CN111751788A - Auxiliary enhancement system for big data intelligent detection equipment - Google Patents
Auxiliary enhancement system for big data intelligent detection equipment Download PDFInfo
- Publication number
- CN111751788A CN111751788A CN202010602753.5A CN202010602753A CN111751788A CN 111751788 A CN111751788 A CN 111751788A CN 202010602753 A CN202010602753 A CN 202010602753A CN 111751788 A CN111751788 A CN 111751788A
- Authority
- CN
- China
- Prior art keywords
- data
- algorithm model
- equipment
- research center
- business algorithm
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/021—Auxiliary means for detecting or identifying radar signals or the like, e.g. radar jamming signals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/52—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S15/00
- G01S7/52001—Auxiliary means for detecting or identifying sonar signals or the like, e.g. sonar jamming signals
-
- 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
- G06F16/21—Design, administration or maintenance of databases
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an auxiliary enhancement system of big data intelligent detection equipment, which relates to the field of artificial intelligence and comprises the following components: an off-line data research center and an on-line real-time processing system. The off-line data research center is used for collecting, storing and managing historical use data of various types of equipment and providing data retrieval service; the off-line data research center is also used for executing algorithm training updating and research and development tasks, training and updating the existing business algorithm model and researching and developing a new business algorithm model. The online real-time processing system generates a calculation result by accessing detection data generated by preset equipment and utilizing a business algorithm model corresponding to the preset equipment for calculation, and the online real-time processing system exports the calculation result and input data and sends the calculation result and the input data back to the offline data research center for storage and is used for updating or iterating the business algorithm model. The invention realizes that the algorithm model can be updated and replaced on the equipment more easily, and realizes that the new model is applied to the equipment quickly and efficiently.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to an auxiliary enhancement system of big data intelligent detection equipment.
Background
Radars use modulated waveforms and directional antennas to transmit electromagnetic energy into a particular area of space to search for targets. Objects (targets) within the search area reflect some of the energy (radar reflection or echoes) back to the radar, and these echoes are then processed by the radar receiver to extract information about the target such as range, velocity, angular position, and other target identification features. The sonar also works in a similar way, except that the sonar utilizes the propagation characteristic of sound signals under water to transmit or receive underwater sound wave signals, and then completes the conversion between sound waves (mechanical waves) and electromagnetic waves through a transducer so as to extract target identification features. According to the detection principle of radar and sonar, extracting the relevant information of the target from the signal waveform received by the equipment is a necessary and key step in the detection process. At present, the most common method is to adopt a technical means in the aspect of Digital Signal Processing (DSP) to perform signal noise reduction, target extraction, target spectrum analysis, feature extraction and other processing processes on a received detection signal, and to visually and audibly present a processing result in real time, so that a user can find, identify and track a target in time.
Aiming at the challenges and difficulties faced by radar and sonar detection, a new solution idea and method is as follows: for signal data of a detection target, on the basis of a digital signal processing method, a deep learning technology in big data mining is utilized, and a target classification deep neural network is trained in a data driving mode and used for realizing classification and identification of the detection target.
Based on mass actual detection data, a deep learning technology is used, and time-frequency signal data of a target are directly used as training input. Compared with the traditional type identification based on theoretical characteristics, the method eliminates the limitation of characteristic extraction on classification models, solves the problem from the characteristics of data, trains different models to correspond to different data conditions according to different environments, and has higher flexibility and universality compared with the traditional method.
However, applying a deep learning model based on data driving on an actual detection device also faces a great challenge. Firstly, a traditional equipment development mode follows a route of algorithm simulation- > hardware system design and construction- > auxiliary control software construction, related business algorithm software is compiled into embedded hardware or chips such as an FPGA through a bottom layer, and rewriting and compiling of the bottom layer algorithm on the hardware consumes more time and is more difficult compared with conventional software coding, especially on equipment which is produced and shaped, a series of problems of equipment disassembly and assembly, reduction and the like are involved, so that in the existing application mode, the algorithm model on the equipment is not easy to update and replace, and the efficiency of applying a new model to the equipment is low.
