Digital agriculture full-chain management traceability system and method based on block chain and AI algorithm
Through blockchain and AI algorithms, the growth status and conditions of agricultural products are obtained, and predictions and comparisons are made, which solves the problem that consumers cannot understand product information in digital agricultural management, and improves the traceability experience effect.
Patent Information
- Application Number
- CN202411425864.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing digital agricultural management traceability system cannot provide pre-trace information of the product before consumers purchase it, resulting in consumers insufficient understanding of product information and poor traceability experience.
Using a digital agriculture full-chain management traceability system based on blockchain and AI algorithms, the growth state prediction is carried out by obtaining the growth state of agricultural products under different time periods and conditions, and storing the difference between the prediction and actual state in the blockchain. In this article, consumers provide consumers with pre-trace and normal traceability comparison information.
It realizes consumers' advance understanding of product information, improves product understanding and traceability experience, provides a stronger sense of difference by comparing information, and enhances traceability experience.
Smart Images

Figure CN118941123A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of digital agriculture management and tracing technology, and specifically to a digital agriculture full-chain management and tracing system and method based on blockchain and AI algorithm. Background Art
[0002] Digital agriculture refers to a modern agricultural method that uses digital technology, information technology and data analysis to improve agricultural production efficiency, sustainability and decision-making capabilities. It integrates emerging technologies such as the Internet of Things, artificial intelligence, big data, blockchain, etc. to optimize agricultural management and production, including the use of sensors, drones, satellite images and other technologies to monitor soil, climate, crop growth conditions and other data in real time. The collected data is processed through data analysis and machine learning algorithms to optimize planting decisions, pest and disease management, harvest forecasts, etc., and precise fertilization, irrigation and pest and disease control are implemented based on real-time data to reduce resource waste and increase crop yield and quality. The Internet of Things interconnects farmland equipment to provide real-time monitoring and control, such as automatic irrigation systems. Blockchain is used to record and trace the production, processing and circulation of agricultural products to ensure product safety and authenticity.
[0003] The patent publication number is CN113807744A, which is a traceability system for the entire industry chain of Radix Pseudostellariae. It is equipped with a planting and production monitoring system, a primary processing and production management system, a packaging and warehousing management system and a data processing platform. It conducts comprehensive monitoring of the planting and production, primary processing, packaging and warehousing of Radix Pseudostellariae, and integrates the data through the data processing platform to form real-time data traceability on the entire industry chain. By integrating data modules in each link, the real-time collected data is more complete.
[0004] In the process of digital agriculture management and traceability in the above and similar timely solutions, the traceability method is to trace the product on the blockchain that stores the product production, processing and circulation process through detailed product information after purchasing the product. A basic understanding of the product can only be achieved through the final traceability result. However, before purchasing the product, consumers still lack information about the product and cannot have a preliminary understanding of the product through "pre-traceability". Moreover, when consumers obtain basic information such as the production, processing and circulation process of the product through traceability, they cannot get a stronger sense of difference through comparison, resulting in a poor traceability experience. Summary of the invention
[0005] The purpose of the present invention is to provide a digital agriculture full-chain management and traceability system and method based on blockchain and AI algorithm to solve the problems raised in the above background technology.
