CN112463841A - Intelligent decision-making and accurate pushing method and engine based on industrial big data - Google Patents
Intelligent decision-making and accurate pushing method and engine based on industrial big data Download PDFInfo
- Publication number
- CN112463841A CN112463841A CN202011211449.4A CN202011211449A CN112463841A CN 112463841 A CN112463841 A CN 112463841A CN 202011211449 A CN202011211449 A CN 202011211449A CN 112463841 A CN112463841 A CN 112463841A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- pushing
- rule
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004519 manufacturing process Methods 0.000 claims abstract description 30
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 39
- 238000012545 processing Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 8
- 230000001174 ascending effect Effects 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent decision and accurate push method and an engine based on industrial big data, which comprises the following steps: s1: a user inputs a detailed pushing decision requirement according to the self post role and the service requirement by logging in a user management unit, and forms a user requirement portrait; s2: the user inputs and stores the self subscription information and the reference rule through the user information unit and summarizes the information and the reference rule to the user database; s3: the invention relates to the technical field of big data, and particularly relates to a method for establishing a user target resource database according to a subsystem type by combining the requirement of user subscription information. According to the method and the engine for intelligent decision and accurate pushing based on the industrial big data, the data resources are searched and matched according to the user requirement sketch and the rules in the engine rule base, and then the data are pushed to the user in a visual mode, so that the difficulty of facing a large amount of industrial data accurate decision in production management of an enterprise manager can be reduced.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an intelligent decision-making and accurate pushing method and engine based on industrial big data.
Background
Under the new trend of the innovation of production and manufacturing technologies, along with the further deepened application of big data analysis and mining technologies, more and more manufacturing enterprises pay more attention to the high-efficiency, lean and intelligent management of links such as scientific research production and manufacturing on the premise that an informatization system is stable and reliable. Particularly, as the modern information system construction system of manufacturing enterprises is gradually improved, the amount of industrial big data in the production link is increased sharply, but the data utilization method and related systems are limited, so that the utilization depth of the industrial big data is insufficient, the utilization rate is not high, most modern manufacturing enterprises still depend on the experience of managers excessively in the aspects of scientific research, production and manufacturing link management, and particularly, as the transformation and upgrading process of the manufacturing enterprises is accelerated, the informatization construction degree is increasingly deepened, and the practical problems of heavy management tasks, high difficulty in accurate decision making, insufficient experience in coordination and policy making and the like in the links of scientific research, production and manufacturing and the like are more obvious and are shown in the following.
The information system construction and development system is gradually improved, various data volumes of the whole production process such as massive research and development, design, manufacture, inventory, operation and maintenance are increased suddenly, the data types are multiple, the dimensionality is complicated, the volume is large, data for effectively supporting the decision of a manager is easily submerged, the problems of heavy tasks, high difficulty and the like are faced when related management work is developed by relying on the traditional management experience, the decision and the strategy progress of the manager are seriously influenced, and although the patent 'APP pushing method and engine system thereof' (application number CN107609086A) provides a mobile service pushing method, the mobile service pushing method is only limited to the decision pushing of specific services and is insufficient in flexibility. Although an information pushing method, an information pushing device and a mobile terminal (application number CN109413216A) are proposed in the patent, the method does not solve the multi-dimensional decision problem, and the application scenario is single and is difficult to be applied to the manufacturing type enterprise scenario of complex production.
In addition, managers facing massive industrial big data are difficult to see problems and make decisions comprehensively based on experience, once the strategies are wrongly implemented, the scientific research and production management of enterprises is influenced, serious managers influence the production and manufacturing progress of the enterprises, and even cause great economic loss.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent decision-making and accurate pushing method and engine based on industrial big data, and solves the problems that a manufacturing enterprise manager is difficult to make an accurate decision on massive industrial big data and the like.
