CN111553709A - Reservoir ecological fish big data traceability system and method - Google Patents
Reservoir ecological fish big data traceability system and method Download PDFInfo
- Publication number
- CN111553709A CN111553709A CN202010219266.0A CN202010219266A CN111553709A CN 111553709 A CN111553709 A CN 111553709A CN 202010219266 A CN202010219266 A CN 202010219266A CN 111553709 A CN111553709 A CN 111553709A
- Authority
- CN
- China
- Prior art keywords
- data
- traceability
- ecological fish
- reservoir ecological
- tracing
- 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
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000007405 data analysis Methods 0.000 claims abstract description 26
- 238000007726 management method Methods 0.000 claims abstract description 13
- 238000013500 data storage Methods 0.000 claims abstract description 10
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 230000005540 biological transmission Effects 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 15
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000013499 data model Methods 0.000 claims description 10
- 238000013075 data extraction Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 4
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 abstract description 8
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000009395 breeding Methods 0.000 abstract 1
- 230000001488 breeding effect Effects 0.000 abstract 1
- 210000003128 head Anatomy 0.000 description 6
- 210000000006 pectoral fin Anatomy 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 235000013332 fish product Nutrition 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002688 persistence Effects 0.000 description 2
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Library & Information Science (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of big data traceability, and particularly relates to a reservoir ecological fish big data traceability system and a reservoir ecological fish big data traceability method, wherein the reservoir ecological fish big data traceability system comprises the following steps: the application terminal is used for reservoir ecological fish traceability data query, acquisition and result feedback; the background server is used for tracing data classification management and transmission control; the data storage unit is in data connection with the background server and realizes the structuring and classified management of the tracing data through a file system and a database; the source tracing data analysis unit obtains result data through calculation and analysis of the source tracing data and feeds the result data back to the application terminal through the background server to realize reservoir ecological fish source tracing result query. The identification traceability of the single-tail fish body is realized by adopting a big data traceability technology, compared with the traditional process monitoring traceability, the identification traceability is more accurate, the actual operability and the confidence level are higher, and an important basis is provided for the quality guarantee and the brand industrialization of the reservoir ecological breeding industry.
Description
Technical Field
The invention belongs to the technical field of big data traceability, and particularly relates to a big data traceability system and method for reservoir ecological fish.
Background
The reservoir water purification fishing industry has good ecological environmental protection benefit, social public benefit and industrial economic benefit. Compared with pond culture fish, the fish cultured in the reservoir has better quality, higher nutrition and better taste, so the price of the fish is far higher than that of the fish cultured in the pond. However, in the fish market, reservoir fish and cultured fish are mixed, and consumers can buy the pond cultured fish at high cost. In order to maintain the rights and interests of consumers and solve the doubts of vast consumers on the quality of the reservoir fish products, a big data traceability system of reservoir fish is needed, when the consumers buy the reservoir fish, the consumers can trace the source of the reservoir fish through the traceability system, and the worry of the consumers on the quality of the reservoir fish products is thoroughly eliminated.
In view of the fact that fish individuals are relatively small, and the number of fishes caught at a time and brought into the market is large, and the single fish bodies are difficult to mark, track and trace the source, the traditional source tracing mode mainly adopts the process monitoring to realize the source tracing at present, for example, the whole process monitoring from catching to transportation and finally to processing and processing on the market is adopted. However, the value of the ecological fish is far higher than that of the artificial feeding fish, and the links from the ecological fish cultivation to the marketing processing process are more, so that monitoring blind areas are easy to occur, and the cost is high and the efficiency is low. The quality guarantee and the market brand value of the ecological fish are difficult to embody by combining the reasons. The method brings great limits to the industrialized development of reservoir ecological fish and the digging of market brand value.
