CN109816428A - A kind of water per analysis system and method based on big data machine learning - Google Patents
A kind of water per analysis system and method based on big data machine learning Download PDFInfo
- Publication number
- CN109816428A CN109816428A CN201811554608.3A CN201811554608A CN109816428A CN 109816428 A CN109816428 A CN 109816428A CN 201811554608 A CN201811554608 A CN 201811554608A CN 109816428 A CN109816428 A CN 109816428A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- core
- pipe network
- machine learning
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 86
- 238000004458 analytical method Methods 0.000 title claims abstract description 49
- 238000010801 machine learning Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000003860 storage Methods 0.000 claims abstract description 20
- 230000007246 mechanism Effects 0.000 claims abstract description 18
- 230000005540 biological transmission Effects 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 12
- 125000001309 chloro group Chemical group Cl* 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000014759 maintenance of location Effects 0.000 claims description 5
- 238000012217 deletion Methods 0.000 claims description 4
- 230000037430 deletion Effects 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 241001269238 Data Species 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims description 2
- 238000000151 deposition Methods 0.000 claims 2
- 230000006870 function Effects 0.000 description 36
- 230000008569 process Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000008400 supply water Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of water per analysis system and methods based on big data machine learning, wherein analysis system includes: data acquisition module, for acquiring the data of city pipe network key position；City pipe network communicating terminal, real-time data transmission for arriving data collecting module collected to database storage module；Data are carried out the classification and filing of system by database storage module；Data preprocessing module rejects underproof data, retains crucial core data；Core data server is handled and is calculated to the core data of reservation, and Various types of data result is stored in core data library module；System prejudges module, prejudges to the district system that whether there is unreasonable use of water in the pipe network of city；Treatment mechanism module needs the measure taken to provide conductive suggestion the accident of generation.The work such as water supply, scheduling that the present invention can instruct the related system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties daily greatly improve the efficiency of management of relevant staff.
Description
Technical field
The present invention relates to city pipe network wisdom management and big data to use field, specially a kind of to be based on big data machine
The water per analysis system and method for study, the work such as the water supply that the related system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties can be instructed daily, scheduling, greatly improves phase
The efficiency of management of the staff of pass.
Background technique
Current China is faced with the critical period of technology upgrading and economic transition, and industrial or agricultural and Income gap are prominent
Out, city pipe network accidents take place frequently, and bring large effect to the daily life of resident.
The importance of water resource is self-evident, and water resource is basic resource, is the controlling element of ecological environment, simultaneously
It is strategic economic resources again, is the organic component of overall national strength.According to United Nations Commission for Sustainable Development etc., 7 have
The investigation that tissue does 153, whole world countries and regions is closed, China year water resource of per capita is 2220m3, come the 121st
Position is classified as one of 13 poor-water states by the United Nations close to " short water supply country ".Therefore, in face of increasingly serious water resource
Supply and demand trend, and the situation of industry rapid development, predict the following water requirement, and formulate practicable water-saving arrange
It applies, is current one of the vital task for solving China's sustainable development.
In the technical solution to be supplied water based on nowadays city pipe network, resident is used in control and distribution for city water supply amount
The water of water and indusqtrial water supply can only make corresponding record according to the metering of water meter, not to how much carry out systems of water consumption
Analysis, scientific and reasonable water supply plan cannot be provided, thus to instruct the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties production water bring biggish puzzlement.
Intricate based on present city pipe network, the factor influenced for water stability and water fluctuation is a lot of, according to
The data of big data record, the operation method based on machine learning provide the specific influence factor of water supply fluctuation, and are directed to phase
The problem of answering provides suitable solution and measure.
Based on city pipe network supply water technical solution in, due to the prediction to water requirement be based on various model foundations,
Still there is deviation in the foundation of model and actual conditions, can only be unilateral provide predicted value, actual conditions cannot be reacted completely, no
It can be directly as the guide data of the water supply production of the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties.
With the raising of computer level and the rapid development of internet, the management philosophy and technology of city pipe network are wanted
It asks and gives higher definition.At home, the utilization with big data in all trades and professions, to utilize big data technology and correlation
Theory analysis and reasoning and calculation analysis pipe network system provide condition, still, currently on the market for big data solve
The system of city pipe network is also seldom.