In order to achieve the purpose, the invention is realized by the following technical scheme: an intelligent decision-making and accurate pushing method based on industrial big data comprises the following steps:
s1: a user inputs a detailed pushing decision requirement according to the self post role and the service requirement by logging in a user management unit, and forms a user requirement portrait;
s2: the user inputs and stores the self subscription information and the reference rule through the user information unit and summarizes the information and the reference rule to the user database;
s3: establishing a user target resource database according to the subsystem type by combining the requirement of user subscription information, extracting related data of the enterprise subsystem in the data resource pool, backing up the related data into the target resource database, and forming a data sample set to be analyzed;
s4: and transferring the data of the target data resource database into an industrial big data processing unit, and firstly carrying out preprocessing such as extraction, main feature selection, data label marking, data classification and the like on the target data. Then loading the preprocessed standard data, analyzing and mining the data according to data characteristics by using a Hadoop analysis tool, and finally successfully displaying the data according to characteristic attribute parameters and the like;
s5: the mining analysis result is summarized into a result base of a system pushing engine according to the type of the user requirement;
s6: and performing rule matching calculation according to the analysis result and the user requirement and forming an auxiliary decision support result, wherein the matching process specifically comprises the following steps:
(4) the number of samples in the result to be matched is N, and the result set is characterized in that:
TK＝{tk|k＝1,2,3,K,N}
the number of parameters of each sample is k, and the characteristic TCThe expression is as follows:
TC＝{tc1,tc2,L,tck}
(5) and carrying out constraint processing on the dimension, the data relation and the like of the analysis result according to the external constraint conditions defined by the user and the internal logical relation of the constraint rule base.
R constraint rule base rules are configured by userOThe parameter variable is r, m are counted, the weight of a single rule is gammaiAnd configuring a rule expression in the rule base as follows:
RO＝{γ1r1,γ2r2,γ3r3L,γmrm0,1, 2.) and γ1+γ2+γ3+L+γm＝1
Ninthly according to gammaiThe factors rank the rules of the constraint rule base, and the limiting condition of the maximum user expectation value is as follows:
γmaxi＝{max{γ1,γ2,γ3L,γm}i|i＝1,2,3,L m}
if the dominant feature of the user in the frequency band (R) is G, the sample parameters are sorted under the dominant feature as follows:
Rank(TC|G)＝{tci|i＝1,2,L,m}
11 ascending rule R obtained from step (I) (-)iComprises the following steps:
Ri＝{R1,R2,L,Rm}
the ordering formula under the constraint rule is Rank (T)C/Ri) Is expressed as
Rank(TC|R)＝{tci|i＝1,2,L,m}
12 in (iv), the stronger the ascending restriction rule is, the greater the restriction strength on the sample feature is, the worse the correlation with the user expectation is. The relevance of the sample single characteristic value of the user expected result under the constraint rule condition is Pt, and the matching calculation formula is as follows:
The Pt set under multidimensional is:
Pt＝{Pti|i＝1,2,3L}
13 user expectation value result sorting form is relevance sorting corresponding to E
Rank(E)＝Rank{EPti|i＝1,2,3L}
Let the dimension W the single dimension weight be Ω, expressed as:
W＝{Ω1,Ω2,Ω3L, Ω s0,1, 2.) and Ω1+Ω2+Ω3+L+Ωs＝1
14 the final result Ed output by the push engine is:
Rank(Ed)＝Rank{Ωj*(EPti)|i＝1,2,3L m；j＝1,2,3L s}
(6) and by combining a pushing rule base, the pushing rules defined for the user mainly comprise local link result pushing, dimension reduction result pushing and the like, so that the complexity of the pushing result is simplified, and the pushing timeliness is improved.
③ local pushing link passing through limitation TKThe range of samples, the number of samples N is reduced;
dimension reduction pushing is to reduce the number of the characteristic dimensions s of the single dimension weight omega in the dimension parameter W by reducing the dimension parameters of the result to be pushed, and the result Ed (k) output by the dimension reduction k engine is set as follows:
Rank[Ed(k)]＝Rank{Ωj*(EPti)|i＝1,2,3L m；1≤k≤s}；
s7: the user triggers the rule base through the user management unit, configures parameters in the rule base and completes the configuration of the analysis result before output;
s8: after constraint processing is carried out on the rule base, the results in the result base are pushed to the user in a visual form or a text form by a pushing engine.
Further, the push engine unit has a relevance rule, and under the condition that the restriction rule is stronger, the greater the restriction strength of the sample features in the result to be matched is, the worse the relevance to the user expectation is, the value range of the relevance is between 0 and 1 (including 0 and 1), and the push engine unit specifically supports two push modes of active query and passive query.
