CN117077847A - On-line deduction and deduction visualization realization method based on business model - Google Patents
On-line deduction and deduction visualization realization method based on business model Download PDFInfo
- Publication number
- CN117077847A CN117077847A CN202310986830.5A CN202310986830A CN117077847A CN 117077847 A CN117077847 A CN 117077847A CN 202310986830 A CN202310986830 A CN 202310986830A CN 117077847 A CN117077847 A CN 117077847A
- Authority
- CN
- China
- Prior art keywords
- analysis
- deduction
- data
- model
- tasks
- 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
- 238000000034 method Methods 0.000 title claims abstract description 100
- 238000012800 visualization Methods 0.000 title claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 190
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 71
- 230000008569 process Effects 0.000 claims abstract description 57
- 230000000007 visual effect Effects 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims description 38
- 230000002159 abnormal effect Effects 0.000 claims description 33
- 238000010586 diagram Methods 0.000 claims description 12
- 238000013473 artificial intelligence Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000005065 mining Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 239000000446 fuel Substances 0.000 claims description 4
- 238000002347 injection Methods 0.000 claims description 4
- 239000007924 injection Substances 0.000 claims description 4
- 238000003064 k means clustering Methods 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 abstract description 4
- 238000004220 aggregation Methods 0.000 abstract description 4
- 238000000354 decomposition reaction Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000007418 data mining Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 239000007789 gas Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000008358 core component Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000010796 Steam-assisted gravity drainage Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online deduction and deduction visualization realization method based on a business model, which comprises the following steps: obtaining industrial data to be deduced; classifying the industrial data to obtain a plurality of sub-industrial data, and generating a plurality of analysis tasks; carrying out online deduction on a plurality of analysis tasks to obtain a plurality of visual algorithm models; and acquiring real-time data, and inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result. Classifying data to be deduced, generating a plurality of analysis tasks, scheduling applications to virtual and physical resources in different spaces by a scheduler for parallel calculation based on group intelligent computing capacity of a distributed cluster, and obtaining a visual algorithm model, so that the load and the complexity of the deduction based on a deduction platform in the prior art are reduced, the utilization rate of computing resources and the overall computing efficiency are improved, and the deduction evolution is subjected to process stage decomposition and aggregation processing in time.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an online deduction and deduction visualization implementation method based on a business model.
Background
At present, with the development of a big data intelligent processing platform, the intelligent capability of the existing enterprises is enabled, the production period of products is effectively shortened, and the utilization rate and the production efficiency of equipment are improved; the traditional business is promoted to be converted and upgraded to intelligent service, so that the scientific configuration of the existing production and service resources is optimized in a wider range, higher efficiency and more precision. The big data intelligent processing platform is based on a high-performance cloud computing environment, adopts core technologies such as edge computing, artificial intelligence, digital twin and the like, and realizes the depth fusion of data-driven information and entity space. The large data intelligent processing platform relates to deduction of a business model, and based on the visual algorithm model obtained by deduction, the large data intelligent processing platform is used as a core component for large data value mining, so that seamless fusion of client requirements and data values is realized.
In the prior art, when the business model is deduced, the deduction is performed based on the integral deduction platform, and various intelligent models are required to be called and various deduction operations are required to be performed in the deduction platform, so that the load of the deduction platform can be increased, meanwhile, the complexity in the deduction process is caused, the deduction speed is influenced, and the inaccuracy of the finally obtained deduction model is also caused.
Disclosure of Invention
The present invention aims to solve, at least to some extent, one of the technical problems in the above-described technology. Therefore, the invention aims to provide an online deduction and deduction visual implementation method based on a service model, which classifies data to be deducted, generates a plurality of analysis tasks, performs parallel computation on virtual and physical resources which are applied to different spaces through a scheduler based on group intelligent computing capability of a distributed cluster, obtains a visual algorithm model, reduces the load of deduction and the complexity of deduction based on a deduction platform in the prior art, improves the utilization rate of computing resources and the overall computing efficiency, and performs process stage decomposition and aggregation processing on deduction evolution in time. And inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result, so as to realize data mining and prediction.
In order to achieve the above objective, an embodiment of the present invention provides an online deduction and deduction visualization implementation method based on a service model, including:
obtaining industrial data to be deduced;
classifying the industrial data to obtain a plurality of sub-industrial data, and generating a plurality of analysis tasks;
carrying out online deduction on a plurality of analysis tasks to obtain a plurality of visual algorithm models;
and acquiring real-time data, and inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result.
