Plant growth and health traceability management method and system based on artificial intelligence

Abstract

The present application provides a plant growth and health traceability management method and system based on artificial intelligence, relating to the technical field of traceability management, which carries out label detection and registration state division on plant information, obtains a new ID allocation process and / or an original ID associated daily management process; carries out new ID classification and recording of plant information according to the new ID allocation process, obtains new plant recording information; carries out daily ACDHMS data collection according to the original ID associated daily management process, carries out image measurement associated growth analysis and growth state determination after integration according to daily growth collection data, and transmits the same to the background storage data; decrypts and checks the background storage data, and then carries out growth and health evaluation analysis, obtains health evaluation analysis data, and generates a new key written into RFID. The present application has the functions of intelligent management, accurate evaluation and safe traceability, and improves the plant growth and health analysis processing capability.

Description

Technical Field

[0001] This invention proposes a plant growth and health traceability management method and system based on artificial intelligence, which relates to the field of health traceability management technology, specifically to the field of plant growth and health traceability management based on artificial intelligence. Background Technology

[0002] In the field of plant cultivation management and traceability, traditional management methods generally suffer from problems such as chaotic identity management and disordered process connections. The mixing of new and old plants is a prominent issue, lacking a unified identity identification and process diversion mechanism. Simultaneously, daily growth data collection is limited in scope, with images and measurement data being fragmented, failing to comprehensively reflect the plant's growth status. Furthermore, data processing relies on manual experience and judgment, leading to strong subjectivity and significant errors, resulting in delayed growth status assessments. In addition, traceability data is mostly stored in raw data, offering poor security, being easily tampered with, and exhibiting low traceability reliability. Moreover, there is a lack of data security updates and closed-loop management mechanisms. These problems result in low precision in plant cultivation management, high labor costs, and unreliable traceability links, failing to meet the needs of modern intelligent cultivation and quality traceability. Summary of the Invention

[0003] This invention provides a method and system for plant growth and health traceability management based on artificial intelligence, in order to solve the above-mentioned problems:

[0004] The present invention proposes an artificial intelligence-based method and system for plant growth and health traceability management, wherein the method includes:

[0005] S1. Perform tag detection and registration status classification on plant information, and obtain the new ID allocation process and / or the existing ID association daily management process;

[0006] S2. Classify and record plant information with new IDs according to the new ID allocation process to obtain new plant record information;

[0007] S3. Based on the existing ID association daily management process, collect daily ACDHMS data, and after integrating the daily growth data with image measurement association growth analysis and growth status determination, transmit it to the background storage data.

[0008] S4. Decrypt and verify the data stored in the background, then perform growth health assessment and analysis, obtain health assessment and analysis data, generate a new key and write it into the RFID.

[0009] Further, S1 includes:

[0010] Determine whether plant information has entered the planting management area to obtain entry judgment information;

[0011] After the information is approved upon entry into the warehouse, the RFID tags containing the plant information are detected by an RFID reader to obtain the tag detection information.

[0012] Based on the tag detection information, the plant information is classified into registration status to obtain registration status classification information;

[0013] Based on the registration status, plant information is assigned IDs to obtain the new ID assignment process and / or the existing ID association daily management process.

[0014] Further, S2 includes:

[0015] When the new ID allocation process is obtained, the plant information is assigned a new ID, and the new ID allocation information of the plant information is obtained.

[0016] The new ID allocation information and plant information are bound together by an RFID reader / writer to obtain plant identification binding information;

[0017] Record new plants by binding plant identifiers to the information, and obtain new plant record information;

[0018] The initial growth data of the new plant is stored to obtain the initial growth data of the new plant.

[0019] Furthermore, the step of recording new plants by binding plant identifiers to obtain new plant record information includes:

[0020] A new encryption key is issued for the plant identification binding information via GSA;

[0021] Record and store new plant information by binding plant identifiers;

[0022] Write the new encryption key into the RFID reader.

[0023] Further, S3 includes:

[0024] When the original ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data.

[0025] Image measurement and growth correlation analysis were performed on the daily growth data to obtain growth correlation analysis data;

[0026] Growth status is determined and labeled in the growth correlation analysis data to obtain growth characteristic status labeling information;

[0027] The growth characteristic status annotation information is integrated and summarized to obtain the growth summary data;

[0028] The growth summary data is encrypted and transmitted to the GSA backend to obtain the backend storage data.

[0029] Furthermore, when the original ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data, including:

[0030] Image classification data is obtained by performing image classification on daily ACDHMS using an image sensor.

[0031] The ACDHMS is used to collect and classify measurements daily using measurement sensors to obtain measurement and classification data.

[0032] By combining image classification data with measurement classification data, daily growth data can be obtained.

[0033] Furthermore, image measurement correlation growth analysis is performed on the daily growth acquisition data to obtain growth correlation analysis data, including:

[0034] Image classification feature extraction is performed on daily growth data to obtain growth image classification extraction information;

[0035] The daily growth data is used to extract measurement and classification features to obtain growth measurement and classification information.