Further, the engine based on the industrial big data intelligent decision and accurate pushing comprises a user management information unit, a data resource pool unit, an enterprise subsystem data unit, an industrial big data processing center, a pushing engine unit and a user information unit, wherein the pushing engine unit can finish the functions of preheating, loading and temporary storage of target data to be analyzed, and can realize rapid data reading operation in a non-power-down mode, the pushing engine unit comprises functional modules such as a matching rule base, a constraint rule base, a pushing rule base and a representation rule base, the pushing engine unit can finish the operation functions such as matching calculation, constraint ordering, result screening and pushing of results to be pushed according to the matching rule base, the pushing engine rule base is started by a user through a triggering mechanism of the user management unit, and the user management unit is started to trigger the pushing engine rule base.
Further, the user information management unit comprises basic information, subscription information, a reference rule, a query subject, a category option, a keyword, a constraint condition and a search vertical type.
Further, the data resource unit comprises a user database and a subsystem database.
Further, the subsystem data unit comprises supplier system data, production process system data, process design and production data, virtual simulation data, test detection data, unqualified lists, equipment management and control system data, remote quality system data, warehousing system data and other system data.
Further, the industrial big data processing center comprises the following steps of preprocessing, tool, analysis, characteristic attribute and relation display: the preprocessing comprises input extraction processing, main feature selection, label marking, dimensionality reduction expression, data classification operation and data normalization; the tool comprises a data preheating loading tool, a temporary storage tool, a Hadoop analysis tool and a multidimensional expression tool; the analysis comprises data clustering analysis, tuple relation analysis, topology analysis and logic analysis.
Further, the user information unit includes key data analysis, decision data analysis, user requirements, and other requirements.
Further, still including embracing the pole, one side of embracing the pole is provided with the display to embrace fixedly connected with limiting plate on the pole, one side of display is rotated and is connected with first kelly and second kelly.
Further, the first clamping rod is matched with the second clamping rod, and the second clamping rod is fixedly connected with the first clamping rod through a bolt.
Compared with the prior art, the invention has the beneficial effects that:
according to the method and the engine for intelligent decision and accurate pushing based on the industrial big data, by drawing images according to user requirements, data screening is carried out on a target data resource library in an enterprise subsystem, mining and analysis of required results are carried out through an industrial big data processing center unit, data resource searching and matching are carried out according to rules in an engine rule library, and then pushing is carried out on users in a visual mode, so that the difficulty of facing an enterprise manager to accurate decision of the mass industrial data in production management can be reduced, the dimensionality of a big data analysis result is reduced by relying on the engine rule library, the dominant features are extracted to be pushed in time, the scientificity and timeliness of the decision are enhanced, and the efficiency and the management capacity of the enterprise in the production management are improved.
Drawings
FIG. 1 is a block diagram of a system architecture of a first embodiment of the present invention;
FIG. 2 is a block diagram of the business process of the present invention;
FIG. 3 is a schematic structural diagram of a second preferred embodiment of the present invention;
fig. 4 is a schematic structural diagram of a rear view portion of the display shown in fig. 3.
In the figure: 1-holding pole, 2-holding pole, 3-holding pole, 4-first clamping pole, 5-first clamping pole and 6-bolt.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
First embodiment
Referring to fig. 1-2, the present invention provides a technical solution: an intelligent decision-making and accurate pushing method and engine based on industrial big data comprises the following steps:
s1: a user inputs a detailed pushing decision requirement according to the self post role and the service requirement by logging in a user management unit, and forms a user requirement portrait;
s2: the user inputs and stores the self subscription information and the reference rule through the user information unit and summarizes the information and the reference rule to the user database;
s3: establishing a user target resource database according to the subsystem type by combining the requirement of user subscription information, extracting related data of the enterprise subsystem in the data resource pool, backing up the related data into the target resource database, and forming a data sample set to be analyzed;
s4: and transferring the data of the target data resource database into an industrial big data processing unit, and firstly carrying out preprocessing such as extraction, main feature selection, data label marking, data classification and the like on the target data. Then loading the preprocessed standard data, analyzing and mining the data according to data characteristics by using a Hadoop analysis tool, and finally successfully displaying the data according to characteristic attribute parameters and the like;
s5: the mining analysis result is summarized into a result base of a system pushing engine according to the type of the user requirement;
s6: and performing rule matching calculation according to the analysis result and the user requirement and forming an auxiliary decision support result, wherein the matching process specifically comprises the following steps:
(7) the number of samples in the result to be matched is N, and the result set is characterized in that:
TK＝{tk|k＝1,2,3,K,N}
the number of parameters of each sample is k, and the characteristic TCThe expression is as follows:
TC＝{tc1,tc2,L,tck}
(8) and carrying out constraint processing on the dimension, the data relation and the like of the analysis result according to the external constraint conditions defined by the user and the internal logical relation of the constraint rule base.