Disclosure of Invention
The invention provides an auxiliary enhancement system for big data intelligent detection equipment, and aims to realize that an algorithm model can be updated and replaced on the equipment easily and to apply a new model to the equipment quickly and efficiently.
In order to achieve the above object, the present invention provides an auxiliary enhancement system for big data intelligent detection equipment, wherein the system comprises:
the system comprises an offline data research center and an online real-time processing system;
the off-line data research center is used for collecting historical use data of various types of equipment, storing and managing the collected historical use data and providing data retrieval service for research and development of a business algorithm model; the off-line data research center is also used for executing algorithm training updating and research and development tasks, training and updating the existing business algorithm model and researching and developing a new business algorithm model according to real-time data in the off-line data research center, and the off-line data research center is used for providing support for the application of the business algorithm model at the equipment end;
the online real-time processing system is built at each equipment end, a business algorithm model in the offline data research center is applied to the equipment end through the online real-time processing system, the online real-time processing system generates a calculation result through accessing detection data generated by preset equipment and calculating by using the business algorithm model corresponding to the preset equipment, the calculation result is displayed through a visual display and control interface, and the online real-time processing system leads out the calculation result and input data and sends the calculation result and the input data back to the offline data research center for storage and is used for updating or iterating the business algorithm model.
The principle of the invention is as follows: the deep learning model has the advantages that retraining iteration can be carried out on the model along with the change of data, so that the performance of the model can be kept at a certain level; secondly, the deep learning model is developed faster than the traditional processing algorithm, and new model designs with better performance are continuously published, so that how to quickly and efficiently apply the new model to the equipment is a pain point which is generally and urgently needed to be solved by the traditional equipment. The invention is based on the existing in-use equipment, builds a corresponding intelligent detection auxiliary enhancement system in a matching way, connects the system with the equipment in the form of external auxiliary equipment, receives real-time data, and then generates a recognition result through calculation of a core business algorithm model. In addition, a corresponding offline data storage and processing center is required to be built for accumulating and storing historical data, continuously iterating and optimizing the lifting model, and updating the lifting model into an external system. The invention separates the operation of the service algorithm from the hardware system of the equipment, and realizes the calculation of the service algorithm in the system by accessing the data stream generated by the detection equipment into the system of the invention. The subsequent algorithm updating only needs to be carried out by using a special software module in the system, the original equipment does not need to be unpacked, and the reprogramming development on the bottom embedded chip is also not needed, so that the algorithm model can be updated and replaced on the equipment easily, and the new model can be applied to the equipment quickly and efficiently.
The invention can provide a feasible route for developing new equipment on one hand, and can provide a set of practical and effective method for upgrading and reconstructing old equipment and improving performance on the other hand.
The intelligent detection auxiliary enhancement system utilizes big data artificial intelligence theory and technical means to build an algorithm model and an application system, is used for assisting detection equipment to quickly and accurately find a target, and improves the comprehensive detection capability of the existing detection equipment such as radar, sonar and the like. The system constructs detection-related business algorithm models (an interference suppression model, a target type identification model and the like) by collecting detection historical data of corresponding equipment on the basis of not changing the structure of original equipment, and is externally connected to detection equipment in an application system mode, so that real-time system application is realized, and intelligent auxiliary detection is carried out.
Preferably, hardware in the offline data research center comprises a plurality of server clusters, signal transmission equipment, an operation and maintenance control terminal and a data service application terminal, the server clusters are connected with the operation and maintenance control terminal and the data service application terminal through the signal transmission equipment, the server clusters are used for achieving distributed storage and parallelization calculation of big data, and the operation and maintenance control terminal and the data service application terminal are used for achieving operation maintenance and data analysis and mining of the offline data research center.
Preferably, the hardware in the online real-time processing system includes a server cabinet and a display unit, the server cabinet is connected to the display unit, and the server cabinet includes: the server cabinet is connected with the intelligent detection equipment through the signal transmission equipment, receives data generated by detection of the intelligent detection equipment, calculates based on a service algorithm model in the server cabinet and the data generated by detection to obtain an analysis result, and displays the analysis result in the display unit.
