Food traceability method based on intelligent Internet of Things information

Abstract

The invention relates to the technical field of data processing, in particular to a food traceability method based on intelligent Internet of Things information, and the method comprises the steps: pre-storing sample information corresponding to a plurality of monitoring subjects, and obtaining seed information, producing area information and an initial subject actual image of the monitoring subjects uploaded by a user side; based on the uploaded IP and the initial subject sample image, judging whether the monitored subject meets a continuous verification standard or not, calling growth rule features, predicting verification time nodes, sending verification demand information to a user side at the corresponding verification time nodes, obtaining feedback information, calling the subject sample image of the corresponding verification time nodes for comparison, and sending verification request information to the user side; and judging whether the growth process of the monitoring subject meets the standard or not, judging a mature feature difference value, and evaluating the storability of the monitoring subject based on the mature feature difference value so as to store the information for the monitoring subject into the block chain. The data authenticity of each uploading node is controlled, and the accuracy of food traceability is ensured.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a food traceability method based on smart Internet of Things information. Background Art

[0002] As users' requirements for food safety and quality continue to increase, the market demand for food traceability continues to grow. Food traceability technology provides users with a channel to understand food information, effectively manage food safety risks, and improve food quality. Blockchain technology, as an emerging technology, has broad application prospects in the field of food traceability. It provides a safe and transparent solution for food traceability. Through a decentralized approach, each participant can view the entire process of food from production to consumption in real time, enhancing the transparency and trust of food traceability.

[0003] Chinese Patent Publication No.: CN115374189A, discloses a food safety traceability method, device and equipment based on blockchain, including: building a food traceability alliance chain based on the cycle nodes of the food processing full cycle data set, selecting text data, ticket data, image data and video data of different cycle nodes, hashing and merging the ticket text extracted from the ticket data, the summary text extracted from the text data, the image data and the video data, obtaining the traceability hash value and storing it in the food traceability alliance chain, building a traceability database and a query database, querying the traceability data original from the traceability database based on the food number to be queried and calculating the verification hash value, querying the target block number from the query database and extracting the target traceability hash value, and obtaining the food traceability result according to the verification hash value and the target traceability hash value.

[0004] However, there are still the following problems in the prior art:

[0005] When using blockchain technology for food traceability, although blockchain ensures the immutability of uploaded data, it is impossible to determine the authenticity of the uploaded data. Once an error occurs in the uploaded data, the error information will be permanently recorded in the blockchain, making the traceability data untrue and inaccurate. In addition, in the prior art, food is not traced back to the source of planting, and the food quality is not verified based on relevant data during the planting process, which reduces the accuracy and efficiency of food traceability. Summary of the invention

[0006] To this end, the present invention provides a food traceability method based on smart IoT information to solve the problem that once an error occurs in the uploaded data, the error information will be permanently recorded in the blockchain, making the traceability data untrue and inaccurate. In addition, in the prior art, food is not traced back from the planting source, and the food quality is not verified based on relevant data in the planting process, which reduces the accuracy and efficiency of food traceability.

[0007] To achieve the above object, the present invention provides a food traceability method based on smart IoT information, which includes:

[0008] Pre-store sample information corresponding to several monitoring subjects, including seed information, origin information, growth law characteristics, and subject sample images at different verification time nodes;

[0009] Obtain the seed information, origin information and initial subject actual image of the monitoring subject uploaded by the user end, so as to determine whether the monitoring subject meets the continuous verification standard based on the uploaded IP and the initial subject sample image;

[0010] In response to the determination result of the continuous verification standard, calling the growth law feature, predicting the required verification time node based on the growth law feature, and sending verification requirement information to the user terminal at the corresponding verification time node;

[0011] Obtaining feedback information from the user terminal based on the verification requirement information, including actual images of the subject corresponding to each verification time node;

[0012] Based on the feedback information, the subject sample image corresponding to the verification time node is called for comparison, and based on the comparison result, whether the growth process of the monitored subject meets the standard;

[0013] In response to the determination result of the growth process of the monitored subject, the actual image of the monitored subject at the maturity stage is obtained for comparison with the called sample image of the maturity stage, and the maturity feature difference value is determined. The storability of the monitored subject is evaluated based on the maturity feature difference value, so as to store the seed information, origin information and actual image of the subject at each verification time node of the monitored subject into the blockchain.

[0014] Furthermore, the process of determining whether the monitoring subject meets the continuous verification standard includes:

[0015] Determine whether the uploading IP is consistent with the origin information;

[0016] Determining whether the seed category corresponding to the initial subject actual image is consistent with the seed information;

[0017] If the upload IP is consistent with the origin information and the seed category corresponding to the actual image of the initial subject is consistent with the seed information, it is determined that the monitored subject meets the continuous verification standards;

[0018] The initial subject actual image is a seed image for the monitored subject.

