consistency assessment for individual data sources in multi-source dataThe expression of the consistency of the attribute relative to the fusion attribute is Consist 2 ＝AConsis(D i )＝AtrSim(DT(D i ) Of which DT (D) i ) Representing the ith data source attribute set, the function AtrSim (x) is to judge the consistency degree of the ith data source attribute relative to the fusion attribute, and the value range of AConsis [0,1 ]]If the AConsis value is 0, it indicates that the attribute of the data source has no consistent part with respect to the fusion attribute, if the AConsis value is 1, it indicates that the fusion attribute is consistent, and the consistency assessment model is expressed asWherein Eval consis Subscript set representing determined consistency evaluation index, k represents Eval consis Number of elements in the collection.
As a further preferable aspect of the above-described technical solution, the data balance between the data sources is a relationship of a ratio of the number of data sets of the plurality of data sources, the balance of the number of the multi-source data sets is evaluated, the attribute balance between the data includes the number of attributes and the same attribute number balance, the attribute balance between the data is evaluated, the plurality of data sources D 1 Data source D 2 .. data Source D n When initializing the model, the number of data sets of the data sources is required to be ordered, namely, the data sets are incrementally ordered, then the data sources are compared in pairs, and if the number of a certain data set is greatly different from the number of other data sets, the data balance is reduced correspondinglyWherein N is i And N j Respectively representing the data quantity of the ith data source and the jth data source, wherein QBA represents the quantity balance rate, the value range is (0, 1), and the result is close to 1, which represents that the data quantity among n data sources is more balanced;
calculating attribute balance among data of a plurality of data sources, firstly calculating the ratio of the number of fusion attributes among the data sources, sharing attribute influence among the data, introducing attribute balance factors, and calculating the expression of the same attribute column ratio among two data sources asWherein Dir (D) i ,D j ) Representing a data source D i And D j Ratio of the number of data attributes, alpha ij Representing a data source D i And D j The attribute balance factor between the middle data is expressed as +.>|attr(D i )∩attr(D j ) I represents the data source D i And D j In the same attribute number, max (attr (D i ),attr(D j ) Representing a data source D i And D j The maximum value of the number of attributes contained in the balance evaluation model is expressed as +.>Wherein Eval bal Subscript set representing determined balance evaluation index, k represents Eval bal Number of elements in the collection.
As a further preferred embodiment of the above-described solution, the correlation evaluation is configured to analyze temporal and spatial correlations from among the multi-source data, and average all data times in each data source to obtain an average time (t 1 ,t 2 ...t n )，t i Representing the average time of the ith data source, and sequentially comparing the average time of every two data sources, wherein the model of the time correlation is as follows Wherein Max (t) i ,t j ) The maximum value between the two values is represented as a reference value, and the value range of TRel is [0,1 ]]A TRel close to 1 indicates that the closer the time between multiple data sources is, the higher the time correlation is;
spatial correlation evaluates the correlation between data from a spatial perspective, grid-divides the geographic space of the intelligent park into a plurality of grid spaces,calculating the number of data of each data source falling in each grid, comparing the ratio of the number of data sources in each grid in sequence, weighting, summing and averaging the ratio in each grid to obtain a spatial correlation score, wherein the spatial correlation calculation model is as follows Wherein h represents the number of divided meshes, and the rate function has the expression +.>Wherein Quan i Indicating that the ith data source data falls on grid G m Dir (x) represents the ratio of the number of different data sources in the computational grid, and the range of values of the spatial correlation SRel is 0,1]If the spatial correlation value is 1, the data in the data source has high correlation on spatial distribution, otherwise, the correlation is low.
As a further preferred aspect of the above technical solution, performing adaptive weighted fusion on the aerial image and the environmental data, and determining weights of the sensors to obtain fused data, includes:
n' sensors are preset to measure the same object, and the mean square error of the multiple sensors is as follows The measured value of each sensor is X 1 、X 2 ...X n' The measured values are fused by adopting proper weighting factors, and the weighting factors of the sensors are respectively W 1 、W 2 ...W n' Then the fused X value and weighting factor W i Satisfy the relation->Total mean square error sigma 2 Expression of (2)Is-> The expression for finding the optimal weight coefficient corresponding to the minimum total mean square error from the extremum of the polytropic function is +.>The corresponding minimum value of the total mean square error is +.>Fusion variance sigma obtained by combining batch estimation + And fusion value T + The expression for calculating the weighting factor is +.> The multisensor data fusion value is +.>
In a second aspect, the invention provides a method for dynamically monitoring and analyzing multi-source data in an intelligent park in real time, which comprises the following steps:
acquiring an aerial image of an intelligent park and environmental data acquired by multiple sensors, wherein the aerial image is photographed by a rotor unmanned aerial vehicle, and the environmental data comprises temperature, humidity and CO 2 Concentration, formaldehyde concentration, TVOC concentration, and PM2.5 concentration;
performing self-adaptive weighted fusion on the aerial image and the environmental data and determining the weight of each sensor to obtain fusion data;
acquiring accuracy, completeness, timeliness, consistency, balance and correlation of the fusion data and constructing an evaluation model corresponding to the fusion data;
and carrying out multi-source fusion data reconstruction on the fusion data according to the evaluation model to complete multi-source data dynamic monitoring and real-time analysis.