Disclosure of Invention
The invention aims to provide a reservoir ecological fish big data traceability system and a reservoir ecological fish big data traceability method.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
the utility model provides a reservoir ecological fish big data traceability system which comprises:
the application terminal is used for reservoir ecological fish traceability data query, acquisition and result feedback so as to realize quick response of a consumer query request;
the background server is used for tracing data classification management and transmission control so as to realize quick calling of tracing data and feedback of result data;
the data storage unit is in data connection with the background server and realizes the structuralization and classification management of the source tracing data through a file system and a database;
the source tracing data analysis unit obtains result data through calculation and analysis of the source tracing data and feeds the result data back to the application terminal through the background server to realize reservoir ecological fish source tracing result query.
The background server is responsible for controlling the specific business module process and the logic application design of the business module, classifies the data transmitted by the application terminal, selects a proper data transmission interface in the data access layer, and finally transmits and stores the data into the cloud database.
Further, the application terminal is any one of APP or WEB.
Further, the tracing data analysis unit comprises one or more combined image feature extraction algorithm models for realizing multi-dimensional convolution processing of the tracing collected image by the convolutional neural network.
Further, the tracing data analysis unit comprises one or more combined image standard training sets as the input of the convolutional neural network to realize the image feature extraction.
Further, the traceable data analysis unit comprises one or more combined algorithm models for accelerating convergence of the image feature extraction error range, so as to realize the deep learning capability of the traceable data analysis unit.
Further, the tracing data analysis unit comprises one or more combined feature data classification algorithm models for realizing result identification of the feature data.
Further, the standard training set of images comprises one or more combined unstructured data models as the convolutional neural network feature data extraction input.
Further, the image standard training set further comprises one or more combined structured data models for further improving the reliability of the image standard training set.
Further, the structured data model comprises 1-50 data points.
Based on the technical proposal, the invention also comprises,
a reservoir ecological fish big data tracing method comprises the following steps:
the method comprises the steps that a consumer opens an application terminal to initiate a source tracing query request, and photographs on-site ecological fish to obtain a real-time source tracing acquisition image;
the background server effectively judges the traceability images acquired by the application terminal, calls the acquired images with optimal definition and integrity and realizes data classification management through the data storage unit;
the tracing data analysis unit calls and standardizes data in the data storage unit, takes the image standard training set as the characteristic data extraction input of the convolutional neural network and carries out multi-dimensional convolution processing on the image standard training set and the tracing data to realize characteristic extraction;
carrying out accelerated convergence verification processing on the image feature extraction error range, and carrying out deep learning optimization on the feature extraction error weight to obtain optimal feature extraction data;
classifying and identifying the feature extraction data through a classifier in an analysis model to obtain result data;
and the source tracing data analysis unit feeds back the result data to the application terminal through the background server to realize reservoir ecological fish source tracing query.
The invention has the following beneficial effects:
1. according to the big data reservoir ecological fish traceability system and method, a big data traceability technology is adopted, consumers only need to take pictures of purchased reservoir ecological fish through a mobile phone and upload the fish to the traceability system, and the fish is analyzed and identified through image feature extraction of the system, so that the technical defect of the traditional traceability mode is overcome, and the traceability reliability is greatly improved;
2. the system and the method for tracing the big data of the ecological fish in the reservoir have the capabilities of on-line learning and optimization, the tracing accuracy is higher, no blind area exists in the whole process, the rights and interests of consumers are effectively maintained, and the doubtful worry of the consumers on the quality of the fish products in the reservoir is solved;
3. meanwhile, the whole participation of consumers increases the further understanding of the consumers on the reservoir ecological fish, and is beneficial to the culture and accumulation of market acceptance.
Drawings
FIG. 1 is a flow chart of a reservoir ecological fish big data traceability system and a reservoir ecological fish big data traceability method;
FIG. 2 is a flow chart of a reservoir ecological fish big data traceability system based on Spring Boot technology;
FIG. 3 is a schematic diagram of structured image marking of a reservoir ecological fish big data traceability system;
fig. 4 is a schematic diagram of an image structured distance measurement mark of a reservoir ecological fish big data traceability system.
Detailed Description
In order that those skilled in the art can better understand the present invention, the following embodiments are further described.