[0006] To achieve the above purpose, the present invention provides the following technical solution: a digital agriculture full-chain management and traceability system based on blockchain and AI algorithm, comprising: Information creation module: obtain the growth status of agricultural products in different time periods and under different conditions, obtain digital agricultural growth data, predict the growth status of target agricultural products, and obtain growth prediction items; Information storage module: Based on the blockchain network, blocks are generated through a consensus mechanism, and growth prediction items are stored in the target block. The growth process of the target agricultural product is divided into at least two stages, and the growth status of the target agricultural product in different stages is obtained based on the digital agricultural growth data, including prediction status items and prediction condition items. Through the first traceability channel, consumers are provided with advance traceability, and the actual growth status of the target agricultural product in different stages is obtained respectively, and the real-time status items and real-time condition items are obtained, and the real-time status items and real-time condition items are stored in the target block; Information comparison module: Based on the growth prediction item, the difference between the real-time status item and the predicted status item and the difference between the real-time condition item and the predicted condition item are obtained. Through the second traceability channel, normal traceability is provided to consumers, thereby obtaining the comparison information between normal traceability and pre-traceability, and then obtaining the traceability comparison item; The methods for obtaining the retrospective comparison items include: Step 1: Obtaining the first difference, obtaining the growth status of the target agricultural product at different stages based on the digital agricultural growth data, the growth status including the product height and the number of leaves, obtaining the first prediction information set, and at the same time obtaining the growth status of the target agricultural product at different stages, obtaining the first actual information set, and then obtaining the difference between the first prediction information set and the first actual information set, obtaining the first difference; Step 2: Obtain the second difference. Based on the digital agricultural growth data, obtain the growth conditions of the target agricultural products in different stages, the growth conditions include temperature and humidity, and obtain the second prediction information set. At the same time, obtain the growth conditions of the target agricultural products in different stages to obtain the second actual information set, and then obtain the difference between the second prediction information set and the second actual information set to obtain the second difference. The first difference and the second difference are combined to obtain the retrospective comparison item.
[0007] Furthermore, the method for obtaining the first difference includes: M1: Image acquisition, based on digital agricultural growth data, the growth data of the target agricultural product at different stages are acquired to obtain the first data set, and the actual growth images of the target agricultural product at different stages are acquired to obtain the second image set; M2: First difference comparison, based on the first data set, the height data and leaf quantity data of the target agricultural product in different stages are obtained, and the height information set and the leaf quantity set are obtained. Based on the second image set, the first feature point is set at the top and bottom of the height of the target agricultural product respectively, and the second feature point is set at the number of leaves to obtain the height difference information set of the first feature point and the second feature point set. The first difference is obtained based on the difference between the height difference information set of the first feature point and the height information set, and the difference between the second feature point set and the leaf quantity set.
[0008] Furthermore, the method for obtaining the second difference includes: X1: Conditional acquisition: Based on digital agricultural growth data, the temperature and humidity data of target agricultural products at different stages are obtained to obtain the predicted temperature set and predicted humidity set. The temperature and humidity data of target agricultural products at different stages are obtained through sensors to obtain the actual temperature set and actual humidity set. X2: second difference comparison, based on the difference between the predicted temperature set and the actual temperature set and the difference between the predicted humidity set and the actual humidity set, a second difference is obtained.
[0009] Furthermore, the method for obtaining the digital agricultural growth data includes: S1: Data collection, obtaining environmental factors during the growth of target agricultural products, obtaining environmental impact items, which include temperature and humidity, dividing temperature and humidity into at least two levels, obtaining at least two temperature ranges and at least two humidity ranges; S2: Information collection, obtaining the growth status information of the target agricultural products in different temperature ranges and humidity ranges through sensors, obtaining at least four groups of growth status information combinations, and then obtaining a growth status information set; S3: Obtaining the average value, repeating step 2 to obtain multiple sets of growth status information sets, and taking the average value of the growth status information sets to obtain digital agricultural growth data.
[0010] Furthermore, the method for obtaining digital agricultural growth data also includes: S4: Screening item setting: in S3, according to the multiple growth status information sets, a deviation range is set, and the growth status information of the target agricultural product in the growth status information set that is not within the deviation range is set as a screening item, so as to obtain multiple sets of optimized growth status information sets; S5: numerical acquisition, based on multiple sets of optimized growth status information sets, the average value of the growth status information of the target agricultural product is obtained, and then the digital agricultural growth data is obtained.
[0011] Furthermore, the first tracing channel includes: N1: Channel selection, select multimedia channels as the first tracing channel, multimedia channels include blockchain browsers; N2: Information acquisition: obtaining the growth status and growth conditions of target agricultural products in different stages based on digital agricultural growth data, and obtaining at least two predicted status items and predicted condition items.
[0012] Furthermore, the second traceability channel includes: attaching a unique identification code to the target agricultural product, and after scanning the unique identification code, consumers can view the actual growth status of the target agricultural product at different stages, and obtain at least two real-time status items and at least two real-time condition items.