The invention provides a system and a method for dynamically monitoring and analyzing multi-source data in an intelligent park, which are characterized in that the intelligent park aerial image and environmental data acquired by a plurality of sensors are acquired, the aerial image and the environmental data are subjected to self-adaptive weighted fusion, the weight of each sensor is determined to obtain fusion data, the accuracy, the integrity, the timeliness, the consistency, the balance and the correlation of the fusion data are acquired, an evaluation model corresponding to the fusion data is constructed, the multi-source fusion data reconstruction is carried out on the fusion data according to the evaluation model, the multi-source data dynamic monitoring and the real-time analysis are completed, the data quality in a multi-source data fusion scene is quantitatively analyzed, a manager can intuitively know the data quality condition, the integration, the intellectualization and the high efficiency of park management can be greatly improved, the labor cost and the time cost are greatly saved for a park manager, and the management efficiency of the intelligent park is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a system for dynamic monitoring and real-time analysis of multi-source data in an intelligent park according to the present invention;
FIG. 2 is a flow chart of the intelligent park multisource data dynamic monitoring and real-time analysis method of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
Referring to fig. 1, the present invention provides a system for dynamically monitoring and analyzing multi-source data in an intelligent park, comprising:
the data acquisition module is used for acquiring an intelligent park aerial image and environmental data acquired by multiple sensors, wherein the aerial image is photographed by adopting a rotor unmanned aerial vehicle, and the environmental data comprises temperature and humidity and CO 2 Concentration, formaldehyde concentration, TVOC concentration, and PM2.5 concentration;
the data fusion module is used for carrying out self-adaptive weighted fusion on the aerial image and the environmental data and determining the weight of each sensor so as to obtain fusion data;
the data quality evaluation module is used for acquiring the accuracy, the completeness, the timeliness, the consistency, the balance and the correlation of the fusion data and constructing an evaluation model corresponding to the fusion data;
and the data analysis module is used for carrying out multisource fusion data reconstruction on the fusion data according to the evaluation model so as to complete multisource data dynamic monitoring and real-time analysis.
In this embodiment, performing multi-source fusion data reconstruction on fusion data according to an evaluation model to complete multi-source data dynamic monitoring and real-time analysis includes: after the measurement values measured by the same type of detection quantity at different spatial positions are divided into a plurality of batches by adopting a batch estimation algorithm, carrying out batch fusion processing, and presetting a first group of data: t (T) 11 ,T 12 ...T 1m M is N; a second set of data: t (T) 21 ,T 22 ...T 2n Calculating arithmetic mean value and corresponding standard error of two groups of measurement data according to a formula, wherein the standard error measured in the previous time is preset to be sigma - The standard error currently measured is sigma + The previous fusion value was T - The current fusion value is T + According to the current first measurement, no measurement statistics data exist before, sigma + 、σ + The corresponding data is input into the batch estimation to calculate, and the expression of the current variance is calculated as sigma + ＝[(σ - ) -1 +HTR -1 H] -1 Wherein, the method comprises the steps of, wherein,as a coefficient matrix, H T Representing transpose of coefficient matrix +.>Representing covariance +_>Representing the variance of the first set of data, +.>Representing the variance of the second set of data, +.>The data fusion value is derived to obtain a fusion result as T + ＝[σ + +(σ - ) -1 ]T - +[σ + +H T R -1 ]T, will R, H, sigma - 、σ + 、T - And->Inputting the final fusion result into the fusion result to obtain the final fusion result expressed as +.> Wherein->Representing the arithmetic mean of the previous group, +.>Representing the arithmetic mean of the second group.
In addition, CO 2 By taking parameters as examples, CO is established 2 The index model is evaluated, the volume fraction of carbon dioxide in normal air is 300-400 ppm, the threshold value is 485ppm,when indoor CO 2 At a concentration of 1000ppm, significant discomfort is caused to the personnel in the room, so that the carbon dioxide evaluation index model isThus, it can be derived that The corresponding concentrations were: 485ppm, 580ppm, 700ppm and 1000ppm, and can establish multi-index evaluation standards.