[0019] Further, in response to the determination result of the continuous verification standard, calling the growth law feature includes:

[0020] If the monitored subject meets the continuous verification criteria, the corresponding growth law characteristics are called;

[0021] Among them, the growth law characteristics include the growth height and total growth time of the plant corresponding to the monitoring subject at different time nodes.

[0022] Furthermore, the process of predicting the required verification time node based on the growth law characteristics includes:

[0023] Obtaining the height change rate of the plant corresponding to the monitoring subject in different time periods;

[0024] If the height change rate in a time period is greater than a predetermined height change rate threshold, the end time of the time period is determined as a verification time node;

[0025] The length of the time period division is determined based on the total growth time.

[0026] Further, the process of calling the subject sample image corresponding to the verification time node for comparison based on the feedback information includes:

[0027] Determine the subject actual contour in the subject actual image, and determine the subject sample contour in each subject sample image;

[0028] Determining a mean value of similarity between the image in the actual outline of the subject and the image in each subject sample outline;

[0029] The average height difference and the average width difference between the actual contour of the subject and each of the sample contours of the subject are determined.

[0030] Further, the process of determining whether the growth progress of the monitored subject meets the standard based on the comparison result includes:

[0031] Compare the similarity mean with a preset similarity threshold,

[0032] Determine whether the height difference mean is within a predetermined height difference range, and determine whether the width difference mean is within a predetermined width difference range;

[0033] If the similarity mean is greater than a preset similarity threshold and the height difference mean is within a predetermined height difference range and the width difference mean is within a predetermined width difference range, it is determined that the growth process of the monitored subject meets the standard.

[0034] Furthermore, if the growth process of the monitored subject meets the standard, the actual image of the monitored subject at the mature stage is obtained and compared with the called sample image at the mature stage. The comparison process includes:

[0035] Determine the actual outline of the mature subject in the actual image of the mature stage subject, and determine the sample outline of the mature subject in the sample images of each mature stage;

[0036] Determine the mean similarity and the mean chromaticity difference between the image in the actual outline of the mature subject and the image in the outline of each mature subject sample;

[0037] The average height difference and the average width difference between the actual contour of the mature subject and the contours of each of the mature subject samples are determined.

[0038] Further, the process of determining the difference value of the maturity characteristic includes,

[0039] Determine the ratio of the similarity threshold to the similarity mean, determine the ratio of the chromaticity difference mean to the standard chromaticity difference threshold, determine the ratio of the height difference mean to the standard height difference threshold, and determine the ratio of the width difference mean to the standard width difference threshold;

[0040] The obtained ratios are weighted and summed to obtain the maturity characteristic difference value.

[0041] Further, evaluating the depositability of the monitoring subject based on the maturity characteristic difference value includes:

[0042] If the maturity characteristic difference value is greater than the preset standard maturity characteristic difference value, the depositability does not meet the standard;

[0043] If the maturity feature difference value is less than or equal to a preset standard maturity feature difference value, the depositability meets the standard.

[0044] Furthermore, the verification requirement information includes a required sending time and required sending content.

[0045] Compared with the prior art, the present invention relates to the field of data processing technology, and in particular to a food traceability method based on smart Internet of Things information. The present invention pre-stores sample information corresponding to a number of monitoring subjects, obtains seed information, origin information and initial subject actual image of the monitoring subject uploaded by the user end, determines whether the monitoring subject meets the continuous verification standard based on the uploaded IP and the initial subject sample image, calls growth law characteristics, predicts the required verification time node based on the growth law characteristics, sends verification requirement information to the user end at the corresponding verification time node, obtains feedback information from the user end based on the verification requirement information, calls the subject sample image of the corresponding verification time node for comparison, determines whether the growth process of the monitoring subject meets the standard, obtains the actual image of the monitoring subject in the mature stage and compares it with the called mature stage sample image, determines the mature feature difference value, evaluates the storability of the monitoring subject based on the mature feature difference value, controls the data authenticity of each upload node, and ensures the accuracy of food traceability.

[0046] In particular, the present invention checks whether each upload node of the monitoring subject meets the standards to determine the storability of the monitoring subject of each upload node. When uploading food information in real situations, users may make upload errors, but due to the special properties of the blockchain, the erroneous data has been stored in the blockchain and cannot be changed. In addition, the existing traceability process does not consider tracing from the planting source, and does not verify the food quality based on relevant data in the planting process. Based on this, the present invention considers confirming the storability of the monitoring subject of each upload node of the food to be uploaded before starting the subsequent verification steps, thereby ensuring the authenticity of the initial node upload information of the food to be uploaded.