[0036] Based on the growth location information, the growth image classification extraction information and the growth measurement classification extraction information are correlated to obtain image measurement classification correlation information;

[0037] The proportion of corresponding category data in the classification extraction information of each growth image and the preset growth image measurement information is obtained to obtain the image classification growth coefficient.

[0038] The average image growth coefficient is obtained by acquiring the average image growth coefficient of multiple growth images and extracting information from them.

[0039] Obtain the proportion of corresponding type data in the growth measurement classification information and the preset growth image measurement information for each growth measurement category, and obtain the measurement category growth coefficient;

[0040] The average growth coefficient of multiple growth measurement categories is obtained by acquiring the average growth coefficient of the measured growth categories;

[0041] The average growth coefficient of the image and the average growth coefficient of the measurement are obtained to obtain growth correlation analysis data.

[0042] Further, S4 includes:

[0043] The backend stored data is decrypted and verified using GSA to obtain the decrypted and verified data.

[0044] Perform growth health assessment and analysis on the decrypted and verified data to obtain health assessment and analysis data;

[0045] Based on health assessment and analysis data, health status is determined and labeled to obtain growth health status labeling information;

[0046] Generate a new key based on the annotation information of growth and health status;

[0047] The new key is sent to the RFID via GSA and then written into the RFID.

[0048] When the RFID receives the monitoring command, it retrieves and tests the new key to obtain the retrieval and testing information.

[0049] Furthermore, the step of performing growth health assessment and analysis on the decrypted verification data to obtain health assessment and analysis data includes:

[0050] Obtain the current actual growth status information and the current target growth status information based on the decrypted verification data;

[0051] Obtain the difference between the current actual growth status information and the current target growth status information to obtain growth status difference information;

[0052] The growth status difference information is compared with the preset growth status difference threshold to obtain the growth status comparison result;

[0053] Based on the growth status comparison results, the daily growth data is compared with the growth health threshold to obtain the growth health comparison results.

[0054] The growth and health comparison results are the health assessment and analysis data.

[0055] Furthermore, the system includes:

[0056] The registration and allocation module is used to perform tag detection and registration status classification of plant information, obtain the new ID allocation process and / or the existing ID association daily management process;

[0057] The new plant record module is used to classify and record plant information with new IDs according to the new ID allocation process, and obtain new plant record information.

[0058] The daily status analysis module is used to collect daily ACDHMS data based on the original ID and daily management process. After integrating the daily growth data collection, image measurement, growth analysis and growth status determination, the data is transmitted to the backend storage.

[0059] The health assessment module is used to decrypt and verify the data stored in the background, and then perform growth health assessment and analysis to obtain health assessment and analysis data, generate a new key and write it into the RFID.

[0060] The beneficial effects of this invention are as follows: This invention solves the core technical problems of confused identification, fragmented processes, scattered data, and unreliable traceability in traditional plant cultivation and management. It achieves refined and intelligent management of the entire plant life cycle. By streamlining processes, it avoids mixing the management of new and old plants, improving the clarity of management logic. Through end-to-end data encryption and dynamic key updates, it ensures the security of growth data and the immutability of traceability information, enhancing the credibility of traceability results. Through AI-driven data correlation analysis and health assessment, it replaces traditional manual experience-based judgment, improving the accuracy and timeliness of growth status assessment. It reduces manual management costs and data traceability difficulties, achieving multiple benefits such as standardized management, secure data, accurate assessment, and reliable traceability. Attached Figure Description

[0061] Figure 1 This is a schematic diagram of an artificial intelligence-based plant growth and health traceability management method.

[0062] Figure 2 This is a schematic diagram of the traceability management process. Detailed Implementation

[0063] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0064] In one embodiment of the present invention, the present invention proposes an artificial intelligence-based plant growth and health traceability management method and system, the method comprising:

[0065] S1. Perform tag detection and registration status classification on plant information, and obtain the new ID allocation process and / or the existing ID association daily management process;

[0066] S2. Classify and record plant information with new IDs according to the new ID allocation process to obtain new plant record information;

[0067] S3. Based on the existing ID association daily management process, collect daily ACDHMS data, and after integrating the daily growth data with image measurement association growth analysis and growth status determination, transmit it to the background storage data.

[0068] S4. Decrypt and verify the data stored in the background, then perform growth health assessment and analysis to obtain health assessment and analysis data, generate a new key and write it into the RFID, as shown in the figure.

[0069] The working principle and technical effects of the above-mentioned technical solution are as follows: This method completes the initial identification and process diversion of plants upon entry into the warehouse through tag detection and registration status classification, ensuring that new plants and existing plants are managed with differentiated logic; for new plants, ID allocation, binding, and initial recording are completed to establish a unique identity file and growth benchmark for each new plant; for existing plants, daily multi-dimensional growth data is collected, correlated, judged, and encrypted and uploaded, realizing dynamic monitoring and data accumulation of the growth process; through the decryption verification and health assessment of uploaded data in the background, a new key is generated and written into the RFID, completing the data security update and traceability link closed loop. The entire process relies on the GSA artificial intelligence backend to realize automated data processing and security control, forming a full-link management logic of identity management, data collection, analysis and evaluation, and secure traceability.