Summary of the invention
The purpose of the present invention is to provide a kind of water per analysis system and methods based on big data machine learning, with solution
Certainly the problems mentioned above in the background art.
To achieve the above object, the invention provides the following technical scheme:
A kind of water per analysis system based on big data machine learning, comprising:
Data acquisition module, for acquiring the data of city pipe network key position, including flow, pressure, chlorine residue and turbidity
Real time data；
City pipe network communicating terminal, real-time data transmission for arriving data collecting module collected to database purchase mould
Block；
Data are carried out the classification and filing of system, by the data put in order with the shape of data packet by database storage module
Formula is sent to data preprocessing module；
Data preprocessing module rejects underproof data, retains crucial core data, and to core data
It is saved, rear end records the timing node of shortage of data；
Core data server is handled and is calculated to the core data of reservation, and Various types of data result is stored in
Core data library module, by the conclusion and integration of big data, to water consumption the case where carries out overall merit and feedback；
System prejudges module, in conjunction with the case where water consumption, overall merit and feedback information, to whether there is in the pipe network of city
The district system of unreasonable use of water is prejudged；
Treatment mechanism module needs the measure taken to provide conductive suggestion the accident of generation, and to final processing
As a result it is fed back；
The data acquisition module is connect with city pipe network communicating terminal, city pipe network communicating terminal and database purchase mould
Block communication connection, database storage module are connect with data preprocessing module, data preprocessing module and core data server
Connection, core data server are connected separately with core data library module and system anticipation module, and system prejudges module and processing
Mechanism module connection.
As a further solution of the present invention, the measuring instrument of the data acquisition module is installed on caliber in the pipe network of city
For on the crucial pipeline of DN100 or more, real-time acquisition and recording flow, pressure, chlorine residue and turbidity real time data, and data are turned
Text, figure, image, video or the audio data that chemical conversion computer is capable of handling.
As a further solution of the present invention, the database storage module includes the memory devices of large capacity, is used for
Collected number, text, picture, audio, video data are processed into the data format convenient for storage, it is real-time to all kinds of pipe networks
Data carry out the operation such as preservation, increase, deletion, update of data.
As a further solution of the present invention, the data preprocessing module is connect with core data server, will be different
The data of type are pre-processed, including the operation such as arrangement, formatting, rejecting, screening, and data are uniformly processed, and will
Data are transferred in core database and are further processed.
As a further solution of the present invention, the core data library module is the memory devices of large capacity, with core
Data server is associated, the preprocessed data needed for handling, saving water consumption management system, among Correlation Reasoning based on
It calculates result, save inherent rule, causality and retention result that core data server provides.
A kind of water per analysis method based on big data machine learning, includes the following steps:
S1, by the data of data collecting module collected city pipe network key position, including flow, pressure, chlorine residue and turbid
Spend real time data；
S2, city pipe network communicating terminal receive the data that arrive of data collecting module collected, and by real-time data transmission to counting
According to library memory module；
S3, the classification and filing that data are carried out to system by database storage module, by the data put in order with data
The form of packet is sent to data preprocessing module；
S4, underproof data are rejected by data preprocessing module, retains crucial core data, and to core
For calculation according to being saved, rear end records the timing node of shortage of data；
S5, it is handled and is calculated by core data of the core data server to reservation, and by Various types of data result
It is stored in core data library module, by the conclusion and integration of big data, to water consumption the case where carries out overall merit and feedback；
S6, the case where module combination water consumption is prejudged by system, overall merit and feedback information, to being in the pipe network of city
The no district system there are unreasonable use of water is prejudged；
It is S7, final, need the measure taken to provide conductive suggestion by accident of the treatment mechanism module to generation, and right
Final processing result is fed back.
As a further solution of the present invention, the system anticipation module in the step S6 is for the complete of the data acquired
Property and accuracy judged, excavate data between relevance, if data before and after beat it is excessive or too small, system can be by data
It is isolated, and the previous big data in maintenance data library, the data of the period is extracted, with the side of machine learning
Method provides the data for meeting the period.
As a further solution of the present invention, the treatment mechanism module in the step 7 prejudges module according to system and provides
Data type analyzed, the number provided in conjunction with machine learning method it is suggested that data exist abnormal place carry out it is pre-
Sentence and provide best solution.
It as a further solution of the present invention, further include Cloud Server, treatment mechanism module will prejudge and provide optimal
Solution is sent to Cloud Server, Cloud Server and user terminal communication connection.