15 the rules of the constraint rule base are configured by the user, and the configuration rule is ROThe parameter variable is r, m are counted, the weight of a single rule is gammaiAnd configuring a rule expression in the rule base as follows:
RO＝{γ1r1,γ2r2,γ3r3L,γmrm0,1, 2.) and γ1+γ2+γ3+L+γm＝1
16 according to gammaiThe factors rank the rules of the constraint rule base, and the limiting condition of the maximum user expectation value is as follows:
γmaxi＝{max{γ1,γ2,γ3L,γm}i|i＝1,2,3,L m}
17 if the user dominant feature is G, the sample parameters are sorted under the dominant feature as follows:
Rank(TC|G)＝{tci|i＝1,2,L,m}
18 ascending rule R obtained from step (I) (-)iComprises the following steps:
Ri＝{R1,R2,L,Rm}
the ordering formula under the constraint rule is Rank (T)C/Ri) Is expressed as
Rank(TC|R)＝{tci|i＝1,2,L,m}
The stronger the ascending restriction rule in (iv) 19 is, the greater the restriction strength on the sample feature is, the worse the correlation with the user's desire is. The relevance of the sample single characteristic value of the user expected result under the constraint rule condition is Pt, and the matching calculation formula is as follows:
The Pt set under multidimensional is:
Pt＝{Pti|i＝1,2,3L}
20 user expectation value result sorting form is relevance sorting corresponding to E
Rank(E)＝Rank{EPti|i＝1,2,3L}
Let the dimension W the single dimension weight be Ω, expressed as:
W＝{Ω1,Ω2,Ω3L, Ω s0,1, 2.) and Ω1+Ω2+Ω3+L+Ωs＝1
21 the final result Ed output by the push engine is:
Rank(Ed)＝Rank{Ωj*(EPti)|i＝1,2,3L m；j＝1,2,3L s}
(9) and by combining a pushing rule base, the pushing rules defined for the user mainly comprise local link result pushing, dimension reduction result pushing and the like, so that the complexity of the pushing result is simplified, and the pushing timeliness is improved.
Local pushing link passing limited TKThe range of samples, the number of samples N is reduced;
reducing the dimension pushing is to reduce the number of the characteristic dimensions s of the single dimension weight omega in the dimension parameter W by reducing the dimension parameter of the result to be pushed, and setting the result Ed (k) output by the dimension reduction k engine as follows:
Rank[Ed(k)]＝Rank{Ωj*(EPti)|i＝1,2,3L m；1≤k≤s}；
s7: the user triggers the rule base through the user management unit, configures parameters in the rule base and completes the configuration of the analysis result before output;
s8: after constraint processing is carried out on the rule base, the results in the result base are pushed to the user in a visual form or a text form by a pushing engine.
The specific operation in step S6 is:
(1) matching the rule base: and matching the analysis result with the user expectation according to the matching rule.
(2) Constraint rule base: and carrying out constraint processing on the dimension, the data relation and the like of the analysis result according to the external constraint conditions defined by the user and the internal logical relation of the constraint rule base.
(3) Pushing a rule base: the pushing rules defined for the user mainly include local link result pushing, dimension reduction result pushing and the like, so that the complexity of the pushing result is simplified, and the pushing timeliness is improved.
(4) A characterization rule base: and defining the number of the features, the dominant dimension of the data, the dominant features and the like of the representation of the result to be pushed for the user.
(5) The pushing mode is as follows: the method is characterized in that the working mode of the engine unit is set for a user, and the system can actively push the engine unit to a user or the user can inquire the engine unit by the user (called passive inquiry) in combination with the user requirement.
The push engine unit has a relevance rule, and under the condition that the limitation rule is stronger, the greater the limitation strength of the sample features in the result to be matched is, the worse the relevance with the expectation of the user is, the value range of the relevance is between 0 and 1 (including 0 and 1), and the push engine unit specifically supports two push modes of active query and passive query.