[0070] This method solves the core technical problems of traditional plant cultivation and management, such as confusing identities, fragmented processes, scattered data, and unreliable traceability. It achieves refined and intelligent management throughout the entire plant lifecycle. By streamlining processes, it avoids mixing the management of new and old plants, improving the clarity of management logic. Through end-to-end data encryption and dynamic key updates, it ensures the security of growth data and the immutability of traceability information, enhancing the credibility of traceability results. AI-driven data correlation analysis and health assessment replace traditional manual experience-based judgment, improving the accuracy and timeliness of growth status assessment. It reduces manual management costs and data traceability difficulties, achieving multiple benefits: standardized management, secure data, accurate assessment, and reliable traceability.

[0071] In one embodiment of the present invention, S1 includes:

[0072] Determine whether plant information has entered the planting management area to obtain entry judgment information;

[0073] After the information is approved upon entry into the warehouse, the RFID tags containing the plant information are detected by an RFID reader to obtain the tag detection information.

[0074] Based on the tag detection information, the plant information is classified into registration status to obtain registration status classification information;

[0075] Based on the registration status, plant information is assigned IDs to obtain the new ID assignment process and / or the existing ID association daily management process.

[0076] The process of assigning IDs to plant information based on registration status, obtaining new IDs, and / or associating existing IDs with daily management processes includes:

[0077] When the registration status is classified as unregistered, the new ID allocation process is triggered.

[0078] When the registration status is classified as "registered", the original ID association daily management process is triggered.

[0079] The working principle and technical effects of the above-mentioned technical solution are as follows: This method focuses on the identity verification and process diversion of plant entry. The core logic is to achieve precise diversion of plant management through progressive steps of entry judgment, tag detection, status classification, and process triggering. The entry detection module of the planting management area determines whether the plant meets the entry conditions and generates entry judgment information to prevent plants that do not meet management requirements from entering the system. After the entry judgment is passed, the RFID reader reads the RFID tag information carried by the plant to obtain tag detection information, which serves as the basis for determining the identity registration status. Based on whether the tag detection information contains a valid registration record, the plant is divided into two categories: registered and unregistered, generating registration status classification information. Based on different registration statuses, corresponding ID management processes are triggered: the unregistered status triggers a new ID allocation process to establish an identity for the new plant; the registered status triggers the existing ID association daily management process, directly connecting to the daily monitoring of existing plants and ensuring the continuity of the process.

[0080] This method solves the technical problems of inaccurate identity verification, mixed management of new and old plants, and disordered process connections in traditional plant entry management. It achieves standardized identity verification for plant entry, ensuring the identifiability of plant identities through RFID tag detection and preventing plants without identification information from entering the management system. By classifying registration status and streamlining processes, it clarifies the differentiated management paths for new and old plants, improving the orderliness and efficiency of the management process. Simultaneously, it proactively intercepts ineligible plants, reducing redundant management costs and ensuring the uniqueness and accuracy of plant identity information within the management system.

[0081] In one embodiment of the present invention, S2 includes:

[0082] When the new ID allocation process is obtained, the plant information is assigned a new ID, and the new ID allocation information of the plant information is obtained.

[0083] The new ID allocation information and plant information are bound together by an RFID reader / writer to obtain plant identification binding information;

[0084] Record new plants by binding plant identifiers to the information, and obtain new plant record information;

[0085] The initial growth data of the new plant is stored to obtain the initial growth data of the new plant.

[0086] The working principle and technical effects of the above technical solution are as follows: This method establishes an identity file for unregistered new plants. The core logic is the full-process identity and data initialization of ID allocation, binding, recording, and initial data storage. When the new ID allocation process is triggered, the system automatically generates a unique new ID as the exclusive identity identifier for the new plant, obtaining the new ID allocation information; the new ID is bound to the physical entity of the new plant through an RFID reader, so that the ID and the plant form a unique correspondence, generating plant identification binding information; based on the bound identification information, a unique growth file is established for the new plant, completing the new plant record and obtaining the new plant record information; at the same time, the initial growth data of the new plant (such as initial plant height, number of leaves, initial growth environment parameters, etc.) is collected and associated with the new plant record information for storage, forming the initial growth data of the new plant.

[0087] This method solves the technical problems of lack of unique identification, missing growth benchmarks, and incomplete records in traditional new plant management. It achieves unique and standardized record-keeping of new plant identities, ensuring traceability throughout the entire life cycle of new plants through exclusive ID binding; the storage of initial growth data avoids the problem of lack of reference for evaluation; at the same time, the standardized record-keeping process reduces the errors and tediousness of manual recording, improves the efficiency of new plant entry management, and ensures a smooth connection between subsequent daily management and traceability.

[0088] In one embodiment of the present invention, the step of recording a new plant by binding plant identifier information to obtain new plant record information includes:

[0089] A new encryption key is issued for the plant identification binding information via GSA;

[0090] Record and store new plant information by binding plant identifiers;

[0091] Write the new encryption key into the RFID reader.