As a further solution of the present invention, the user terminal includes computer, smart phone or IPAD, and user passes through
Computer, smart phone or IPAD terminal carry out the tracking and feedback of event.
Compared with prior art, the beneficial effects of the present invention are:
1, it is analyzed with water consumption of the big data to city, more accurately.After the big data system, to various
The processing operational capability of data can be quick with family, is compared comprehensive receipts by flow, pressure, water quality parameter acquisition module
Collection arranges, classifies and in the database that is stored in, is capable of forming that comparison is comprehensive, believable basic data.Everybody institute
Know, the daily remote meter reading of the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties can not collect and analyze whole data, even if occurring the error of very little in the process
It will also result in biggish deviation.But the water per analysis system based on big data can, processing speed huge by its data scale of construction
Degree is fast to wait many advantages, greatly reduces the probability of happening of such accident.
2, reduce the workload of system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff, it is more efficient.The big data management system, is able to use correlation and pushes away
The reasoning and comprehensive analysis that collected data are carried out with correlation are managed, system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff is helped to capture relevant issues
Present and following prediction uses water trend, while useless information is fallen in automatic fitration, and valuable information is supplied to the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties
Staff greatly reduces amount of reading；The water consumption system of machine learning based on big data can also to before use water
It measures result and carries out intelligent retention, analysis result and resolution policy before saving, convenient for the quick solution of similar problems later,
The workload for greatly reducing system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff improves its working efficiency.
3, precise solution is provided, specific aim is stronger.In traditional system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties's water supply work, due to simple and crude equipment and
Impolitic method, the scheme that system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff finds the problem and proposes is not enough precisely and thorough in terms of suggestion and analysis,
Therefore usually ignored by policymaker；The present invention uses the method for machine learning to provide commenting for a quantization for system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff
Estimate tool, the analysis that incoherent factor carries out system will be seemed in system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties's routine work, finds out connection between things and interior
It in rule, allows system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff that can obtain more accurate data in a short time, to obtain more detailed report, allows
Policymaker payes attention to various as a result, fundamentally solving the problems in system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties's routine work.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of present system.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the present invention provides a kind of technical solution: a kind of water per analysis system based on big data machine learning
System, comprising:
Data acquisition module 100, for acquiring the data of city pipe network key position, including flow, pressure, chlorine residue and turbid
Spend real time data；
Picture, figure and monitoring data can use digital camera and high-definition camera, be converted to using CCD imaging original part
For digital signal for computer disposal, common equipment includes mobile phone camera, slr camera, card type camera etc..
Clearly image or video, including PDF (format are provided using high-precision digital camera or video camera for system
The text pattern of change, conventional belt picture combination use the image that can search for of text, MRC, PDF/A), JPG, DOC, TXT, XPS etc.
City pipe network communicating terminal 101 is used for the collected real-time data transmission of data acquisition module 100 to database
Memory module 102；
Data are carried out the classification and filing of system, by the data put in order with data packet by database storage module 102
Form is sent to data preprocessing module 103；
Data preprocessing module 103 rejects underproof data, retains crucial core data, and to core
Data are saved, and rear end records the timing node of shortage of data；
Core data server 104 is handled and is calculated to the core data of reservation, and Various types of data result is saved
In core data library module 105, by the conclusion and integration of big data, to water consumption the case where carries out overall merit and feedback；
System prejudges module 106, in conjunction with the case where water consumption, overall merit and feedback information, in the pipe network of city whether
There are the district systems of unreasonable use of water to be prejudged；
Treatment mechanism module 107 needs the measure taken to provide conductive suggestion the accident of generation, and to final place
Reason result is fed back；
The data acquisition module 100 is connect with city pipe network communicating terminal 101, city pipe network communicating terminal 101 and number
According to 102 communication connection of library memory module, database storage module 102 is connect with data preprocessing module 103, data prediction mould
Block 103 is connect with core data server 104, and core data server 104 is connected separately with core data library module 105 and is
System anticipation module 106, system anticipation module 106 are connect with treatment mechanism module 107.
The measuring instrument of the data acquisition module 100 is installed on the key that caliber in the pipe network of city is DN100 or more
On pipeline, real-time acquisition and recording flow, pressure, chlorine residue and turbidity real time data, and convert the data into computer and be capable of handling
Text, figure, image, video or audio data.
