Artificial intelligence agricultural product food material traceable device system and method

Abstract

The invention discloses an artificial intelligence agricultural product food material traceability device system and method, and relates to the technical field of agricultural product traceability. The system comprises an information acquisition module, a data processing module, a block chain storage module, a user interaction module and an AI analysis module. The information acquisition module acquires full-life-cycle information of agricultural products through Internet of Things equipment; the data processing module is used for cleaning and standardizing the acquired information; the block chain storage module ensures that the data cannot be tampered and can be traced; the user interaction module provides a multi-terminal query entry; and the AI analysis module performs data mining analysis through a machine learning model to realize intelligent presentation of traceability information and abnormal early warning. The method can achieve the precise tracing of the whole information of agricultural products from planting to selling, improves the tracing efficiency and information credibility, guarantees the food safety, and meets the tracing demands of consumers for high-quality agricultural products.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural product traceability, and particularly relates to an artificial intelligence agricultural product and food material traceable device system and method. BACKGROUND

[0002] With the improvement of people's living standards, the requirements for the quality and safety of agricultural products are increasing, especially for high-end agricultural products such as high-sugar tomatoes. Consumers not only pay attention to the quality, but also hope to know the whole process information from planting to sales. The existing agricultural product traceability system mostly uses centralized database to store information, which has the problems of easy tampering of data and low credibility. Moreover, the traceability information presentation mode is single, lacks intelligent analysis and early warning function, and it is difficult to meet the needs of consumers for deep mining and accurate query of traceability information. Therefore, an apparatus system and method capable of realizing credible traceability of whole-process information and having intelligent analysis capability are urgently needed. SUMMARY

[0003] The present application aims to provide an artificial intelligence agricultural product and food material traceable device system and method to solve the problems of low data credibility and lack of intelligent analysis and early warning in the prior art.

[0004] Technical scheme: An artificial intelligence agricultural product and food material traceable device system, characterized in that it comprises: an information collection module for collecting information of agricultural products from planting, processing, transportation to sales throughout the life cycle, the information including planting environment data, farming operation records, processing technology parameters, transportation temperature and humidity data and sales information, the information collection module comprising Internet of Things sensors, high-definition cameras, RFID tags and handheld terminals; a data processing module connected with the information collection module for cleaning, deduplicating and standardizing the collected information, and converting unstructured data into structured data; a blockchain storage module connected with the data processing module for storing the processed information into a blockchain to realize non-tamperable and distributed storage of data; an AI analysis module connected with the blockchain storage module and the data processing module respectively for analyzing the historical data stored in the blockchain and the real-time collected data through a machine learning model, generating a traceability report, performing abnormal early warning and predicting the quality of agricultural products; and a user interaction module connected with the blockchain storage module and the AI analysis module respectively for providing a user query interface, enabling the user to query the traceability information of agricultural products and receive the report and early warning information output by the AI analysis module.

[0005] The Internet of Things sensors include temperature and humidity sensors, light sensors, soil nutrient sensors, and water quality sensors for collecting planting environment data; the high-definition camera is used to record the process of agricultural operations and the appearance characteristics of agricultural products; the RFID tag is used to record the individual identification information and flow record of agricultural products; the handheld terminal is used to input the details of agricultural operations and manual record information in processing and sales links.

[0006] The data processing module includes a data cleaning unit, a data conversion unit, and a data fusion unit; the data cleaning unit is used to remove redundant data and correct error data; the data conversion unit is used to convert unstructured data such as image data and audio data into structured data; the data fusion unit is used to fuse and correlate information of different sources and different types to form a unified agricultural product traceability data set.

[0007] The blockchain storage module adopts a consortium chain architecture and includes multiple nodes, including planting base nodes, processing enterprise nodes, logistics enterprise nodes, sales terminal nodes, and supervision nodes, and each node writes data into the blockchain after verification through a consensus mechanism.

[0008] The AI analysis module includes a model training unit, a traceability analysis unit, an abnormality early warning unit, and a quality prediction unit; the model training unit is used to train machine learning models based on historical traceability data, including decision tree models and neural network models; the traceability analysis unit is used to extract relevant data from the blockchain and generate a visual traceability report according to user query requests; the abnormality early warning unit is used to compare real-time data with historical normal data and issue a warning when the deviation exceeds a preset threshold; the quality prediction unit is used to predict quality parameters such as sugar content and taste of agricultural products based on planting and processing data.