[0047] In particular, the present invention predicts the verification time node to restrict the user terminal to upload the actual image of the subject within the corresponding time, and determines whether the growth status of the monitored subject meets the standard in combination with the comparison result of the subject sample image. In order to avoid the situation in which the monitored subject may develop prematurely in actual conditions, resulting in the destruction of the growth status of the monitored subject and causing food safety problems, the present invention takes into account that fruit and vegetable foods have obvious staged growth patterns, predicts the verification time node of fruit and vegetable foods, compares the actual image of the subject with the sample image, determines whether the growth process of the monitored subject meets the standard, determines the storability of the monitored subject at the verification time node, ensures the authenticity of the food to be uploaded, and improves the efficiency of food traceability.

[0048] In particular, the present invention determines the maturity stage subject based on the comparison between the actual image of the subject and the called maturity stage sample image, and determines the maturity feature difference value. In real life, improper application of drugs may cause abnormal enlargement of food, causing harm to the human body. Based on this, the present invention considers calculating and evaluating the storability of the monitoring subject. Preferably, only the monitoring subject whose maturity feature difference value is less than or equal to the preset standard maturity feature difference value can be uploaded on the maturity node, which ensures the authenticity of the food to be uploaded and improves the efficiency of food traceability. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of the method steps of a food traceability method based on smart IoT information according to an embodiment of the invention;

[0050] Figure 2 A logic block diagram of an embodiment of the invention for determining whether the monitoring subject meets the continuous verification standard;

[0051] Figure 3 A logic block diagram for determining whether the growth process of the monitoring subject meets the standard according to an embodiment of the invention;

[0052] Figure 4 A logical block diagram of the storability of the monitoring subject of the embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0055] See also Figures 1 to 4 As shown, Figure 1 This is a schematic diagram of the method steps of the food traceability method based on smart IoT information according to an embodiment of the invention. Figure 2 This is a logic block diagram of an embodiment of the invention for determining whether the monitoring subject meets the continuous verification standard. Figure 3 This is a logic block diagram of an embodiment of the invention for determining whether the growth process of the monitored subject meets the standard. Figure 4 To illustrate the logic block diagram of the monitoring subject of the embodiment, the food traceability method based on smart IoT information of the present invention includes:

[0056] Step S1, pre-storing sample information corresponding to a number of monitoring subjects, including seed information, origin information, growth law characteristics, and subject sample images at different verification time nodes;

[0057] Step S2, obtaining the seed information, origin information and initial subject actual image of the monitoring subject uploaded by the user end, so as to determine whether the monitoring subject meets the continuous verification standard based on the uploaded IP and the initial subject sample image;

[0058] Step S3, in response to the determination result of the continuous verification standard, calling the growth law feature, predicting the required verification time node based on the growth law feature, and sending verification requirement information to the user terminal at the corresponding verification time node;

[0059] Step S4, obtaining feedback information from the user terminal based on the verification requirement information, including actual images of the subject corresponding to each verification time node;

[0060] Based on the feedback information, the subject sample image corresponding to the verification time node is called for comparison, and based on the comparison result, whether the growth process of the monitored subject meets the standard;

[0061] Step S5, in response to the determination result of the growth process of the monitored subject, the actual image of the monitored subject at the maturity stage is obtained for comparison with the called sample image of the maturity stage, the maturity feature difference value is determined, and the storability of the monitored subject is evaluated based on the maturity feature difference value, so as to store the seed information, origin information and actual image of the subject at each verification time node of the monitored subject into the blockchain.

[0062] Specifically, there is no limitation on the method of obtaining the pre-stored sample information. Those skilled in the art can pre-collect seed information, origin information, growth pattern characteristics and subject sample images of different verification time nodes corresponding to different monitoring subjects to obtain sample information, which will not be elaborated here.

[0063] Taking the monitoring subject as a certain type of corn from a certain origin as an example, the seed information may include the seed name of the type of corn and the corresponding certification number, the origin information includes the origin of the type of corn, the growth pattern characteristics include the growth height and total growth time of the corresponding plants of the type of corn at different time nodes, and the main sample image includes pictures of different verification time nodes during the growth process of the type of corn.

[0064] It is understandable that the IP address can be obtained synchronously when the user uploads information, thereby determining the actual geographic location of the user, which will not be elaborated here.

[0065] Specifically, there is no limitation on the method of acquiring the actual image of the subject, which may be pre-photographed and then uploaded by the user end, which will not be elaborated here.

[0066] Specifically, the present invention checks whether each upload node of the monitoring subject meets the standards to determine the storability of the monitoring subject of each upload node. When uploading food information in real situations, users may make upload errors, but due to the special properties of the blockchain, the erroneous data has been stored in the blockchain and cannot be changed. In addition, the existing traceability process does not consider tracing from the planting source, and does not verify the food quality based on relevant data in the planting process. Based on this, the present invention considers confirming the storability of the monitoring subject of each upload node of the food to be uploaded before starting the subsequent verification steps, thereby ensuring the authenticity of the initial node upload information of the food to be uploaded.