[0092] The working principle and technical effects of the above-mentioned technical solution are as follows: This method focuses on data security management during the recording process of new plants. The core logic is to achieve the binding of new plant identity and data security through key issuance, record storage, and key writing. After the plant identification binding is completed, the GSA AI planting backend issues a unique new encryption key for the binding information. This key serves as the core credential for the encrypted transmission and storage of subsequent new plant growth data. The plant identification binding information, including the new ID and binding relationship, is stored in a structured manner to form a complete basic file of the new plant. The new encryption key issued by the GSA backend is written into the RFID tag of the plant through an RFID reader, so that the key is directly associated with the physical identity of the plant, ensuring the unique correspondence between identity and key during subsequent data transmission.

[0093] This method addresses the technical challenges of insecure data transmission and storage, and the lack of secure binding between identity and data, in the traditional process of new plant registration. It achieves source control of new plant data security by issuing a dedicated encryption key through the GSA backend, ensuring encrypted transmission and storage of subsequent growth data and reducing the risk of data tampering or leakage. Direct writing of the key to the RFID tag establishes a strong association between plant identity and the encryption key, enhancing the targetedness and reliability of data security control. Simultaneously, the introduction of the encryption key provides security for end-to-end traceability data, improving the credibility of traceability information and avoiding the security risks caused by unprotected data transmission in traditional registration processes.

[0094] In one embodiment of the present invention, S3 includes:

[0095] When the original ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data.

[0096] Image measurement and growth correlation analysis were performed on the daily growth data to obtain growth correlation analysis data;

[0097] Growth status is determined and labeled in the growth correlation analysis data to obtain growth characteristic status labeling information;

[0098] The growth characteristic status annotation information is integrated and summarized to obtain the growth summary data;

[0099] The growth summary data is encrypted and transmitted to the GSA backend to obtain the backend storage data.

[0100] The working principle and technical effects of the above technical solution are as follows: This method is for the daily growth monitoring and data management of registered plants. The core logic is a dynamic monitoring and data accumulation process of data collection, correlation analysis, status determination, and integrated uploading. When the original ID association daily management process is triggered, the daily ACDHMS growth parameters of the plants are collected using various sensor devices to obtain daily growth collection data. Through image measurement correlation growth analysis algorithms, the collected data is processed in multiple dimensions to extract growth correlation analysis data and explore the inherent correlation between image features and measurement data. Based on the correlation analysis data, the growth status of the plants is determined and labeled to clarify the current growth status of the plants and generate growth feature status label information. The labeled status information is integrated and summarized with the original collected data to form structured growth summary data. The growth summary data is uploaded to the GSA backend through an encrypted transmission channel to form backend storage data, completing the accumulation of daily growth data.

[0101] This method solves the technical problems of fragmented data collection, in-depth analysis, delayed status assessment, and insecure data transmission in traditional daily plant management. It achieves comprehensive and structured collection of daily plant growth data, avoiding the limitations of single data points through multi-dimensional parameter collection; it enhances the analytical depth of growth data through image measurement and correlation analysis, making growth status assessment more scientific; encrypted transmission ensures the security of daily data transmission, preventing data tampering or leakage during transmission; and the structured data integration and backend storage provide complete data support for subsequent health assessments and traceability queries, improving the precision of daily management and data utilization efficiency, while reducing the cost and lag of manual data analysis.

[0102] In one embodiment of the present invention, when the original ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data, including:

[0103] Image classification data is obtained by performing image classification on daily ACDHMS using an image sensor.

[0104] The ACDHMS is used to collect and classify measurements daily using measurement sensors to obtain measurement and classification data.

[0105] By combining image classification data with measurement classification data, daily growth data can be obtained.

[0106] ACDHMS includes a set of growth parameters such as air temperature and humidity (A), light intensity (C), plant height (D), soil moisture (H), soil nutrients (M), and growth cycle stage (S).

[0107] The preset growth image measurement information includes database information on standard image features (such as leaf RGB values ​​and morphological parameters) and measurement features (such as plant height and stem diameter thresholds) of ginseng plants at each growth stage.

[0108] The working principle and technical effects of the above-mentioned technical solution are as follows: This method focuses on the accurate collection of daily growth data. The core logic is classification collection and data combination. Through the collaborative work of image and measurement sensors, comprehensive coverage of growth parameters is achieved. The core parameters of ACDHMS are clearly defined (air temperature and humidity, light intensity, plant height, soil moisture, soil nutrients, and growth cycle stage) to ensure the targeted scope of collection. Image sensors are used to classify and collect visual characteristic parameters of the plant (such as leaf morphology, color, and visual manifestations of growth cycle stages) to obtain image classification collection data, capturing the visual appearance information of plant growth. Measurement sensors are used to accurately measure and classify the plant's physical and environmental parameters (such as plant height, soil moisture, soil nutrients, air temperature and humidity, and light intensity) to obtain measurement classification collection data, capturing quantitative data of plant growth. The image classification collection data and measurement classification collection data are associated and combined according to the plant's growth location and time dimension to form daily growth collection data containing both visual appearance and quantitative data, ensuring the integrity and relevance of the data.