[0009] The user interaction module includes image recognition query and RFID tag scanning query.

[0010] The application discloses an artificial intelligence agricultural product and food material traceability method, which is applied to the system and comprises the following steps: S1, information collection: collecting various types of information of the whole life cycle of agricultural products through an information collection module, including collecting planting environment data by using an Internet of Things sensor, recording agricultural operation and appearance characteristics by using a high-definition camera, recording individual identification and circulation information by using an RFID tag, and inputting manual recorded information by using a handheld terminal; S2, data processing: a data processing module performs cleaning and deduplication on the collected information, converts unstructured data into structured data, performs data fusion, and forms a unified traceability dataset; S3, blockchain storage: uploading the processed traceability dataset to a blockchain storage module, and writing the traceability dataset into a blockchain after verification by each node through a consensus mechanism, so that data is stored in a manner that cannot be tampered with; S4, AI analysis: an AI analysis module calls a trained machine learning model, analyzes historical data in the blockchain and real-time collected data, generates a traceability report, issues a warning when detecting data anomalies, and predicts the quality of agricultural products; and S5, user query: a user initiates a query request through a user interaction module, the system extracts relevant traceability information and AI analysis results from the blockchain, and feeds back the information to the user.

[0011] In the method step S1, the planting environment data includes temperature, humidity, light intensity, soil pH value, nutrient content and irrigation water quality; the agricultural operation record includes sowing time, fertilizer type and dosage, pest control measures and picking time; the processing process parameters include cleaning method, sterilization temperature and time, and packaging specifications; the transportation temperature and humidity data are collected in real time by a temperature and humidity sensor installed on a transportation vehicle, and recorded once every 5-10 minutes; and the sales information includes sales location, sales time and sales personnel.

[0012] In the method step S4, the abnormal warning includes planting environment abnormal warning, transportation temperature and humidity abnormal warning and processing parameter abnormal warning; when the real-time collected planting environment data exceeds the preset suitable range, the planting environment abnormal warning is issued; when the transportation temperature and humidity data exceed the suitable temperature and humidity range for storing agricultural products, the transportation abnormal warning is issued; and when the processing parameters deviate from the standard process parameter range, the processing abnormal warning is issued.

[0013] In the method step S5, the user query mode includes inputting an agricultural product unique identification code for query, scanning a two-dimensional code on an agricultural product package for query, shooting an agricultural product image for query through image recognition, and scanning an RFID tag for query; and the information fed back to the user includes agricultural product whole life cycle traceability information, an AI generated quality evaluation report and an abnormal warning record.

[0014] Beneficial effects: Compared with the prior art, the application has the following beneficial effects:

[0015] 1. Adopting blockchain storage technology to ensure the traceability data of agricultural products is tamper-proof, improve the credibility of information, and solve the problem of centralized storage data being easily tampered with.

[0016] 2. Integrating multiple information collection devices to achieve comprehensive collection of agricultural product lifecycle information, providing a complete data basis for traceability.

[0017] 3. Introducing an AI analysis module to deeply analyze data through machine learning models, enabling intelligent generation of traceability reports, anomaly early warning, and quality prediction, and improving the intelligence level of the traceability system.

[0018] 4. Providing multi-terminal and multi-way query portals to facilitate users to obtain traceability information, meet the query needs of different users, and enhance user experience. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a schematic diagram of the overall framework of the device system.

[0020] Figure 2 is a schematic diagram of the steps of the artificial intelligence agricultural product food material traceability method. DETAILED DESCRIPTION

[0021] The present application will be further described in detail below with reference to specific embodiments. As shown in the drawings: Figure 1 An artificial intelligence agricultural product food material traceable device system, comprising: an information collection module 10 for collecting information of agricultural products from planting, processing, transportation to sales throughout the life cycle, the information including planting environment data, farming operation records, processing technology parameters, transportation temperature and humidity data and sales information, the information collection module 10 including Internet of Things sensors 11, high-definition cameras 12, RFID tags 13 and handheld terminals 14; the data processing module 20 is connected with the information collection module 10, for cleaning, deduplication, standardization processing of the collected information, converting unstructured data into structured data; the blockchain storage module 21 is connected with the data processing module 20, for storing the processed information into the blockchain, realizing the tamper-proof and distributed storage of data; the AI analysis module 22 is connected with the blockchain storage module 21 and the data processing module 20 respectively, for analyzing the historical data stored in the blockchain and the real-time collected data through the machine learning model, generating the traceability report, performing the anomaly early warning and predicting the quality of agricultural products; the user interaction module 40 is connected with the blockchain storage module 21 and the AI analysis module 22 respectively, for providing a user query interface, enabling the user to query the traceability information of agricultural products and receiving the report and early warning information output by the AI analysis module 22.