Preferably, the software in the off-line data research center includes: the system comprises a big data base platform, a big data management system, a big data analysis and mining system and a big data visualization system;
the big data base platform provides distributed data storage, a parallel computing engine, a distributed resource management system, a distributed application coordination service and a platform operation and maintenance management system, and is used for supporting other big data application systems based on the platform;
the big data management system is used for importing and transferring mass detection data, carrying out unified storage management on the mass detection data and efficiently and flexibly retrieving, inquiring and using the mass detection data;
the big data analysis and mining system is used for analyzing, mining and modeling massive structured data, analyzing and mining hidden information and knowledge from the massive data, improving the efficiency of data value discovery and realizing data-driven business innovation;
and the big data visualization system is used for carrying out service evaluation and customized comprehensive detection situation display on the modeling result generated by the big data analysis and mining system.
Preferably, the software in the online real-time processing system comprises:
the data access acquisition module is used for receiving real-time detection data generated by the intelligent detection equipment;
the model calling calculation analysis module is used for calling a built-in service algorithm model to realize corresponding detection service;
the model and data management module is used for managing all business algorithm models, detection data and calculation results in the online real-time processing system;
the display control interaction module is used for connecting the display unit and realizing the online real-time processing system service display and the corresponding human-computer interaction function;
and the storage and resource management module is used for managing, distributing and scheduling the storage resources and the computing resources in the online real-time processing system.
Preferably, the research and development and application process of the business algorithm model is as follows:
collecting and labeling detection data of the intelligent detection equipment, and uniformly storing and managing the detection data by an offline data research center;
the off-line data research center builds, trains and verifies a business algorithm model based on data in the center;
exporting the verified business algorithm model from an offline data research center, and importing the business algorithm model into an online real-time processing system;
and the online real-time processing system is applied to the business algorithm model to complete corresponding business.
Preferably, the usage process of the auxiliary enhancement system is as follows:
building an auxiliary enhancement system, researching and developing and verifying a business algorithm model in an offline data research center after the building is finished, detecting historical data by using intelligent detection equipment stored in the offline data research center, building the business algorithm model, verifying the business algorithm model in an offline manner, and exporting the business algorithm model after verification;
after the business algorithm model is exported, the business algorithm model is sent to an online real-time processing system at the equipment end, the business algorithm model is uploaded to the online real-time processing system, the online real-time processing system is accessed into intelligent detection equipment data, the business algorithm model is called to analyze and process the real-time detection data, and the calculation result of the business algorithm model is displayed through a display unit to complete the corresponding business function;
storing the calculation result of the business algorithm model and the input data, exporting the stored data and sending the exported data back to the offline data research center, and updating or iterating the business algorithm model;
the off-line data research center updates the stored related data of the intelligent detection equipment, and develops a new business algorithm model or updates or iterates the business algorithm model being used based on the updated data.
Preferably, the intelligent detection device is a radar or sonar detection device.
Preferably, the server is an x86 server and the signaling device is a switch.
Preferably, the business algorithm model is an interference suppression model or an object type identification model.
One or more technical schemes provided by the invention at least have the following technical effects or advantages:
by adding the big data intelligent detection auxiliary enhancement system to the existing equipment, a large amount of time and resources required by developing new-type equipment are avoided, resources can be concentrated on research and development construction of the enhancement system, and an actual effective service model and a mature application mode are explored. The radar and sonar intelligent detection auxiliary enhancement system is built, on one hand, the intelligent degree and the actual detection capability of old equipment are improved, on the other hand, a large amount of practical experience is accumulated for the development of subsequent new equipment from system construction to core algorithm model construction, and the development of the equipment and the improvement of the detection efficiency are facilitated. The system can well apply the latest deep learning model on the old and new equipment, and can rapidly update the iterative model along with the change of environment, time and data, so that the detection effect is guaranteed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention;
FIG. 1 is a schematic diagram of a logic structure of a big data intelligent detection auxiliary enhancement system;
FIG. 2 is a schematic diagram of an off-line data research center hardware architecture;
FIG. 3 is a diagram of an on-line real-time processing system hardware architecture;
FIG. 4 is a schematic diagram of an off-line data research center software architecture;
FIG. 5 is a diagram of an on-line real-time processing system software architecture.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflicting with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described and thus the scope of the present invention is not limited by the specific embodiments disclosed below.