[0013] Furthermore, the digital agriculture full-chain management and traceability method based on blockchain and AI algorithm uses any of the digital agriculture full-chain management and traceability systems based on blockchain and AI algorithm described above.
[0014] Compared with the prior art, the present invention has the following beneficial effects: The digital agriculture full-chain management and traceability system and method based on blockchain and AI algorithm, based on the AI algorithm, obtains the growth status of various agricultural products in different time periods and under different conditions in the past, obtains digital agriculture growth data, predicts the growth status and growth demand of target agricultural products, and divides the entire growth process of agricultural products into at least two stages. The actual growth status, actual growth conditions, and predicted growth status and predicted growth conditions of each stage are stored in the blockchain respectively to form growth comparison values, and traceability channels for predicted growth status and predicted growth conditions are opened in advance for consumers, realizing "pre-traceability" of consumers and improving consumers' understanding of products.
[0015] At the same time, according to the growth time period of the target agricultural products, the real-time growth status of the target agricultural products in the germination period, the growth period and the maturity period are obtained respectively, including the real-time status and the real-time conditions. The real-time status and the real-time conditions are also stored in the target block in the above manner. At this time, the difference between the real-time status and the predicted status and the difference between the real-time conditions and the predicted conditions can be obtained. The normal traceability information is obtained through the normal traceability channel, and compared with the "pre-traceability" information. The actual growth status, the actual growth conditions and the difference between the predicted growth status and the predicted growth conditions are obtained by using the growth comparison values to obtain a stronger traceability effect comparison, thereby improving the traceability experience effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A schematic diagram showing the relationship between the information creation module and the storage and comparison modules of the present invention; Figure 2 A schematic diagram of a first difference acquisition relationship of the present invention; Figure 3 A schematic diagram of a second difference acquisition relationship of the present invention; Figure 4 It is a schematic diagram of the relationship between the prediction state and the prediction condition of the present invention; Figure 5 It is a schematic diagram of the relationship between the real-time state and the real-time condition of the present invention; Figure 6 It is a schematic diagram of the positional relationship between the first characteristic point and the second characteristic point of the present invention. DETAILED DESCRIPTION
[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0018] The normal tracing method is to check the whole process from planting to sales through the relevant information of the product after obtaining the specific product, including environmental monitoring data and processing records. However, this method can only obtain a relevant specific value or step. When consumers do not get the product, the product is not yet mature and they cannot have a preliminary understanding of the product, which will affect the consumer experience. The technical solution provided by this application is based on the AI algorithm. By obtaining the growth status of various agricultural products in different time periods and under different conditions, digital agricultural growth data is obtained, and the current growth status and growth conditions of agricultural products are obtained through sensors, and through the digital agricultural growth The blockchain can compare long-term data, predict the growth status and growth demand of the target agricultural products, divide the entire growth process of agricultural products into at least two stages, and store the actual growth status, actual growth conditions, predicted growth status and predicted growth conditions in each stage respectively in the blockchain to form growth comparison values. The traceability channels for predicted growth status and predicted growth conditions are opened in advance for consumers to achieve "pre-traceability" for consumers, improve consumers' understanding of the products, and then use the growth comparison values obtained through normal tracing to obtain the actual growth status, actual growth conditions and the difference between predicted growth status and predicted growth conditions to obtain a stronger traceability effect comparison and improve the traceability experience.