As shown in fig. 1, a big data traceability system of reservoir ecological fish is characterized by comprising:
the application terminal is used for reservoir ecological fish traceability data query, acquisition and result feedback so as to realize quick response of a consumer query request;
the background server is used for tracing data classification management and transmission control so as to realize quick calling of tracing data and feedback of result data;
the data storage unit is in data connection with the background server and realizes the structuralization and classification management of the source tracing data through a file system and a database;
the source tracing data analysis unit obtains result data through calculation and analysis of the source tracing data and feeds the result data back to the application terminal through the background server to realize reservoir ecological fish source tracing result query.
The background server is responsible for controlling a specific business module process and logic application design of the business module, carries out classification processing on data transmitted by the application terminal, selects a suitable data transmission interface in the data access layer, and finally transmits and stores the data to the cloud database, wherein the application terminal is any one of APP or WEB.
In order to make the operation and operation of the system more scientific and reasonable, the system adopts the following technical design and support:
the method comprises the steps of constructing and managing projects by adopting a Maven technology, continuously integrating by adopting Jenkins, realizing service modularization and management by using a SpringBoot technology, and constructing a distributed micro-service cloud architecture platform.
The background server framework part adopts Spring MVC technology, and the Spring framework provides a full-function MVC module for constructing the Web application program. And (4) using an MVC (model view controller) architecture in which Spring can be inserted, and performing customization selection through a policy interface and a Web framework. The Spring framework is highly configurable and contains multiple view technologies, and Spring MVC separates the roles of controller, model objects, dispatcher, and handler objects, which separation is easier to customize, and enables decoupling of the customizations of the customization layer.
And the file system persistence layer supports customized SQL, a storage process and high-level mapping by adopting a MyBatis persistence layer framework. MyBatis can avoid JDBC code and manual setting of parameters and acquisition of result sets. MyBatis can use simple XML or annotations to configure and map native types, interfaces, and Java's POJO as records in a database.
The database layer adopts Java API which is used for executing SQL statements by JDBC (Java database connection), can provide uniform access for various relational databases, and is composed of classes and interfaces written by a group of Java languages. JDBC provides a benchmark by which more advanced tools and interfaces can be built to enable database developers to write database applications.
The cache layer adopts Redis technology to customize an open source, uses ANSI C language to write, supports network, can be based on a memory and can also be persistent log-type, Key-Value database, and provides API of multiple languages.
The APP application terminal is used for constructing and configuring a running environment JDK 1.8 or a complieSdkVersion 27 in Android Studio, and the APP program is composed of an Xml layout file and a Java program file.
Web page terminal: based on a Bootstrap front-end UI open source framework, CSS, JavaScript language, HTML And JQuery framework libraries are applied, Ajax technology, namely asynchronous JavaScript And XML (asynchronous JavaScript And XML) is adopted, partial web pages can be updated on the premise that the whole web page can not be refreshed, a background server is used for exchanging a small amount of data, And the web pages are enabled to be updated asynchronously.
The JSON technology is adopted to realize the exchange transmission between the application terminal and the background server.
As shown in fig. 2, the system of the present invention employs a Spring Boot technology, which can create an independent and self-starting application container, does not need to create War package and publish it to the container, and creates and maintains War package, configuration and management of the container, and through a customized label of Maven, an application program of the Spring Boot can be quickly created, which can automatically configure Spring to the maximum extent, without manually configuring various parameters, and reduce human input.
The tracing data analysis unit comprises one or more combined image feature extraction algorithm models for realizing the multidimensional convolution processing of the tracing collected images by the convolution neural network.
The method preferably adopts an improved BOF algorithm model to realize the extraction of the image characteristics of the ecological fish of the reservoir, and mainly comprises the steps of constructing a Hessian matrix, constructing a scale space and accurately positioning characteristic points; drawing a circle field with 6s as a radius by taking each feature point as a center, wherein s represents the scale of the feature point, calculating Haar wavelet responses of all the feature points in the radius in the x and y directions, and assigning a weight according to the distance between the feature point and the center point, wherein the closer the weight is, the larger the weight is; and then forming a new vector by using the responding characteristic points within the range of 60 degrees, traversing the whole circular area, and selecting the longest vector direction as the main direction of the characteristic points to generate the characteristic descriptors.