The first embodiment is as follows:
the embodiment of the invention provides an auxiliary enhancement system for big data intelligent detection equipment.
The system has the main functions:
the big data intelligent detection auxiliary enhancement system constructs a detection interference suppression and target recognition algorithm model from a data angle through a big data artificial intelligence related theoretical technology, assists decision-making of users, improves detection capability of equipment, and has the following system function points:
uniformly storing and managing the detection data;
rapidly retrieving and inquiring the detection data;
analyzing and mining detection data and modeling off line;
verifying and exporting and calling an offline model;
acquiring and storing real-time detection data of the equipment;
real-time detection data calls a model to perform online calculation analysis;
storing and visually displaying an analysis result;
and (5) operating a human-computer interaction interface.
The system structure comprises:
logical structure of system
The big data intelligent detection auxiliary enhancement system is logically divided into two parts: an offline data research center and an online real-time processing system are shown in fig. 1, wherein the offline data research center is built in a relevant base or a supporting scientific research unit, is built in a data center mode, and is an integrated data research center integrating functions of data unified storage, management, retrieval, analysis mining, modeling and the like. The offline data research center is mainly responsible for centralizing the real historical use data of various types of equipment, uniformly storing and managing the data and providing data retrieval service for an algorithm model research team. The off-line data research center is also responsible for algorithm research and development tasks, continuously trains and updates the existing algorithm model according to the latest warehousing data, and develops a new algorithm model with stronger performance, so as to provide long-time and high-efficiency core technology support for the model application of the equipment end.
The online real-time processing system is built at each equipment end and is attached beside the equipment in the form of an external cabinet or an integrated hardware box. The on-line real-time processing system is an application system of a core algorithm model, and generates a result through algorithm calculation through detection data generated by access equipment. And finally, displaying the result through a visual display control interface, providing detection assistance for users, and improving the detection capability of the equipment.
The system construction method comprises the following steps:
hardware system construction:
the hardware system construction comprises two parts, namely, the hardware system construction of an offline data research center; secondly, constructing an online real-time processing hardware system;
firstly, constructing a hardware system of an offline data research center
The hardware structure of the offline data research center is schematically shown in fig. 2, and the center comprises a server cluster consisting of a plurality of x86 servers and a ten-gigabit switch, so that distributed storage and parallelization calculation of big data are realized. In addition, a plurality of PCs (personal computers) such as an operation and maintenance control terminal and a data service application terminal are connected with the cluster, so that the center operation and maintenance and data analysis and mining research are realized.
Second, on-line real-time processing hardware system construction
The hardware structure of the online real-time processing system is shown in fig. 3, and the system hardware structure includes a small server cabinet composed of a plurality of x86 servers or embedded chips plus switches, and an external display and control screen. The equipment cabinet is connected with the equipment, the data generated by the equipment detection are received, and the result after the model calculation and analysis is displayed on the display control screen, so that the assistance is provided for the user.
Constructing a software system:
the corresponding software system construction also comprises two parts, namely firstly, the off-line data research center software system construction; secondly, constructing an online real-time processing software system;
firstly, constructing a software system of an offline data research center
The off-line data research center software architecture is shown in fig. 4, and the core software includes: the data service layer of a 1+3 architecture of 1 basic platform +3 application software systems is formed, data of a source layer is led into service layer software to be uniformly stored and managed, and data retrieval support is provided for data application services of an upper layer, such as interference suppression, target identification and the like.
