Big data analysis platform for germplasm resources of blanched garlic leaves

Abstract

The invention discloses a big data analysis platform for germplasm resources of blanched garlic leaves, and relates to the technical field of agricultural information. And a data acquisition and management module. Precise classification and germination prediction of blanched garlic leaf germplasm resources are realized by using a growth prediction and decision support module, the automation degree is high, the germplasm screening efficiency is remarkably improved, the accuracy of germplasm resource classification and identification is effectively improved by combining a DNA back-stepping technology and a morphological processing algorithm, a guarantee is provided for high-quality planting, and the method is suitable for popularization and application. Through use of a knowledge fusion and learning module, knowledge and experience of breeding experts are fused into a big data analysis platform, technologies such as a knowledge graph and rule reasoning are utilized, a cooperation mechanism of expert experience and an intelligent algorithm is constructed, the guiding function of traditional experience is fully played, and meanwhile scientificity and adaptability of an algorithm model are improved. The deep fusion of a traditional breeding technology and a modern intelligent technology is realized.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, specifically a big data analysis platform for garlic sprout germplasm resources. Background Art

[0002] Garlic sprouts are a common vegetable with a relatively short growth cycle. Under suitable planting conditions, they can efficiently absorb nutrients such as selenium and strontium in the soil and nutrient solution. This characteristic gives garlic sprouts broad application prospects in specific fields such as functional agriculture, food processing industry, and health product development. On this basis, to improve the application and development value of garlic sprouts in specific fields, for example, garlic sprout products rich in selenium or strontium can be produced according to different consumer needs, and garlic sprout roots can be used to produce garlic sprout oil for people with unbalanced nutritional intake.

[0003] In the field of garlic sprout germplasm resources, the problem of the correlation between garlic sprout germplasm gene information and phenotypic characteristics currently faces significant technical bottlenecks and challenges, mainly reflected in the complexity of germplasm resources, the differences in growth environments, and the limitations of traditional breeding methods. The content and distribution characteristics of trace elements such as allicin, selenium, and strontium in garlic sprouts directly determine their quality and functional value. However, due to significant differences between and within species, for example, the same group of garlic cloves or different garlic species, the expression of trace elements is affected by multiple factors such as genetic background, cultivation techniques, and growth environment. This complexity greatly increases the difficulty of accurate analysis of germplasm resources. At the same time, different regions and climatic conditions have an important impact on the growth and quality of garlic sprouts. The content of trace elements fluctuates greatly under different growth environments, making adaptive breeding the key to high-quality production of garlic sprouts. In the traditional breeding process, it mainly relies on artificial experience and phenotypic observation, lacking in-depth analysis of the distribution law of trace elements, resulting in low utilization rate of germplasm resources and low efficiency of screening high-quality varieties. Therefore, realizing accurate analysis and regulation of trace elements and prediction of germination rate in garlic sprouts, and conducting in-depth mining combined with big data technology, has become the core technical difficulty in improving the planting quality and production efficiency of garlic sprouts. Summary of the Invention

[0004] The object of the present invention is to provide a big data analysis platform for garlic sprout germplasm resources to solve the problems in the above background art.

[0005] To achieve the above object, the present invention is realized through the following technical solutions: A big data analysis platform for garlic sprout germplasm resources, including:

[0006] A processor for data processing during the use of the system;

[0007] A data collection and management module for collecting and integrating multi-dimensional data information during the growth of garlic sprouts and storing and managing the multi-dimensional data information;

[0008] The germplasm resource analysis module is used to analyze the external characteristics of garlic sprouts at different growth stages, and then realize the screening of garlic sprout germplasm and germination prediction. Combining with garlic sprout gene data, it analyzes the correlation between garlic sprout phenotypic characteristics and trace element distribution;

[0009] The growth prediction and decision support module is used to dynamically predict the germination time, growth trend and final quality of garlic sprouts, and recommend the best garlic sprout germplasm selection plan according to the regional environmental characteristics;

[0010] The visualization and interaction module is used to realize the visual analysis of the multi-dimensional data information, generate personalized reports, and provide intuitive data support for growers and breeders;

