CN107995278A - A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data - Google Patents

A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data Download PDF

Info

Publication number
CN107995278A
CN107995278A CN201711214859.2A CN201711214859A CN107995278A CN 107995278 A CN107995278 A CN 107995278A CN 201711214859 A CN201711214859 A CN 201711214859A CN 107995278 A CN107995278 A CN 107995278A
Authority
CN
China
Prior art keywords
mrow
information
metropolitan area
msub
data
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
Application number
CN201711214859.2A
Other languages
Chinese (zh)
Other versions
CN107995278B (en
Inventor
鲍敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Terminus Beijing Technology Co Ltd
Original Assignee
Terminus Beijing Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Terminus Beijing Technology Co Ltd filed Critical Terminus Beijing Technology Co Ltd
Priority to CN201711214859.2A priority Critical patent/CN107995278B/en
Publication of CN107995278A publication Critical patent/CN107995278A/en
Priority to PCT/CN2018/087233 priority patent/WO2019104952A1/en
Application granted granted Critical
Publication of CN107995278B publication Critical patent/CN107995278B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Computer And Data Communications (AREA)

Abstract

The invention belongs to Internet of Things analysis technical field, more particularly, to a kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data.A kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data, including metropolitan area level thing network sensing layer, metropolitan area level Internet of Things network layer, metropolitan area level Internet of Things data layer and metropolitan area level internet of things application layer.A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data of the present invention, in metropolitan area level spatial dimension, utilize polytype Internet of Things gathered data, data are carried out with multiple dimensioned be abstracted, such as the scale in more macroscopical whole city, some local scale of more microcosmic city；The pattern recognition analysis of scene is performed using various factors, the factors such as air particle situation, discharge of pollutant sources situation, wind direction and wind speed, city traffic situation can be integrated, carries out the analysis of many reference amounts model, the means of artificial intelligence can be used to carry out decision-making.