The database storage module 102 include large capacity memory devices, for by collected number, text,
Picture, audio, video data be processed into convenient for storage data format, to all kinds of pipe network real time datas carry out data preservation,
The operations such as increase, deletion, update.
The database storage module 102 includes computer server, each for data acquisition module 100 to be collected into
Kind of real time data carries out necessary valence working process and calculating, and treated data and calculated result are further transferred to number
Data preprocess module 103.
The data preprocessing module 103 is connect with core data server 104, and different types of data are located in advance
Reason, including the operation such as arrangement, formatting, rejecting, screening, data are uniformly processed, and transfer data to core data
It is further processed in library.
It may be preferred that the core data server 104 includes that Correlation Reasoning module and forecast analysis intelligence are retained
Module compares the data that system stores for the analysis to various water consumptions, forms final water consumption report and knot
Fruit.
It is most important in decision logic function summarization generation in big data machine learning to seek to accurately find program
In logic sentence null point, the often insensitive global analysis of our passage paths, syntax tree such as simple based on abstract syntax tree
It searches for and determines that deposits in program sentences sky test point.However by the search of simple syntax tree can only search it is literal sentence null point,
For semantic level to sentence this method of null point often helpless, we, which use, in this case sentences empty check technology,
Namely certain mapping relations is established on judging point, constantly detect the point after mapping, so that available more accurate
Sentence null point.
It is a complementary process, this process that do-nothing function summarization generation and transmitting are sentenced in big data machine learning
It is important that being utilized in program abstraction expression: function topological sequence.Due to having used function call topological sorting, so that
Code scans are always since the bottom node of point of invocation.This guarantees, when in analysis, certain is function, intrinsic call
The function abstract of subfunction is that oneself is analyzed and instantiated and records.For the function of bottom, significant proportion is all journey
The library function of sequence programming language will take the mode for reading external file.The function abstract of library function will be by manually summarizing simultaneously
Record.In bottom-up defects detection, abstract will be also communicated up step by step, be realized in function call by this method
The instantiation of function abstract and transmitting.
The core data server 104 is installed on the central server of water per analysis system, for collected
Various data are calculated and are handled, and the core data server 104 is installed on the water consumption point of big data machine learning
The central server cluster of analysis system.
The core data server 104 is connected with core data library module 105, for the big data data mining and
Data analysis, and respond inquiry, retrieval, modification, deletion, output, the printing, push operation of user.It can further run
Correlation Reasoning module and intelligent retention module, summarize the mass data in data analysis process, are concluded, therefrom looked for
Inherent law and causality out, and with the visualization analysis technique and data mining technology of big data, find out in data
Rule, common problem and development trend.
The core data library module 105 is the memory devices of large capacity, associated with core data server 104,
For preprocessed data, Correlation Reasoning results of intermediate calculations needed for handling, saving water consumption management system, save core number
Inherent rule, causality and the retention result provided according to server 104.
A kind of water per analysis method based on big data machine learning, includes the following steps:
S1, by data acquisition module 100 acquire city pipe network key position data, including flow, pressure, chlorine residue and
Turbidity real time data；
S2, city pipe network communicating terminal 101 receive the collected data of data acquisition module 100, and data are passed in real time
It is defeated to arrive database storage module 102；
S3, the classification and filing that data are carried out to system by database storage module 102, by the data put in order with number
Data preprocessing module 103 is sent to according to the form of packet；
S4, underproof data are rejected by data preprocessing module 103, retains crucial core data, and
Core data is saved, rear end records the timing node of shortage of data；
S5, the core data retained by 104 Duis of core data server are handled and are calculated, and by Various types of data knot
Fruit is stored in core data library module 105, by the conclusion and integration of big data, to water consumption the case where carry out overall merit and
Feedback；
S6, the case where module 106 combines water consumption, overall merit and feedback information are prejudged by system, to city pipe network
In prejudged with the presence or absence of the district system of unreasonable use of water；
S7, final, the accident occurred by 107 Duis for the treatment of mechanism module needs the measure taken to provide conductive suggestion,
And final processing result is fed back.
Abstract syntax tree module is mainly and carries out initial grammer to source program to be abstracted in logic judgment, each sentence,
The definition of expression formula, function or variable is indicated using the node having in tree, and supports to carry out in abstract syntax tree
Search.By traversal of tree, upper layer user is enabled to inquire relevant function, variable, expression formula and their attribute special
Value indicative.