It should be understood that, the original image is obtained by oblique photography, meanwhile, a POS file and a camera file are generated, the original image, POS data and the camera file are subjected to space three-encryption processing in a one-to-one correspondence manner, the process mainly comprises the steps of performing space three-measurement on the image, reading coordinate information and height information of the image, performing multi-view dense matching on the obtained space geographic coordinate information and the image data, and performing three-dimensional grid construction to obtain a white three-dimensional model. And acquiring data of the park by adopting a plurality of sensors, fusing the data acquired by the sensors by adopting a plurality of data algorithms, and performing fuzzy comprehensive evaluation on the final fused data, so that the environmental condition grade of the current park is obtained, and the related manager can make environmental protection decisions. Because the data obtained by the environment monitoring sensor is not completely correct, the data are often random and abnormal values are likely to appear, the abnormal values can seriously influence the accuracy of the following data statistics, and a large error is generated to cause the serious deviation of a final result from an expected state, so that the data quality is effectively evaluated, and the detection error and the data fusion quality can be reduced.
Optionally, obtaining accuracy, completeness, timeliness, consistency, balance and correlation of the fusion data and constructing an evaluation model corresponding to the fusion data includes:
the accuracy dimension of the accuracy evaluation model contains two evaluation indexes of data accuracy and source authority, and specific evaluation indexes are processedModeling to obtain an accuracy assessment model, determining whether the accuracy of the data reflects the data truly and accurately describing an application scene, and presetting the j-th data of the i-th data as D ij The ith data source shares N i Data, an important attribute set attr (D i )＝{A 1 ,A 2 ...A l The reference value standard in this scenario is m= { M 1 ,M 2 ...M l Then there is a mapping function of Wherein->Representing an accuracy judgment function, if D ij In attribute A k The value of the value meets the reference value standard M k Then->1 and vice versa, so data D ij In the attribute set attr (D i ) When the values are correct, the data are true and effective, and mu (x) value is 1;
the data accuracy measurement model is:wherein the DAcc's range of values represents 0,1]When the DAcc takes a value of 0, the data representing the ith data source are inaccurate; when the DAcc takes the value of 1, the data representing the data source are very accurate;
the selection of the evaluation index has flexibility, and the accuracy evaluation model is thatWherein Eval acc Subscript set of accuracy evaluation index representing the accuracy of the selection, k being Eval acc Number of elements in the collection.
In the present embodiment, obtainTaking the integrity of the fusion data to construct an evaluation model corresponding to the fusion data, wherein the evaluation model comprises the following steps: the integrity evaluation is based on two evaluation indexes of data non-empty and data normative, the integrity score of the data is measured, when multi-source data are fused, if some attribute values required by fusion are missing, the data are not provided with a fusion function, the usability of the data is directly reduced, and the j-th data of the i-th data source is preset as D ij Its paper-out combination on one important attribute is attrVal ij Then there is a mapping function,the expression of the data non-empty metric model isWherein Y (D) ij ) Mapping function for judging whether the jth data of the ith data source is non-empty, and the value range of DComp is [0,1 ]]When the DComp value is 0, the important attribute values of all data of the ith source are null, and when the DComp value is 1, the important attribute values of all data are not null.
It should be noted that, the data normalization is used to evaluate whether each attribute value description in the data is normalized, its normalization degree has a great influence on the mutual identification degree of the multi-source data, and the j-th data of the i-th data source is preset as D ij Its value set on the important attribute is attrVal ij Then the expression with mapping function isTherefore, the expression of the data normalization metric model is +.>Wherein Z (D) ij ) A mapping function for judging whether the jth data of the ith data source is standard or not, wherein the value range of DStd is [0,1 ]]If DStd is 0, the values of the important attributes of all the data from the ith source are normalized, and the integrity assessment model is expressed as followsWherein Eval comp Subscript set representing determined integrity assessment index, k represents Eval comp Number of elements in the collection. Accuracy refers to the degree of true reliability of data relative to the field, completeness refers to the degree of complete specification of information, timeliness refers to the degree of time between creation of data and the current time interval, consistency refers to the degree of consistency of attributes or data contents among data, balance refers to the degree of balance of data quantity and attribute quantity among multi-source data, and relativity refers to the degree of strength of relativity of certain attributes or characteristics among multi-source data.
Optionally, the timeliness evaluation is to reflect the timeliness of the data update, calculate the time difference between the data generation time and the current time, set the current time as the reference time and r, and then have the expression of the data timeliness model asWherein t is i The recording time of the ith data is represented, the range of the DTime is (0, 1), and the expression of the timeliness evaluation model containing the data timeliness evaluation index in the timeliness dimension is timel=dtime (x).