The big data base platform comprises: the system comprises a distributed data storage system, a parallel computing engine, a distributed resource management system, a distributed application coordination service and a platform operation and maintenance management system, wherein the platform operation and maintenance management system is used for supporting a platform-based big data application system. The distributed storage system is used for storing mass data; the parallel computing engine is used for fast and efficient computation of mass data; the distributed resource management system and the distributed application coordination service are used for carrying out coordination distribution on the computing resources of the basic platform and information synchronization among the nodes; the platform operation and maintenance management system is used for creating, managing and monitoring the whole distributed cluster and the cluster ecosphere, and comprises management and monitoring of a storage system, a computing engine, a resource management system and a coordination service system.
The big data management system comprises the following functions: the system comprises a data collection and migration function, a file and data field management function, a file attribute marking function, a data key field analysis and storage management function, a file-level data query and retrieval function, a content-level data query and retrieval function, a data downloading and exporting function and the like;
the big data analysis and mining system comprises the following functions: the system comprises an authentication and authorization function, an analysis data import function, a data life cycle management function, a feature engineering function, a workflow operation scheduling function, a model export function, an online deployment function and the like.
Big data visualization system functions include: the comprehensive situation map display function, the characteristic and detection recognition result display function, the detection result report analysis function and the like.
Second, on-line real-time processing software system construction
The software architecture of the online real-time processing system is shown in fig. 5, and the system comprises a data access acquisition module, a model calling, calculation and analysis module, a model and data management module, a display and control interaction module and a storage and resource management module. The data access acquisition module is used for receiving real-time detection data generated by equipment; the model calling calculation analysis module is used for calling a built-in service algorithm model to realize corresponding detection service; the model and data management module is used for managing all models, detection data and calculation results of the system; the display control interaction module is connected with display control screen equipment to realize system service display and corresponding human-computer interaction functions; the storage and resource management module is used for carrying out unified management, allocation and scheduling on the storage resources and the computing resources of the whole system.
Research and development and integrated application of a business algorithm model:
based on the software and hardware system which is constructed, firstly, collecting and labeling equipment detection data, uniformly storing and managing historical data by using a data management system on a data center platform, and then constructing, training and experimentally verifying a business algorithm model by using a data analysis mining and visualization system on the data center platform; and after the construction is finished, the model is exported to the center, the model is imported into online real-time processing software, and the business algorithm model is applied to finish the corresponding business.
The system use flow comprises the following steps:
after the system is built, firstly, algorithm model research and development and offline model verification are carried out in an offline data research center, existing equipment is used for detecting historical data, business models such as a radar clutter suppression algorithm model and a target type identification model are built, the model is guaranteed to be in a certain accuracy rate through offline verification, and finally the model is exported.
And after the model is derived, the model is sent to an equipment end online real-time processing system, the model is uploaded to the system, equipment data is accessed, the model is called to analyze and process real-time detection data, and a model calculation result is displayed through a display control module and equipment to complete a corresponding service function. The calculation result and the input data can be stored, so that the calculation result can be conveniently exported and sent back to an offline data research center for model updating iteration.
The off-line data research center continuously acquires new data, develops a new model or updates the model used by iteration, and guarantees the system efficiency.
By using the system in the embodiment, a certain type of low-altitude aircraft detection radar is selected, historical detection data are collected, stored and managed by building an offline data center, intelligent detection auxiliary identification and other business models are researched and developed based on historical mass data, the model effect is verified, the model is ensured to realize certain detection indexes, and finally the model is exported.
And then constructing an online real-time processing system based on the equipment and the use environment requirements, sending the derived model to the equipment end online real-time processing system, uploading the model to the system, accessing the equipment data, calling the model to analyze and process the real-time detection data, and displaying the model calculation result with the equipment through a display and control module to complete the corresponding service function.