By being just called the topological sorting of relationship to all functions in the program abstraction modelling phase, if wherein deposited
Ring operation will be then carried out brokenly in function call ring, so that the sequence list an of scanning analysis can be finally obtained, it is subsequent to lack
Falling into the pattern analysis stage is also to carry out according to this sequence.In the generation module of function abstract, if passing through this function call
Sequence list carry out abstract instantiation, it is ensured that in the Defect Scanning analysis phase, the function abstract of subfunction must be generated
It finishes.
The attribute information for having correlated variables in controlling stream graph node includes block information etc., and the section codomain of variable is direct
Determine the execution route of program, and the section codomain of variable can then pass through previous research achievement: the data flow in abstract section
Analysis is to calculate.
Logic judgment is the rarefaction representation about variable data stream information using chain and definition-use chain is defined, and is while quilt
It extracts, and is typically expressed as list structure.Their abstract representations are from variable-definition basic statement block position to variable
Using a dual pair set function of sentence basic block position, each, which defines or uses, corresponds to a set.' from definition
Using in chain, energy is so efficient and convenient that find the definition position of some variable or all use positions in program.These information are
It checks whether variable codomain state changes and provides technical support.
System anticipation module 106 in the step S6 is directed to the integrality of the data of acquisition and accuracy is judged,
The relevance between data is excavated, if beat is excessive or too small before and after data, data can be isolated for system, and maintenance data
Previous big data in library, extracts the data of the period, with the method for machine learning, provides and meets the period
Data.
The related data that system anticipation module 106 transmits core data server 104 judges, prevent due to
The data distortion that data acquisition module 100 and city pipe network communicating terminal 101 upload, guarantees the real reliability of data, for
After the data of upload are prejudged, the related data in database is compared and analyzed, guarantees the true of data.
Treatment mechanism module 107 in the step 7 prejudges the data type that module 106 provides according to system and is divided
Analysis, the number provided in conjunction with machine learning method are prejudged and are provided optimal solution it is suggested that there is abnormal place to data
Certainly scheme.
The treatment mechanism module 107 is used to track abnormal data, is built according to the correlation that system anticipation provides
View instructs staff to carry out the work such as maintenance and the reinspection of pipe network to the place of data exception.
It further include Cloud Server 108, treatment mechanism module 107 will prejudge and provide best solution and is sent to cloud clothes
Business device 108, Cloud Server 108 and user terminal communication connection；The user terminal includes computer, smart phone or IPAD,
User carries out the tracking and feedback of event by computer, smart phone or IPAD terminal.
Wherein, after big data machine learning is stored and is analyzed for the Various types of data in pipe network, the processing in system
Various types of data is carried out Put on file and marked by calculation mechanism, and the abnormal point of data is divided, is with guarantee the later period
Operation in system is supplemented for various data, and the incremental result to various water consumptions carries out statistical classification, with most
The system of a perfect solution pipe network water consumption accident is presented eventually.
Water per analysis system of the invention is the product of big data centralized processing operation and veritification, small for solving city
Area, big water user are analyzed with regimen condition, formulate water supply.Be conducive to the water regulation scheme of the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties and the system of water supply
It is fixed, it can directly know the daily work of the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties.
The correlation of Function feature information representative function internal influence Function Call Context is used with big data machine learning
The logic judgment information and influence function of variable call the dereference information of the correlated variables (Reference Type Variable) of context；Then
Setting constraint information indicates influence after the function call to program context.
With in big data machine learning, the extraction that logic sentences the opposite dereference feature of extraction of sky feature is more complex, because
Dereference feature only need to carry out searching judgement in syntactic level, and to sentence sky feature then different for logic.
With in big data machine learning, when handling the logic judgment carried out between two variables, a mould will create first
Type establishes model mapping relations to two variables, and will be set as 0.Then range analysis is carried out to from variable, if walked herein
Less than its codomain information, the codomain from variable is exactly analyzed since this function with data stream analysis techniques.Analytic process
In if encountered when participating in another logic judgment from variable, use similar method a pair of newly to judge relationship for this
Variable establishes model, and the master variable in newly-established model is just the slave variable in first model at this time, and by flag bit
It is set as 1, indicates that this is the interim of an intermediate analysis, does not have to create characteristic information abstract for it.