An engine based on intelligent decision and accurate push of industrial big data comprises a user management information unit, a data resource pool unit, an enterprise subsystem data unit, an industrial big data processing center, a push engine unit and a user information unit, wherein the push engine unit can finish the functions of preheating, loading and temporary storage of target data to be analyzed, and can realize rapid data reading operation in a non-power-down mode, the push engine unit comprises functional modules such as a matching rule base, a constraint rule base, a push rule base and a representation rule base, the push engine unit can finish the operation functions such as matching calculation of results to be pushed, constraint sequencing, result screening and push according to the matching rule base, and the push engine rule base is pushed, and a starting user of the rule base is triggered through a triggering mechanism of the user management unit.
The user information management unit comprises basic information, subscription information, a reference rule, a query subject, a category option, a keyword, a constraint condition and a search vertical type.
The method and the device are used for storing and managing the user information, are convenient for data pushing according to user habits, and are convenient for users to inquire.
The data resource unit comprises a user database and a subsystem database.
The user database provides different data for different users to achieve the effect of accurate pushing, and the system database is a unified storage center for all data.
The subsystem data unit comprises supplier system data, production process system data, process design and production data, virtual simulation data, test detection data, unqualified lists, equipment management and control system data, remote quality system data, warehousing system data and other system data.
According to a plurality of lists of different kinds of data, the user can conveniently and quickly inquire and the inquiry related content is pushed to the user.
The industrial big data processing center comprises the following steps of preprocessing, tool, analysis, characteristic attribute and relationship display: the preprocessing comprises input extraction processing, main feature selection, label marking, dimensionality reduction expression, data classification operation and data normalization; the tool comprises a data preheating loading tool, a temporary storage tool, a Hadoop analysis tool and a multidimensional expression tool; the analysis comprises data clustering analysis, tuple relation analysis, topology analysis and logic analysis.
And analyzing according to the big data, so that the pushed data more meets the retrieval requirements of the user.
The user information unit includes key data analysis, decision data analysis, user requirements, and other requirements.
And the required keywords are extracted according to the user retrieval information and then retrieved, so that the retrieval range is conveniently improved, and the accuracy of the data is analyzed, compared and arranged one by one and then pushed to the user.
Second embodiment
Referring to fig. 3 and fig. 4, based on the method and engine for intelligent decision and accurate push based on industrial big data provided in the first embodiment of the present application, a second embodiment of the present application provides another method and engine for intelligent decision and accurate push based on industrial big data. The second embodiment is only the preferred mode of the first embodiment, and the implementation of the second embodiment does not affect the implementation of the first embodiment alone.
Specifically, the difference between the method and the engine for the intelligent decision and the accurate pushing based on the industrial big data provided by the second embodiment of the application is that the method and the engine for the intelligent decision and the accurate pushing based on the industrial big data further comprise a holding pole 1, one side of the holding pole 1 is provided with a display 2, the holding pole 1 is fixedly connected with a limiting plate 3, and one side of the display 2 is rotatably connected with a first clamping rod 4 and a second clamping rod 5.
The first clamping rod 4 is matched with the second clamping rod 5, and the second clamping rod is fixedly connected with the first clamping rod 4 through a bolt 6.
When in work:
through fixing display 2 on embracing pole 1, improve the height of display 2, it carries out open air advertisement propelling movement to facilitate the use display 2, one side of first kelly 4 is fluted, there is the arch one side of second kelly 5, use through the cooperation of first kelly 4 and second kelly 5, bolt 6 passes first kelly 4 and second kelly 5 and conveniently rotates regulation with 2 chucking of display on embracing pole 1, can conveniently rotate the place direction of display 2 again, rethread limiting plate 3 is spacing to first kelly 4 and second kelly 5, prevent that display 2 from extending to embrace that pole 1 produces the ascending slip of vertical side.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An intelligent decision-making and accurate pushing method based on industrial big data comprises the following steps:
s1: a user inputs a detailed pushing decision requirement according to the self post role and the service requirement by logging in a user management unit, and forms a user requirement portrait;
s2: the user inputs and stores the self subscription information and the reference rule through the user information unit and summarizes the information and the reference rule to the user database;
s3: establishing a user target resource database according to the subsystem type by combining the requirement of user subscription information, extracting related data of the enterprise subsystem in the data resource pool, backing up the related data into the target resource database, and forming a data sample set to be analyzed;
s4: and transferring the data of the target data resource database into an industrial big data processing unit, and firstly carrying out preprocessing such as extraction, main feature selection, data label marking, data classification and the like on the target data. Then loading the preprocessed standard data, analyzing and mining the data according to data characteristics by using a Hadoop analysis tool, and finally successfully displaying the data according to characteristic attribute parameters and the like;
s5: the mining analysis result is summarized into a result base of a system pushing engine according to the type of the user requirement;
s6: and performing rule matching calculation according to the analysis result and the user requirement and forming an auxiliary decision support result, wherein the matching process specifically comprises the following steps:
(1) the number of samples in the result to be matched is N, and the result set is characterized in that:
TK＝{tk|k＝1,2,3,K,N}
the number of parameters of each sample is k, and the characteristic TCThe expression is as follows:
TC＝{tc1,tc2,L,tck}
(2) and carrying out constraint processing on the dimension, the data relation and the like of the analysis result according to the external constraint conditions defined by the user and the internal logical relation of the constraint rule base.