[0011] The knowledge fusion and learning module is used to transform the experience of breeding experts and domain knowledge into operable rules and model parameters;

[0012] The achievement sharing module is used to provide technical support for the preservation and management of high-quality garlic sprout germplasm resources, and then realize data sharing and collaboration between breeders and researchers;

[0013] The growth prediction and decision support module includes a dynamic prediction module, a germplasm adaptation analysis module and a quality improvement guidance module. There are two-way signal connections between the dynamic prediction module, the germplasm adaptation analysis module and the quality improvement guidance module. The knowledge fusion and learning module includes a knowledge base module, a rule reasoning module and an algorithm model optimization module. There are two-way signal connections between the knowledge base module, the rule reasoning module and the algorithm model optimization module;

[0014] The output end of the knowledge base module in the knowledge fusion and learning module is two-way signal connected to the input end of the dynamic prediction module in the growth prediction and decision support module.

[0015] Furthermore, the data acquisition and management module includes a data acquisition module, a data storage module, a data management module and a data transmission module. There are two-way signal connections between the data acquisition module, the data storage module, the data management module and the data transmission module.

[0016] Furthermore, the germplasm resource analysis module includes an image recognition module, a feature extraction module, a correlation analysis module and a trace element distribution law research module. There are two-way signal connections between the image recognition module, the feature extraction module, the correlation analysis module and the trace element distribution law research module.

[0017] Furthermore, the visualization and interaction module includes a data visualization display module and an interaction module. There are two-way signal connections between the data visualization display module and the interaction module.

[0018] Further, the achievement sharing module includes a germplasm resource protection module, a technical achievement sharing module, and a report generation module, and there are two-way signal connections between the germplasm resource protection module, the technical achievement sharing module, and the report generation module.

[0019] Further, the output end of the processor is two-way signal connected to the input end of the data transmission module in the data acquisition and management module, and the output end of the processor is two-way signal connected to the input end of the image recognition module in the germplasm resource analysis module.

[0020] Further, the output end of the processor is two-way signal connected to the input end of the dynamic prediction module in the growth prediction and decision support module, and the output end of the processor is two-way signal connected to the input end of the interaction module in the visualization and interaction module.

[0021] Further, the output end of the processor is two-way signal connected to the input end of the knowledge base module in the knowledge fusion and learning module, and the output end of the processor is two-way signal connected to the input end of the technical achievement sharing module in the achievement sharing module.

[0022] Further, the output end of the dynamic prediction module in the growth prediction and decision support module is two-way signal connected to the input end of the data transmission module in the data acquisition and management module.

[0023] Further, the output end of the data transmission module in the data acquisition and management module is two-way signal connected to the input end of the image recognition module in the germplasm resource analysis module.

[0024] The present invention provides a big data analysis platform for garlic sprout germplasm resources. It has the following beneficial effects:

[0025] (1) For this big data analysis platform for garlic sprout germplasm resources, through the use of the growth prediction and decision support module, accurate classification and germination prediction of garlic sprout germplasm resources are realized. It has a high degree of automation, significantly improves the efficiency of germplasm screening, and combines DNA reverse deduction technology and morphological processing algorithms to effectively improve the accuracy of germplasm resource classification and identification, providing guarantee for high-quality planting.

[0026] (2) For this big data analysis platform for garlic sprout germplasm resources, through the use of the knowledge fusion and learning module, the knowledge and experience of breeding experts are integrated into the big data analysis platform. By using technologies such as knowledge graphs and rule reasoning, a collaborative mechanism between expert experience and intelligent algorithms is constructed, giving full play to the guiding role of traditional experience, while improving the scientificity and adaptability of the algorithm model, and realizing the deep integration of traditional breeding technology and modern intelligent technology.

[0027] (3) The big data analysis platform for garlic yellow germplasm resources establishes a dynamic germplasm resource library, optimizes garlic seed selection and cultivation strategies according to the environmental characteristics of different regions, makes the cultivation of garlic yellow more adaptable to regional needs, improves planting efficiency and resource utilization rate, analyzes and determines the best cultivation environment, maximizes the expression potential of trace elements, and realizes a green and efficient planting mode.