[0019] like Figure 1-Figure 4As shown, the present invention provides a technical solution: a digital agriculture full-chain management and traceability system based on blockchain and AI algorithm, including: an information creation module: obtaining the growth status of agricultural products in different time periods and under different conditions, obtaining digital agricultural growth data, predicting the growth status of target agricultural products, and obtaining growth prediction items; an information storage module: based on the blockchain network, generating blocks through a consensus mechanism, and storing the growth prediction items in the target blocks, dividing the growth process of the target agricultural products into at least two stages, and obtaining the growth status of the target agricultural products in different stages based on the digital agricultural growth data, including predicted status items and predicted condition items, providing consumers with advance traceability through a first traceability channel, and obtaining the actual growth status of the target agricultural products in different stages respectively, obtaining real-time status items and real-time condition items, and storing the real-time status items and real-time condition items in the target blocks; an information comparison module: based on the growth prediction item, obtaining the difference between the real-time status item and the predicted status item and the difference between the real-time condition item and the predicted status item. The difference of the condition items is used to provide normal traceability for consumers through the second traceability channel, so as to obtain the comparison information between the normal traceability and the pre-traceability, and then obtain the traceability comparison items; the method of obtaining the traceability comparison items includes: step one: obtaining the first difference, obtaining the growth status of the target agricultural product at different stages based on the digital agricultural growth data, the growth status includes the product height and the number of leaves, and obtaining the first prediction information set, and at the same time obtaining the growth status of the target agricultural product at different stages to obtain the first actual information set, and then obtaining the difference between the first prediction information set and the first actual information set to obtain the first difference; step two: obtaining the second difference, obtaining the growth conditions of the target agricultural product at different stages based on the digital agricultural growth data, the growth conditions include temperature and humidity, and obtaining the second prediction information set, and at the same time obtaining the growth conditions of the target agricultural product at different stages to obtain the second actual information set, and then obtaining the difference between the second prediction information set and the second actual information set to obtain the second difference, and the first difference and the second difference are combined to obtain the traceability comparison items.
[0020] It should be noted that digital agriculture includes various agricultural products, and different agricultural products may have different growth cycles and growth conditions. Therefore, the growth status of all previous agricultural products in different time periods and under different conditions is obtained through the information creation module. The growth status includes specific status and growth conditions, and the digital agricultural growth data is obtained. The growth status of the target agricultural product is predicted based on the digital agricultural growth data, and the predicted results are packaged into a block. According to the blockchain network used, such as Ethereum, Hyperledger, etc., the newly generated block is confirmed through a consensus mechanism such as Proof of Work or Proof of Stake. After the consensus is completed, the new block is broadcast to the entire blockchain network to complete the blockchain recording of the prediction results. The growth process of the target agricultural product is divided into three stages, namely, the germination period, the growth period and the maturity period. At this time, the growth status of the target agricultural product in these three stages can be predicted through the digital agricultural growth data. The predicted results include the predicted status and the predicted conditions. At this time, the first traceability channel is opened to provide consumers with a pre-traceability effect, so that the specific information of the target agricultural product can be obtained without obtaining the target agricultural product, thereby achieving the effect of "pre-traceability".
[0021] It should be noted that, according to the growth period of the target agricultural products, the real-time growth status of the target agricultural products in the germination period, the growth period and the maturity period are respectively obtained, including the real-time status and the real-time conditions. The real-time status and the real-time conditions are also stored in the target block in the above manner. At this time, the difference between the real-time status and the predicted status and the difference between the real-time conditions and the predicted conditions can be obtained. The normal traceability information is obtained through the normal traceability channel, and compared with the "pre-traceability" information to obtain the traceability comparison item.
[0022] It should be noted that, since the specific status includes product height and the number of leaves, the difference between the predicted growth status information and the actually measured growth status information is the first difference. Since the growth conditions include temperature and humidity, the difference between the predicted growth condition information and the actually measured growth condition information is the second difference. The first difference and the second difference are combined to obtain the retrospective comparison item.
[0023] In the specific implementation process, the current target agricultural product is wheat. In the germination period, about 7-10 days after sowing, its height is about 4-9cm, and the number of leaves is usually 1-2 seedling leaves; in the growth period, about 4-6 weeks, the height usually reaches 20-60cm (within 2-3 months after sowing), and the number of leaves is usually 5-7; in the maturity period, usually from flowering to harvesting, the height can generally reach 70-90cm, and the number of leaves is about 7-9. The information obtained at this time is the first prediction information set. Afterwards, the specific status of wheat at different stages is actually obtained in the germination period. During the growth period, about 4-6 weeks, the height usually reaches 30-70cm (within 2-3 months after sowing), and the number of leaves is usually 6-8; during the maturity period, usually from flowering to harvesting, the height can generally reach 80-100cm, and some high-yield varieties may exceed 120cm, with about 8-10 leaves. The information obtained at this time is the first actual information set, and then the difference information between the first predicted information set and the first actual information set is obtained, and the first difference is obtained.