With in big data machine learning, Function feature information unit has recorded influence function in a function and calls context
Relevant variable sentence sky information or dereference operation information.Empty behaviour is sentenced in case of multiple logic in a function
Make, then also only note is primary, is also similarly equally, all only to record whether the function has and be not recorded in function for dereference
Concrete operations are had an effect a little.
With in big data machine learning, system library function can not establish abstract syntax tree with traversal source code to extract function
Corresponding information carries out function summarization generation, but this class function is present in really and largely in program called again.
Water per analysis system of the invention can be joined with other pipe network monitoring systems, pipe network model management system
Operation is closed, and the data of various systems are subjected to docking exchange, greatly improves the water per analysis of big data machine learning
The efficiency of system facilitates and integrates the existing system of the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties.
Water per analysis system of the invention can be used for the push of the analysis result of water consumption, and user can pass through calculating
The terminal devices such as machine, smart phone, IPAD check various reports and correlation analysis result.
Replace the artificial analysis method calculated and performance model is built using big data machine learning, calculated result is more quasi-
Really；Reduce the workload of system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties staff, it is more efficient；Accurate solution is provided, specific aim is stronger；Collected processing
Data it is relatively reliable, it is with a high credibility, can directly instruct the production work of the system of appointing national minority hereditary headmen in the Yuan, Ming and Qing Dynasties.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (10)
1. a kind of water per analysis system based on big data machine learning characterized by comprising
Data acquisition module (100), for acquiring the data of city pipe network key position, including flow, pressure, chlorine residue and turbidity
Real time data；
City pipe network communicating terminal (101) is used for data acquisition module (100) collected real-time data transmission to database
Memory module (102)；
Data are carried out the classification and filing of system, by the data put in order with the shape of data packet by database storage module (102)
Formula is sent to data preprocessing module (103)；
Data preprocessing module (103), underproof data are rejected, and retain crucial core data, and to core number
According to being saved, rear end records the timing node of shortage of data；
Core data server (104) is handled and is calculated to the core data of reservation, and Various types of data result is stored in
Core data library module (105), by the conclusion and integration of big data, to water consumption the case where carries out overall merit and feedback；
Whether system prejudges module (106), in conjunction with the case where water consumption, overall merit and feedback information, to depositing in the pipe network of city
It is prejudged in the district system of unreasonable use of water；
Treatment mechanism module (107) needs the measure taken to provide conductive suggestion the accident of generation, and to final processing
As a result it is fed back；
The data acquisition module (100) connect with city pipe network communicating terminal (101), city pipe network communicating terminal (101) with
Database storage module (102) communication connection, database storage module (102) are connect with data preprocessing module (103), data
Preprocessing module (103) is connect with core data server (104), and core data server (104) is connected separately with core number
According to library module (105) and system anticipation module (106), system anticipation module (106) is connect with treatment mechanism module (107).
2. the water per analysis system according to claim 1 based on big data machine learning, which is characterized in that the number
Being installed on caliber in the pipe network of city according to the measuring instrument of acquisition module (100) is to adopt in real time on the crucial pipeline of DN100 or more
Collection record flow, pressure, chlorine residue and turbidity real time data, and convert the data into text, figure, figure that computer is capable of handling
Picture, video or audio data.
3. the water per analysis system according to claim 1 based on big data machine learning, which is characterized in that the number
Include the memory devices of large capacity according to library memory module (102), is used for collected number, text, picture, audio, view
Frequency carries out the preservations of data, increase, deletion, more according to the data format being processed into convenient for storage, to all kinds of pipe network real time datas
It is new to wait operation.
4. the water per analysis system according to claim 1 based on big data machine learning, which is characterized in that the number
Data preprocess module (103) is connect with core data server (104), different types of data is pre-processed, including whole
Reason, format, reject, screening etc. operation, data are uniformly processed, and transfer data in core database carry out into
The processing of one step.
5. the water per analysis system according to claim 1 based on big data machine learning, which is characterized in that the core
Heart database module (105) is the memory devices of large capacity, associated with core data server (104), for handling, protecting
Preprocessed data needed for depositing water consumption management system, saves core data server at Correlation Reasoning results of intermediate calculations
(104) inherent rule, causality and the retention result provided.