[0109] This method addresses the technical problems of traditional data acquisition, such as single data dimensions, separation of visual and quantitative data, and insufficient targeting. It achieves multi-dimensional and comprehensive acquisition of growth data. Through the synergistic supplementation of image and measurement data, it captures both the visual appearance of plant growth and obtains accurate quantitative data, improving the comprehensiveness and richness of the data. Clear ACDHMS parameter definitions and classification acquisition logic enhance the targeting and standardization of data acquisition, avoiding the generation of redundant data. The correlation and combination of image and measurement data solves the problem that single data points cannot fully reflect the plant's growth status, while also reducing the difficulty of subsequent data processing and improving data utilization efficiency.

[0110] In one embodiment of the present invention, image measurement-related growth analysis is performed on the daily growth acquisition data to obtain growth correlation analysis data, including:

[0111] Image classification feature extraction is performed on daily growth data to obtain growth image classification extraction information;

[0112] The daily growth data is used to extract measurement and classification features to obtain growth measurement and classification information.

[0113] Based on the growth location information, the growth image classification extraction information and the growth measurement classification extraction information are correlated to obtain image measurement classification correlation information;

[0114] The proportion of corresponding category data in the classification extraction information of each growth image and the preset growth image measurement information is obtained to obtain the image classification growth coefficient.

[0115] The average image growth coefficient is obtained by acquiring the average image growth coefficient of multiple growth images and extracting information from them.

[0116] Obtain the proportion of corresponding type data in the growth measurement classification information and the preset growth image measurement information for each growth measurement category, and obtain the measurement category growth coefficient;

[0117] The average growth coefficient of multiple growth measurement categories is obtained by acquiring the average growth coefficient of the measured growth categories;

[0118] The average growth coefficient of the image and the average growth coefficient of the measurement are obtained to obtain growth correlation analysis data.

[0119] For example:

[0120] Extract key features from plant photos (such as leaf color and the presence or absence of disease spots);

[0121] Extract key data (such as plant height and soil moisture) from actual measurements.

[0122] Determine that these characteristics and data all belong to the same plant and match them accordingly;

[0123] By comparing the characteristics of the photos, the actual measurement data, and the standards for healthy plants, the degree of compliance of each plant can be calculated.

[0124] The average of the degree of compliance of the photographic features and the degree of compliance of the actual measurement is taken to obtain the final result as an assessment of the plant's growth status.

[0125] The working principle and technical effect of the above technical solution are as follows: The core of this method is to achieve deep fusion analysis of image features and measurement features through feature extraction, association matching, coefficient calculation, and mean fusion, so as to accurately characterize the plant growth status. Image classification features (such as leaf color, presence or absence of disease spots, etc.) and measurement classification features (such as plant height, soil moisture, etc.) are extracted from daily growth data to obtain growth image classification extraction information and growth measurement classification extraction information. Based on growth location information, the two types of extracted information are matched one-to-one to ensure that the data corresponds to the same plant, thus obtaining image measurement classification association information. The image classification extraction information of each type is compared with the corresponding standard data in the preset growth image measurement information, and the ratio of the two is calculated as the image classification growth coefficient to quantify the degree of compliance of image features. By calculating the mean of multiple image classification growth coefficients, the image growth average coefficient is obtained, which comprehensively reflects the overall growth status of the image dimension. Similarly, the measurement classification growth coefficient and the measurement growth average coefficient are calculated to comprehensively reflect the overall growth status of the measurement dimension. The average of the image growth average coefficient and the measurement growth average coefficient is taken to obtain growth association analysis data that fuses the two types of data, thus comprehensively and objectively characterizing the plant growth status.

[0126] This method addresses the technical problems of traditional growth analysis, such as the separation of images and measurement data, limited analytical dimensions, and incomplete characterization of growth states. It achieves deep fusion analysis of images and measurement data, overcoming the limitations of single data dimensions through feature correlation and coefficient fusion, thereby improving the comprehensiveness and objectivity of growth state analysis. By comparing and calculating with preset standard data, qualitative image features are transformed into quantitative coefficient indicators, enhancing the accuracy and quantifiability of the analysis results. The fused growth correlation analysis data replaces traditional manual judgment, reducing subjective errors and improving the scientific rigor and accuracy of growth state analysis.

[0127] In one embodiment of the present invention, S4 includes:

[0128] The backend stored data is decrypted and verified using GSA to obtain the decrypted and verified data.

[0129] Perform growth health assessment and analysis on the decrypted and verified data to obtain health assessment and analysis data;

[0130] Based on health assessment and analysis data, health status is determined and labeled to obtain growth health status labeling information;

[0131] Generate a new key based on the annotation information of growth and health status;

[0132] The new key is sent to the RFID via GSA and then written into the RFID.

[0133] When the RFID receives the monitoring command, it retrieves and checks the new key to obtain retrieval and detection information, such as... Figure 2 As shown.