[0024] In the specific implementation process, during the germination period, about 7-10 days after sowing, the temperature is 15-25°C, and the soil moisture needs to be maintained at a relatively high level, about 55%-75%; during the growth period, the time is about 4-6 weeks, the temperature is 15-20°C, and the upper limit of 25°C can be reached under high temperature, and the relative humidity is maintained at 45%-65%; during the maturity period, the time is from flowering to harvesting, the temperature is 20-30°C, and the relative humidity is controlled at 35%-55% to promote drying and grain maturity. The information obtained at this time is the second prediction information set. After that, through the actual growth conditions of wheat at different stages, during the germination period, about 7-1 0 days, the temperature is 15-25°C, and the soil moisture needs to be maintained at a relatively high level, about 60%-80%; in the growth period, the time is about 4-6 weeks, the temperature is 15-20°C, and the upper limit of 25°C can be reached under high temperature, and the relative humidity is maintained at 50%-70%; in the maturity period, the time is from flowering to harvesting, the temperature is 20-30°C, and the relative humidity is controlled at 40%-60% to promote drying and grain maturity. The information obtained at this time is the second actual information set, and then the difference between the second predicted information set and the second actual information set is obtained, and the second difference is obtained, and then the comparison information of normal tracing and pre-tracing is obtained through the first difference and the second difference.
[0025] like Figure 5As shown, the method for obtaining the first difference includes: M1: image acquisition, obtaining the growth data of the target agricultural product in different stages based on the digital agricultural growth data to obtain the first data set, obtaining the actual growth images of the target agricultural product in different stages to obtain the second image set; M2: first difference comparison, based on the first data set, obtaining the height data and leaf number data of the target agricultural product in different stages to obtain the height information set and the leaf number set, based on the second image set, setting the first feature point with the top and bottom of the height of the target agricultural product respectively, setting the second feature point with the number of leaves to obtain the height difference information set of the first feature point and the second feature point set, and obtaining the first difference based on the difference between the height difference information set of the first feature point and the height information set and the difference between the second feature point set and the leaf number set.
[0026] It should be noted that the first data set includes the predicted growth status of the target agricultural products during the germination, growth and maturity stages, including product height and the number of leaves. Then, based on the actual growth images of the target agricultural products during the germination, growth and maturity stages, the first feature point is set at the top and bottom of the height of the target agricultural product, and the second feature point is set at the number of leaves to obtain the changes in the height difference information of the first feature point and the changes in the number of the second feature points.
[0027] The method for obtaining the second difference includes: X1: conditional acquisition, obtaining the temperature and humidity data of the target agricultural products in different stages based on the digital agricultural growth data, obtaining the predicted temperature set and the predicted humidity set, obtaining the temperature and humidity data of the target agricultural products in different stages through sensors, and obtaining the actual temperature set and the actual humidity set; X2: second difference comparison, obtaining the second difference based on the difference between the predicted temperature set and the actual temperature set and the difference between the predicted humidity set and the actual humidity set.
[0028] It should be noted that the predicted temperature set and the predicted humidity set include the predicted temperature and humidity information of the target agricultural products during the germination period, the growth period and the maturity period. The actual temperature and humidity information of the target agricultural products during the actual growth process in the germination period, the growth period and the maturity period is obtained through sensors to obtain the second difference.
[0029] The method for obtaining digital agricultural growth data includes: S1: data collection, obtaining environmental factors in the growth process of target agricultural products, obtaining environmental impact items, the environmental impact items include temperature and humidity, dividing the temperature and humidity into at least two levels respectively, obtaining at least two temperature ranges and at least two humidity ranges; S2: information collection, obtaining the growth status information of the target agricultural products in different temperature ranges and humidity ranges through sensors, obtaining at least four groups of growth status information combinations, and then obtaining a growth status information set; S3: average value acquisition, repeating step 2 to obtain multiple groups of growth status information sets, taking the average value of the growth status information set to obtain digital agricultural growth data.