The calculation result and the input data can be stored, so that the calculation result can be conveniently exported and sent back to an offline data research center for model updating iteration. The off-line data research center continuously acquires new data, develops a new model or updates the model used by iteration, and guarantees the system efficiency.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A big data intelligent detection device auxiliary enhancement system, characterized in that, the system includes:
the system comprises an offline data research center and an online real-time processing system;
the off-line data research center is used for collecting historical use data of various types of equipment, storing and managing the collected historical use data and providing data retrieval service for research and development of a business algorithm model; the off-line data research center is also used for executing algorithm training updating and research and development tasks, training and updating the existing business algorithm model and researching and developing a new business algorithm model according to real-time data in the off-line data research center, and the off-line data research center is used for providing support for the application of the business algorithm model at the equipment end;
the online real-time processing system is built at each equipment end, a business algorithm model in the offline data research center is applied to the equipment end through the online real-time processing system, the online real-time processing system generates a calculation result through accessing detection data generated by preset equipment and calculating by using the business algorithm model corresponding to the preset equipment, the calculation result is displayed through a visual display and control interface, and the online real-time processing system leads out the calculation result and input data and sends the calculation result and the input data back to the offline data research center for storage and is used for updating or iterating the business algorithm model.
2. The big data intelligent detection equipment auxiliary enhancement system according to claim 1, characterized in that hardware in the offline data research center comprises a plurality of server clusters, signal transmission equipment, an operation and maintenance control terminal and a data service application terminal, the server clusters are connected with the operation and maintenance control terminal and the data service application terminal through the signal transmission equipment, the plurality of server clusters are used for realizing big data distributed storage and parallelization calculation, and the operation and maintenance control terminal and the data service application terminal are used for realizing operation maintenance and data analysis mining of the offline data research center.
3. The big data intelligent detection equipment auxiliary enhancement system according to claim 1, wherein hardware in the online real-time processing system comprises a server cabinet and a display unit, the server cabinet is connected with the display unit, and the server cabinet comprises: the server cabinet is connected with the intelligent detection equipment through the signal transmission equipment, receives data generated by detection of the intelligent detection equipment, calculates based on a service algorithm model in the server cabinet and the data generated by detection to obtain an analysis result, and displays the analysis result in the display unit.
4. The big data intelligent probe device auxiliary enhancement system of claim 1, wherein the software in the offline data research center comprises: the system comprises a big data base platform, a big data management system, a big data analysis and mining system and a big data visualization system;
the big data base platform provides distributed data storage, a parallel computing engine, a distributed resource management system, a distributed application coordination service and a platform operation and maintenance management system, and is used for supporting other big data application systems based on the platform;
the big data management system is used for importing and transferring mass detection data, carrying out unified storage management on the mass detection data and efficiently and flexibly retrieving, inquiring and using the mass detection data;
the big data analysis and mining system is used for analyzing, mining and modeling massive structured data, analyzing and mining hidden information and knowledge from the massive data, improving the efficiency of data value discovery and realizing data-driven business innovation;
and the big data visualization system is used for carrying out service evaluation and customized comprehensive detection situation display on the modeling result generated by the big data analysis and mining system.
5. The big data intelligent detecting equipment auxiliary enhancement system according to claim 1, wherein the software in the online real-time processing system comprises:
the data access acquisition module is used for receiving real-time detection data generated by the intelligent detection equipment;
the model calling calculation analysis module is used for calling a built-in service algorithm model to realize corresponding detection service;
the model and data management module is used for managing all business algorithm models, detection data and calculation results in the online real-time processing system;
the display control interaction module is used for connecting the display unit and realizing the online real-time processing system service display and the corresponding human-computer interaction function;
and the storage and resource management module is used for managing, distributing and scheduling the storage resources and the computing resources in the online real-time processing system.
6. The big data intelligent detection equipment auxiliary enhancement system according to claim 1, wherein the development and application process of the business algorithm model is as follows:
collecting and labeling detection data of the intelligent detection equipment, and uniformly storing and managing the detection data by an offline data research center;
the off-line data research center builds, trains and verifies a business algorithm model based on data in the center;
exporting the verified business algorithm model from an offline data research center, and importing the business algorithm model into an online real-time processing system;
the on-line real-time processing system applies the service algorithm model to complete the corresponding service.