Description

A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data
Technical field
The invention belongs to Internet of Things analysis technical field, more particularly, to a kind of based on metropolitan area level Internet of Things perception data Scene intelligent analysis system and method.
Background technology
Internet of Things (The Internet of Things, abbreviation IOT) is after computer, internet and communication network The tide of the information industry development again, it is considered to be third time information revolution.Internet of Things is with complete perception, reliable biography Defeated, Intelligent treatment feature, is the network that can connect physical world.It, which has, perceives, transmits, information processing three-tier architecture, is Internet and the expansion application of communication network and Network stretch, it can change the Working Life mode of people, lifting to the world It is precisely controlled, so as to fulfill the function such as science decision and most optimum distribution of resources.The Chinese government is in 2009 " development Internet of Things Net industry " writes into " government work report ", is classified as one of strategic industry emerging greatly of China five, has greatly promoted Internet of Things Net industry development.As the generation and development of a kind of new technology, the influence that Internet of Things includes entire society transportation industry is huge It is and far-reaching.The feature of information gathering, transmission, processing and the service under Internet of Things is furtherd investigate, to based on the area under Internet of Things Domain information network carries out system research, is the current demand of industrial application of information technology development, is beneficial to lifting System Effectiveness, promotes production Adjustment of agricultural stracture and industrial upgrading.Internet of Things is not the product of single technical logic, we can be understood to people and thing Depth dialogue mechanism and two-way information translating mechanism, it is difficult to efficiently solve the virtual intersexuality that information is propagated between subject of nature Topic.Thingsization process has become the more direct historical practice theme of the mankind and more conscious social development choosing in the present age Select, the inherent mechanism of Internet of Things is annotated by the visual angle of information theory, the evolution of Internet of Things is understood by the change of medium sight Rule, dissects the epistemic logic of Internet of Things, by nature and human society in the Internet of Things ken by superorganic thinking The foundation of real contacts relation on deeper theoretical basic point, be that the humanistic nature of science and the social of technology must faces The important proposition faced, has good social history value and realistic meaning.Advantage of the Internet of Things in information propagation releases Its media value, the penetration that Internet of Things transmits the cohesion and information of information resources have established the richness of its propagating influence Basis, has naturally also expedited the emergence of the deep reform of communication form.We are based on " one machine of people, one thing " three human subjects under environment of internet of things Corresponding user's space domain, information space domain, the ternary system framework in physical space domain, and through control stream therebetween, Data flow, perceives the dynamic interaction pattern of stream, for the information communication process in ternary dynamic space domain, it is proposed that in the Internet of Things world Contacts morphology issues, emphasis solve how to possess physical environment Entity heterogeneity, information space dynamic interaction, Yong Huxu at the same time Ask in environment of internet of things complicated and changeable and realize that wisdom Internet of Things is propagated by the interaction between multiagent relation.
Look back to the evolution circuit of Internet technology revolution：" the content propagation information search " in epoch, when being the general propagation of network Generation；" individual creates group collaboration " in epoch, is a networked society forming age；" all things on earth perceives wisdom control " in epoch, is people Class society and the information exchange epoch of the comprehensive interconnection of the material world.The present extensive interconnection for completing computer and data Shared mission, the scale of future network realize more intelligent and ubiquitousization interconnection by considerably beyond present internet, The interconnection of mobile phone and mobile phone in mobile Internet first, the interconnection of person to person in social networks, Internet of Things netter and thing, thing with The interconnection of thing, is finally completed real world and is merged with the complete of information world.This will be a super-large dimension, it is unlimited poly- melt, layer The complex network system of abundant, the harmonious operation of level, realizes that any information agent accesses any letter at any time and any place World's form in breath source, it for we depict various information main body between be overlapped mutually, height merges, the ideal freely changed Change interaction view, our earth is really become one and integrate unified three-dimensional information system.
But there is presently no one can be fully solved Internet of Things carried out in metropolitan area data acquisition, it is abstract, point Analyse and then realize overall sexual system or the method for decision-making to solve the problems, such as that existing whole efficiency is not strong.
The content of the invention
It is an object of the invention to provide it is a kind of towards metropolitan area Internet of Things carry out efficient data analysis based on metropolitan area level thing The scene intelligent analysis system of networking perception data.It is a kind of based on the perception of metropolitan area level Internet of Things the present invention also aims to provide The scene intelligent analysis method of data.
A kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data, including metropolitan area level Internet of Things perceive Layer, metropolitan area level Internet of Things network layer, metropolitan area level Internet of Things data layer and metropolitan area level internet of things application layer；
The metropolitan area level thing network sensing layer includes electromagnetism by interactive space module composition, the interactive space module Inductive pick-up, spectrum sensor, audio and food sensor, satellite remote sensing system, GNSS sensors, infrared sensor, suddenly That sensor；Interactive space module is that the information network of whole Internet of Things gathers according to control set in advance and administrative standard All physical events and total data occurred in environment；
The metropolitan area level Internet of Things network layer is made of exchange channels and interaction protocol, exchange channels include PAN networks, Lan network, wlan network, WAN network, GPRS network, GPS network network, 3G network, 4G networks；The interaction protocol is applicable In all kinds of agreements of exchange channels；Metropolitan area level thing network sensing layer is uploaded all physics to come by exchange channels and interaction protocol Event and total data pass to metropolitan area level Internet of Things data layer and are stored, and metropolitan area level Internet of Things data layer is received The decision information of metropolitan area level internet of things application layer is sent to interactive space module；
The metropolitan area level Internet of Things data layer is the large server being combined based on memory and hard disk；Including Mongo DB databases, Hbase databases, Redis databases, NoSQL databases, Redis databases, Cassandra databases；Metropolitan area Level Internet of Things data layer stores metropolitan area level Internet of Things network layer by distributed storage architecture and metropolitan area level internet of things application layer passes The isomerization passed, structural data；
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into Row analysis, according to result provide user needed for service, in Internet of Things object carry out it is intelligentized identification, positioning, tracking, The data terminal of monitoring, decision-making and management.
All physical events and the particular content of total data occurred in the collection environment include：
(1) form information of collection event is defined as syntactic information, and the semantic information of collection event is defined as semantic information, The utility information of event is known as pragmatic information, and difference uses symbol Δ l successivelyg、Δls、ΔlpRepresent, full information set：Δ l=Q (Δlg+Δls+Δlp), Q represents operator, is uncertain computing when event is unstable, is definite fortune when event is stablized Calculate；
(2) the prior information l of main body is introducedr(X；A), posterior information lo(X；A it is), real to obtain information Δ ln(X；A) and it is expected to believe Cease le(X；A)；Main body A on the prior information of event X refer to that main body had before the actual observation event on The information of the event；Main body A on the posterior information of event X refer to that main body obtained after the actual observation event on The information of the event；Main body A is on the real that information refers to main body due to the event observed the event and actually obtained of event X Net information；Main body A refers to that main body under various regimes it is expected event the information obtained on the expectation information of event X；
Prior information, posterior information, reality obtain information and the operation relation of full information is expressed as：
Δ l=Q (Δ ln(X；A))=Q (lo(X；A)-lr(X；A))；
Syntactic information, semantic information, pragmatic information are expressed as：
(3) by elapsed time sequence tiPrior information, posterior information, the reality obtained afterwards obtains information and is；
Δlg=Δ lg(X,ti；A)=log(X,ti；A)-lrg(X,ti；A)
Δls=Δ ls(X,ti；A)=los(X,ti；A)-lrs(X,ti；A)
Δlp=Δ lp(X,ti；A)=lop(X,ti；A)-lsp(X,ti；A),
I=1,2,3 ... m；M represents time sequence number；
Above-mentioned elapsed time sequence tiThe prior information that obtains afterwards, posterior information, real information are used for describing event external The sensation of the dominance condition of structure and the stimulus signal sent to event, consciousness and presentation, including the color of event, shape, Size, sound, speed, temperature, the status information of frequency.
The exchange channels and interaction protocol metropolitan area level thing network sensing layer is uploaded all physical events for coming and The particular content that total data passes to metropolitan area level Internet of Things data layer includes：
(1) data processing：
If GnFor information figureofmerit ordered series of numbers in respect of time in a certain region,N represents region sequence Number,
(2) GM (h, l) model in gray model for prediction is established：
A and u is the model parameter determined by initial data,