In this embodiment, the consistency evaluation model includes semantic consistency and attribute consistency, which is to determine whether the thresholds of the attribute values of the same fusion text included in the data describing the same entity are consistent, and preset the logarithm of the data describing the same entity in n source data sets to be SN, where the i-th set of attribute values of the fusion text representing the data of the same entity is DCont i Then there is Wherein the function semSim (DCont i ) For determining whether the text data are semantically identical, with a value of 1 indicating that the text data in the collection are identical, whereas with a value of 0 indicating that the text data are semantically inconsistent, a range of SConsis valuesIs [0,1]If the SConsis close to 1, the semantic consistency degree of the data is high, otherwise, the SConsis close to 0, the semantic difference between the data is large, and the consistency degree is low; attribute consistency evaluation the expression of the consistency degree of the attributes of each data source in the multi-source data relative to the fusion attribute is Consist 2 ＝AConsis(D i )＝AtrSim(DT(D i ) Of which DT (D) i ) Representing the ith data source attribute set, the function AtrSim (x) is to judge the consistency degree of the ith data source attribute relative to the fusion attribute, and the value range of AConsis [0,1 ]]If AConsis 0, it indicates that the attribute of the data source has no consistent part with respect to the fusion attribute, if AConsis 1, it indicates that the fusion attribute is consistent, and the consistency evaluation model is indicated as +.> Wherein Eval consis Subscript set representing determined consistency evaluation index, k represents Eval consis Number of elements in the collection.
The data balance between data sources is a relationship of the ratio of the number of data sets of a plurality of data sources, the balance of the number of the multi-source data sets is evaluated, the attribute balance between the data includes the balance of the number of attributes and the same attribute number, the attribute balance between the data is evaluated, and the data sources D 1 Data source D 2 .. data Source D n When initializing the model, the number of data sets of the data sources is required to be ordered, namely, the data sets are incrementally ordered, then the data sources are compared in pairs, and if the number of a certain data set is greatly different from the number of other data sets, the data balance is reduced correspondinglyWherein N is i And N j The data amount of the ith and jth data source is represented respectively, QBA represents the number balance rate, the value range is (0, 1), and the result is close to 1 to represent n data sourcesThe more balanced the data volume between; calculating attribute balance among data of a plurality of data sources, firstly calculating the ratio of the number of fusion attributes among the data sources, introducing attribute balance factors, and calculating the expression of the same attribute column ratio between every two data sources as +.> Wherein Dir (D) i ,D j ) Representing a data source D i And D j Ratio of the number of data attributes, alpha ij Representing a data source D i And D j The attribute balance factor between the middle data is expressed as +.>|attr(D i )∩attr(D j ) I represents the data source D i And D j In the same attribute number, max (attr (D i ),attr(D j ) Representing a data source D i And D j The maximum value of the number of attributes contained in the balance evaluation model is expressed as +.>Wherein Eval bal Subscript set representing determined balance evaluation index, k represents Eval bal Number of elements in the collection.
Alternatively, correlation evaluation is used to analyze temporal and spatial correlations from among the multi-source data, averaging all data times in each data source to obtain an average time (t 1 ,t 2 ...t n )，t i Representing the average time of the ith data source, and sequentially comparing the average time of every two data sources, wherein the model of the time correlation is as followsWherein Max (t) i ,t j ) The maximum value between the two values is represented as a reference value, and the value range of TRel is represented as[0,1]A TRel close to 1 indicates that the closer the time between multiple data sources is, the higher the time correlation is;
the correlation between data is evaluated by the space correlation from the space angle, the geographic space of the intelligent park is subjected to grid division to obtain a plurality of grid spaces, the number of data of each data source falling in each grid is calculated, the ratio of the number of data sources is compared between every two data sources in the grid in sequence, the ratio in each grid is weighted and summed to average to obtain a space correlation score, and the space correlation calculation model is that Wherein h represents the number of divided meshes, and the rate function has the expression +.>Wherein Quan i Indicating that the ith data source data falls on grid G m Dir (x) represents the ratio of the number of different data sources in the computational grid, and the range of values of the spatial correlation SRel is 0,1]If the spatial correlation value is 1, the data in the data source has high correlation on spatial distribution, otherwise, the correlation is low.