7. The big data intelligent detection device auxiliary enhancement system according to claim 1, wherein the auxiliary enhancement system is used by the following procedures:
building an auxiliary enhancement system, researching and developing a business algorithm model and verifying an offline business algorithm model in an offline data research center after the building is finished, detecting historical data by using intelligent detection equipment stored in the offline data research center, building the business algorithm model, verifying the business algorithm model in an offline manner, and exporting the business algorithm model after verification;
after the business algorithm model is exported, the business algorithm model is sent to an online real-time processing system at the equipment end, the business algorithm model is uploaded to the online real-time processing system, the online real-time processing system is accessed into intelligent detection equipment data, the business algorithm model is called to analyze and process the real-time detection data, and the calculation result of the business algorithm model is displayed through a display unit to complete the corresponding business function;
storing the calculation result of the business algorithm model and the input data, exporting the stored data and sending the exported data back to the offline data research center, and updating or iterating the business algorithm model;
the off-line data research center updates the stored related data of the intelligent detection equipment, and develops a new business algorithm model or updates or iterates the business algorithm model being used based on the updated data.
8. The big data smart probe device aiding enhancement system of claim 1, wherein the smart probe device is a radar or sonar probe device.
9. The big data intelligent detection device auxiliary enhancement system according to claim 2, wherein the server is an x86 server, and the signal transmission device is a switch.
10. The big data intelligent detection device auxiliary enhancement system of claim 8, wherein the business algorithm model is an interference suppression model or an object type recognition model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010602753.5A CN111751788A (en) | 2020-06-29 | 2020-06-29 | Auxiliary enhancement system for big data intelligent detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010602753.5A CN111751788A (en) | 2020-06-29 | 2020-06-29 | Auxiliary enhancement system for big data intelligent detection equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111751788A true CN111751788A (en) | 2020-10-09 |
Family
ID=72677883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010602753.5A Pending CN111751788A (en) | 2020-06-29 | 2020-06-29 | Auxiliary enhancement system for big data intelligent detection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111751788A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915793A (en) * | 2015-06-30 | 2015-09-16 | 北京西塔网络科技股份有限公司 | Public information intelligent analysis platform based on big data analysis and mining |
| CN105631764A (en) * | 2015-12-31 | 2016-06-01 | 国网电力科学研究院武汉南瑞有限责任公司 | Smart power grid big data application system orienting smart city |
| US20160300156A1 (en) * | 2015-04-10 | 2016-10-13 | Facebook, Inc. | Machine learning model tracking platform |
| CN106407278A (en) * | 2016-08-26 | 2017-02-15 | 武汉钢铁工程技术集团自动化有限责任公司 | Architecture design system of big data platform |
| CN106649773A (en) * | 2016-12-27 | 2017-05-10 | 北京大数有容科技有限公司 | Big data collaborative analysis tool platform |
| CN107515927A (en) * | 2017-08-24 | 2017-12-26 | 深圳市云房网络科技有限公司 | A kind of real estate user behavioural analysis platform |
| CN107729413A (en) * | 2017-09-25 | 2018-02-23 | 安徽畅通行交通信息服务有限公司 | Regional traffic intelligent management system based on big data |
| US20180359201A1 (en) * | 2017-06-09 | 2018-12-13 | Equinix, Inc. | Near real-time messaging service for data center infrastructure monitoring data |
| CN110097144A (en) * | 2019-06-15 | 2019-08-06 | 青岛大学 | A kind of tire detects big data and cloud computing system and its application study automatically |
| CN110288035A (en) * | 2019-06-28 | 2019-09-27 | 海南树印网络科技有限公司 | A kind of online autonomous learning method and system of intelligent garbage bin |
| CN111327681A (en) * | 2020-01-21 | 2020-06-23 | 北京工业大学 | Cloud computing data platform construction method based on Kubernetes |
-
2020
- 2020-06-29 CN CN202010602753.5A patent/CN111751788A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160300156A1 (en) * | 2015-04-10 | 2016-10-13 | Facebook, Inc. | Machine learning model tracking platform |