6. a kind of water per analysis method based on big data machine learning, which comprises the steps of:
S1, the data that pipe network key position in city is acquired by data acquisition module (100), including flow, pressure, chlorine residue and turbid
Spend real time data；
S2, city pipe network communicating terminal (101) receive data acquisition module (100) collected data, and data are passed in real time
It is defeated to arrive database storage module (102)；
S3, the classification and filing that data are carried out to system by database storage module (102), by the data put in order with data
The form of packet is sent to data preprocessing module (103)；
S4, underproof data are rejected by data preprocessing module (103), retains crucial core data, and right
Core data is saved, and rear end records the timing node of shortage of data；
S5, the core data of reservation is handled and is calculated by core data server (104), and by Various types of data result
Be stored in core data library module (105), by the conclusion and integration of big data, to water consumption the case where carry out overall merit and
Feedback；
S6, the case where module (106) combine water consumption, overall merit and feedback information are prejudged by system, in the pipe network of city
It is prejudged with the presence or absence of the district system of unreasonable use of water；
It is S7, final, need the measure taken to provide conductive suggestion by accident of the treatment mechanism module (107) to generation, and
Final processing result is fed back.
7. the water per analysis method according to claim 6 based on big data machine learning, which is characterized in that the step
System anticipation module (106) in rapid S6 is judged for the integrality and accuracy of the data acquired, is excavated between data
Relevance, if beat is excessive or too small before and after data, data can be isolated for system, and previous in maintenance data library
Big data extracts the data of the period, with the method for machine learning, provides the data for meeting the period.
8. the water per analysis method according to claim 7 based on big data machine learning, which is characterized in that the step
Treatment mechanism module (107) in rapid 7 prejudges the data type that module (106) provide according to system and is analyzed, in conjunction with machine
The number that learning method provides is prejudged and is provided best solution it is suggested that there is abnormal place to data.
9. the water per analysis method according to claim 8 based on big data machine learning, which is characterized in that further include
Cloud Server (108), treatment mechanism module (107) will prejudge and provide best solution and be sent to Cloud Server (108),
Cloud Server (108) and user terminal communication connection.
10. the water per analysis method according to claim 9 based on big data machine learning, which is characterized in that described
User terminal includes computer, smart phone or IPAD, and user carries out event by computer, smart phone or IPAD terminal
Tracking and feedback.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554608.3A CN109816428A (en) | 2018-12-18 | 2018-12-18 | A kind of water per analysis system and method based on big data machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811554608.3A CN109816428A (en) | 2018-12-18 | 2018-12-18 | A kind of water per analysis system and method based on big data machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109816428A true CN109816428A (en) | 2019-05-28 |
Family
ID=66602163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811554608.3A Pending CN109816428A (en) | 2018-12-18 | 2018-12-18 | A kind of water per analysis system and method based on big data machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109816428A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737272A (en) * | 2020-06-02 | 2020-10-02 | 脑谷人工智能研究院(南京)有限公司 | Big data automatic management platform capable of interactively displaying various indexes |
| CN114579686A (en) * | 2022-03-11 | 2022-06-03 | 澜途集思生态科技集团有限公司 | Dynamic system and method of basin water quality and water quantity mechanism model |
| CN114611764A (en) * | 2022-02-18 | 2022-06-10 | 济南优格信息科技有限公司 | Monitoring and early warning method for enterprise industrial water abnormity in specific area |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101286132A (en) * | 2008-06-02 | 2008-10-15 | 北京邮电大学 | Test method and system based on software defect mode |
| US20100141459A1 (en) * | 2007-05-04 | 2010-06-10 | Suez Environnement | Method and installation for real-time inspection of the quality of water in a delivery network |
| CN101894064A (en) * | 2009-05-21 | 2010-11-24 | 北京邮电大学 | Method for testing software by applying across function analysis |
| CN104899147A (en) * | 2015-06-19 | 2015-09-09 | 北京理工大学 | Code static analysis method oriented to security check |