[0134] The verification includes data integrity verification (determining whether key parameters are missing) and data rationality verification (determining whether the data is within the normal range of growth parameters for ginseng plants).

[0135] The working principle and technical effects of the above technical solution are as follows: The GSA backend uses the corresponding key to decrypt the uploaded growth summary data, and simultaneously performs data integrity verification (determining whether key parameters are missing) and data rationality verification (determining whether the data is within the normal range of growth parameters for ginseng plants), ensuring the validity and reliability of the data and obtaining decrypted verification data; based on the decrypted verification data, a growth health assessment analysis is performed to determine the current health status of the plant and obtain health assessment analysis data; based on the assessment data, the health status of the plant is clearly determined and marked, generating growth health status marking information; to ensure the security of subsequent data transmission, a new encryption key is generated based on the health status marking information; the new key is sent to the plant's RFID tag through the GSA backend to complete the writing and update of the new key; when the RFID receives a monitoring command, the system retrieves the new key for detection, verifies the validity and integrity of the key writing, ensures successful key update, and completes the entire data processing and security update closed loop.

[0136] This method addresses the technical challenges of unreliable data validity, lack of evidence for health assessments, and untimely data security updates in traditional backend data processing. Dual verification ensures the reliability of uploaded data, preventing invalid or abnormal data from interfering with subsequent assessments and improving the accuracy of health assessments. Health assessments and status labeling based on valid data enable timely detection and response to emerging issues. Dynamic generation and writing of new keys ensures the security of subsequent data transmission and storage, avoiding security risks associated with fixed keys and enhancing the security and reliability of the traceability chain. The key retrieval and detection process ensures the validity of key updates, preventing management gaps caused by key writing failures, reducing data security risks and management vulnerabilities, and achieving a virtuous cycle of data processing, security updates, and traceability.

[0137] In one embodiment of the present invention, the step of performing growth health assessment analysis on the decryption verification data to obtain health assessment analysis data includes:

[0138] Obtain the current actual growth status information and the current target growth status information based on the decrypted verification data;

[0139] Obtain the difference between the current actual growth status information and the current target growth status information to obtain growth status difference information;

[0140] The growth status difference information is compared with the preset growth status difference threshold to obtain the growth status comparison result;

[0141] Based on the growth status comparison results, the daily growth data is compared with the growth health threshold to obtain the growth health comparison results.

[0142] The growth and health comparison results are the health assessment and analysis data.

[0143] For example:

[0144] From the decrypted growth data, find out the actual growth status of the seedling (e.g., yellowish leaves, short stature), and then retrieve the standard growth status that a healthy seedling should have in the system (e.g., dark green leaves, height meets the standard).

[0145] Identify the discrepancies between the actual and standard conditions and compare these two situations to pinpoint where the differences lie: leaf color is lighter than the standard, and height is shorter than the standard. This indicates a difference in growth status.

[0146] By comparing the differences with the acceptable range, you can check the system's preset acceptable range of differences (for example, it's okay if the leaf color is a little lighter, but it's not acceptable if it's too short) to determine whether the actual difference of this seedling is within the acceptable range and obtain the comparison results of its growth status.

[0147] After verifying the growth data against the above comparison results, the photo and measurement data of the seedling are checked again against the health thresholds in the system (such as the color standard of healthy leaves and the minimum value of healthy plant height). The final conclusion of whether the growth data meets the standard or not is the health assessment analysis data.

[0148] The working principle and technical effect of the above technical solution are as follows: Accurate assessment of plant health status is achieved through a progressive logic of comparing actual and target growth, determining the difference, and verifying the threshold. The actual growth status information of the plant (such as actual plant height, leaf color, and soil nutrients) is extracted from the decrypted verification data, while simultaneously retrieving the preset target growth status information for the current growth stage (i.e., the standard growth parameters of a healthy plant). The difference between the actual and target growth status information is calculated to clarify the gap and obtain the growth status difference information. The growth status difference information is compared with the preset growth status difference threshold to determine whether the difference is within an acceptable range, obtaining the growth status comparison result (e.g., the difference is within the allowable range, or the difference exceeds the allowable range). Based on the growth status comparison result, daily growth data is further precisely compared with the growth health threshold. If the difference is within the allowable range, key health indicators are verified; if the difference exceeds the range, all growth parameters are comprehensively verified, ultimately obtaining the growth health comparison result. This result is the health assessment analysis data, directly representing the plant's health status.

[0149] This method addresses the technical problems of unclear assessment criteria, large subjective errors, and inaccurate health judgments in traditional health assessments. By comparing the difference between the actual and target states, it clarifies the direction and extent of plant growth deviations, providing a quantitative basis for health assessment and avoiding the subjectivity of traditional experience-based judgments. The introduction of preset thresholds makes the assessment criteria clearer, improving the standardization and consistency of health assessments. Stratified verification based on the comparison results of growth states ensures both the comprehensiveness and efficiency of the assessment, avoiding redundant verification. The final growth and health comparison results accurately characterize the plant's health status, providing a clear direction for subsequent planting control, enabling early detection and intervention of growth problems, reducing yield losses caused by health issues, and improving the precision of planting management.