In this embodiment, performing adaptive weighted fusion on the aerial image and the environmental data and determining weights of the sensors to obtain fused data includes: n' sensors are preset to measure the same object, and the mean square error of the multiple sensors is as followsThe measured value of each sensor is X 1 、X 2 ...X n' The measured values are fused by adopting proper weighting factors, and the weighting factors of the sensors are respectively W 1 、W 2 ...W n' Then the fused X value and weighting factor W i Satisfy the relationTotal mean square error sigma 2 The expression of (2) is +.>The expression for finding the optimal weight coefficient corresponding to the minimum total mean square error from the extremum of the polytropic function is +.>The corresponding minimum value of the total mean square error is +.>Fusion variance sigma obtained by combining batch estimation + And fusion value T + The expression for calculating the weighting factor is +.>The multisensor data fusion value is +.>
It should be noted that, the intelligent park collects park data by adopting multiple sensors, analyzes and preprocesses the data, combines batch estimation and a multi-sensor fusion algorithm to achieve the purpose of optimizing and fusing the data, and comprehensively evaluates the park environment, thereby obtaining an evaluation result which is more in line with users.
Referring to fig. 2, the invention provides a method for dynamically monitoring and analyzing multi-source data in an intelligent park in real time, which comprises the following steps:
s1: acquiring an aerial image of an intelligent park and environmental data acquired by multiple sensors, wherein the aerial image is photographed by a rotor unmanned aerial vehicle, and the environmental data comprises temperature, humidity and CO 2 Concentration, formaldehyde concentration, TVOC concentration, and PM2.5 concentration;
s2: performing self-adaptive weighted fusion on the aerial image and the environmental data and determining the weight of each sensor to obtain fusion data;
s3: acquiring accuracy, completeness, timeliness, consistency, balance and correlation of the fusion data and constructing an evaluation model corresponding to the fusion data;
s4: and carrying out multi-source fusion data reconstruction on the fusion data according to the evaluation model to complete multi-source data dynamic monitoring and real-time analysis.
In this embodiment, by acquiring the aerial image of the smart park and the environmental data acquired by the multiple sensors, performing adaptive weighted fusion on the aerial image and the environmental data, determining the weight of each sensor to obtain the fused data, acquiring the accuracy, the integrity, the timeliness, the consistency, the balance and the correlation of the fused data, constructing an evaluation model corresponding to the fused data, performing multi-source fused data reconstruction on the fused data according to the evaluation model to complete multi-source data dynamic monitoring and real-time analysis, quantitatively analyzing the data quality in a multi-source data fusion scene, and enabling a manager to intuitively know the data quality condition, and simultaneously greatly improving the integrity, the intellectualization and the high efficiency of park management, so that the labor cost and the time cost are greatly saved for the park manager, and the management efficiency of the smart park is improved.
Any particular values in all examples shown and described herein are to be construed as merely illustrative and not a limitation, and thus other examples of exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The above examples merely represent a few embodiments of the present invention, which are described in more detail and are not to be construed as limiting the scope of the present invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (10)
1. An intelligent campus multisource data dynamic monitoring and real-time analysis system, which is characterized by comprising:
data acquisitionThe module is used for acquiring an intelligent park aerial image and environmental data acquired by multiple sensors, wherein the aerial image is photographed by adopting a rotor unmanned aerial vehicle, and the environmental data comprises temperature and humidity and CO 2 Concentration, formaldehyde concentration, TVOC concentration, and PM2.5 concentration;
the data fusion module is used for carrying out self-adaptive weighted fusion on the aerial image and the environmental data and determining the weight of each sensor so as to obtain fusion data;
the data quality evaluation module is used for acquiring the accuracy, the completeness, the timeliness, the consistency, the balance and the correlation of the fusion data and constructing an evaluation model corresponding to the fusion data;
and the data analysis module is used for carrying out multisource fusion data reconstruction on the fusion data according to the evaluation model so as to complete multisource data dynamic monitoring and real-time analysis.
2. The intelligent campus multisource data dynamic monitoring and real-time analysis system according to claim 1, wherein multisource fusion data reconstruction of fusion data according to the evaluation model has completed multisource data dynamic monitoring and real-time analysis, comprising:
after the measurement values measured by the same type of detection quantity at different spatial positions are divided into a plurality of batches by adopting a batch estimation algorithm, carrying out batch fusion processing, and presetting a first group of data: t (T) 11 ,T 12 ...T 1m M is N; a second set of data: t (T) 21 ,T 22 ...T 2n Calculating arithmetic mean value and corresponding standard error of two groups of measurement data according to a formula, wherein the standard error measured in the previous time is preset to be sigma - The standard error currently measured is sigma + The previous fusion value was T - The current fusion value is T + According to the current first measurement, no measurement statistics data exist before, sigma + 、σ + The corresponding data is input into the batch estimation to calculate, and the expression of the current variance is calculated as sigma + ＝[(σ - ) -1 +H T R -1 H] -1 Wherein, the method comprises the steps of, wherein,as a coefficient matrix, H T Representing transpose of coefficient matrix +.>Representing covariance +_>Representing the variance of the first set of data, +.>Representing the variance of the second set of data, +.>The data fusion value is derived to obtain a fusion result as T + ＝[σ + +(σ - ) -1 ]T - +[σ + +H T R -1 ]T, will R, H, sigma - 、σ + 、T - And->Input into the fusion result to obtain the final fusion result expressed asWherein->Representing the arithmetic mean of the previous group, +.>Representing the arithmetic mean of the second group.