[0028] (4) The big data analysis platform for garlic yellow germplasm resources provides a scientific basis for realizing the precise regulation of trace elements and optimizing planting plans, can cultivate garlic yellow rich in specific functional components, meet the diversified market demands, promote the development of garlic yellow products towards high added value, realize the efficient utilization and added value improvement of garlic yellow resources, promote the development of the garlic yellow industrial chain towards the direction of intelligence, greenness and high quality, and fully meet the diversified demands of modern agriculture and the health industry. Description of the Drawings

[0029] Figure 1 It is the overall system diagram of the big data analysis platform for garlic yellow germplasm resources of the present invention;

[0030] Figure 2 It is the schematic diagram of the data collection and management module of the big data analysis platform for garlic yellow germplasm resources of the present invention;

[0031] Figure 3 It is the schematic diagram of the germplasm resource analysis module of the big data analysis platform for garlic yellow germplasm resources of the present invention;

[0032] Figure 4 It is the schematic diagram of the growth prediction and decision support module of the big data analysis platform for garlic yellow germplasm resources of the present invention;

[0033] Figure 5 It is the schematic diagram of the visualization and interaction module of the big data analysis platform for garlic yellow germplasm resources of the present invention;

[0034] Figure 6 It is the schematic diagram of the knowledge fusion and learning module of the big data analysis platform for garlic yellow germplasm resources of the present invention;

[0035] Figure 7 It is the schematic diagram of the achievement sharing module of the big data analysis platform for garlic yellow germplasm resources of the present invention.

[0036] In the figure: 1. Processor; 2. Data collection and management module; 3. Germplasm resource analysis module; 4. Growth prediction and decision support module; 5. Visualization and interaction module; 6. Knowledge fusion and learning module; 7. Achievement sharing module. Detailed Embodiments

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments.

[0038] Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present invention, and should not be construed as a limitation of the present invention.

[0039] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0040] Please refer to Figure 1-7 , the present invention provides a technical solution: a big data analysis platform for garlic sprout germplasm resources, including:

[0041] A processor 1 for data processing during the use of the system;

[0042] A data acquisition and management module 2 for collecting and integrating multi-dimensional data information during the growth process of garlic sprouts and storing and managing the multi-dimensional data information;

[0043] A germplasm resource analysis module 3 for analyzing the external characteristics of garlic sprouts at different growth stages, thereby realizing the screening of garlic sprout germplasm and germination prediction, and combining the garlic sprout gene data to analyze the correlation between the phenotypic characteristics of garlic sprouts and the distribution of trace elements;

[0044] A growth prediction and decision support module 4 for dynamically predicting the germination time, growth trend and final quality of garlic sprouts, and recommending the best germplasm selection scheme for garlic sprouts according to the regional environmental characteristics;

[0045] A visualization and interaction module 5 for realizing the visualization analysis of the multi-dimensional data information and generating a personalized report to provide intuitive data support for growers and breeders;

[0046] A knowledge fusion and learning module 6 for transforming the experience and domain knowledge of breeding experts into operable rules and model parameters;

[0047] An achievement sharing module 7 for providing technical support for the preservation and management of high-quality garlic sprout germplasm resources, thereby realizing data sharing and collaboration between breeders and researchers;

[0048] The growth prediction and decision support module 4 includes a dynamic prediction module, a germplasm adaptation analysis module, and a quality improvement guidance module. There are two-way signal connections between the dynamic prediction module, the germplasm adaptation analysis module, and the quality improvement guidance module. The knowledge fusion and learning module 6 includes a knowledge base module, a rule reasoning module, and an algorithm model optimization module. There are two-way signal connections between the knowledge base module, the rule reasoning module, and the algorithm model optimization module;

[0049] The output end of the knowledge base module in the knowledge fusion and learning module 6 is two-way signal connected to the input end of the dynamic prediction module in the growth prediction and decision support module 4.

[0050] Dynamic prediction module: Dynamically predict the germination time, growth trend, and final quality of garlic sprouts through a machine learning model.

[0051] Germplasm adaptation analysis module: Recommend the best germplasm selection plan based on regional environmental characteristics (such as climate, soil, etc.).