[0150] According to one embodiment of the present invention, the system includes:

[0151] The registration and allocation module is used to perform tag detection and registration status classification of plant information, obtain the new ID allocation process and / or the existing ID association daily management process;

[0152] The new plant record module is used to classify and record plant information with new IDs according to the new ID allocation process, and obtain new plant record information.

[0153] The daily status analysis module is used to collect daily ACDHMS data based on the original ID and daily management process. After integrating the daily growth data collection, image measurement, growth analysis and growth status determination, the data is transmitted to the backend storage.

[0154] The health assessment module is used to decrypt and verify the data stored in the background, and then perform growth health assessment and analysis to obtain health assessment and analysis data, generate a new key and write it into the RFID.

[0155] The working principle and technical effects of the above-mentioned technical solution are as follows: This method completes the initial identification and process diversion of plants upon entry into the warehouse through tag detection and registration status classification, ensuring that new plants and existing plants are managed with differentiated logic; for new plants, ID allocation, binding, and initial recording are completed to establish a unique identity file and growth benchmark for each new plant; for existing plants, daily multi-dimensional growth data is collected, correlated, judged, and encrypted and uploaded, realizing dynamic monitoring and data accumulation of the growth process; through the decryption verification and health assessment of uploaded data in the background, a new key is generated and written into the RFID, completing the data security update and traceability link closed loop. The entire process relies on the GSA artificial intelligence backend to realize automated data processing and security control, forming a full-link management logic of identity management, data collection, analysis and evaluation, and secure traceability.

[0156] This method solves the core technical problems of traditional plant cultivation and management, such as confusing identities, fragmented processes, scattered data, and unreliable traceability. It achieves refined and intelligent management throughout the entire plant lifecycle. By streamlining processes, it avoids mixing the management of new and old plants, improving the clarity of management logic. Through end-to-end data encryption and dynamic key updates, it ensures the security of growth data and the immutability of traceability information, enhancing the credibility of traceability results. AI-driven data correlation analysis and health assessment replace traditional manual experience-based judgment, improving the accuracy and timeliness of growth status assessment. It reduces manual management costs and data traceability difficulties, achieving multiple benefits: standardized management, secure data, accurate assessment, and reliable traceability.

[0157] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A plant growth and health traceability management method based on artificial intelligence, characterized in that, The method includes: S1. Perform tag detection and registration status classification on plant information, and obtain the new ID allocation process and / or the existing ID association daily management process; S2. Classify and record plant information with new IDs according to the new ID allocation process to obtain new plant record information; S3. Based on the existing ID association daily management process, collect daily ACDHMS data, and after integrating the daily growth data with image measurement association growth analysis and growth status determination, transmit it to the background storage data. S4. Decrypt and verify the data stored in the background, then perform growth health assessment and analysis, obtain health assessment and analysis data, generate a new key and write it into RFID; Wherein, S2 includes: When the new ID allocation process is obtained, the plant information is assigned a new ID, and the new ID allocation information of the plant information is obtained. The new ID allocation information and plant information are bound together by an RFID reader / writer to obtain plant identification binding information; Record new plants by binding plant identifiers to the information, and obtain new plant record information; The initial growth data of the new plant records is stored to obtain the initial growth data of the new plant. The step of recording new plants by binding plant identifiers to obtain new plant record information includes: A new encryption key is issued for the plant identification binding information via GSA; Record and store new plant information by binding plant identifiers; Write the new encryption key into the RFID reader; Wherein, S3 includes: When the original ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data. Image measurement and growth correlation analysis were performed on the daily growth data to obtain growth correlation analysis data; Growth status is determined and labeled in the growth correlation analysis data to obtain growth characteristic status labeling information; The growth characteristic status annotation information is integrated and summarized to obtain the growth summary data; The growth summary data is encrypted and transmitted to the GSA backend to obtain the backend stored data. The process involves performing image measurement-related growth analysis on the daily growth data to obtain growth correlation analysis data, including: Image classification feature extraction is performed on daily growth data to obtain growth image classification extraction information; The daily growth data is used to extract measurement and classification features to obtain growth measurement and classification information. Based on the growth location information, the growth image classification extraction information and the growth measurement classification extraction information are correlated to obtain image measurement classification correlation information; The proportion of corresponding category data in the classification extraction information of each growth image and the preset growth image measurement information is obtained to obtain the image classification growth coefficient. The average image growth coefficient is obtained by acquiring the average image growth coefficient of multiple growth images and extracting information from them. Obtain the proportion of corresponding type data in the growth measurement classification information and the preset growth image measurement information for each growth measurement category, and obtain the measurement category growth coefficient; The average growth coefficient of multiple growth measurement categories is obtained by acquiring the average growth coefficient of the measured growth categories; The average value of the image growth average coefficient and the measured growth average coefficient is obtained to obtain growth correlation analysis data; Wherein, S4 includes: The backend stored data is decrypted and verified using GSA to obtain the decrypted and verified data. Perform growth health assessment and analysis on the decrypted and verified data to obtain health assessment and analysis data; Based on health assessment and analysis data, health status is determined and labeled to obtain growth health status labeling information; Generate a new key based on the annotation information of growth and health status; The new key is sent to the RFID via GSA and then written into the RFID. When the RFID receives the monitoring command, it retrieves and tests the new key to obtain the retrieval and testing information.