(3) reduction treatment：
The inverse operation of generation data is carried out, prediction data is the corresponding index of each event；
For Gn(ti) predicted value；
(4) accuracy test：
Inspection of the residual sum with respect to residual error includes：
Residual error
With respect to residual error
G0(ti) be the standard area ti moment information figureofmerit ordered series of numbers；
(5) if E (ti), e (t) be less than or equal to default threshold value E0 and e0, then by Gn(ti) it is sent to metropolitan area level Internet of Things Network data layer；If E (ti), e (t) be more than default threshold value E0 and e0, then suspend region Internet of Things work, treat threshold Value is less than threshold value E0 and e0 less than or equal to default again, then replys metropolitan area level Internet of Things network layer work.
The data message of the metropolitan area level Internet of Things data layer storage includes：
Boolean types, for storing Boolean type data；
Double types, for storing type real data；
Int types, for storing the data of integer type；
String types, for storing string data；
Datetime types, for storage time and date data；
Image types, for storing the picture for being less than 8MB sizes；
Video types, for storing the video data of arbitrary size；
Blob types, for storing other binary data；
Object types, for the expansible object type of storage organization.
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into The particular content of row analysis includes：
(1) each event and object are set as node, task balance are assigned on each node, in adjacent segments Between point, a beacon frame with current time stamp is sent in neighbor node f to another node f by one of node q After receiving the beacon frame, the time stamp T S in the data packet is extracted immediately, and creates a return ACK bag, by the time Stamp data are added in ACK bags, push to large server；
(2) after origin node q receives the ACK bags, the timestamp information TS of needs is therefrom extracted, further according to present system time TM, the propagation delay time of calculate node
T=(TM-TS)/2；
(3) each node calculates propagation delay time successively with its surroundings nodes respectively, and these time delays deposit routing table is believed In breath, wherein the value of the propagation delay time of the origin node of system is 0；Information will be re-started and given out a contract for a project every one section of set time, , according to real-time network state, to update routing table；
(4) propagation delay time for the origin node that system is reached by A node paths is calculated, when being transmitted between neighbor node After the completion of prolonging estimation, a broadcast request is sent in the 1st row node i, the iteration for obtaining adjacent node adds up time delay；The 2nd After trade node i receives the return bag of neighbor node, extract iteration therein and add up time delay；It is about to what is extracted in the 3rd, 4 The neighbor node iteration time delay that adds up is added with itself transmission experiment estimate between neighbor node, is as a result saved into node i The iteration of the origin node for being transmitted to system via neighbor node of node i adds up time delay collection；
(5) node i according to iteration add up time delay collection result and large server send operation information tire out in iteration Operated after added-time Yan Ji.
A kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data, includes the following steps：
(1) level thing network sensing layer in metropolitan area including electromagnetic induction sensor, spectrum sensor, audio and food by sensing Device, satellite remote sensing system, GNSS sensors, infrared sensor, the interactive space module of Hall sensor are according to set in advance Control and administrative standard, all physical events occurred in environment and total data are gathered for the information network of whole Internet of Things；
(2) by including PAN networks, lan network, wlan network, WAN network, GPRS network, GPS network network, 3G network, 4G The exchange channels of network and suitable for exchange channels all kinds of agreements form interaction protocol form metropolitan area level Internet of Things network Metropolitan area level thing network sensing layer is uploaded layer all physical events to come and total data passes to metropolitan area level Internet of Things data Layer is stored, and the decision information for the metropolitan area level internet of things application layer that metropolitan area level Internet of Things data layer is received is sent to friendship Mutual space module；
(3) Mongo DB databases, Hbase databases, Redis databases, NoSQL databases, Redis data are included The metropolitan area level Internet of Things data layer that storehouse, the large server being combined based on memory and hard disk of Cassandra databases are formed Metropolitan area level Internet of Things network layer and isomerization, the structure of metropolitan area level internet of things application layer transmission are stored by distributed storage architecture Change data；
(4) the metropolitan area level internet of things application layer described in be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things The data message of network data layer transmission is analyzed, is handled, stored, filtered, and to the ring residing for metropolitan area level thing network sensing layer Border is analyzed, according to result provide user needed for service, in Internet of Things object carry out it is intelligentized identification, positioning, The data terminal of tracking, monitoring, decision-making and management.
All physical events and the particular content of total data occurred in the collection environment include：
(1) form information of collection event is defined as syntactic information, and the semantic information of collection event is defined as semantic information, The utility information of event is known as pragmatic information, and difference uses symbol Δ l successivelyg、Δls、ΔlpRepresent, full information set：Δ l=Q (Δlg+Δls+Δlp), Q represents operator, is uncertain computing when event is unstable, is definite fortune when event is stablized Calculate；
(2) the prior information l of main body is introducedr(X；A), posterior information lo(X；A it is), real to obtain information Δ ln(X；A) and it is expected to believe Cease le(X；A)；Main body A on the prior information of event X refer to that main body had before the actual observation event on The information of the event；Main body A on the posterior information of event X refer to that main body obtained after the actual observation event on The information of the event；Main body A is on the real that information refers to main body due to the event observed the event and actually obtained of event X Net information；Main body A refers to that main body under various regimes it is expected event the information obtained on the expectation information of event X；
Prior information, posterior information, reality obtain information and the operation relation of full information is expressed as：
Δ l=Q (Δ ln(X；A))=Q (lo(X；A)-lr(X；A))；
Syntactic information, semantic information, pragmatic information are expressed as：
(3) by elapsed time sequence tiPrior information, posterior information, the reality obtained afterwards obtains information and is；
Δlg=Δ lg(X,ti；A)=log(X,ti；A)-lrg(X,ti；A)
Δls=Δ ls(X,ti；A)=los(X,ti；A)-lrs(X,ti；A)
Δlp=Δ lp(X,ti；A)=lop(X,ti；A)-lsp(X,ti；A),
I=1,2,3 ... n；
Above-mentioned elapsed time sequence tiThe prior information that obtains afterwards, posterior information, real information are used for describing event external The sensation of the dominance condition of structure and the stimulus signal sent to event, consciousness and presentation, including the color of event, shape, Size, sound, speed, temperature, the status information of frequency.
The exchange channels and interaction protocol metropolitan area level thing network sensing layer is uploaded all physical events for coming and The particular content that total data passes to metropolitan area level Internet of Things data layer includes：
(1) data processing：
If GnFor information figureofmerit ordered series of numbers in respect of time in a certain region,N represents region sequence Number,
(2) GM (h, l) model in gray model for prediction is established：
A and u is the model parameter determined by initial data,
(3) reduction treatment：
The inverse operation of generation data is carried out, prediction data is the corresponding index of each event；
For Gn(ti) predicted value；
(4) accuracy test：
Inspection of the residual sum with respect to residual error includes：
Residual error
With respect to residual error
G0(ti) be the standard area ti moment information figureofmerit ordered series of numbers；
(5) if E (ti), e (t) be less than or equal to default threshold value E0 and e0, then by Gn(ti) it is sent to metropolitan area level Internet of Things Network data layer；If E (ti), e (t) be more than default threshold value E0 and e0, then suspend region Internet of Things work, treat threshold Value is less than threshold value E0 and e0 less than or equal to default again, then replys metropolitan area level Internet of Things network layer work.
The data message of the metropolitan area level Internet of Things data layer storage includes：
Boolean types, for storing Boolean type data；
Double types, for storing type real data；
Int types, for storing the data of integer type；
String types, for storing string data；
Datetime types, for storage time and date data；
Image types, for storing the picture for being less than 8MB sizes；
Video types, for storing the video data of arbitrary size；
Blob types, for storing other binary data；
Object types, for the expansible object type of storage organization.
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into The particular content of row analysis includes：
(1) each event and object are set as node, task balance are assigned on each node, in adjacent segments Between point, a beacon frame with current time stamp is sent in neighbor node f to another node f by one of node q After receiving the beacon frame, the time stamp T S in the data packet is extracted immediately, and creates a return ACK bag, by the time Stamp data are added in ACK bags, push to large server；
(2) after origin node q receives the ACK bags, the timestamp information TS of needs is therefrom extracted, further according to present system time TM, the propagation delay time of calculate node
T=(TM-TS)/2；
(3) each node calculates propagation delay time successively with its surroundings nodes respectively, and these time delays deposit routing table is believed In breath, wherein the value of the propagation delay time of the origin node of system is 0；Information will be re-started and given out a contract for a project every one section of set time, , according to real-time network state, to update routing table；
(4) propagation delay time for the origin node that system is reached by A node paths is calculated, when being transmitted between neighbor node After the completion of prolonging estimation, a broadcast request is sent in the 1st row node i, the iteration for obtaining adjacent node adds up time delay；The 2nd After trade node i receives the return bag of neighbor node, extract iteration therein and add up time delay；It is about to what is extracted in the 3rd, 4 The neighbor node iteration time delay that adds up is added with itself transmission experiment estimate between neighbor node, is as a result saved into node i The iteration of the origin node for being transmitted to system via neighbor node of node i adds up time delay collection；