[0022] The Internet of Things sensor 11 in the information collection module 20, including temperature and humidity sensor, light sensor, etc., is installed in the planting greenhouse, and the planting environment data of high-sugar tomatoes is collected in real time; the high-definition camera 12 is installed in the field and the processing workshop, and records the processes of fertilization, picking, processing, etc.; each tomato fruit is attached with a unique RFID tag 13, which records its growth and circulation information; the grower enters the details of agricultural operations such as fertilizer type and dosage through the handheld terminal 14.

[0023] The data processing module 20 analyzes the image data shot by the camera, extracts information such as agricultural operation time and operator, and fuses with sensor data and RFID tag 13 information to form structured traceability data.

[0024] The blockchain storage module 21 includes nodes such as planting bases, processing enterprises, logistics companies, supermarkets and regulatory departments, and the processed traceability data is written into the blockchain after being verified by each node.

[0025] The AI analysis module 22 trains a neural network model based on historical data, and issues a planting environment abnormality warning when the real-time collected greenhouse temperature exceeds the suitable range of 15-28℃; predicts the sugar content of tomatoes according to the light and fertilization data during planting; and users can view the whole-process traceability information from planting to sales and the AI-predicted sugar content, taste and other quality reports through the mobile phone APP scanning the two-dimensional code on the tomato package.

[0026] As shown in Figure 2 An artificial intelligence agricultural product and food material traceability method, the steps are as follows: S1. Information collection: the Internet of Things sensor collects greenhouse temperature and humidity, light and other data every 30 minutes; the high-definition camera shoots the growth state of tomatoes and agricultural operations at regular time every day; the RFID tag records the picking time and transportation vehicle information; the grower enters the fertilization information through the handheld terminal. S2. Data processing: remove the abnormal fluctuation data collected by the sensor, convert the camera image into timestamp, operation type and other structured information, and fuse with other data. S3. Blockchain storage: the fused traceability data is sent to each blockchain node, and the node is written into the blockchain after verification. S4. AI analysis: the AI model compares the real-time temperature and humidity with the historical suitable data, discovers the abnormality and issues a timely warning; predicts the sugar content of tomatoes according to the growth data. S5. User query: the consumer scans the two-dimensional code, the system extracts the information from the blockchain, and displays the traceability process and AI analysis results.

[0027] The above only describes the preferred embodiments of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An artificial intelligence agricultural product food material traceability device system, characterized by, The application relates to an agricultural product traceability system based on a blockchain, which comprises the following: an information collection module (10) for collecting information of agricultural products from planting, processing, transportation to sales of a whole life cycle, wherein the information comprises planting environment data, farming operation records, processing process parameters, transportation temperature and humidity data and sales information, the information collection module (10) comprises an Internet of Things sensor (11), a high-definition camera (12), an RFID tag (13) and a handheld terminal (14); a data processing module (20) connected with the information collection module (10) and used for cleaning, deduplicating and standardizing the collected information and converting unstructured data into structured data; a blockchain storage module (21) connected with the data processing module (20) and used for storing the processed information into a blockchain to realize tamper-proof and distributed storage of data; an AI analysis module (22) connected with the blockchain storage module (21) and the data processing module (20) respectively and used for analyzing historical data stored in the blockchain and real-time collected data through a machine learning model, generating a traceability report, giving an abnormality early warning and predicting agricultural product quality; and a user interaction module (40) connected with the blockchain storage module (21) and the AI analysis module (22) respectively and used for providing a user query interface, enabling a user to query agricultural product traceability information and receiving a report and early warning information output by the AI analysis module (22). The Internet of Things sensor (11) comprises a temperature and humidity sensor, an illumination sensor, a soil nutrient sensor and a water quality sensor and is used for collecting planting environment data; the high-definition camera (12) is used for recording farming operation processes and agricultural product appearance characteristics; the RFID tag (13) is used for recording agricultural product individual identification information and circulation records; and the handheld terminal (14) is used for inputting farming operation details and manual record information of processing and sales links. The data processing module (20) comprises a data cleaning unit, a data conversion unit and a data fusion unit; the data cleaning unit is used for removing redundant data and correcting error data; the data conversion unit is used for converting unstructured data such as image data and audio data into structured data; and the data fusion unit is used for fusing and correlating information of different sources and different types to form a unified agricultural product traceability data set.