| CN104915793A (en) * | 2015-06-30 | 2015-09-16 | 北京西塔网络科技股份有限公司 | Public information intelligent analysis platform based on big data analysis and mining |
| CN105631764A (en) * | 2015-12-31 | 2016-06-01 | 国网电力科学研究院武汉南瑞有限责任公司 | Smart power grid big data application system orienting smart city |
| CN106407278A (en) * | 2016-08-26 | 2017-02-15 | 武汉钢铁工程技术集团自动化有限责任公司 | Architecture design system of big data platform |
| CN106649773A (en) * | 2016-12-27 | 2017-05-10 | 北京大数有容科技有限公司 | Big data collaborative analysis tool platform |
| US20180359201A1 (en) * | 2017-06-09 | 2018-12-13 | Equinix, Inc. | Near real-time messaging service for data center infrastructure monitoring data |
| CN107515927A (en) * | 2017-08-24 | 2017-12-26 | 深圳市云房网络科技有限公司 | A kind of real estate user behavioural analysis platform |
| CN107729413A (en) * | 2017-09-25 | 2018-02-23 | 安徽畅通行交通信息服务有限公司 | Regional traffic intelligent management system based on big data |
| CN110097144A (en) * | 2019-06-15 | 2019-08-06 | 青岛大学 | A kind of tire detects big data and cloud computing system and its application study automatically |
| CN110288035A (en) * | 2019-06-28 | 2019-09-27 | 海南树印网络科技有限公司 | A kind of online autonomous learning method and system of intelligent garbage bin |
| CN111327681A (en) * | 2020-01-21 | 2020-06-23 | 北京工业大学 | Cloud computing data platform construction method based on Kubernetes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Travel time prediction system based on data clustering for waste collection vehicles | |
| CN110135654A (en) | Method and apparatus for predicting strong convective weather | |
| AU2021240155A9 (en) | Control Pulse Generation Method, Apparatus, System, Device And Storage Medium | |
| CN110462644A (en) | The system and method for the cognitive engineering technology of automation and control for system | |
| CN110178149A (en) | Digital twins' figure | |
| CN108648020A (en) | User behavior quantization method, system, equipment and storage medium | |
| CN111044045B (en) | Navigation method and device based on neural network and terminal equipment | |
| CN111741133B (en) | Cloud-side-end-collaborative meteorological intelligent early warning system | |
| CN103186575B (en) | A kind of clustering method of sensing data and system | |
| CN101872313B (en) | Method for developing intelligent control-oriented virtual instrument capable of reconfiguring functions | |
| CN109726763A (en) | A kind of information assets recognition methods, device, equipment and medium | |
| CN110766151B (en) | Open type neural network model management system based on scene | |
| CN110378410A (en) | Multi-tag scene classification method, device and electronic equipment | |
| CN105353644A (en) | Radar target track derivative system on the basis of information mining of real-equipment data and method thereof | |
| CN109634644A (en) | The method and its equipment of firmware upgrade are carried out for sensor by wireless communication | |
| CN109978619A (en) | Method, system, equipment and the medium of air ticket pricing Policy Filtering | |
| KR101478639B1 (en) | Service system Of Synthetic Oceanography Environment Data | |
| CN101419623A (en) | Geographical simulation optimizing system | |
| JP2023022185A (en) | Map data processing method and device, electronic equipment, storage medium, and computer program | |
| CN115130894A (en) | Production planning method and device based on artificial intelligence, computer equipment and medium | |
| CN111523570A (en) | Smart city system based on community post house and control method thereof | |
| CN111751788A (en) | Auxiliary enhancement system for big data intelligent detection equipment | |
| Li | Application of Artificial Intelligence System Based on Wireless Sensor Network in Enterprise Management | |
| CN110457208A (en) | Bootstrap technique, device, equipment and the computer readable storage medium of semiology analysis | |
| CN106446382B (en) | The mathematics library of domain-oriented entity and analysis system and its implementation |
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 | ||
| CB02 | Change of applicant information |
Address after: 610042 No. 270, floor 2, No. 8, Jinxiu street, Wuhou District, Chengdu, Sichuan Applicant after: Chengdu shuzhilian Technology Co.,Ltd. Address before: No.2, floor 4, building 1, Jule road crossing, Section 1, West 1st ring road, Wuhou District, Chengdu City, Sichuan Province 610041 Applicant before: CHENGDU SHUZHILIAN TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information |