According to some embodiments of the invention, the industrial data includes overall operational situation analysis data of the oil field and boiler early warning data; wherein,
the overall operation situation analysis data comprises statistics data of gas injection conditions, steam instructions, energy efficiency conditions, unqualified boilers, water supply, fuel and faults under different time dimensions, and a data diagram generated according to the statistics data;
the boiler early warning data comprises: based on the processing of the boiler data acquired in real time, corresponding data in the hearth, the convection section, the superheating section, the radiation section, the burner and the water supply pump are obtained.
According to some embodiments of the present invention, online deduction is performed on a plurality of parsing tasks to obtain a plurality of visualized algorithm models, including:
establishing a first queuing queue of a plurality of analysis tasks;
establishing a second queuing sequence comprising analytic nodes of the artificial intelligence model;
determining matched analysis nodes for analysis tasks, establishing an association relation between first sequence information of the analysis tasks in a first queuing queue and second sequence information of a second queuing sequence of the analysis nodes, and dispatching the analysis tasks to the corresponding analysis nodes according to the association relation;
based on the analytic data determined by each analytic node, a plurality of visual algorithm models are generated.
According to some embodiments of the invention, the artificial intelligence model comprises at least one of a multisource perception, a multiscale understanding, a population intelligence, a statistical analysis model, a data dimension reduction model, a classification/logistic regression model, a spatio-temporal representation, a decision and reasoning model, a trajectory mining model, a clustering and similarity model, a topic recommendation model, a model optimization method model.
According to some embodiments of the present invention, before acquiring real-time data, inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result, the method further includes:
adding an early warning rule and an early warning grade for the visual algorithm model;
sample data are acquired and input into a plurality of visual algorithm models to obtain risk early warning information, whether the risk early warning information is consistent with risk early warning information corresponding to the sample data or not is judged, and when the consistency is confirmed, the visual algorithm models are verified.
According to some embodiments of the present invention, in the online deduction process of the plurality of analysis tasks, the method further includes obtaining a previous model deduction amount, deduction efficiency, deduction status, service model analysis, evaluation of energy efficiency of the service, and process monitoring and displaying.
According to some embodiments of the present invention, after performing online deduction on a plurality of parsing tasks to obtain a plurality of visualization algorithm models, the method further includes:
obtaining and displaying a deduction result and deduction process data; the deduction process data comprise task information of analysis tasks, scheduling information and corresponding analysis nodes.
According to some embodiments of the invention, after obtaining the plurality of visualization algorithm models, the method further comprises:
monitoring model names, ports, positions and states of a plurality of visual algorithm models to obtain first monitoring data;
obtaining analysis data of model early warning rates and abnormal rates of a plurality of visual algorithm models to obtain second monitoring data;
monitoring the memory, the disk and the CPU of the operation node of the plurality of visual algorithm models to obtain third monitoring data;
judging whether the first monitoring data, the second monitoring data and the third monitoring data are abnormal or not, and sending out alarm prompt information when the abnormality exists.
According to some embodiments of the invention, classifying the industrial data includes classifying using a fuzzy K-means clustering method.
According to some embodiments of the present invention, in the process of performing online deduction on a plurality of parsing tasks, the method further includes:
acquiring process information of online deduction of each analysis task;
pre-analyzing the process information, and establishing an analysis dimension parameter table for carrying out online deduction on each analysis task; the analysis dimension parameter table comprises analysis accuracy, analysis speed, analysis difficulty of analysis tasks, analysis tools and analysis models;
determining an abnormal analysis task according to the analysis dimension parameter table, and reallocating corresponding target analysis equipment for the abnormal analysis task;
executing analysis actions on the corresponding abnormal analysis tasks based on the target analysis equipment, capturing a weblog of the target analysis equipment when executing the analysis tasks, and acquiring delay parameter points in the weblog;
establishing a preset time stamp of each analysis process of each abnormal analysis task, marking each delay parameter point on a corresponding point of the time stamp, and obtaining a delay time period of each analysis process of each abnormal analysis task;
and determining an analysis process with a delay time period larger than a preset threshold value as a target analysis process, and accelerating the target analysis process.