2. The system of claim 1, wherein, The blockchain storage module (21) adopts a consortium chain architecture and comprises a plurality of nodes, wherein the nodes comprise a planting base node, a processing enterprise node, a logistics enterprise node, a sales terminal node and a supervision node, and each node writes data into the blockchain after the data is verified through a consensus mechanism. ​ 3. The system of claim 1, wherein, ​ 4. The system of claim 1, wherein, ​ 5. The system of claim 1, wherein, The AI analysis module (22) includes a model training unit, a traceability analysis unit, an abnormality early warning unit, and a quality prediction unit; the model training unit is used to train a machine learning model based on historical traceability data, and the machine learning model includes a decision tree model and a neural network model; the traceability analysis unit is used to extract relevant data from the blockchain and generate a visual traceability report according to a user query request; the abnormality early warning unit is used to compare real-time data with historical normal data, and issue a warning when the deviation exceeds a preset threshold; and the quality prediction unit is used to predict quality parameters such as sugar content and taste of agricultural products according to planting and processing data.

6. The system of claim 1, wherein, The user interaction module (40) includes image recognition query and RFID tag scanning query.

7. An artificial intelligence agricultural product food material traceability method applied to the system of any one of claims 1-6, characterized in that, The method includes the following steps: S1. Information collection: Collect various types of information of the whole life cycle of agricultural products through the information collection module, including collecting planting environment data using Internet of Things sensors, recording agricultural operations and appearance characteristics using high-definition cameras, recording individual identification and circulation information using RFID tags, and manually recording information using handheld terminals; S2. Data processing: The data processing module cleans, de-duplicates, and converts unstructured data into structured data, and performs data fusion to form a unified traceability dataset; S3. Blockchain storage: The processed traceability dataset is uploaded to the blockchain storage module, and each node writes the data into the blockchain after verification by the consensus mechanism, realizing data storage that cannot be tampered with; S4. AI analysis: The AI analysis module calls the trained machine learning model to analyze historical data in the blockchain and real-time collected data, generates a traceability report, issues a warning when data anomalies are detected, and predicts agricultural product quality; S5. User query: The user initiates a query request through the user interaction module, and the system extracts relevant traceability information and AI analysis results from the blockchain and feeds them back to the user.

8. The method of claim 7, wherein, In step S1, the planting environment data includes temperature, humidity, light intensity, soil pH value, nutrient content, and irrigation water quality; the agricultural operation records include sowing time, fertilizer type and amount, pest control measures, and picking time; the processing parameters include cleaning method, sterilization temperature and time, and packaging specifications; the transportation temperature and humidity data are collected in real time by temperature and humidity sensors installed on the transportation vehicle, and recorded every 5-10 minutes; and the sales information includes sales location, sales time, and sales personnel.

9. The method of claim 7, wherein, In step S4, the abnormality early warning includes planting environment abnormality early warning, transportation temperature and humidity abnormality early warning, and processing parameter abnormality early warning; when the real-time collected planting environment data exceeds the preset suitable range, a planting environment abnormality early warning is issued; when the transportation temperature and humidity data exceed the suitable temperature and humidity range for storing agricultural products, a transportation abnormality early warning is issued; and when the processing parameters deviate from the standard process parameter range, a processing abnormality early warning is issued.

10. The method of claim 7, wherein, In step S5, the user query mode includes inputting the unique identification code of the agricultural product for query, scanning the two-dimensional code on the packaging of the agricultural product for query, shooting the image of the agricultural product for query through image recognition, and scanning the RFID tag for query; and the information fed back to the user includes the whole life cycle traceability information of the agricultural product, the quality evaluation report generated by AI, and the abnormal early warning record.

Images