3. The intelligent campus multisource data dynamic monitoring and real-time analysis system according to claim 1, wherein obtaining accuracy, integrity, timeliness, consistency, balance and correlation of the fused data and constructing an evaluation model corresponding to the fused data comprises:
the accuracy dimension of the accuracy assessment model contains two assessment indexes of data accuracy and source authority, the specific assessment indexes are modeled to obtain the accuracy assessment model, the accuracy of the data reflects whether the data truly and accurately describe an application scene, and the j data of the i data is preset as D ij The ith data source shares N i Data, an important attribute set attr (D i )＝{A 1 ,A 2 ...A l The reference value standard in this scenario is m= { M 1 ,M 2 ...M l Then there is a mapping function of Wherein->Representing an accuracy judgment function, if D ij In attribute A k The value of the value meets the reference value standard M k Then->1 and vice versa, so data D ij In the attribute set attr (D i ) When the values are correct, the data are true and effective, and mu (x) value is 1;
the data accuracy measurement model is:wherein the DAcc's range of values represents 0,1]When the DAcc takes a value of 0, the data representing the ith data source are inaccurate; when the DAcc takes the value of 1, the data representing the data source are very accurate;
the selection of the evaluation index has flexibility, and the accuracy evaluation model is thatWherein Eval acc Subscript set of accuracy evaluation index representing the accuracy of the selection, k being Eval acc Number of elements in the collection.
4. The intelligent campus multisource data dynamic monitoring and real-time analysis system according to claim 3, wherein obtaining the integrity of the fusion data builds an evaluation model corresponding to the fusion data, comprising:
the integrity evaluation is based on two evaluation indexes of data non-empty and data normative, the integrity score of the data is measured, when multi-source data are fused, if some attribute values required by fusion are missing, the data are not provided with a fusion function, the usability of the data is directly reduced, and the j-th data of the i-th data source is preset as D ij Its paper-out combination on one important attribute is attrVal ij Then there is a mapping function,therefore, the expression of the data non-empty metric model is +.>Wherein Y (D) ij ) Mapping function for judging whether the jth data of the ith data source is non-empty, and the value range of DComp is [0,1 ]]When the DComp value is 0, the important attribute values of all data of the ith source are null, and when the DComp value is 1, the important attribute values of all data are not null;
data normalization is used for evaluating whether each attribute value description in data is normalized, the normalization degree has a great influence on the mutual identification degree of multi-source data, and the j-th data of the i-th data source is preset as D ij Its value set on the important attribute is attrVal ij Then the expression with mapping function isTherefore, the expression of the data normalization metric model is +.> Wherein Z (D) ij ) A mapping function for judging whether the jth data of the ith data source is standard or not, wherein the value range of DStd is [0,1 ]]If DStd is 0, the values of the important attributes of all the data from the ith source are normalized, and the integrity assessment model has the expression +.>Wherein Eval comp Subscript set representing determined integrity assessment index, k represents Eval comp Number of elements in the collection.
5. The system for dynamic monitoring and real-time analysis of multi-source data in intelligent park according to claim 3, wherein the timeliness assessment is to reflect the timeliness of the update of the data, calculate the time difference between the data generation time and the current time, and take the current time as the reference time and set as r, the expression of the timeliness model of the data isWherein t is i The recording time of the ith data is represented, the range of the DTime is (0, 1), and the expression of the timeliness evaluation model containing the data timeliness evaluation index in the timeliness dimension is timel=dtime (x).
6. The system of claim 3, wherein the consistency assessment model includes semantic consistency and attribute consistency, and is configured to determine whether a threshold value of a same fusion text attribute value included between data describing a same entity is consistent, and preset n source data sets to describe a same entityThe data logarithm of the volume is SN, wherein the i-th fusion text attribute value set representing the same entity data is DCont i Then there is Wherein the function SemSim (DCont i ) For determining whether text data is semantically identical, with a value of 1, indicating that the text data in the set is identical, whereas with a value of 0, indicating that the text data is semantically inconsistent, the SConsis has a value range of [0,1 ]]If the SConsis close to 1, the semantic consistency degree of the data is high, otherwise, the SConsis close to 0, the semantic difference between the data is large, and the consistency degree is low;
attribute consistency evaluation the expression of the consistency degree of the attributes of each data source in the multi-source data relative to the fusion attribute is Consist 2 ＝AConsis(D i )＝AtrSim(DT(D i ) Wherein DT (Di) represents the ith data source attribute set, and the function AtrSim (x) is to judge the consistency degree of the ith data source attribute relative to the fusion attribute, and the value range of AConsis [0,1 ]]If the AConsis value is 0, it indicates that the attribute of the data source has no consistent part with respect to the fusion attribute, if the AConsis value is 1, it indicates that the fusion attribute is consistent, and the consistency assessment model is expressed asWherein Eval consis Subscript set representing determined consistency evaluation index, k represents Eval consis Number of elements in the collection.