The rule of constraint rule base is configured by user, and the configuration rule is ROThe parameter variable is r, m are counted, the weight of a single rule is gammaiAnd configuring a rule expression in the rule base as follows:
RO＝{γ1r1,γ2r2,γ3r3L,γmrm0,1, 2.) and γ1+γ2+γ3+L+γm＝1
Is according to gammaiThe factors rank the rules of the constraint rule base, and the limiting condition of the maximum user expectation value is as follows:
γmaxi＝{max{γ1,γ2,γ3L,γm}i|i＝1,2,3,L m}
and thirdly, if the user leading characteristic is G, the sequencing of the sample parameters under the leading characteristic is as follows:
Rank(TC|G)＝{tci|i＝1,2,L,m}
fourthly, the ascending rule R obtained in the first stepiComprises the following steps:
Ri＝{R1,R2,L,Rm}
the ordering formula under the constraint rule is Rank (T)C|Ri) Is expressed as
Rank(TC|R)＝{tci|i＝1,2,L,m}
Fifthly, the stronger the ascending order limiting rule in the fourth step, the greater the limiting strength of the sample characteristics, the worse the correlation with the user expectation. The relevance of the sample single characteristic value of the user expected result under the constraint rule condition is Pt, and the matching calculation formula is as follows:
The Pt set under multidimensional is:
Pt＝{Pti|i＝1,2,3L}
sixthly, the relevance sequencing corresponding to the sequencing form of the result of the expected value of the user in E
Rank(E)＝Rank{EPti|i＝1,2,3L}
Let the dimension W the single dimension weight be Ω, expressed as:
W＝{Ω1,Ω2,Ω3L,Ωs0,1, 2.) and Ω1+Ω2+Ω3+L+Ωs＝1
Seventhly, the result Ed output by the final pushing engine is as follows:
Rank(Ed)＝Rank{Ωj*(EPti)|i＝1,2,3L m；j＝1,2,3L s}
(3) and by combining a pushing rule base, the pushing rules defined for the user mainly comprise local link result pushing, dimension reduction result pushing and the like, so that the complexity of the pushing result is simplified, and the pushing timeliness is improved.
Firstly, local pushing links pass through limitation TKThe range of samples, the number of samples N is reduced;
reducing dimensionality push, namely reducing the number of the characteristic dimensionality s of a single dimensionality weight omega in a dimensionality parameter W by reducing dimensionality parameters of a result to be pushed, and setting a result Ed (k) output by a dimensionality reduction k engine as follows:
Rank[Ed(k)]＝Rank{Ωj*(EPti)|i＝1,2,3L m；1≤k≤s}；
s7: the user triggers the rule base through the user management unit, configures parameters in the rule base and completes the configuration of the analysis result before output;
s8: after constraint processing is carried out on the rule base, the results in the result base are pushed to the user in a visual form or a text form by a pushing engine.
2. The method for intelligent decision and accurate pushing based on industrial big data according to claim 1, wherein: the push engine unit has a relevance rule, and under the condition that the limitation rule is stronger, the greater the limitation strength of the sample features in the result to be matched is, the worse the relevance with the expectation of the user is, the value range of the relevance is between 0 and 1 (including 0 and 1), and the push engine unit specifically supports two push modes of active query and passive query.
3. The industrial big data-based intelligent decision and accurate push engine according to claim 1, characterized in that: the system comprises a user management information unit, a data resource pool unit, an enterprise subsystem data unit, an industrial big data processing center, a push engine unit and a user information unit, wherein the push engine unit can complete the functions of preheating, loading and temporary storage of target data to be analyzed, and can realize the rapid data reading operation in a non-power-down mode, the push engine unit comprises functional modules such as a matching rule base, a constraint rule base, a push rule base and a representation rule base, the push engine unit can complete the operation functions such as matching calculation of results to be pushed, constraint sequencing, result screening and pushing according to the matching rule base, the push engine rule base is used, and a starting user of the rule base is triggered through a triggering mechanism of the user management unit.