(5) node i according to iteration add up time delay collection result and large server send operation information tire out in iteration Operated after added-time Yan Ji.
The beneficial effects of the present invention are：
A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data of the present invention, in city In the level spatial dimension of domain, using polytype Internet of Things gathered data, multiple dimensioned to data progress is abstract such as grander The scale in the whole city seen, some local scale of more microcosmic city；The pattern that scene is performed using various factors is known Do not analyze, such as the tendency for air pollution, air particle situation, discharge of pollutant sources situation, wind direction and wind can be integrated The factors such as speed, city traffic situation, carry out the analysis of many reference amounts model, and the means of artificial intelligence can be used to carry out decision-making.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution of the prior art Embodiment or attached drawing needed to be used in the description of the prior art are briefly described, it should be apparent that, in describing below Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor Put, other attached drawings can also be obtained according to these attached drawings.
Fig. 1 shows present system structure chart.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with attached drawing to the present invention Technical solution be clearly and completely described, it is clear that described embodiment is part of the embodiment of the present invention, rather than Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise Lower all other embodiments obtained, belong to the scope of protection of the invention.
A kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data, including metropolitan area level Internet of Things perceive Layer, metropolitan area level Internet of Things network layer, metropolitan area level Internet of Things data layer and metropolitan area level internet of things application layer；
The metropolitan area level thing network sensing layer includes electromagnetism by interactive space module composition, the interactive space module Inductive pick-up, spectrum sensor, audio and food sensor, satellite remote sensing system, GNSS sensors, infrared sensor, suddenly That sensor；Interactive space module is that the information network of whole Internet of Things gathers according to control set in advance and administrative standard All physical events and total data occurred in environment；
The metropolitan area level Internet of Things network layer is made of exchange channels and interaction protocol, exchange channels include PAN networks, Lan network, wlan network, WAN network, GPRS network, GPS network network, 3G network, 4G networks；The interaction protocol is applicable In all kinds of agreements of exchange channels；Metropolitan area level thing network sensing layer is uploaded all physics to come by exchange channels and interaction protocol Event and total data pass to metropolitan area level Internet of Things data layer and are stored, and metropolitan area level Internet of Things data layer is received The decision information of metropolitan area level internet of things application layer is sent to interactive space module；
The metropolitan area level Internet of Things data layer is the large server being combined based on memory and hard disk；Including Mongo DB databases, Hbase databases, Redis databases, NoSQL databases, Redis databases, Cassandra databases；Metropolitan area Level Internet of Things data layer stores metropolitan area level Internet of Things network layer by distributed storage architecture and metropolitan area level internet of things application layer passes The isomerization passed, structural data；
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into Row analysis, according to result provide user needed for service, in Internet of Things object carry out it is intelligentized identification, positioning, tracking, The data terminal of monitoring, decision-making and management.
All physical events and the particular content of total data occurred in the collection environment include：
(1) form information of collection event is defined as syntactic information, and the semantic information of collection event is defined as semantic information, The utility information of event is known as pragmatic information, and difference uses symbol Δ l successivelyg、Δls、ΔlpRepresent, full information set：Δ l=Q (Δlg+Δls+Δlp), Q represents operator, is uncertain computing when event is unstable, is definite fortune when event is stablized Calculate；
(2) the prior information l of main body is introducedr(X；A), posterior information lo(X；A it is), real to obtain information Δ ln(X；A) and it is expected to believe Cease le(X；A)；Main body A on the prior information of event X refer to that main body had before the actual observation event on The information of the event；Main body A on the posterior information of event X refer to that main body obtained after the actual observation event on The information of the event；Main body A is on the real that information refers to main body due to the event observed the event and actually obtained of event X Net information；Main body A refers to that main body under various regimes it is expected event the information obtained on the expectation information of event X；
Prior information, posterior information, reality obtain information and the operation relation of full information is expressed as：
Δ l=Q (Δ ln(X；A))=Q (lo(X；A)-lr(X；A))；
Syntactic information, semantic information, pragmatic information are expressed as：
(3) by elapsed time sequence tiPrior information, posterior information, the reality obtained afterwards obtains information and is；
Δlg=Δ lg(X,ti；A)=log(X,ti；A)-lrg(X,ti；A)
Δls=Δ ls(X,ti；A)=los(X,ti；A)-lrs(X,ti；A)
Δlp=Δ lp(X,ti；A)=lop(X,ti；A)-lsp(X,ti；A),
I=1,2,3 ... n；
Above-mentioned elapsed time sequence tiThe prior information that obtains afterwards, posterior information, real information are used for describing event external The sensation of the dominance condition of structure and the stimulus signal sent to event, consciousness and presentation, including the color of event, shape, Size, sound, speed, temperature, the status information of frequency.
The exchange channels and interaction protocol metropolitan area level thing network sensing layer is uploaded all physical events for coming and The particular content that total data passes to metropolitan area level Internet of Things data layer includes：
(1) data processing：
If GnFor information figureofmerit ordered series of numbers in respect of time in a certain region,N represents region sequence Number,
(2) GM (h, l) model in gray model for prediction is established：
A and u is the model parameter determined by initial data,
(3) reduction treatment：
The inverse operation of generation data is carried out, prediction data is the corresponding index of each event；
For Gn(ti) predicted value；
(4) accuracy test：
Inspection of the residual sum with respect to residual error includes：
Residual error
With respect to residual error
G0(ti) be the standard area ti moment information figureofmerit ordered series of numbers；
(5) if E (ti), e (t) be less than or equal to default threshold value E0 and e0, then by Gn(ti) it is sent to metropolitan area level Internet of Things Network data layer；If E (ti), e (t) be more than default threshold value E0 and e0, then suspend region Internet of Things work, treat threshold Value is less than threshold value E0 and e0 less than or equal to default again, then replys metropolitan area level Internet of Things network layer work.
Since the direct factor for influencing information requirement is Regional Economic Development situation, communications and transportation activity intensity, population shape The factors such as condition.Either regional economic development or communications and transportation activity, are all a multi-level, multifactor complication systems, External concentrated expression of the quantity of information requirement as this complication system, its level each with system, the relation of each factor are very complicated, deposit Many completely uncertain or oneself is but difficult to the contacts that are definitely described with quantitative relationship through determining, but each level of system, In the case of each factor is metastable, useful information can be excavated from one group of time series data, seeks information content in itself Changing rule, and the mathematical model of quantitative analysis is established accordingly, to predict the regional traffic information content of following special time period. Therefore, one can consider that the regional traffic information network of one " a small number of evidences, imperfect information " is exactly a gray system, adopt It is suitable that traffic information demand, which is predicted, with grey forecasting model, and this method is the effective work quantified to information Tool and means.Therefore, it is capable of the data cases of accurate, efficient conversion zone to information content prediction model structure with the model.
The data message of the metropolitan area level Internet of Things data layer storage includes：
Boolean types, for storing Boolean type data；
Double types, for storing type real data；
Int types, for storing the data of integer type；
String types, for storing string data；
Datetime types, for storage time and date data；
Image types, for storing the picture for being less than 8MB sizes；
Video types, for storing the video data of arbitrary size；
Blob types, for storing other binary data；
Object types, for the expansible object type of storage organization.
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into The particular content of row analysis includes：
(1) each event and object are set as node, task balance are assigned on each node, in adjacent segments Between point, a beacon frame with current time stamp is sent in neighbor node f to another node f by one of node q After receiving the beacon frame, the time stamp T S in the data packet is extracted immediately, and creates a return ACK bag, by the time Stamp data are added in ACK bags, push to large server；
(2) after origin node q receives the ACK bags, the timestamp information TS of needs is therefrom extracted, further according to present system time TM, the propagation delay time of calculate node
T=(TM-TS)/2；
(3) each node calculates propagation delay time successively with its surroundings nodes respectively, and these time delays deposit routing table is believed In breath, wherein the value of the propagation delay time of the origin node of system is 0；Information will be re-started and given out a contract for a project every one section of set time, , according to real-time network state, to update routing table；