| CN107193742A (en) * | 2017-05-23 | 2017-09-22 | 电子科技大学 | A kind of symbolism function digest algorithm of path-sensitive based on state |
| CN108052540A (en) * | 2017-11-22 | 2018-05-18 | 永高股份有限公司 | A kind of pipeline fault anticipation and preprocess method based on GIS pipe network systems |
-
2018
- 2018-12-18 CN CN201811554608.3A patent/CN109816428A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100141459A1 (en) * | 2007-05-04 | 2010-06-10 | Suez Environnement | Method and installation for real-time inspection of the quality of water in a delivery network |
| CN101286132A (en) * | 2008-06-02 | 2008-10-15 | 北京邮电大学 | Test method and system based on software defect mode |
| CN101894064A (en) * | 2009-05-21 | 2010-11-24 | 北京邮电大学 | Method for testing software by applying across function analysis |
| CN104899147A (en) * | 2015-06-19 | 2015-09-09 | 北京理工大学 | Code static analysis method oriented to security check |
| CN107193742A (en) * | 2017-05-23 | 2017-09-22 | 电子科技大学 | A kind of symbolism function digest algorithm of path-sensitive based on state |
| CN108052540A (en) * | 2017-11-22 | 2018-05-18 | 永高股份有限公司 | A kind of pipeline fault anticipation and preprocess method based on GIS pipe network systems |
Non-Patent Citations (2)
| Title |
|---|
| 唐冬致: "GPRS技术在供水管网监测系统中的应用研究", 《安徽电子信息职业技术学院学报》 * |
| 唐冬致: "GPRS技术在供水管网监测系统中的应用研究", 《安徽电子信息职业技术学院学报》, no. 01, 20 February 2005 (2005-02-20), pages 62 - 63 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737272A (en) * | 2020-06-02 | 2020-10-02 | 脑谷人工智能研究院(南京)有限公司 | Big data automatic management platform capable of interactively displaying various indexes |
| CN114611764A (en) * | 2022-02-18 | 2022-06-10 | 济南优格信息科技有限公司 | Monitoring and early warning method for enterprise industrial water abnormity in specific area |
| CN114611764B (en) * | 2022-02-18 | 2024-09-20 | 济南优格信息科技有限公司 | Abnormal monitoring and early warning method for industrial water of enterprises in specific area |
| CN114579686A (en) * | 2022-03-11 | 2022-06-03 | 澜途集思生态科技集团有限公司 | Dynamic system and method of basin water quality and water quantity mechanism model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113392227B (en) | Metadata knowledge graph engine system oriented to rail transit field | |
| CN103631882B (en) | Semantization service generation system and method based on graph mining technique | |
| CN106067094A (en) | A kind of dynamic assessment method and system | |
| CN107886238A (en) | A kind of business process management system and method based on mass data analysis | |
| CN109816428A (en) | A kind of water per analysis system and method based on big data machine learning | |
| CN106681300A (en) | Data clustering analysis method and system of power devices | |
| CN112241402A (en) | Empty pipe data supply chain system and data management method | |
| CN116976043A (en) | Knowledge graph-based intelligent auxiliary decision-making method for SDSS (Standard data System) power grid | |
| CN115423429A (en) | Multimode integrated distribution network operation system based on image and sound information | |
| CN115983809B (en) | Enterprise office management method and system based on intelligent portal platform | |
| CN112817958A (en) | Electric power planning data acquisition method and device and intelligent terminal | |
| CN113269435B (en) | New energy station running state coupling monitoring and evaluating system | |
| CN111125450A (en) | Management method of multilayer topology network resource object | |
| CN118013825A (en) | Multi-level multi-type city space-time collaborative design method, system, terminal and medium | |
| Liu et al. | [Retracted] Economic Benefit Evaluation and Analysis Based on Intelligent Agriculture Internet of Things | |
| CN116795816A (en) | Stream processing-based multi-bin construction method and system | |
| CN116467437A (en) | Automatic flow modeling method for complex scene description | |
| Xu | Research on enterprise knowledge unified retrieval based on industrial big data | |
| CN109379219A (en) | TMS and mobile O&M terminal towards power communication scene share exchange method | |
| CN109325700A (en) | Multi-point remote cooperation interaction method based on power telecom network O&M | |
| Chen et al. | Application of data mining technology and intelligent information technology in the construction and management of the water conservancy project in Area A | |
| Li | Construction of an interactive sharing platform for competitive intelligence data of marine resources under the background of intelligence construction | |
| CN117934209B (en) | Regional power system carbon emission big data analysis method based on knowledge graph | |
| Ma et al. | Data management of salt cavern gas storage based on data model | |
| Cheng et al. | Design of Digital Campus Platform Data Integration System Based on Xml |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190528 |