[0030] In the specific implementation process, the temperature and humidity are divided into three levels, namely high temperature, medium temperature, low temperature and high humidity, medium humidity and low humidity. The high temperature range is 25-30°C, the medium temperature range is 20-25°C, the low temperature range is 15-20°C, the high humidity range is 60%-80%, the medium humidity range is 50%-60%, and the low humidity range is 40%-50%, thereby obtaining nine groups of growth condition combinations.
[0031] The method for obtaining digital agricultural growth data also includes: S4: screening item setting, in S3, according to multiple groups of growth status information sets, setting the deviation range, and setting the growth status information of the target agricultural product in the growth status information set that is not within the deviation range as the screening item, so as to obtain multiple groups of optimized growth status information sets; S5: numerical acquisition, based on the multiple groups of optimized growth status information sets, obtaining the average value of the growth status information of the target agricultural product, and then obtaining the digital agricultural growth data.
[0032] It should be noted that the deviation range of temperature is ±5°C, and the deviation range of humidity is ±10%. When the temperature exceeds ±5°C in the range of 15-30°C, it is judged as a screening item. When the humidity exceeds ±10% in the range of 40%-80%, it is judged as a screening item. The average value of the growth status information of the target agricultural products is re-obtained to obtain digital agricultural growth data.
[0033] The first traceability channel includes: N1: channel selection, selecting a multimedia channel as the first traceability channel, and the multimedia channel includes a blockchain browser; N2: information acquisition, obtaining the growth status and growth conditions of target agricultural products in different stages based on digital agricultural growth data, and obtaining at least two predicted status items and predicted condition items.
[0034] The second traceability channel includes: attaching a unique identification code to the target agricultural product, and after consumers scan the unique identification code, they can view the actual growth status of the target agricultural product at different stages, and obtain at least two real-time status items and at least two real-time condition items.
[0035] The digital agriculture full-chain management and traceability method based on blockchain and AI algorithm uses any of the above-mentioned digital agriculture full-chain management and traceability systems based on blockchain and AI algorithm.
[0036] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.
Claims
1. A digital agriculture full-chain management and traceability system based on blockchain and AI algorithms. It is characterized in that include: Information creation module: obtain the growth status of agricultural products in different time periods and under different conditions, obtain digital agricultural growth data, predict the growth status of target agricultural products, and obtain growth prediction items; Information storage module: Based on the blockchain network, blocks are generated through a consensus mechanism, and growth prediction items are stored in the target block. The growth process of the target agricultural product is divided into at least two stages, and the growth status of the target agricultural product in different stages is obtained based on the digital agricultural growth data, including prediction status items and prediction condition items. Through the first traceability channel, consumers are provided with advance traceability, and the actual growth status of the target agricultural product in different stages is obtained respectively, and the real-time status items and real-time condition items are obtained, and the real-time status items and real-time condition items are stored in the target block; Information comparison module: Based on the growth prediction item, the difference between the real-time status item and the predicted status item and the difference between the real-time condition item and the predicted condition item are obtained. Through the second traceability channel, normal traceability is provided to consumers, thereby obtaining the comparison information between normal traceability and pre-traceability, and then obtaining the traceability comparison item; The methods for obtaining the retrospective comparison items include: Step 1: Obtaining the first difference, obtaining the growth status of the target agricultural product at different stages based on the digital agricultural growth data, the growth status including the product height and the number of leaves, obtaining the first prediction information set, and at the same time obtaining the growth status of the target agricultural product at different stages, obtaining the first actual information set, and then obtaining the difference between the first prediction information set and the first actual information set, obtaining the first difference; Step 2: Obtain the second difference. Based on the digital agricultural growth data, obtain the growth conditions of the target agricultural products in different stages, the growth conditions include temperature and humidity, and obtain the second prediction information set. At the same time, obtain the growth conditions of the target agricultural products in different stages to obtain the second actual information set, and then obtain the difference between the second prediction information set and the second actual information set to obtain the second difference. The first difference and the second difference are combined to obtain the retrospective comparison item.