The invention provides an online deduction and deduction visual implementation method based on a business model, which classifies data to be deducted, generates a plurality of analysis tasks, performs parallel computation on virtual and physical resources which are applied to different spaces through a scheduler based on group intelligent computing capability of a distributed cluster, obtains a visual algorithm model, reduces the load of deduction and the complexity of deduction based on a deduction platform in the prior art, improves the utilization rate of computing resources and the overall computing efficiency, and performs process stage decomposition and aggregation processing on deduction evolution in time. And inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result, so as to realize data mining and prediction.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a flow chart of a business model-based online deduction and deduction visualization implementation method according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of overall operational situation analysis data, according to one embodiment of the invention;
FIG. 3 is a schematic diagram of boiler warning data according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of online deduction according to one embodiment of the present invention;
FIG. 5 is a schematic diagram of a presentation of deduction results and deduction process data according to one embodiment of the invention;
FIG. 6 is a schematic diagram of monitoring data according to one embodiment of the invention;
FIG. 7 is a diagram of the loading of a visualization algorithm model, according to one embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
As shown in fig. 1, the embodiment of the invention provides an online deduction and deduction visualization implementation method based on a service model, which comprises the following steps of S1-S4:
s1, obtaining industrial data to be deduced;
s2, classifying the industrial data to obtain a plurality of sub-industrial data, and generating a plurality of analysis tasks;
s3, carrying out online deduction on a plurality of analysis tasks to obtain a plurality of visual algorithm models;
s4, acquiring real-time data, and inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result.
The working principle of the technical scheme is as follows: in this embodiment, each sub-industrial data is of a class, and each sub-industrial data generates a parsing task.
In the embodiment, the visual algorithm model is obtained based on each analysis task, and in the process of carrying out online deduction on the analysis tasks, rules are found from complex data based on the artificial intelligent model, new knowledge is extracted, and the automatically generated algorithm model is a core component for mining large data value, so that seamless fusion of client demands and data values is realized.
In the embodiment, the implementation data are input into a plurality of visual algorithm models, so that the value and the rule of the real-time data can be conveniently mined, and meanwhile, based on a prediction algorithm, a corresponding prediction result is given, so that corresponding warning information can be conveniently given.
The beneficial effects of the technical scheme are that: classifying data to be deduced, generating a plurality of analysis tasks, scheduling applications to virtual and physical resources in different spaces by a scheduler for parallel calculation based on group intelligent computing capacity of a distributed cluster, and obtaining a visual algorithm model, so that the load and the complexity of the deduction based on a deduction platform in the prior art are reduced, the utilization rate of computing resources and the overall computing efficiency are improved, and the deduction evolution is subjected to process stage decomposition and aggregation processing in time. And inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result, so as to realize data mining and prediction.
According to some embodiments of the invention, the industrial data includes overall operational situation analysis data of the oil field and boiler early warning data; wherein,
the overall operation situation analysis data comprises statistics data of gas injection conditions, steam instructions, energy efficiency conditions, unqualified boilers, water supply, fuel and faults under different time dimensions, and a data diagram generated according to the statistics data;
the boiler early warning data comprises: based on the processing of the boiler data acquired in real time, corresponding data in the hearth, the convection section, the superheating section, the radiation section, the burner and the water supply pump are obtained.
The working principle of the technical scheme is as follows: in this embodiment, as shown in fig. 2, the overall operation situation analysis data is statistics of different time dimensions such as year, month, day, etc. for indexes such as gas injection conditions, steam instructions, energy efficiency conditions, unqualified boilers, water supply, fuels, faults, etc., and the data is queried according to the different time dimensions to generate a column diagram or a line diagram for presentation.
As shown in fig. 3, in this embodiment, the boiler pre-warning data includes: based on processing boiler data acquired in real time, corresponding data in a hearth, a convection section, a superheating section, a radiation section, a burner and a water supply pump are obtained, stored in a buffer memory for real-time presentation by a front end, and abnormal alarm is carried out through data comparison.
The beneficial effects of the technical scheme are that: and acquiring integral operation situation analysis data and boiler early warning data of the oil field as accurate and comprehensive industrial data, so as to facilitate the follow-up on-line deduction.