[0052] Quality improvement guidance module: Optimize the utilization of trace elements and the garlic sprout variety improvement plan by combining expert knowledge and data analysis.

[0053] Knowledge base module: Transform the experience and domain knowledge of breeding experts into operable rules or model parameters.

[0054] Rule reasoning module: Improve the scientificity of germplasm resource utilization and the accuracy of decision-making through a knowledge graph and reasoning algorithms.

[0055] Algorithm model optimization module: Continuously optimize the algorithm model based on new data to achieve the dynamic evolution and function improvement of the platform.

[0056] Specifically, the data acquisition and management module 2 includes a data acquisition module, a data storage module, a data management module, and a data transmission module. There are two-way signal connections between the data acquisition module, the data storage module, the data management module, and the data transmission module.

[0057] Data acquisition module: Integrate the phenotypic characteristics of garlic sprouts, genotype information, environmental parameters (such as temperature, humidity, light, soil composition), and the experience of breeding experts.

[0058] Database construction: Establish a germplasm resource database with trace elements such as allicin, selenium, and strontium as the core, covering the interspecific differences and intraspecific characteristics of germplasms.

[0059] Data storage module and data management module: Achieve efficient multi-dimensional data storage, classification, and query functions, and support real-time data update and historical data traceability.

[0060] Specifically, the germplasm resource analysis module 3 includes an image recognition module, a feature extraction module, a correlation analysis module, and a research module on the distribution law of trace elements. There are two-way signal connections between the image recognition module, the feature extraction module, the correlation analysis module, and the research module on the distribution law of trace elements.

[0061] Image recognition module and feature extraction module: Using deep learning algorithms, analyze the external characteristics of garlic sprouts at different growth stages to achieve germplasm screening and germination prediction.

[0062] Correlation analysis module: Combine gene data to analyze the correlation between the phenotypic characteristics of garlic sprouts and the distribution of trace elements.

[0063] Research module on the distribution law of trace elements: Systematically analyze the absorption and expression laws of functional components such as allicin, selenium, and strontium in different garlic varieties and environmental conditions.

[0064] Specifically, the visualization and interaction module 5 includes a data visualization display module and an interaction module. There are two-way signal connections between the data visualization display module and the interaction module.

[0065] Data visualization display module: Provide visualization analysis functions for multi-dimensional data, such as trace element distribution maps, germplasm classification maps, environmental adaptability analysis maps, etc.

[0066] Interaction module: Support users to query, filter, and analyze, generate personalized reports, and provide intuitive data support for growers and breeders.

[0067] Specifically, the achievement sharing module 7 includes a germplasm resource protection module, a technology achievement sharing module, and a report generation module. There are two-way signal connections between the germplasm resource protection module, the technology achievement sharing module, and the report generation module.

[0068] Germplasm resource protection module: Provide technical support for the preservation and management of high-quality germplasm resources.

[0069] Technology achievement sharing module: Support data sharing and collaboration between breeders and researchers, and promote the collective development of the garlic sprout industry.

[0070] Report generation module: Automatically generate technical reports according to the analysis results, covering planting suggestions, resource utilization efficiency evaluation, and improvement plans.

[0071] Specifically, the output end of the processor 1 is two-way signal connected to the input end of the data transmission module in the data acquisition and management module 2, and the output end of the processor 1 is two-way signal connected to the input end of the image recognition module in the germplasm resource analysis module 3.

[0072] Specifically, the output end of the processor 1 is bidirectionally signal-connected to the input end of the dynamic prediction module in the growth prediction and decision support module 4, and the output end of the processor 1 is bidirectionally signal-connected to the input end of the interaction module in the visualization and interaction module 5.

[0073] Specifically, the output end of the processor 1 is bidirectionally signal-connected to the input end of the knowledge base module in the knowledge integration and learning module 6, and the output end of the processor 1 is bidirectionally signal-connected to the input end of the technical achievement sharing module in the achievement sharing module 7.

[0074] Specifically, the output end of the dynamic prediction module in the growth prediction and decision support module 4 is bidirectionally signal-connected to the input end of the data transmission module in the data acquisition and management module 2.

[0075] Specifically, the output end of the data transmission module in the data acquisition and management module 2 is bidirectionally signal-connected to the input end of the image recognition module in the germplasm resource analysis module 3.