(4) propagation delay time for the origin node that system is reached by A node paths is calculated, when being transmitted between neighbor node After the completion of prolonging estimation, a broadcast request is sent in the 1st row node i, the iteration for obtaining adjacent node adds up time delay；The 2nd After trade node i receives the return bag of neighbor node, extract iteration therein and add up time delay；It is about to what is extracted in the 3rd, 4 The neighbor node iteration time delay that adds up is added with itself transmission experiment estimate between neighbor node, is as a result saved into node i The iteration of the origin node for being transmitted to system via neighbor node of node i adds up time delay collection；
(5) node i according to iteration add up time delay collection result and large server send operation information tire out in iteration Operated after added-time Yan Ji.
A kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data, includes the following steps：
(1) level thing network sensing layer in metropolitan area including electromagnetic induction sensor, spectrum sensor, audio and food by sensing Device, satellite remote sensing system, GNSS sensors, infrared sensor, the interactive space module of Hall sensor are according to set in advance Control and administrative standard, all physical events occurred in environment and total data are gathered for the information network of whole Internet of Things；
(2) by including PAN networks, lan network, wlan network, WAN network, GPRS network, GPS network network, 3G network, 4G The exchange channels of network and suitable for exchange channels all kinds of agreements form interaction protocol form metropolitan area level Internet of Things network Metropolitan area level thing network sensing layer is uploaded layer all physical events to come and total data passes to metropolitan area level Internet of Things data Layer is stored, and the decision information for the metropolitan area level internet of things application layer that metropolitan area level Internet of Things data layer is received is sent to friendship Mutual space module；
(3) Mongo DB databases, Hbase databases, Redis databases, NoSQL databases, Redis data are included The metropolitan area level Internet of Things data layer that storehouse, the large server being combined based on memory and hard disk of Cassandra databases are formed Metropolitan area level Internet of Things network layer and isomerization, the structure of metropolitan area level internet of things application layer transmission are stored by distributed storage architecture Change data；
(4) the metropolitan area level internet of things application layer described in be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things The data message of network data layer transmission is analyzed, is handled, stored, filtered, and to the ring residing for metropolitan area level thing network sensing layer Border is analyzed, according to result provide user needed for service, in Internet of Things object carry out it is intelligentized identification, positioning, The data terminal of tracking, monitoring, decision-making and management.
All physical events and the particular content of total data occurred in the collection environment include：
(1) form information of collection event is defined as syntactic information, and the semantic information of collection event is defined as semantic information, The utility information of event is known as pragmatic information, and difference uses symbol Δ l successivelyg、Δls、ΔlpRepresent, full information set：Δ l=Q (Δlg+Δls+Δlp), Q represents operator, is uncertain computing when event is unstable, is definite fortune when event is stablized Calculate；
(2) the prior information l of main body is introducedr(X；A), posterior information lo(X；A it is), real to obtain information Δ ln(X；A) and it is expected to believe Cease le(X；A)；Main body A on the prior information of event X refer to that main body had before the actual observation event on The information of the event；Main body A on the posterior information of event X refer to that main body obtained after the actual observation event on The information of the event；Main body A is on the real that information refers to main body due to the event observed the event and actually obtained of event X Net information；Main body A refers to that main body under various regimes it is expected event the information obtained on the expectation information of event X；
Prior information, posterior information, reality obtain information and the operation relation of full information is expressed as：
Δ l=Q (Δ ln(X；A))=Q (lo(X；A)-lr(X；A))；
Syntactic information, semantic information, pragmatic information are expressed as：
(3) by elapsed time sequence tiPrior information, posterior information, the reality obtained afterwards obtains information and is；
Δlg=Δ lg(X,ti；A)=log(X,ti；A)-lrg(X,ti；A)
Δls=Δ ls(X,ti；A)=los(X,ti；A)-lrs(X,ti；A)
Δlp=Δ lp(X,ti；A)=lop(X,ti；A)-lsp(X,ti；A),
I=1,2,3 ... n；
Above-mentioned elapsed time sequence tiThe prior information that obtains afterwards, posterior information, real information are used for describing event external The sensation of the dominance condition of structure and the stimulus signal sent to event, consciousness and presentation, including the color of event, shape, Size, sound, speed, temperature, the status information of frequency.
Each main body is described the full information of event widely different due to the difference of state.The main body of perception is more paid close attention to The structural form of event, the main body of rationality more pays close attention to the functional meaning of event, and the main body of reality then more focuses on the valency of event It is worth effectiveness, here it is the effect of gathered data in advance.When the state of main body is also unstable, uncertain computing is shown as；And work as Main body it is in stable condition when, show as certainty computing.
The exchange channels and interaction protocol metropolitan area level thing network sensing layer is uploaded all physical events for coming and The particular content that total data passes to metropolitan area level Internet of Things data layer includes：
(1) data processing：
If GnFor information figureofmerit ordered series of numbers in respect of time in a certain region,N represents region sequence Number,
(2) GM (h, l) model in gray model for prediction is established：
A and u is the model parameter determined by initial data,
(3) reduction treatment：
The inverse operation of generation data is carried out, prediction data is the corresponding index of each event；
For Gn(ti) predicted value；
(4) accuracy test：
Inspection of the residual sum with respect to residual error includes：
Residual error
With respect to residual error
G0(ti) be the standard area ti moment information figureofmerit ordered series of numbers；
(5) if E (ti), e (t) be less than or equal to default threshold value E0 and e0, then by Gn(ti) it is sent to metropolitan area level Internet of Things Network data layer；If E (ti), e (t) be more than default threshold value E0 and e0, then suspend region Internet of Things work, treat threshold Value is less than threshold value E0 and e0 less than or equal to default again, then replys metropolitan area level Internet of Things network layer work.
The data message of the metropolitan area level Internet of Things data layer storage includes：
Boolean types, for storing Boolean type data；
Double types, for storing type real data；
Int types, for storing the data of integer type；
String types, for storing string data；
Datetime types, for storage time and date data；
Image types, for storing the picture for being less than 8MB sizes；
Video types, for storing the video data of arbitrary size；
Blob types, for storing other binary data；
Object types, for the expansible object type of storage organization.
Obtain the data object of unified form, it is necessary to pattern definition is carried out to the Compatible object of this isomery, this is with regard to class It is similar in traditional relational model, first defines a binary crelation and its constraint, can just obtains the two-dimentional relation of storage data Table.In the present invention, the data pattern is described into usage type system.Which is unified for Internet of Things overall data Form, easy to the transmission of information.
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into The particular content of row analysis includes：
(1) each event and object are set as node, task balance are assigned on each node, in adjacent segments Between point, a beacon frame with current time stamp is sent in neighbor node f to another node f by one of node q After receiving the beacon frame, the time stamp T S in the data packet is extracted immediately, and creates a return ACK bag, by the time Stamp data are added in ACK bags, push to large server；
(2) after origin node q receives the ACK bags, the timestamp information TS of needs is therefrom extracted, further according to present system time TM, the propagation delay time of calculate node
T=(TM-TS)/2；
(3) each node calculates propagation delay time successively with its surroundings nodes respectively, and these time delays deposit routing table is believed In breath, wherein the value of the propagation delay time of the origin node of system is 0；Information will be re-started and given out a contract for a project every one section of set time, , according to real-time network state, to update routing table；
(4) propagation delay time for the origin node that system is reached by A node paths is calculated, when being transmitted between neighbor node After the completion of prolonging estimation, a broadcast request is sent in the 1st row node i, the iteration for obtaining adjacent node adds up time delay；The 2nd After trade node i receives the return bag of neighbor node, extract iteration therein and add up time delay；It is about to what is extracted in the 3rd, 4 The neighbor node iteration time delay that adds up is added with itself transmission experiment estimate between neighbor node, is as a result saved into node i The iteration of the origin node for being transmitted to system via neighbor node of node i adds up time delay collection；
(5) node i according to iteration add up time delay collection result and large server send operation information tire out in iteration Operated after added-time Yan Ji.
This method is by obtaining all nodal informations being in set of node, according in the information of each node and network The remaining information synthesis of all nodes, calculates the Delay of each node.According to the information, random function is called, is being saved Point concentrates the forwarding of selection node progress data packet, to increase the robustness of network entirety, balance network load.
A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data of the present invention, in city In the level spatial dimension of domain, using polytype Internet of Things gathered data, multiple dimensioned to data progress is abstract such as grander The scale in the whole city seen, some local scale of more microcosmic city；The pattern that scene is performed using various factors is known Do not analyze, such as the tendency for air pollution, air particle situation, discharge of pollutant sources situation, wind direction and wind can be integrated The factors such as speed, city traffic situation, carry out the analysis of many reference amounts model, and the means of artificial intelligence can be used to carry out decision-making.