According to some embodiments of the present invention, online deduction is performed on a plurality of parsing tasks to obtain a plurality of visualized algorithm models, including:
establishing a first queuing queue of a plurality of analysis tasks;
establishing a second queuing sequence comprising analytic nodes of the artificial intelligence model;
determining matched analysis nodes for analysis tasks, establishing an association relation between first sequence information of the analysis tasks in a first queuing queue and second sequence information of a second queuing sequence of the analysis nodes, and dispatching the analysis tasks to the corresponding analysis nodes according to the association relation;
based on the analytic data determined by each analytic node, a plurality of visual algorithm models are generated.
The technical scheme has the working principle and beneficial effects that: establishing a first queuing queue of a plurality of analysis tasks; establishing a second queuing sequence comprising analytic nodes of the artificial intelligence model; determining matched analysis nodes for analysis tasks, establishing an association relation between first sequence information of the analysis tasks in a first queuing queue and second sequence information of a second queuing sequence of the analysis nodes, and dispatching the analysis tasks to the corresponding analysis nodes according to the association relation; based on the analytic data determined by each analytic node, a plurality of visual algorithm models are generated. The method is convenient for processing the corresponding analysis tasks based on the corresponding analysis nodes, and improves the accuracy of analysis, thereby improving the accuracy of the obtained visual algorithm model.
According to some embodiments of the invention, the artificial intelligence model comprises at least one of a multisource perception, a multiscale understanding, a population intelligence, a statistical analysis model, a data dimension reduction model, a classification/logistic regression model, a spatio-temporal representation, a decision and reasoning model, a trajectory mining model, a clustering and similarity model, a topic recommendation model, a model optimization method model.
According to some embodiments of the present invention, before acquiring real-time data, inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result, the method further includes:
adding an early warning rule and an early warning grade for the visual algorithm model;
sample data are acquired and input into a plurality of visual algorithm models to obtain risk early warning information, whether the risk early warning information is consistent with risk early warning information corresponding to the sample data or not is judged, and when the consistency is confirmed, the visual algorithm models are verified.
The technical scheme has the working principle and beneficial effects that: the risk early warning information comprises model names, abnormal alarm levels, responsible persons, contact ways, alarm sources, treatment measures and treatment states, and generates a risk early warning report. In order to monitor risks, early warning is triggered in a risk event-driven mode, and future trends of the events are predicted by utilizing evolution law operation and development logic of a visual algorithm model according to data monitoring to obtain risk early warning information. Judging whether the risk early-warning information is consistent with the risk early-warning information corresponding to the sample data, and when the risk early-warning information is consistent with the risk early-warning information, indicating that the visual algorithm model passes verification. Judging whether the early warning performance of the visual algorithm model is qualified or not. When the risk early warning is carried out, firstly, the early warning rules are configured, and different early warning rules are configured according to different models. According to the model category, corresponding parameters such as temperature, air pressure, saturation and the like are selected, then a threshold value is determined, the alarm is divided into five levels, and the alarm description is added to give a processing measure.
According to some embodiments of the present invention, in the online deduction process of the plurality of analysis tasks, the method further includes obtaining a previous model deduction amount, deduction efficiency, deduction status, service model analysis, evaluation of energy efficiency of the service, and process monitoring and displaying.
The technical scheme has the working principle and beneficial effects that: as shown in fig. 4, the deduction amount includes an energy system, an ERP system, a CRM system, an energy consumption device, and a file system. The deduction status includes sequence number, name, completion, start time and end time. The names include marketing, electronic fence protection, customer value, sales prediction information, boiler pre-warning, etc. The energy efficiency evaluation comprises the score of the overall operation situation, the score of sales prediction information, the score of boiler early warning, the score of client value, the score of an air compressor and the score of a waste heat boiler, and the process detection comprises marketing, electronic fence protection, client value, sales prediction information, the maximum quantity and the activity quantity of boiler early warning. And each deduction data and deduction process in the online deduction process are accurately and comprehensively displayed, and user experience is improved.
According to some embodiments of the present invention, after performing online deduction on a plurality of parsing tasks to obtain a plurality of visualization algorithm models, the method further includes:
obtaining and displaying a deduction result and deduction process data; the deduction process data comprise task information of analysis tasks, scheduling information and corresponding analysis nodes.
The technical scheme has the working principle and beneficial effects that: as shown in fig. 5, after online deduction is performed on a plurality of analysis tasks to obtain a plurality of visual algorithm models, deduction results and deduction process data are obtained and displayed; based on the historical disk recovery, the result of on-line deduction is restored, the deduction data is cached in the memory, the efficiency is improved, the data can be synchronized from the main server to any number of slave servers, and the method has the expandability of reading operation and the data redundancy backup function. In the history task list, task information, scheduling information and corresponding analysis nodes of analysis tasks can be checked and displayed in the interface in the form of a tree diagram.