[0076] Technical solution

[0077] 1. Germplasm screening and germination prediction based on deep learning

[0078] The system uses a high-resolution industrial camera to capture the images of garlic seeds and identify the appearance features of garlic seeds, including size, shape, color, surface defects, etc. Classify garlic seeds, such as sorting by size (large garlic seeds, small garlic seeds) and health status (healthy, damaged, moldy). Achieve automatic sorting and transport the classified garlic seeds to the corresponding storage areas.

[0079] Use image recognition technology to collect the appearance features of garlic sprouts at different growth stages, and construct a germination prediction model through deep learning and machine learning algorithms to achieve precise screening of germplasm resources and scientific evaluation of germination rates. Combining external feature analysis and DNA reverse inference technology can further improve the classification and identification ability of germplasm resources.

[0080] The germination prediction model comprehensively analyzes the germination potential and growth trend by extracting the external morphological features of seeds (such as size, color, surface texture, etc.), combining maturity types (such as early maturity, medium maturity, late maturity) and regional distribution. The model further integrates environmental data (such as temperature, humidity, light, etc.) and germplasm characteristics to achieve dynamic prediction of the germination time and growth status of garlic sprouts. In addition, morphological processing algorithms are used to optimize the overall morphology of garlic sprout germplasm, and by removing image noise and refining or thickening the contours of target objects, the accuracy and stability of feature extraction are effectively improved, thus providing technical support for the in-depth research and efficient utilization of garlic sprout germplasm resources.

[0081] 2. Multi-dimensional trace element data fusion

[0082] By fusing multi-dimensional trace element data, a data model centered on key trace elements such as allicin, strontium, and selenium is constructed. Combining phenotypic data with genotype information, the distribution patterns and differences of trace elements among different garlic varieties and individuals within the same variety are systematically analyzed. At the same time, the absorption capacity of each variety for different trace elements is deeply analyzed, providing accurate data support for the functional characteristics of garlic sprout germplasm resources. Achieve precise regulation of trace elements, optimize fertilizer ratios and cultivation strategies, and cultivate special application-type garlic sprout plants (such as high-allicin, high-selenium, high-strontium, garlic sprout root oil extraction, etc.), meeting the needs of modern agriculture for high-quality and multi-functional products, and promoting the development of the garlic sprout industry towards intelligence and high added value.

[0083] 3. Construction of a dynamic germplasm resource bank

[0084] Establish a seed bank for garlic sprout germplasm resources suitable for different growth environments. According to the environmental characteristics of each region (such as temperature, humidity, soil composition, and light conditions), optimize the selection of garlic seeds to improve their adaptability and production efficiency. Through the germplasm resource database and multi-dimensional data analysis technology, systematically analyze the absorption capacity and expression patterns of different garlic varieties for functional trace elements such as allicin, strontium, and selenium, and evaluate their application potential under different growth conditions, thereby providing scientific guidance for the maximum utilization of functional components.

[0085] At the same time, deeply analyze the optimal cultivation environment required for each garlic sprout germplasm. Combining its genotype characteristics and phenotypic performance, clarify the key environmental factors (such as nutrient supply, cultivation mode, etc.) that affect growth quality and trace element content. Through intelligent data analysis and regional adaptability research, construct a garlic sprout cultivation plan with strong adaptability and prominent functionality, further promoting the precise and efficient development of garlic sprout cultivation, and providing customized planting solutions for agricultural production in different regions.

[0086] 4. Intelligent optimization integrating artificial experience

[0087] Integrate the experience of breeding experts into the big data analysis platform for garlic sprout germplasm resources. By constructing a collaborative mechanism of an expert knowledge base and an algorithm model, give full play to the advantages of traditional experience, and combine the high efficiency and precision of modern intelligent technologies. Using technologies such as knowledge graphs and rule reasoning, transform the experts' profound understanding of garlic sprout growth laws, trace element distribution, and quality improvement into quantifiable algorithm parameters, and deeply integrate them with the above big data analysis model.