Claims (10)

1. a kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data, including metropolitan area level thing network sensing layer, Metropolitan area level Internet of Things network layer, metropolitan area level Internet of Things data layer and metropolitan area level internet of things application layer；It is characterized in that：
The metropolitan area level thing network sensing layer includes electromagnetic induction by interactive space module composition, the interactive space module Sensor, spectrum sensor, audio and food sensor, satellite remote sensing system, GNSS sensors, infrared sensor, Hall pass Sensor；Interactive space module is that the information network of whole Internet of Things gathers environment according to control set in advance and administrative standard All physical events and total data of middle generation；
The metropolitan area level Internet of Things network layer is made of exchange channels and interaction protocol, and exchange channels include PAN networks, LAN Network, wlan network, WAN network, GPRS network, GPS network network, 3G network, 4G networks；The interaction protocol is suitable for handing over All kinds of agreements of mutual passage；Metropolitan area level thing network sensing layer is uploaded all physical events to come by exchange channels and interaction protocol Metropolitan area level Internet of Things data layer is passed to total data to be stored, and the metropolitan area that metropolitan area level Internet of Things data layer is received The decision information of level internet of things application layer is sent to interactive space module；
The metropolitan area level Internet of Things data layer is the large server being combined based on memory and hard disk；Including Mongo DB numbers According to storehouse, Hbase databases, Redis databases, NoSQL databases, Redis databases, Cassandra databases；Metropolitan area level thing Networking data layer stores metropolitan area level Internet of Things network layer and metropolitan area level internet of things application layer transmission by distributed storage architecture Isomerization, structural data；
The metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things data layer The data message of transmission is analyzed, is handled, stored, filtered, and the environment residing for metropolitan area level thing network sensing layer is divided Analysis, the service according to needed for result provides user, carries out the object in Internet of Things in intelligentized identification, positioning, tracking, prison The data terminal of survey, decision-making and management.
2. a kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data according to claim 1, it is special Sign is that all physical events and the particular content of total data occurred in the collection environment include：
(1.1) form information of collection event is defined as syntactic information, and the semantic information of collection event is defined as semantic information, thing The utility information of part is known as pragmatic information, and difference uses symbol Δ l successivelyg、Δls、ΔlpRepresent, full information set：Δ l=Q (Δs lg+Δls+Δlp), Q represents operator, is uncertain computing when event is unstable, is definite computing when event is stablized；
(1.2) the prior information l of main body is introducedr(X；A), posterior information lo(X；A it is), real to obtain information Δ ln(X；A) and it is expected information le(X；A)；Main body A on the prior information of event X refer to that main body had before the actual observation event on this The information of event；Main body A on the posterior information of event X refer to that main body obtained after the actual observation event on this The information of event；Main body A refers to main body due to the event observing the event and actually obtain on real the information of event X Net information；Main body A refers to that main body under various regimes it is expected event the information obtained on the expectation information of event X；
Prior information, posterior information, reality obtain information and the operation relation of full information is expressed as：
Δ l=Q (Δ ln(X；A))=Q (lo(X；A)-lr(X；A))；
Syntactic information, semantic information, pragmatic information are expressed as：
<mrow> <mtable> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;l</mi> <mi>g</mi> </msub> <mo>=</mo> <msub> <mi>&amp;Delta;l</mi> <mi>g</mi> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>l</mi> <mrow> <mi>o</mi> <mi>g</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>l</mi> <mrow> <mi>r</mi> <mi>g</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;l</mi> <mi>s</mi> </msub> <mo>=</mo> <msub> <mi>&amp;Delta;l</mi> <mi>s</mi> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>l</mi> <mrow> <mi>o</mi> <mi>s</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>l</mi> <mrow> <mi>r</mi> <mi>s</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;l</mi> <mi>p</mi> </msub> <mo>=</mo> <msub> <mi>&amp;Delta;l</mi> <mi>p</mi> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>l</mi> <mrow> <mi>o</mi> <mi>p</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>l</mi> <mrow> <mi>s</mi> <mi>p</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> <mo>;</mo> </mrow>
(1.3) by elapsed time sequence tiPrior information, posterior information, the reality obtained afterwards obtains information and is；
Δlg=Δ lg(X,ti；A)=log(X,ti；A)-lrg(X,ti；A)
Δls=Δ ls(X,ti；A)=los(X,ti；A)-lrs(X,ti；A)
Δlp=Δ lp(X,ti；A)=lop(X,ti；A)-lsp(X,ti；A),
I=1,2,3 ... m；M represents time sequence number；
Above-mentioned elapsed time sequence tiPrior information, posterior information, the real information that obtains obtained afterwards is used for describing event formal structure The sensation of dominance condition and the stimulus signal sent to event, consciousness and presentation, including the color of event, shape, size, sound Sound, speed, temperature, the status information of frequency.
3. a kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data according to claim 1, it is special Sign is, metropolitan area level thing network sensing layer is uploaded all physical events for coming and complete by the exchange channels and interaction protocol Portion's data transfer includes to the particular content of metropolitan area level Internet of Things data layer：
(2.1) data processing：
If GnFor information figureofmerit ordered series of numbers in respect of time in a certain region,N represents region sequence number,
(2.2) GM (h, l) model in gray model for prediction is established：
<mrow> <mfrac> <mrow> <msup> <mi>dG</mi> <mi>n</mi> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <mi>d</mi> <mi>t</mi> </mrow> </mfrac> <mo>+</mo> <msup> <mi>aG</mi> <mi>n</mi> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mi>u</mi> </mrow>
A and u is the model parameter determined by initial data,
<mrow> <msup> <mi>G</mi> <mi>n</mi> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mo>&amp;lsqb;</mo> <msup> <mi>G</mi> <mn>1</mn> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>-</mo> <mfrac> <mi>u</mi> <mi>a</mi> </mfrac> <mo>&amp;rsqb;</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <msub> <mi>at</mi> <mi>i</mi> </msub> </mrow> </msup> <mo>+</mo> <mfrac> <mi>u</mi> <mi>a</mi> </mfrac> <mo>;</mo> </mrow>
(2.3) reduction treatment：
The inverse operation of generation data is carried out, prediction data is the corresponding index of each event；
For Gn(ti) predicted value；
(2.4) accuracy test：
Inspection of the residual sum with respect to residual error includes：
Residual error
With respect to residual error
G0(ti) be the standard area ti moment information figureofmerit ordered series of numbers；
(2.5) if E (ti), e (t) be less than or equal to default threshold value E0 and e0, then by Gn(ti) it is sent to metropolitan area level Internet of Things Data Layer；If E (ti), e (t) be more than default threshold value E0 and e0, then suspend region Internet of Things work, treat threshold value Again it is less than the threshold value E0 and e0 less than or equal to default, then replys metropolitan area level Internet of Things network layer work.
4. a kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data according to claim 1, it is special Sign is that the data message of the metropolitan area level Internet of Things data layer storage includes：
Boolean types, for storing Boolean type data；
Double types, for storing type real data；
Int types, for storing the data of integer type；
String types, for storing string data；
Datetime types, for storage time and date data；
Image types, for storing the picture for being less than 8MB sizes；
Video types, for storing the video data of arbitrary size；
Blob types, for storing other binary data；
Ob ject types, for the expansible object type of storage organization.
5. a kind of scene intelligent analysis system based on metropolitan area level Internet of Things perception data according to claim 1, it is special Sign is, the metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into The particular content of row analysis includes：
(4.1) each event and object are set as node, task balance are assigned on each node, in adjacent node Between, a beacon frame with current time stamp is sent to another node f by one of node q and is received in neighbor node f To after the beacon frame, the time stamp T S in the data packet is extracted immediately, and creates a return ACK bag, by timestamp Data are added in ACK bags, push to large server；
(4.2) after origin node q receives the ACK bags, the timestamp information TS of needs is therefrom extracted, further according to present system time TM, the propagation delay time of calculate node
T=(TM-TS)/2；
(4.3) each node calculates propagation delay time successively with its surroundings nodes respectively, and these time delays are stored in routing table information In, wherein the value of the propagation delay time of the origin node of system is 0；Information will be re-started and given out a contract for a project, come every one section of set time According to real-time network state, routing table is updated；
(4.4) propagation delay time for the origin node that system is reached by A node paths is calculated, when propagation delay time between neighbor node After the completion of estimation, a broadcast request is sent in the 1st row node i, the iteration for obtaining adjacent node adds up time delay；In the 2nd row After node i receives the return bag of neighbor node, extract iteration therein and add up time delay；In the neighbour that the 3rd, 4 are about to extract Occupy the node iteration time delay that adds up to be added with itself transmission experiment estimate between neighbor node, be as a result saved into the section of node i The iteration of the origin node for being transmitted to system via neighbor node of point i adds up time delay collection；
(4.5) node i according to iteration add up time delay collection result and large server send operation information add up in iteration Operated after time delay collection.
6. a kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data, it is characterised in that include the following steps：