4. The method and engine for intelligent decision and accurate pushing based on industrial big data according to claim 3, characterized in that: the user information management unit comprises basic information, subscription information, a reference rule, a query subject, a category option, a keyword, a constraint condition and a search vertical type.
5. The industrial big data-based intelligent decision and accurate pushing engine according to claim 3, characterized in that: the data resource unit comprises a user database and a subsystem database.
6. The industrial big data-based intelligent decision and accurate pushing engine according to claim 3, characterized in that: the subsystem data unit comprises supplier system data, production process system data, process design and production data, virtual simulation data, test detection data, unqualified lists, equipment management and control system data, remote quality system data, warehousing system data and other system data.
7. The industrial big data-based intelligent decision and accurate pushing engine according to claim 3, characterized in that: the industrial big data processing center comprises the following steps of preprocessing, tool, analysis, characteristic attribute and relationship display:
the preprocessing comprises input extraction processing, main feature selection, label marking, dimensionality reduction expression, data classification operation and data normalization;
the tool comprises a data preheating loading tool, a temporary storage tool, a Hadoop analysis tool and a multidimensional expression tool;
the analysis comprises data clustering analysis, tuple relation analysis, topology analysis and logic analysis.
8. The industrial big data-based intelligent decision and accurate pushing engine according to claim 3, characterized in that: the user information unit includes key data analysis, decision data analysis, user requirements, and other requirements.
9. The engine of claim 3, further comprising a holding pole, wherein a display is arranged on one side of the holding pole, a limiting plate is fixedly connected to the holding pole, and a first clamping rod and a second clamping rod are rotatably connected to one side of the display.
10. The industrial big data-based intelligent decision-making and accurate pushing engine of claim 93, wherein: the first clamping rod is matched with the second clamping rod, and the second clamping rod is fixedly connected with the first clamping rod through a bolt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011211449.4A CN112463841B (en) | 2020-11-03 | 2020-11-03 | Intelligent decision and accurate pushing method and engine based on industrial big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011211449.4A CN112463841B (en) | 2020-11-03 | 2020-11-03 | Intelligent decision and accurate pushing method and engine based on industrial big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112463841A true CN112463841A (en) | 2021-03-09 |
| CN112463841B CN112463841B (en) | 2023-04-21 |
Family
ID=74835852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011211449.4A Active CN112463841B (en) | 2020-11-03 | 2020-11-03 | Intelligent decision and accurate pushing method and engine based on industrial big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112463841B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884599A (en) * | 2021-03-22 | 2021-06-01 | 树根互联股份有限公司 | Custom furniture factory matching method and device and computer equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180089325A1 (en) * | 2016-09-26 | 2018-03-29 | Alibaba Group Holding Limited | Method, Apparatus and Client of Processing Information Recommendation |
| CN109413216A (en) * | 2018-12-29 | 2019-03-01 | 微梦创科网络科技（中国）有限公司 | A kind of information-pushing method, device and mobile terminal |
| CN109684537A (en) * | 2018-10-29 | 2019-04-26 | 昆明理工大学 | A kind of the knowledge resource intelligently pushing system and its method for pushing of Business Process-oriented |
| CN110059249A (en) * | 2019-04-03 | 2019-07-26 | 华为技术有限公司 | Method, terminal device and the system of personalized recommendation |
| CN110427472A (en) * | 2019-08-02 | 2019-11-08 | 深圳追一科技有限公司 | The matched method, apparatus of intelligent customer service, terminal device and storage medium |
| US20200162371A1 (en) * | 2018-11-20 | 2020-05-21 | Cisco Technology, Inc. | Route optimization using real time traffic feedback |
| US20200184278A1 (en) * | 2014-03-18 | 2020-06-11 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| CN111353013A (en) * | 2018-12-05 | 2020-06-30 | 中兴通讯股份有限公司 | Method and system for realizing intelligent delivery and reception |