The tracing data analysis unit comprises one or more combined algorithm models for accelerating convergence of image feature extraction error ranges, so that the deep learning capability of the tracing data analysis unit is realized.
The invention preferably adopts an improved CNN algorithm model to realize the accelerated convergence of the error range of image feature extraction and improve the deep learning capability of a tracing data analysis unit, and mainly comprises the following steps: setting the number m of elements of convolution kernel and initializing acceleration constant c1、c2And an inertia weight ω value, initializing the element position X vector and the atomic velocity V vector to random numbers between (0, 1); calculating each element in the set m elements of the convolution kernel in a convolution neural network to obtain forward propagation; after forward propagation is obtained, calculating to obtain an error; and if the error value reaches the minimum value of the error threshold range, stopping the algorithm.
The tracing data analysis unit comprises one or more combined characteristic data classification algorithm models for realizing result identification of the characteristic data.
The invention preferably adopts an improved KNN algorithm model to realize the result identification of the characteristic data, and mainly comprises the following steps: calculating the distance between the test data features and the data features of each training set; sorting according to the distance increasing order, and then selecting K features with the minimum distance; taking the maximum occurrence times of the categories in the K adjacent training data as the categories of the ecological fish picture examples input into the new reservoir; and (4) classifying the reservoir ecological fish by analyzing and comparing the characteristic distances of the reservoir ecological fish image to be classified and the classified reservoir ecological fish image.
As shown in fig. 3 to 4, the traceback data analysis unit includes one or more combined image standard training sets as an input of the convolutional neural network to implement image feature extraction. The standard training set of images comprises one or more combined unstructured data models as the feature data extraction input of the convolutional neural network. And the original image of the training set unstructured data model which is preferably not marked with any labels is used as the characteristic data extraction input of the convolutional neural network for convolution processing.
The image standard training set also comprises one or more combined structured data models for further improving the reliability of the image standard training set. The structured data model contains 1-50 data points. The reservoir ecological fish shape structure and distance measurement are marked through image intelligent processing, and the optimization and improvement of the reliability of a training set are facilitated.
Wherein the ecological fish morphological structure data points include: weight, head length, head weight, length of kisses, eye diameter, eye distance, length of head behind eyes, length of trunk, height of body, length of caudal peduncle, height of caudal peduncle, length of caudal peduncle, total length, body length, head width, body width, tail width, etc.
The distance measurement indicators are: head width: maximum width and body width of the head left and right axes: maximum width of right and left axes of trunk, tail width: maximum width of the tail left and right axes, AB (distance from the osculum to the head-back end), AC (distance from the osculum to the pectoral fin start point), AE (distance from the osculum to the ventral fin start point), BC (distance from the pectoral fin start point to the head-back end), BD (distance from the head-back end to the dorsal fin start point), BE (distance from the head-back end to the pectoral fin start point), CD (distance from the pectoral fin start point to the dorsal fin start point), CE (distance from the pectoral fin start point to the ventral fin start point), DE (distance from the dorsal fin start point to the ventral fin start point), DF (dorsal fin base length), DG (distance from the dorsal fin start point to the hip fin start point), EF (distance from the ventral fin start point to the dorsal fin base end), FG (distance from the dorsal fin start point to the hip fin start point), DH (distance from the dorsal fin start point to the hip fin base end), FH (distance from the dorsal fin base end to the hip fin base end), FI (distance from the base end of the dorsal fin to the starting point of the base back of the caudal fin), FJ (distance from the base end of the dorsal fin to the starting point of the base back of the caudal fin), HI (distance from the base end of the hip fin to the starting point of the base back of the caudal fin), HJ (distance from the base end of the hip fin to the starting point of the back of the caudal fin), IJ (distance from the starting point of the back of the caudal fin to the starting point of the abdomen of the caudal fin), EE (distance from the starting point of the pectoral fin), and GG (distance from the starting.