2. According to the digital agriculture full-chain management and traceability system based on blockchain and AI algorithm according to claim 1, Features: The method for obtaining the first difference includes: M1: Image acquisition, based on digital agricultural growth data, the growth data of the target agricultural product at different stages are acquired to obtain the first data set, and the actual growth images of the target agricultural product at different stages are acquired to obtain the second image set; M2: First difference comparison, based on the first data set, the height data and leaf quantity data of the target agricultural product in different stages are obtained, and the height information set and the leaf quantity set are obtained. Based on the second image set, the first feature point is set at the top and bottom of the height of the target agricultural product respectively, and the second feature point is set at the number of leaves to obtain the height difference information set of the first feature point and the second feature point set. The first difference is obtained based on the difference between the height difference information set of the first feature point and the height information set, and the difference between the second feature point set and the leaf quantity set.
3. According to the digital agriculture full-chain management and traceability system based on blockchain and AI algorithm according to claim 1, Features: The method for obtaining the second difference includes: X1: Conditional acquisition: Based on digital agricultural growth data, the temperature and humidity data of target agricultural products at different stages are obtained to obtain the predicted temperature set and predicted humidity set. The temperature and humidity data of target agricultural products at different stages are obtained through sensors to obtain the actual temperature set and actual humidity set. X2: second difference comparison, based on the difference between the predicted temperature set and the actual temperature set and the difference between the predicted humidity set and the actual humidity set, a second difference is obtained.
4. According to the digital agriculture full-chain management and traceability system based on blockchain and AI algorithm according to claim 1, Features: The method for obtaining the digital agricultural growth data comprises: S1: Data collection, obtaining environmental factors during the growth of target agricultural products, obtaining environmental impact items, which include temperature and humidity, dividing temperature and humidity into at least two levels, obtaining at least two temperature ranges and at least two humidity ranges; S2: Information collection, obtaining the growth status information of the target agricultural products in different temperature ranges and humidity ranges through sensors, obtaining at least four groups of growth status information combinations, and then obtaining a growth status information set; S3: Obtaining the average value, repeating step 2 to obtain multiple sets of growth status information sets, and taking the average value of the growth status information sets to obtain digital agricultural growth data.
5. According to the digital agriculture full-chain management and traceability system based on blockchain and AI algorithm according to claim 4, Features: The method for obtaining digital agricultural growth data also includes: S4: Screening item setting: in S3, according to the multiple growth status information sets, a deviation range is set, and the growth status information of the target agricultural product in the growth status information set that is not within the deviation range is set as a screening item, so as to obtain multiple sets of optimized growth status information sets; S5: numerical acquisition, based on multiple sets of optimized growth status information sets, the average value of the growth status information of the target agricultural product is obtained, and then the digital agricultural growth data is obtained.
6. According to the digital agriculture full-chain management and traceability system based on blockchain and AI algorithm according to claim 1, Features: The first tracing channel includes: N1: Channel selection, select multimedia channels as the first tracing channel, multimedia channels include blockchain browsers; N2: Information acquisition: obtaining the growth status and growth conditions of target agricultural products in different stages based on digital agricultural growth data, and obtaining at least two predicted status items and predicted condition items.
7. According to the digital agriculture full-chain management and traceability system based on blockchain and AI algorithm according to claim 1, Features: The second traceability channel includes: attaching a unique identification code to the target agricultural product, and after the consumer scans the unique identification code, he can view the actual growth status of the target agricultural product in different stages, and obtain at least two real-time status items and at least two real-time condition items.
8. Digital agriculture full-chain management and traceability method based on blockchain and AI algorithm, Features: A digital agriculture full-chain management and traceability system based on blockchain and AI algorithm as described in any one of claims 1-7 is used.
Citation Information
Patent Citations
Traceable self-feedback learning urban plant factory
CN113221723A
Intelligent agricultural production and fusion comprehensive service platform
CN113657751A
Agricultural greenhouse data traceability and management method based on block chain
CN115292753A
Crop production management method and device, storage medium and electronic equipment
CN116686512A
Field environment control method and device based on Internet of Things
CN118348900A
Cited By
Agricultural production and marketing full-chain dynamic tracking and control method based on space-time big data
CN122134284A