| CN111435344A (en) * | 2019-01-15 | 2020-07-21 | 中国石油集团川庆钻探工程有限公司长庆钻井总公司 | Big data-based drilling acceleration influence factor analysis model |
-
2020
- 2020-11-03 CN CN202011211449.4A patent/CN112463841B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200184278A1 (en) * | 2014-03-18 | 2020-06-11 | Z Advanced Computing, Inc. | System and Method for Extremely Efficient Image and Pattern Recognition and Artificial Intelligence Platform |
| US20180089325A1 (en) * | 2016-09-26 | 2018-03-29 | Alibaba Group Holding Limited | Method, Apparatus and Client of Processing Information Recommendation |
| CN109684537A (en) * | 2018-10-29 | 2019-04-26 | 昆明理工大学 | A kind of the knowledge resource intelligently pushing system and its method for pushing of Business Process-oriented |
| US20200162371A1 (en) * | 2018-11-20 | 2020-05-21 | Cisco Technology, Inc. | Route optimization using real time traffic feedback |
| CN111353013A (en) * | 2018-12-05 | 2020-06-30 | 中兴通讯股份有限公司 | Method and system for realizing intelligent delivery and reception |
| CN109413216A (en) * | 2018-12-29 | 2019-03-01 | 微梦创科网络科技（中国）有限公司 | A kind of information-pushing method, device and mobile terminal |
| CN111435344A (en) * | 2019-01-15 | 2020-07-21 | 中国石油集团川庆钻探工程有限公司长庆钻井总公司 | Big data-based drilling acceleration influence factor analysis model |
| CN110059249A (en) * | 2019-04-03 | 2019-07-26 | 华为技术有限公司 | Method, terminal device and the system of personalized recommendation |
| CN110427472A (en) * | 2019-08-02 | 2019-11-08 | 深圳追一科技有限公司 | The matched method, apparatus of intelligent customer service, terminal device and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| YU GUO 等: "Enabling Privacy-Preserving Header Matching for Outsourced Middleboxes", 《2018 IEEE/ACM 26TH INTERNATIONAL SYMPOSIUM ON QUALITY OF SERVICE (IWQOS)》 * |
| 张永亮 等: "基于知识的智能指挥决策运行机制及其支撑技术研究", 《军事运筹与系统工程》 * |
| 王体春 等: "面向汽车发动机设计的可拓知识推送模型", 《华南理工大学学报(自然科学版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112884599A (en) * | 2021-03-22 | 2021-06-01 | 树根互联股份有限公司 | Custom furniture factory matching method and device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112463841B (en) | 2023-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8266147B2 (en) | Methods and systems for database organization | |
| US8131684B2 (en) | Adaptive archive data management | |
| Fayyad | Knowledge discovery in databases: An overview | |
| US6212526B1 (en) | Method for apparatus for efficient mining of classification models from databases | |
| CN106528599B (en) | A kind of character string Fast Fuzzy matching algorithm in magnanimity audio data | |
| CN104123346B (en) | A kind of structured data search method | |
| CN101119326B (en) | Method and device for managing instant communication conversation record | |
| EP3014488B1 (en) | Incremental maintenance of range-partitioned statistics for query optimization | |
| CN107729336A (en) | Data processing method, equipment and system | |
| US20100235347A1 (en) | Techniques for exact cardinality query optimization | |
| US20060242102A1 (en) | Relaxation-based approach to automatic physical database tuning | |
| CA2543401A1 (en) | System and method for classification of documents | |
| Ljosa et al. | Top-k spatial joins of probabilistic objects | |
| US20110191335A1 (en) | Method and system for conducting legal research using clustering analytics | |
| CN112508743B (en) | Technology transfer office general information interaction method, terminal and medium | |
| CN109299235A (en) | Knowledge base searching method, apparatus and computer readable storage medium | |
| US11847169B2 (en) | Method for data processing and interactive information exchange with feature data extraction and bidirectional value evaluation for technology transfer and computer used therein | |
| CN112463841A (en) | Intelligent decision-making and accurate pushing method and engine based on industrial big data | |
| Manne et al. | Text categorization with K-nearest neighbor approach | |
| CN109213793A (en) | A kind of stream data processing method and system | |
| Kontaki et al. | Continuous k-dominant skyline computation on multidimensional data streams | |
| Zhu et al. | Approximate continuous top-k query over sliding window | |
| Hassan et al. | Sampling technique selection framework for knowledge discovery | |
| CN115203136A (en) | Artificial intelligence management system based on big data | |
| CN114064821A (en) | Data resource classification organization method and system based on semantic recognition |
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 |