According to some embodiments of the invention, after obtaining the plurality of visualization algorithm models, the method further comprises:
monitoring model names, ports, positions and states of a plurality of visual algorithm models to obtain first monitoring data;
obtaining analysis data of model early warning rates and abnormal rates of a plurality of visual algorithm models to obtain second monitoring data;
monitoring the memory, the disk and the CPU of the operation node of the plurality of visual algorithm models to obtain third monitoring data;
judging whether the first monitoring data, the second monitoring data and the third monitoring data are abnormal or not, and sending out alarm prompt information when the abnormality exists.
The technical scheme has the working principle and beneficial effects that: as shown in fig. 6, monitoring model names, ports, positions and states of a plurality of visual algorithm models to obtain first monitoring data;
obtaining analysis data of model early warning rates and abnormal rates of a plurality of visual algorithm models to obtain second monitoring data;
monitoring the memory, the disk and the CPU of the operation node of the plurality of visual algorithm models to obtain third monitoring data;
judging whether the first monitoring data, the second monitoring data and the third monitoring data are abnormal or not, and sending out alarm prompt information when the abnormality exists. And (3) realizing scene model measurement of the visual algorithm model, and further determining whether the visual algorithm model is abnormal.
According to some embodiments of the invention, classifying the industrial data includes classifying using a fuzzy K-means clustering method.
The technical scheme has the working principle and beneficial effects that: and classifying the industrial data, wherein the classification comprises a fuzzy K-means clustering method, so that the accuracy of data classification is improved.
In one embodiment, as shown in fig. 7, the visualization algorithm model is loaded, in a model list page, relevant information of all models is shown in a list form, and the functions of loading, starting and deleting the models are provided in the interface. Such as serial number, model category, model name, model purpose, creation time, status, provider, contact, operation, etc. are included in fig. 7. The model category comprises an analysis algorithm model, a business model, an intelligent early warning model, a basic algorithm model and the like. The analysis algorithm model comprises a basic algorithm model, a high-dry boiler early warning model, an energy consumption analysis model and the like. The service model comprises a common steam boiler early warning model, an SAGD temperature monitoring model and the like. The intelligent early warning model comprises an overheat boiler early warning model, an electronic fence early warning model, an equipment operation maintenance model and the like. The basic algorithm model comprises an equipment operation maintenance model, an intelligent early warning model and the like.
According to some embodiments of the present invention, in the process of performing online deduction on a plurality of parsing tasks, the method further includes:
acquiring process information of online deduction of each analysis task;
pre-analyzing the process information, and establishing an analysis dimension parameter table for carrying out online deduction on each analysis task; the analysis dimension parameter table comprises analysis accuracy, analysis speed, analysis difficulty of analysis tasks, analysis tools and analysis models;
determining an abnormal analysis task according to the analysis dimension parameter table, and reallocating corresponding target analysis equipment for the abnormal analysis task;
executing analysis actions on the corresponding abnormal analysis tasks based on the target analysis equipment, capturing a weblog of the target analysis equipment when executing the analysis tasks, and acquiring delay parameter points in the weblog;
establishing a preset time stamp of each analysis process of each abnormal analysis task, marking each delay parameter point on a corresponding point of the time stamp, and obtaining a delay time period of each analysis process of each abnormal analysis task;
and determining an analysis process with a delay time period larger than a preset threshold value as a target analysis process, and accelerating the target analysis process.