[0088] Beneficial effects

[0089] This application can break through the bottlenecks of traditional planting and breeding, achieve remarkable results in improving the utilization rate of garlic sprout germplasm resources and the efficiency of quality improvement, and promote the technological upgrading and innovative development of the garlic sprout industry.

[0090] 1. Traditional garlic sprout cultivation methods often rely on growers' experience and relatively fixed processes, with limitations in many aspects. The garlic sprout germplasm resource big data analysis platform demonstrates many significant advantages.

[0091] (1) Ecological benefits

[0092] In terms of the efficiency of germplasm resource screening, the garlic sprout germplasm resources are complex, and the distribution characteristics of trace elements (such as allicin, selenium, strontium, etc.) are affected by multiple factors such as genetic background, cultivation techniques, and growth environment. The traditional germplasm resource analysis methods lack precision, resulting in low efficiency of high-quality germplasm screening and difficulty in meeting the needs of high-quality production. This solution realizes the precise classification and germination prediction of garlic sprout germplasm resources through germplasm screening technologies based on image recognition and deep learning, with a high degree of automation, significantly improving the germplasm screening efficiency. Combining DNA reverse inference technology and morphological processing algorithms effectively improves the accuracy of germplasm resource classification and identification, providing guarantee for high-quality cultivation.

[0093] Planting environment and germplasm, the climate, soil, and light conditions in different regions have a significant impact on the growth of garlic sprouts and the content of trace elements. The existing planting models have not effectively optimized the selection of germplasm resources and cultivation strategies according to the characteristics of different regions, resulting in low planting efficiency and resource utilization rate. This solution establishes the construction of a dynamic germplasm resource library, optimizes the selection of garlic seeds and cultivation strategies according to the environmental characteristics (such as climate, soil, light, etc.) of different regions, making garlic sprout cultivation more adaptable to regional needs, improving planting efficiency and resource utilization rate. Analyze and clarify the best cultivation environment, maximize the expression potential of trace elements, and achieve a green and efficient planting mode.

[0094] In terms of seed selection and breeding, traditional breeding mainly relies on artificial experience and phenotypic observation, lacking the excavation and analysis of in-depth data of germplasm resources, and unable to efficiently screen out high-quality germplasm rich in specific functional components, restricting the potential of garlic sprout variety improvement and industrial development. This solution integrates the knowledge and experience of breeding experts into the big data analysis platform, uses technologies such as knowledge graphs and rule reasoning to construct a collaborative mechanism between expert experience and intelligent algorithms, gives full play to the guiding role of traditional experience, and at the same time improves the scientificity and adaptability of the algorithm model, realizing the deep integration of traditional breeding technology and modern intelligent technology.

[0095] (2) Economic benefits

[0096] In terms of the utilization and regulation of trace elements, there is currently a lack of systematic research on the distribution patterns and absorption capacities of key functional trace elements (such as allicin, selenium, and strontium) in garlic sprouts. This has led to difficulties in achieving precise regulation and efficient utilization of trace elements, making it impossible to meet the market demands of functional agriculture and health product development. This solution uses machine learning and image recognition technologies to build a multi-dimensional data model centered around key trace elements such as allicin, selenium, and strontium, systematically analyzing the distribution patterns and absorption capacities of trace elements in germplasm resources, and providing a scientific basis for achieving precise regulation of trace elements and optimizing planting plans. Through data fusion and mathematical model optimization, garlic sprouts rich in specific functional components (such as selenium-rich and high-strontium) can be cultivated to meet diversified market demands and promote the development of garlic sprout products towards high added value. By optimizing the scientific planting mode and introducing intelligent management technologies, the efficient utilization and added value of garlic sprout resources can be realized, promoting the development of the garlic sprout industrial chain towards intelligence, greenness, and high quality, and comprehensively meeting the diversified needs of modern agriculture and the health industry.

[0097] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the inventive concept of the present invention, several modifications and improvements can be made, and these all fall within the protection scope of the present invention.