A reservoir ecological fish big data tracing method comprises the following steps:
the method comprises the steps that a consumer opens an application terminal to initiate a source tracing query request, and photographs on-site ecological fish to obtain a real-time source tracing acquisition image;
the background server effectively judges the traceability images acquired by the application terminal, calls the acquired images with optimal definition and integrity and realizes data classification management through the data storage unit;
the tracing data analysis unit calls and standardizes data in the data storage unit, takes the image standard training set as the characteristic data extraction input of the convolutional neural network and carries out multi-dimensional convolution processing on the image standard training set and the tracing data to realize characteristic extraction;
carrying out accelerated convergence verification processing on the image feature extraction error range, and carrying out deep learning optimization on the feature extraction error weight to obtain optimal feature extraction data;
classifying and identifying the feature extraction data through a classifier in an analysis model to obtain result data;
and the source tracing data analysis unit feeds back the result data to the application terminal through the background server to realize reservoir ecological fish source tracing query.
The KNN-based reservoir ecological fish classification method provided by the invention is introduced in detail. The description of the specific embodiments is only intended to facilitate an understanding of the method of the invention and its core ideas. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Claims (10)
1. The utility model provides a reservoir ecological fish big data traceability system which comprises:
the application terminal is used for reservoir ecological fish traceability data query, acquisition and result feedback so as to realize quick response of a consumer query request;
the background server is used for tracing data classification management and transmission control so as to realize quick calling of tracing data and feedback of result data;
the data storage unit is in data connection with the background server and realizes the structuralization and classification management of the source tracing data through a file system and a database;
the source tracing data analysis unit obtains result data through calculation and analysis of the source tracing data and feeds the result data back to the application terminal through the background server to realize reservoir ecological fish source tracing result query.
2. The reservoir ecological fish big data traceability system of claim 1, wherein the application terminal comprises any one of APP or WEB.
3. The reservoir ecological fish big data traceability system of claim 1, wherein the traceability data analysis unit comprises one or more combined image feature extraction algorithm models for realizing multi-dimensional convolution processing of traceability acquired images by a convolutional neural network.
4. The reservoir ecological fish big data traceability system of claim 3, wherein the traceability data analysis unit comprises one or more combined image standard training sets as an input of a convolutional neural network to realize image feature extraction.
5. The reservoir ecological fish big data traceability system of claim 4, wherein the traceability data analysis unit comprises one or more combined algorithm models for accelerated convergence of image feature extraction error ranges, so as to realize the deep learning capability of the traceability data analysis unit.
6. The reservoir ecological fish big data traceability system of claim 5, wherein the traceability data analysis unit comprises one or more combined feature data classification algorithm models for realizing result identification of feature data.
7. The reservoir ecological fish big data traceability system of claim 4, wherein the image standard training set comprises one or more combined unstructured data models as convolutional neural network feature data extraction inputs.
8. The reservoir ecological fish big data traceability system of claim 7, wherein the image standard training set further comprises one or more combined structured data models for further improving the reliability of the image standard training set.
9. The reservoir ecological fish big data traceability system of claim 8, wherein said structured data model comprises 1-50 data points.