The technical scheme has the working principle and beneficial effects that: acquiring process information of online deduction of each analysis task; pre-analyzing the process information, and establishing an analysis dimension parameter table for carrying out online deduction on each analysis task; the analysis dimension parameter table comprises analysis accuracy, analysis speed, analysis difficulty of analysis tasks, analysis tools and analysis models; and determining an abnormal analysis task according to the analysis dimension parameter list, wherein the abnormal analysis task can be represented when any parameter in the analysis dimension parameter list does not meet a threshold value. And reassigning corresponding target analytic devices for the abnormal analytic tasks; the method is convenient to parse again based on the target parsing equipment in time, and avoids the problem that parsing errors are found after the target parsing equipment is executed, so that time is wasted and deduction speed is influenced. Executing analysis actions on the corresponding abnormal analysis tasks based on the target analysis equipment, capturing a weblog of the target analysis equipment when executing the analysis tasks, and acquiring delay parameter points in the weblog; establishing a preset time stamp of each analysis process of each abnormal analysis task, marking each delay parameter point on a corresponding point of the time stamp, and obtaining a delay time period of each analysis process of each abnormal analysis task; and determining an analysis process with a delay time period larger than a preset threshold value as a target analysis process, and accelerating the target analysis process. When the target analysis equipment executes an abnormal analysis task, the analysis process with the delay time period larger than the preset threshold value is accelerated, so that the gap between the target analysis equipment and the original time is reduced, the corresponding synchronous processing of each analysis process in the analysis task is facilitated due to the reduction of the delay time period, waiting due to the analysis process with stronger association is avoided, more time is wasted, and the deduction speed and accuracy are facilitated.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The method for realizing online deduction and deduction visualization based on the service model is characterized by comprising the following steps:
obtaining industrial data to be deduced;
classifying the industrial data to obtain a plurality of sub-industrial data, and generating a plurality of analysis tasks;
carrying out online deduction on a plurality of analysis tasks to obtain a plurality of visual algorithm models;
and acquiring real-time data, and inputting the real-time data into a plurality of visual algorithm models to obtain a prediction result.
2. The business model-based online deduction and deduction visualization implementation method according to claim 1, wherein the industrial data comprises integral operation situation analysis data of an oil field and boiler early warning data; wherein,
the overall operation situation analysis data comprises statistics data of gas injection conditions, steam instructions, energy efficiency conditions, unqualified boilers, water supply, fuel and faults under different time dimensions, and a data diagram generated according to the statistics data;
the boiler early warning data comprises: based on the processing of the boiler data acquired in real time, corresponding data in the hearth, the convection section, the superheating section, the radiation section, the burner and the water supply pump are obtained.
3. The business model-based online deduction and deduction visualization implementation method of claim 1, wherein the online deduction is performed on a plurality of analysis tasks to obtain a plurality of visualization algorithm models, comprising:
establishing a first queuing queue of a plurality of analysis tasks;
establishing a second queuing sequence comprising analytic nodes of the artificial intelligence model;
determining matched analysis nodes for analysis tasks, establishing an association relation between first sequence information of the analysis tasks in a first queuing queue and second sequence information of a second queuing sequence of the analysis nodes, and dispatching the analysis tasks to the corresponding analysis nodes according to the association relation;
based on the analytic data determined by each analytic node, a plurality of visual algorithm models are generated.
4. The business model-based on-line deduction and deduction visualization implementation method according to claim 3, wherein the artificial intelligence model comprises at least one of multisource perception, multimode understanding, population intelligence, statistical analysis model, data dimension reduction model, classification/logistic regression model, space-time representation, decision and reasoning model, trajectory mining model, clustering and similarity model, topic recommendation model, model optimization method model.
5. The method for implementing online deduction and deduction visualization based on a business model according to claim 1, wherein before acquiring real-time data, inputting the real-time data into a plurality of visualization algorithm models to obtain a prediction result, the method further comprises:
adding an early warning rule and an early warning grade for the visual algorithm model;
sample data are acquired and input into a plurality of visual algorithm models to obtain risk early warning information, whether the risk early warning information is consistent with risk early warning information corresponding to the sample data or not is judged, and when the consistency is confirmed, the visual algorithm models are verified.
6. The method for realizing online deduction and deduction visualization based on a business model according to claim 1, wherein the method further comprises the steps of obtaining and displaying the deduction quantity, deduction efficiency, deduction state, business model analysis, energy efficiency evaluation and process monitoring of the business in the process of carrying out online deduction on a plurality of analysis tasks.
7. The method for implementing online deduction and deduction visualization based on a business model according to claim 1, wherein after performing online deduction on a plurality of analysis tasks to obtain a plurality of visualization algorithm models, the method further comprises:
obtaining and displaying a deduction result and deduction process data; the deduction process data comprise task information of analysis tasks, scheduling information and corresponding analysis nodes.