Claims

1. A big data analysis platform for garlic yellow germplasm resources, characterized in that, Comprising: A processor (1) for implementing data processing; A data acquisition and management module (2) for acquiring and integrating multi-dimensional data information during the growth process of garlic sprouts, and storing and managing the multi-dimensional data information; A germplasm resource analysis module (3) for analyzing the external characteristics of garlic sprouts at different growth stages, thereby realizing garlic sprout germplasm screening and germination prediction, and combining garlic sprout gene data to analyze the correlation between garlic sprout phenotypic characteristics and trace element distribution; A growth prediction and decision support module (4) for dynamically predicting the germination time, growth trend and final quality of garlic sprouts, and recommending the best garlic sprout germplasm selection scheme according to the regional environmental characteristics; A visualization and interaction module (5) for realizing visual analysis of the multi-dimensional data information and generating a personalized report to provide intuitive data support for growers and breeders; A knowledge fusion and learning module (6) for transforming the experience of breeding experts and domain knowledge into operable rules and model parameters; An achievement sharing module (7) for providing technical support for the preservation and management of high-quality garlic sprout germplasm resources, thereby realizing data sharing and collaboration between breeders and researchers; The growth prediction and decision support module (4) includes a dynamic prediction module, a germplasm adaptation analysis module and a quality improvement guidance module, and there are two-way signal connections between the dynamic prediction module, the germplasm adaptation analysis module and the quality improvement guidance module. The knowledge fusion and learning module (6) includes a knowledge base module, a rule reasoning module and an algorithm model optimization module, and there are two-way signal connections between the knowledge base module, the rule reasoning module and the algorithm model optimization module; The output end of the knowledge base module in the knowledge fusion and learning module (6) is two-way signal connected to the input end of the dynamic prediction module in the growth prediction and decision support module (4).

2. The garlic sprout germplasm resource big data analysis platform according to claim 1, wherein: The data acquisition and management module (2) includes a data acquisition module, a data storage module, a data management module and a data transmission module, and there are two-way signal connections between the data acquisition module, the data storage module, the data management module and the data transmission module.

3. The big data analysis platform for garlic sprout germplasm resources according to claim 1, characterized in that: The germplasm resource analysis module (3) includes an image recognition module, a feature extraction module, a correlation analysis module and a trace element distribution law research module, and there are two-way signal connections between the image recognition module, the feature extraction module, the correlation analysis module and the trace element distribution law research module.

4. The big data analysis platform for garlic sprout germplasm resources according to claim 1, characterized in that: The visualization and interaction module (5) includes a data visualization display module and an interaction module, and there are two-way signal connections between the data visualization display module and the interaction module.

5. The garlic yellow germplasm resource big data analysis platform according to claim 1, characterized in that: The achievement sharing module (7) includes a germplasm resource protection module, a technical achievement sharing module and a report generation module, and there are two-way signal connections between the germplasm resource protection module, the technical achievement sharing module and the report generation module.

6. The big data analysis platform for garlic yellow germplasm resources according to claim 1, characterized in that: The output end of the processor (1) is two-way signal connected to the input end of the data transmission module in the data acquisition and management module (2), and the output end of the processor (1) is two-way signal connected to the input end of the image recognition module in the germplasm resource analysis module (3).

7. The garlic sprout germplasm resource big data analysis platform according to claim 1, characterized in that: The output end of the processor (1) is bidirectionally signal-connected to the input end of the dynamic prediction module in the growth prediction and decision support module (4), and the output end of the processor (1) is bidirectionally signal-connected to the input end of the interaction module in the visualization and interaction module (5).

8. The big data analysis platform for garlic sprout germplasm resources according to claim 1, characterized in that: The output end of the processor (1) is bidirectionally signal-connected to the input end of the knowledge base module in the knowledge fusion and learning module (6), and the output end of the processor (1) is bidirectionally signal-connected to the input end of the technical achievement sharing module in the achievement sharing module (7).

9. The big data analysis platform for garlic yellow germplasm resources according to claim 1, characterized in that: The output end of the dynamic prediction module in the growth prediction and decision support module (4) is bidirectionally signal-connected to the input end of the data transmission module in the data acquisition and management module (2).

10. The garlic sprout germplasm resource big data analysis platform according to claim 1, characterized in that: The output end of the data transmission module in the data acquisition and management module (2) is bidirectionally signal-connected to the input end of the image recognition module in the germplasm resource analysis module (3).

Images