(1) metropolitan area level thing network sensing layer by including electromagnetic induction sensor, spectrum sensor, audio and food sensor, Satellite remote sensing system, GNSS sensors, infrared sensor, the interactive space module of Hall sensor are according to control set in advance And administrative standard, gather all physical events occurred in environment and total data for the information network of whole Internet of Things；
(2) by including PAN networks, lan network, wlan network, WAN network, GPRS network, GPS network network, 3G network, 4G networks Exchange channels and will suitable for the metropolitan area level Internet of Things network layer that forms of the interaction protocol that forms of all kinds of agreements of exchange channels Metropolitan area level thing network sensing layer uploads all physical events to come and total data pass to metropolitan area level Internet of Things data layer into Row storage, and the decision information for the metropolitan area level internet of things application layer that metropolitan area level Internet of Things data layer is received is sent to interaction sky Between module；
(3) include Mongo DB databases, Hbase databases, Redis databases, NoSQL databases, Redis databases, The metropolitan area level Internet of Things data layer that the large server being combined based on memory and hard disk of Cassandra databases is formed passes through Distributed storage architecture stores isomerization, the structuring number of metropolitan area level Internet of Things network layer and metropolitan area level internet of things application layer transmission According to；
(4) the metropolitan area level internet of things application layer described in be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into Row analysis, according to result provide user needed for service, in Internet of Things object carry out it is intelligentized identification, positioning, tracking, The data terminal of monitoring, decision-making and management.
7. a kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data according to claim 6, it is special Sign is that all physical events and the particular content of total data occurred in the collection environment include：
The form information of collection event is defined as syntactic information, and the semantic information of collection event is defined as semantic information, event Utility information is known as pragmatic information, and difference uses symbol Δ l successivelyg、Δls、ΔlpRepresent, full information set：Δ l=Q (Δ lg+ Δls+Δlp), Q represents operator, is uncertain computing when event is unstable, is definite computing when event is stablized；
Introduce the prior information l of main bodyr(X；A), posterior information lo(X；A it is), real to obtain information Δ ln(X；A) and information l it is expectede(X； A)；Main body A on the prior information of event X refer to that main body had before the actual observation event on the event Information；Main body A on the posterior information of event X refer to that main body obtained after the actual observation event on the event Information；Main body A is on the real that information refers to that main body is believed due to the net of the event observed the event and actually obtained of event X Breath；Main body A refers to that main body under various regimes it is expected event the information obtained on the expectation information of event X；
Prior information, posterior information, reality obtain information and the operation relation of full information is expressed as：
Δ l=Q (Δ ln(X；A))=Q (lo(X；A)-lr(X；A))；
Syntactic information, semantic information, pragmatic information are expressed as：
<mrow> <mtable> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;l</mi> <mi>g</mi> </msub> <mo>=</mo> <msub> <mi>&amp;Delta;l</mi> <mi>g</mi> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>l</mi> <mrow> <mi>o</mi> <mi>g</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>l</mi> <mrow> <mi>r</mi> <mi>g</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;l</mi> <mi>s</mi> </msub> <mo>=</mo> <msub> <mi>&amp;Delta;l</mi> <mi>s</mi> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>l</mi> <mrow> <mi>o</mi> <mi>s</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>l</mi> <mrow> <mi>r</mi> <mi>s</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>&amp;Delta;l</mi> <mi>p</mi> </msub> <mo>=</mo> <msub> <mi>&amp;Delta;l</mi> <mi>p</mi> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>l</mi> <mrow> <mi>o</mi> <mi>p</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> <mo>-</mo> <msub> <mi>l</mi> <mrow> <mi>s</mi> <mi>p</mi> </mrow> </msub> <mrow> <mo>(</mo> <mrow> <mi>X</mi> <mo>;</mo> <mi>A</mi> </mrow> <mo>)</mo> </mrow> </mrow> </mtd> </mtr> </mtable> <mo>;</mo> </mrow>
By elapsed time sequence tiPrior information, posterior information, the reality obtained afterwards obtains information and is；
Δlg=Δ lg(X,ti；A)=log(X,ti；A)-lrg(X,ti；A)
Δls=Δ ls(X,ti；A)=los(X,ti；A)-lrs(X,ti；A)
Δlp=Δ lp(X,ti；A)=lop(X,ti；A)-lsp(X,ti；A),
I=1,2,3 ... n；
Above-mentioned elapsed time sequence tiPrior information, posterior information, the real information that obtains obtained afterwards is used for describing event formal structure The sensation of dominance condition and the stimulus signal sent to event, consciousness and presentation, including the color of event, shape, size, sound Sound, speed, temperature, the status information of frequency.
8. a kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data according to claim 6, it is special Sign is, metropolitan area level thing network sensing layer is uploaded all physical events for coming and complete by the exchange channels and interaction protocol Portion's data transfer includes to the particular content of metropolitan area level Internet of Things data layer：
Data processing：
If GnFor information figureofmerit ordered series of numbers in respect of time in a certain region,N represents region sequence number,
Establish GM (h, l) model in gray model for prediction：
<mrow> <mfrac> <mrow> <msup> <mi>dG</mi> <mi>n</mi> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <mi>d</mi> <mi>t</mi> </mrow> </mfrac> <mo>+</mo> <msup> <mi>aG</mi> <mi>n</mi> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mi>u</mi> </mrow>
A and u is the model parameter determined by initial data,
<mrow> <msup> <mi>G</mi> <mi>n</mi> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mi>i</mi> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mo>&amp;lsqb;</mo> <msup> <mi>G</mi> <mn>1</mn> </msup> <mrow> <mo>(</mo> <msub> <mi>t</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>-</mo> <mfrac> <mi>u</mi> <mi>a</mi> </mfrac> <mo>&amp;rsqb;</mo> <msup> <mi>e</mi> <mrow> <mo>-</mo> <msub> <mi>at</mi> <mi>i</mi> </msub> </mrow> </msup> <mo>+</mo> <mfrac> <mi>u</mi> <mi>a</mi> </mfrac> <mo>;</mo> </mrow>
Reduction treatment：
The inverse operation of generation data is carried out, prediction data is the corresponding index of each event；
For Gn(ti) predicted value；
Accuracy test：
Inspection of the residual sum with respect to residual error includes：
Residual error
With respect to residual error
G0(ti) be the standard area ti moment information figureofmerit ordered series of numbers；
If E (ti), e (t) be less than or equal to default threshold value E0 and e0, then by Gn(ti) it is sent to metropolitan area level Internet of Things data Layer；If E (ti), e (t) be more than default threshold value E0 and e0, then suspend region Internet of Things work, treat threshold value again Less than the threshold value E0 and e0 less than or equal to default, then reply metropolitan area level Internet of Things network layer work.
9. a kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data according to claim 6, it is special Sign is that the data message of the metropolitan area level Internet of Things data layer storage includes：
Boolean types, for storing Boolean type data；
Double types, for storing type real data；
Int types, for storing the data of integer type；
String types, for storing string data；
Datetime types, for storage time and date data；
Image types, for storing the picture for being less than 8MB sizes；
Video types, for storing the video data of arbitrary size；
Blob types, for storing other binary data；
Ob ject types, for the expansible object type of storage organization.
10. a kind of scene intelligent analysis method based on metropolitan area level Internet of Things perception data according to claim 6, it is special Sign is, the metropolitan area level internet of things application layer be metropolitan area level thing network sensing layer is got, metropolitan area level Internet of Things netting index Analyzed, handled, stored, filtered according to the data message of layer transmission, and to the environment residing for metropolitan area level thing network sensing layer into The particular content of row analysis includes：
Each event and object are set as node, task balance is assigned on each node, between adjacent node, One beacon frame with current time stamp is sent to another node f by one of node q and receives the letter in neighbor node f After marking frame, the time stamp T S in the data packet is extracted immediately, and creates a return ACK bag, by time stamp data plus Enter into ACK bags, push to large server；
After origin node q receives the ACK bags, the timestamp information TS of needs is therefrom extracted, further according to present system time TM, is calculated The propagation delay time of node
T=(TM-TS)/2；
Each node calculates propagation delay time successively with its surroundings nodes respectively, and these time delays are stored in routing table information, its The value of the propagation delay time of the origin node of middle system is 0；Information will re-start and give out a contract for a project, carry out basis every one section of set time Real-time network state, updates routing table；
The propagation delay time for the origin node that system is reached by A node paths is calculated, when propagation delay time is estimated between neighbor node After the completion of, a broadcast request is sent in the 1st row node i, the iteration for obtaining adjacent node adds up time delay；In the 2nd trade section After point i receives the return bag of neighbor node, extract iteration therein and add up time delay；It is about to the neighbours' section extracted in the 3rd, 4 The point iteration time delay that adds up is added with itself transmission experiment estimate between neighbor node, is as a result saved into the node i of node i The iteration that the origin node of system is transmitted to via neighbor node adds up time delay collection；
The operation information that node i adds up the result of time delay collection according to iteration and large server is sent adds up time delay collection in iteration After operated.
CN201711214859.2A 2017-11-28 2017-11-28 A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data Active CN107995278B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201711214859.2A CN107995278B (en) 2017-11-28 2017-11-28 A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data
PCT/CN2018/087233 WO2019104952A1 (en) 2017-11-28 2018-05-17 Scene intelligent analysis system and method based on metropolitan area level internet of things perceptual data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711214859.2A CN107995278B (en) 2017-11-28 2017-11-28 A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data