8. The method for implementing online deduction and deduction visualization based on a business model according to claim 1, further comprising, after obtaining a plurality of visualization algorithm models:
monitoring model names, ports, positions and states of a plurality of visual algorithm models to obtain first monitoring data;
obtaining analysis data of model early warning rates and abnormal rates of a plurality of visual algorithm models to obtain second monitoring data;
monitoring the memory, the disk and the CPU of the operation node of the plurality of visual algorithm models to obtain third monitoring data;
judging whether the first monitoring data, the second monitoring data and the third monitoring data are abnormal or not, and sending out alarm prompt information when the abnormality exists.
9. The business model-based on-line deduction and deduction visualization implementation method according to claim 1, wherein the classification of the industrial data comprises classification by a fuzzy K-means clustering method.
10. The method for implementing online deduction and deduction visualization based on service model as claimed in claim 1, wherein in the process of performing online deduction on a plurality of analysis tasks, the method further comprises:
acquiring process information of online deduction of each analysis task;
pre-analyzing the process information, and establishing an analysis dimension parameter table for carrying out online deduction on each analysis task; the analysis dimension parameter table comprises analysis accuracy, analysis speed, analysis difficulty of analysis tasks, analysis tools and analysis models;
determining an abnormal analysis task according to the analysis dimension parameter table, and reallocating corresponding target analysis equipment for the abnormal analysis task;
executing analysis actions on the corresponding abnormal analysis tasks based on the target analysis equipment, capturing a weblog of the target analysis equipment when executing the analysis tasks, and acquiring delay parameter points in the weblog;
establishing a preset time stamp of each analysis process of each abnormal analysis task, marking each delay parameter point on a corresponding point of the time stamp, and obtaining a delay time period of each analysis process of each abnormal analysis task;
and determining an analysis process with a delay time period larger than a preset threshold value as a target analysis process, and accelerating the target analysis process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310986830.5A CN117077847A (en) | 2023-08-07 | 2023-08-07 | On-line deduction and deduction visualization realization method based on business model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310986830.5A CN117077847A (en) | 2023-08-07 | 2023-08-07 | On-line deduction and deduction visualization realization method based on business model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117077847A true CN117077847A (en) | 2023-11-17 |
Family
ID=88712586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310986830.5A Pending CN117077847A (en) | 2023-08-07 | 2023-08-07 | On-line deduction and deduction visualization realization method based on business model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117077847A (en) |
-
2023
- 2023-08-07 CN CN202310986830.5A patent/CN117077847A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11037080B2 (en) | Operational process anomaly detection | |
| US8924328B1 (en) | Predictive models for configuration management of data storage systems | |
| CN112799369A (en) | Product assembly process control method and device | |
| CN111539493A (en) | Alarm prediction method and device, electronic equipment and storage medium | |
| CN111459698A (en) | Database cluster fault self-healing method and device | |
| CN115564071A (en) | Method and system for generating data labels of power Internet of things equipment | |
| CN113516417A (en) | Service evaluation method and device based on intelligent modeling, electronic equipment and medium | |
| Malhotra et al. | Severity assessment of software defect reports using text classification | |
| CN117408561A (en) | Residential engineering construction supervision method and device and electronic equipment | |
| CN111666191A (en) | Data quality monitoring method and device, electronic equipment and storage medium | |
| US20180089637A1 (en) | Framework for industrial asset repair recommendations | |
| CN117077847A (en) | On-line deduction and deduction visualization realization method based on business model | |
| CN116149895A (en) | Big data cluster performance prediction method and device and computer equipment | |
| CN116225848A (en) | Log monitoring method, device, equipment and medium | |
| CN115168509A (en) | Processing method and device of wind control data, storage medium and computer equipment | |
| CN115062023A (en) | Wide table optimization method and device, electronic equipment and computer readable storage medium | |
| CN111221704B (en) | Method and system for determining running state of office management application system | |
| CN114819367A (en) | Public service platform based on industrial internet | |
| CN114742430A (en) | User retention early warning visualization method, device, equipment and storage medium | |
| CN109754186B (en) | Probability calculation method and device based on energy consumption analysis | |
| CN113590835A (en) | Method and device for establishing knowledge graph of textile industry data and processor | |
| CN115427986A (en) | Algorithm learning engine for dynamically generating predictive analytics from high-volume, high-speed streaming data | |
| CN111967774A (en) | Software quality risk prediction method and device | |
| US11281689B1 (en) | Distributed interaction feature generation system | |
| TWI813448B (en) | Expert system and expert method |
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 |