2. The plant growth and health traceability management method based on artificial intelligence according to claim 1, characterized in that, S1 includes: Determine whether plant information has entered the planting management area to obtain entry judgment information; After the information is approved upon entry into the warehouse, the RFID tags containing the plant information are detected by an RFID reader to obtain the tag detection information. Based on the tag detection information, the plant information is classified into registration status to obtain registration status classification information; Based on the registration status, plant information is assigned IDs, and a new ID assignment process and / or an existing ID association daily management process are obtained.

3. The plant growth and health traceability management method based on artificial intelligence according to claim 1, characterized in that, When the existing ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data, including: Image classification data is obtained by performing image classification on daily ACDHMS using an image sensor. The ACDHMS is used to collect and classify measurements daily using measurement sensors to obtain measurement and classification data. By combining image classification data with measurement classification data, daily growth data can be obtained.

4. The plant growth and health traceability management method based on artificial intelligence according to claim 1, characterized in that, The process of performing growth health assessment and analysis on the decrypted verification data to obtain health assessment and analysis data includes: Obtain the current actual growth status information and the current target growth status information based on the decrypted verification data; Obtain the difference between the current actual growth status information and the current target growth status information to obtain growth status difference information; The growth status difference information is compared with the preset growth status difference threshold to obtain the growth status comparison result; Based on the growth status comparison results, the daily growth data is compared with the growth health threshold to obtain the growth health comparison results. The growth and health comparison results are the health assessment and analysis data.

5. A plant growth and health traceability management system based on artificial intelligence, characterized in that, The system includes: The registration and allocation module is used to perform tag detection and registration status classification of plant information, obtain the new ID allocation process and / or the existing ID association daily management process; The new plant record module is used to classify and record plant information with new IDs according to the new ID allocation process, and obtain new plant record information. The daily status analysis module is used to collect daily ACDHMS data based on the original ID and daily management process. After integrating the daily growth data collection, image measurement, growth analysis and growth status determination, the data is transmitted to the backend storage. The health assessment module is used to decrypt and verify the data stored in the background, and then perform growth health assessment and analysis to obtain health assessment and analysis data, generate a new key and write it into the RFID. The new plant recording module includes: When the new ID allocation process is obtained, the plant information is assigned a new ID, and the new ID allocation information of the plant information is obtained. The new ID allocation information and plant information are bound together by an RFID reader / writer to obtain plant identification binding information; Record new plants by binding plant identifiers to the information, and obtain new plant record information; The initial growth data of the new plant records is stored to obtain the initial growth data of the new plant. The step of recording new plants by binding plant identifiers to obtain new plant record information includes: A new encryption key is issued for the plant identification binding information via GSA; Record and store new plant information by binding plant identifiers; Write the new encryption key into the RFID reader; The daily status analysis module includes: When the original ID is associated with the daily management process, daily ACDHMS data is collected through sensor devices to obtain daily growth data. Image measurement and growth correlation analysis were performed on the daily growth data to obtain growth correlation analysis data; Growth status is determined and labeled in the growth correlation analysis data to obtain growth characteristic status labeling information; The growth characteristic status annotation information is integrated and summarized to obtain the growth summary data; The growth summary data is encrypted and transmitted to the GSA backend to obtain the backend stored data. The process involves performing image measurement-related growth analysis on the daily growth data to obtain growth correlation analysis data, including: Image classification feature extraction is performed on daily growth data to obtain growth image classification extraction information; The daily growth data is used to extract measurement and classification features to obtain growth measurement and classification information. Based on the growth location information, the growth image classification extraction information and the growth measurement classification extraction information are correlated to obtain image measurement classification correlation information; The proportion of corresponding category data in the classification extraction information of each growth image and the preset growth image measurement information is obtained to obtain the image classification growth coefficient. The average image growth coefficient is obtained by acquiring the average image growth coefficient of multiple growth images and extracting information from them. Obtain the proportion of corresponding type data in the growth measurement classification information and the preset growth image measurement information for each growth measurement category, and obtain the measurement category growth coefficient; The average growth coefficient of multiple growth measurement categories is obtained by acquiring the average growth coefficient of the measured growth categories; The average value of the image growth average coefficient and the measured growth average coefficient is obtained to obtain growth correlation analysis data; The health assessment module includes: The backend stored data is decrypted and verified using GSA to obtain the decrypted and verified data. Perform growth health assessment and analysis on the decrypted and verified data to obtain health assessment and analysis data; Based on health assessment and analysis data, health status is determined and labeled to obtain growth health status labeling information; Generate a new key based on the annotation information of growth and health status; The new key is sent to the RFID via GSA and then written into the RFID. When the RFID receives the monitoring command, it retrieves and tests the new key to obtain the retrieval and testing information.

Images