10. A reservoir ecological fish big data tracing method is characterized by comprising the following steps:
the method comprises the steps that a consumer opens an application terminal to initiate a source tracing query request, and photographs on-site ecological fish to obtain a real-time source tracing acquisition image;
the background server effectively judges the traceability images acquired by the application terminal, calls the acquired images with optimal definition and integrity and realizes data classification management through the data storage unit;
the tracing data analysis unit calls and standardizes data in the data storage unit, takes the image standard training set as the characteristic data extraction input of the convolutional neural network and carries out multi-dimensional convolution processing on the image standard training set and the tracing data to realize characteristic extraction;
carrying out accelerated convergence verification processing on the image feature extraction error range, and carrying out deep learning optimization on the feature extraction error weight to obtain optimal feature extraction data;
classifying and identifying the feature extraction data through a classifier in an analysis model to obtain result data;
and the source tracing data analysis unit feeds back the result data to the application terminal through the background server to realize reservoir ecological fish source tracing query.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010219266.0A CN111553709A (en) | 2020-03-25 | 2020-03-25 | Reservoir ecological fish big data traceability system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010219266.0A CN111553709A (en) | 2020-03-25 | 2020-03-25 | Reservoir ecological fish big data traceability system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111553709A true CN111553709A (en) | 2020-08-18 |
Family
ID=72004199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010219266.0A Pending CN111553709A (en) | 2020-03-25 | 2020-03-25 | Reservoir ecological fish big data traceability system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553709A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742806A (en) * | 2022-04-21 | 2022-07-12 | 海南大学 | Fish body morphological feature measurement method based on key point coordinate regression |
-
2020
- 2020-03-25 CN CN202010219266.0A patent/CN111553709A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742806A (en) * | 2022-04-21 | 2022-07-12 | 海南大学 | Fish body morphological feature measurement method based on key point coordinate regression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898225B (en) | Data labeling method based on man-machine collaborative learning | |
| CN111240662A (en) | Spark machine learning system and learning method based on task visual dragging | |
| Wu et al. | Improved ResNet-50 deep learning algorithm for identifying chicken gender | |
| CN110547210A (en) | feed supply method and system, computer system, and storage medium | |
| CN112633822B (en) | Asset management method based on digital twin technology, storage medium and mobile terminal | |
| US20230222768A1 (en) | Multiscale point cloud classification method and system | |
| Premkumar et al. | IoT-enabled edge computing model for smart irrigation system | |
| CN114936835A (en) | BIM-based compliance automatic review method and system | |
| CN111291803B (en) | Image grading granularity migration method, system, equipment and medium | |
| CN116295022A (en) | Pig body ruler measurement method based on deep learning multi-parameter fusion | |
| Fang et al. | Using channel and network layer pruning based on deep learning for real-time detection of ginger images | |
| Plum et al. | replicAnt: a pipeline for generating annotated images of animals in complex environments using Unreal Engine | |
| Xu et al. | Digital twin for aquaponics factory: Analysis, opportunities, and research challenges | |
| Zhang et al. | A cascaded individual cow identification method based on DeepOtsu and EfficientNet | |
| CN114419372A (en) | Multi-scale point cloud classification method and system | |
| Arıkan et al. | Estrus detection and dairy cow identification with cascade deep learning for augmented reality-ready livestock farming | |
| CN111553709A (en) | Reservoir ecological fish big data traceability system and method | |
| CN115861720A (en) | Small sample subclass image classification and identification method | |
| CN116168392A (en) | Target labeling method and system based on optimal source domain of multidimensional space feature model | |
| Zhang et al. | Improved YOLOv4 recognition algorithm for pitaya based on coordinate attention and combinational convolution | |
| CN115169578A (en) | AI model production method and system based on meta-space data markers | |
| Sinnott et al. | Run or pat: using deep learning to classify the species type and emotion of pets | |
| CN114969325A (en) | Multi-element urban geological big data storage management and mining analysis system | |
| CN112016515A (en) | File cabinet vacancy detection method and device | |
| Lu et al. | Using coarse label constraint for fine-grained visual classification |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240512 Address after: 400717 Tainong garden, Jizhen village, Jingguan Town, Beibei District, Chongqing Applicant after: CHONGQING LIANGJIANG ECOLOGICAL FISHERIES DEVELOPMENT CO.,LTD. Country or region after: China Address before: 401147 North Bank Xinzhou Community, No. 28 Jincheng Road, Yubei District, Chongqing Applicant before: Tian Qingbing Country or region before: China Applicant before: Wang Kai Applicant before: Zhu Hanchun Applicant before: Xiao Chuanming Applicant before: Zeng Yan Applicant before: Guo Linxin Applicant before: Zheng Gang |