7. The intelligent campus multi-source data dynamic monitoring and real-time analysis system according to claim 3, wherein the data balance between data sources is a relationship of the ratio of the number of data sets of a plurality of data sources, the balance of the number of multi-source data sets is evaluated, the attribute balance between data includes the balance of the number of attributes and the same number of attributes, the evaluation numberAttribute balance among data sources D 1 Data source D 2 .. data Source D n When initializing the model, the number of data sets of the data sources is required to be ordered, namely, the data sets are incrementally ordered, then the data sources are compared in pairs, and if the number of a certain data set is greatly different from the number of other data sets, the data balance is reduced correspondingly Wherein N is i And N j Respectively representing the data quantity of the ith data source and the jth data source, wherein QBA represents the quantity balance rate, the value range is (0, 1), and the result is close to 1, which represents that the data quantity among n data sources is more balanced;
calculating attribute balance among data of a plurality of data sources, firstly calculating the ratio of the number of fusion attributes among the data sources, sharing attribute influence among the data, introducing attribute balance factors, and calculating the expression of the same attribute column ratio among two data sources asWherein Dir (D) i ,D j ) Representing a data source D i And D j Ratio of the number of data attributes, alpha ij Representing a data source D i And D j The expression of the attribute balance factor among the middle data is|attr(D i )∩attr(D j ) I represents the data source D i And D j In the same attribute number, max (attr (D i ),attr(D j ) Representing a data source D i And D j The maximum value of the number of attributes contained in the balance evaluation model is expressed as +.>Wherein Eval bal Subscript set representing determined balance evaluation index, k represents Eval bal Number of elements in the collection.
8. A system for dynamic monitoring and real-time analysis of multisource data in a smart park according to claim 3, wherein the correlation assessment is used to analyze the temporal and spatial correlation between multisource data, and to average all data time in each data source to obtain an average time (t 1 ,t 2 ...t n )，t i Representing the average time of the ith data source, and sequentially comparing the average time of every two data sources, wherein the model of the time correlation is as followsWherein Max (t) i ,t j ) The maximum value between the two values is represented as a reference value, and the value range of TRel is [0,1 ]]A TRel close to 1 indicates that the closer the time between multiple data sources is, the higher the time correlation is;
the correlation between data is evaluated by the space correlation from the space angle, the geographic space of the intelligent park is subjected to grid division to obtain a plurality of grid spaces, the number of data of each data source falling in each grid is calculated, the ratio of the number of data sources is compared between every two data sources in the grid in sequence, the ratio in each grid is weighted and summed to average to obtain a space correlation score, and the space correlation calculation model is that Wherein h represents the number of divided meshes, and the rate function has the expression +.>Wherein Quan i Indicating that the ith data source data falls on grid G m Dir (x) represents the number of non-computing gridsThe value range of the space correlation SRel is [0,1 ] according to the number ratio of the same data sources]If the spatial correlation value is 1, the data in the data source has high correlation on spatial distribution, otherwise, the correlation is low.