Publications (2)

Publication Number Publication Date
CN107995278A true CN107995278A (en) 2018-05-04
CN107995278B CN107995278B (en) 2019-02-22

Family

ID=62033659

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711214859.2A Active CN107995278B (en) 2017-11-28 2017-11-28 A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data

Country Status (2)

Country Link
CN (1) CN107995278B (en)
WO (1) WO2019104952A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108764746A (en) * 2018-06-01 2018-11-06 重庆市映天辉氯碱化工有限公司 Security and environment management device and system based on big data
WO2019104952A1 (en) * 2017-11-28 2019-06-06 特斯联（北京）科技有限公司 Scene intelligent analysis system and method based on metropolitan area level internet of things perceptual data
CN114021778A (en) * 2021-10-15 2022-02-08 金茂数字科技有限公司 Intelligent environment management method and system based on intelligent Internet of things

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810528A (en) * 2012-11-08 2014-05-21 无锡津天阳激光电子有限公司 Internet of Things smart city method and device
CN104253724A (en) * 2014-08-29 2014-12-31 朱顺利 Networking method using intelligent network elements as basic network units and network formed by method
CN106302683A (en) * 2016-08-10 2017-01-04 成都秦川科技发展有限公司 Smart city system
US20170041873A1 (en) * 2015-08-05 2017-02-09 Samsung Electronics Co., Ltd Apparatus and method for power saving for cellular internet of things devices

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107995278B (en) * 2017-11-28 2019-02-22 特斯联（北京）科技有限公司 A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103810528A (en) * 2012-11-08 2014-05-21 无锡津天阳激光电子有限公司 Internet of Things smart city method and device
CN104253724A (en) * 2014-08-29 2014-12-31 朱顺利 Networking method using intelligent network elements as basic network units and network formed by method
US20170041873A1 (en) * 2015-08-05 2017-02-09 Samsung Electronics Co., Ltd Apparatus and method for power saving for cellular internet of things devices
CN106302683A (en) * 2016-08-10 2017-01-04 成都秦川科技发展有限公司 Smart city system

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
王岩: "物联网控制系统中信息传输关键技术研究", 《中国博士学位论文全文数据库》 *
艾莉莎: "物联网空间域的泛传播构型", 《中国博士学位论文全文数据库》 *
闾远: "物联网中基于全局信息决策的实时响应路由", 《中国优秀硕士学位论文全文数据库》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019104952A1 (en) * 2017-11-28 2019-06-06 特斯联（北京）科技有限公司 Scene intelligent analysis system and method based on metropolitan area level internet of things perceptual data
CN108764746A (en) * 2018-06-01 2018-11-06 重庆市映天辉氯碱化工有限公司 Security and environment management device and system based on big data
CN114021778A (en) * 2021-10-15 2022-02-08 金茂数字科技有限公司 Intelligent environment management method and system based on intelligent Internet of things

Also Published As

Publication number Publication date
CN107995278B (en) 2019-02-22
WO2019104952A1 (en) 2019-06-06

Similar Documents

Publication Publication Date Title
Zhang Design and application of fog computing and Internet of Things service platform for smart city
Tong et al. A survey on algorithms for intelligent computing and smart city applications
Mallapuram et al. Smart city: The state of the art, datasets, and evaluation platforms
CN110263280B (en) Multi-view-based dynamic link prediction depth model and application
Wang et al. Hierarchical traffic flow prediction based on spatial-temporal graph convolutional network
Su et al. Applying deep learning algorithms to enhance simulations of large-scale groundwater flow in IoTs
Mora et al. Smart-city development paths: Insights from the first two decades of research
CN107423814A (en) A kind of method that dynamic network model is established using depth convolutional neural networks
CN109255743A (en) Conserve total management system
He et al. Simultaneously simulate vertical and horizontal expansions of a future urban landscape: A case study in Wuhan, Central China
CN107995278B (en) A kind of scene intelligent analysis system and method based on metropolitan area grade Internet of Things perception data
Zhang et al. Urban traffic flow forecast based on FastGCRNN
CN107203619A (en) A kind of core subgraph extraction algorithm under complex network
CN103258027A (en) Context awareness service platform based on intelligent terminal
Holme et al. A map of approaches to temporal networks
CN109062956A (en) A kind of space-time characteristic method for digging of facing area integrated energy system
Dai et al. Spatio-temporal deep learning framework for traffic speed forecasting in IoT
CN114063995A (en) Development engine system and method based on managed pipe city visualization
Liao et al. Air quality prediction by integrating mechanism model and machine learning model
Rong et al. Inferring origin-destination flows from population distribution
Abou El Seoud Towards sustainability: smart cities in the Egyptian environment, how much smart to be smart?
Yao Internet of Things in the Quality Control of Cement Mixing Pile Construction
Gu et al. Predicting the network shift of large urban agglomerations in China using the deep-learning gravity model: A perspective of population migration
Bhatnagar et al. Role of machine learning in sustainable engineering: a review
Wang et al. C3Meta: A Context-Aware Cloud-Edge-End Collaboration Framework Toward Green Metaverse

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