9. The intelligent campus multisource data dynamic monitoring and real-time analysis system of claim 1, wherein adaptively weighted fusing the aerial image and the environmental data and determining the weights of the sensors to obtain fused data comprises:
n' sensors are preset to measure the same object, and the mean square error of the multiple sensors is as followsi=1, 2..n', the measurement values of each sensor are X, respectively 1 、X 2 ...X n' The measured values are fused by adopting proper weighting factors, and the weighting factors of the sensors are respectively W 1 、W 2 ...W n' Then the fused X value and weighting factor W i Satisfy the relation->Total mean square error sigma 2 The expression of (2) is +.> The expression for finding the optimal weight coefficient corresponding to the minimum total mean square error from the extremum of the polytropic function is +.>The corresponding minimum value of the total mean square error is +.>Fusion variance sigma obtained by combining batch estimation + And fusion valueT + The expression for calculating the weighting factor is +.> The multisensor data fusion value is +.>
10. A method for dynamic monitoring and real-time analysis of multi-source data of a smart park according to any one of claims 1-9, comprising the steps of:
acquiring an aerial image of an intelligent park and environmental data acquired by multiple sensors, wherein the aerial image is photographed by a rotor unmanned aerial vehicle, and the environmental data comprises temperature, humidity and CO 2 Concentration, formaldehyde concentration, TVOC concentration, and PM2.5 concentration;
performing self-adaptive weighted fusion on the aerial image and the environmental data and determining the weight of each sensor to obtain fusion data;
acquiring accuracy, completeness, timeliness, consistency, balance and correlation of the fusion data and constructing an evaluation model corresponding to the fusion data;
and carrying out multi-source fusion data reconstruction on the fusion data according to the evaluation model to complete multi-source data dynamic monitoring and real-time analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310636835.5A CN116665001A (en) | 2023-06-01 | 2023-06-01 | Intelligent park multisource data dynamic monitoring and real-time analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310636835.5A CN116665001A (en) | 2023-06-01 | 2023-06-01 | Intelligent park multisource data dynamic monitoring and real-time analysis system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116665001A true CN116665001A (en) | 2023-08-29 |
Family
ID=87713234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310636835.5A Pending CN116665001A (en) | 2023-06-01 | 2023-06-01 | Intelligent park multisource data dynamic monitoring and real-time analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665001A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116881850A (en) * | 2023-09-04 | 2023-10-13 | 山东航天九通车联网有限公司 | Safety early warning system based on multi-mode data fusion |
| CN117390590A (en) * | 2023-12-07 | 2024-01-12 | 江苏天创科技有限公司 | CIM model-based data management method and system |
| CN118072255A (en) * | 2024-04-24 | 2024-05-24 | 杭州澎湃数智科技有限公司 | Intelligent park multisource data dynamic monitoring and real-time analysis system and method |
-
2023
- 2023-06-01 CN CN202310636835.5A patent/CN116665001A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116881850A (en) * | 2023-09-04 | 2023-10-13 | 山东航天九通车联网有限公司 | Safety early warning system based on multi-mode data fusion |
| CN116881850B (en) * | 2023-09-04 | 2023-12-08 | 山东航天九通车联网有限公司 | Safety early warning system based on multi-mode data fusion |
| CN117390590A (en) * | 2023-12-07 | 2024-01-12 | 江苏天创科技有限公司 | CIM model-based data management method and system |
| CN117390590B (en) * | 2023-12-07 | 2024-02-20 | 江苏天创科技有限公司 | CIM model-based data management method and system |
| CN118072255A (en) * | 2024-04-24 | 2024-05-24 | 杭州澎湃数智科技有限公司 | Intelligent park multisource data dynamic monitoring and real-time analysis system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116665001A (en) | Intelligent park multisource data dynamic monitoring and real-time analysis system and method | |
| Lvovich et al. | Managing developing internet of things systems based on classification and predictive models and algorithms | |
| CN116431975A (en) | Environment monitoring method and system for data center | |
| CN111935820B (en) | Positioning implementation method based on wireless network and related equipment | |
| CN110188882A (en) | A kind of high conflicting evidence fusion method based on fuzzy reasoning | |
| CN106952289A (en) | The WiFi object localization methods analyzed with reference to deep video | |
| CN102970692A (en) | Method for detecting boundary nodes of wireless sensor network event | |
| CN115775085B (en) | Digital twinning-based smart city management method and system | |
| CN111382278B (en) | Social network construction method and system based on space-time track | |
| CN113936413A (en) | Early fire monitoring and early warning method and device | |
| CN118365005B (en) | Pollution and carbon reduction coupling index analysis method and system based on big data | |
| CN112433139B (en) | Method and device for prolonging cycle life of super capacitor | |
| CN115342814A (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| CN109902681A (en) | User group's relationship determines method, apparatus, equipment and storage medium | |
| CN107645493B (en) | IP group similarity calculation method | |
| CN112883527A (en) | Simulation evaluation method for network system | |
| CN113065223A (en) | Multi-level probability correction method for digital twin model of tower mast cluster | |
| Cui et al. | Indoor Wi-Fi positioning algorithm based on location fingerprint | |
| CN107507255A (en) | Picture compression quality factor acquisition methods, system, equipment and storage medium | |
| CN113516229A (en) | Credible user optimization selection method facing crowd sensing system | |
| CN108519579B (en) | WiFi fingerprint positioning method for analyzing optimal AP based on interval overlapping degree | |
| CN115619605A (en) | Traditional residential environment quality evaluation method based on semantic information | |
| CN113890833B (en) | Network coverage prediction method, device, equipment and storage medium | |
| CN115859765A (en) | Method, device, equipment and storage medium for predicting city expansion | |
| CN108260155B (en) | Wireless sensor network anomaly detection method based on space-time similarity |
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 |