[0067] Specifically, the process of determining whether the monitoring subject meets the continuous verification standards includes:

[0068] Determine whether the uploading IP is consistent with the origin information;

[0069] Determining whether the seed category corresponding to the initial subject actual image is consistent with the seed information;

[0070] If the upload IP is consistent with the origin information and the seed category corresponding to the actual image of the initial subject is consistent with the seed information, it is determined that the monitored subject meets the continuous verification standards;

[0071] The initial subject actual image is a seed image for the monitored subject.

[0072] Specifically, there is no limitation on the method of determining the seed category corresponding to the actual image of the initial subject. An image processing model that can identify the seed category in the image can be pre-trained to achieve the corresponding function. There is no limitation on the architecture of the image processing model. For example, it can be an image processing model with a neural network architecture, which will not be elaborated here.

[0073] Specifically, in response to the determination result of the continuous verification standard, calling the growth law feature includes:

[0074] If the monitored subject meets the continuous verification criteria, the corresponding growth law characteristics are called;

[0075] Among them, the growth law characteristics include the growth height and total growth time of the plant corresponding to the monitoring subject at different time nodes.

[0076] Specifically, it can be understood that there is a one-to-one correspondence between the growth height and the total growth time, that is, different total growth times correspond to growth heights, which will not be elaborated here.

[0077] Specifically, the process of predicting the verification time node required based on the growth law characteristics includes:

[0078] Obtaining the height change rate of the plant corresponding to the monitoring subject in different time periods;

[0079] If the height change rate in a time period is greater than a predetermined height change rate threshold, the end time of the time period is determined as a verification time node;

[0080] The length of the time period division is determined based on the total growth time.

[0081] It is understandable that during the rapid growth stage, the plants change rapidly and are prone to abnormalities. Therefore, verification requirement information is sent to the user terminal at each verification time node to verify the growth of the plants in a timely manner.

[0082] Specifically, the process of calculating the rate of change of altitude includes,

[0083] Determine the growth height of the monitored subject at different time periods;

[0084] The ratio of the growth height to the corresponding duration of the time period is determined as the height change rate.

[0085] Specifically, the altitude change rate threshold is determined according to the altitude change rate mean, and the altitude change rate threshold is set to 1.24 times the altitude change rate mean.

[0086] Specifically, the length of the time period is 10% to 20% of the total growth period.

[0087] Specifically, the process of calling the subject sample image corresponding to the verification time node for comparison based on the feedback information includes:

[0088] Determine the subject actual contour in the subject actual image, and determine the subject sample contour in each subject sample image;

[0089] Determining a mean value of similarity between the image in the actual outline of the subject and the image in each subject sample outline;

[0090] The average height difference and the average width difference between the actual contour of the subject and each of the sample contours of the subject are determined.

[0091] Specifically, there is no limitation on the method for obtaining the actual contour of the subject. For example, contour detection may be performed using OpenCV, or other methods may be used, which will not be described in detail.

[0092] Specifically, there is no limitation on the method of calculating the similarity. For example, any image processing algorithm or model can be used to solve the similarity between images. It is only necessary to calculate the similarity between the image in the actual contour of the subject and the image in the contour of each subject sample. This will not be repeated here.

[0093] It is understandable that the height and width of the monitored subject can be determined through the actual contour of the subject, and then the average height difference and the average width difference can be calculated.

[0094] Specifically, the process of determining whether the growth process of the monitored subject meets the standard based on the comparison result includes:

[0095] Compare the similarity mean with a preset similarity threshold,

[0096] Determine whether the height difference mean is within a predetermined height difference range, and determine whether the width difference mean is within a predetermined width difference range;

[0097] If the similarity mean is greater than a preset similarity threshold and the height difference mean is within a predetermined height difference range and the width difference mean is within a predetermined width difference range, it is determined that the growth process of the monitored subject meets the standard.

[0098] Specifically, the similarity threshold is predetermined, wherein the subject sample images corresponding to the same monitored subject at the same verification time node are obtained in advance, the subject sample contour in the subject sample image is determined, the mean similarity between the images within the subject sample contour is solved, and the similarity threshold is set to between 0.85 times and 0.95 times the similarity mean.

[0099] Specifically, the predetermined height difference range is determined based on the average height of the subject sample contour, and is usually set between 0 and 0.25 times the average height.

[0100] Specifically, the predetermined width difference range is determined based on the average width of the subject sample contour, and is usually set between 0 and 0.1 times the average height.

[0101] Specifically, if the growth process of the monitored subject meets the standard, the actual image of the monitored subject at the mature stage is obtained and compared with the called sample image at the mature stage. The comparison process includes:

[0102] Determine the actual outline of the mature subject in the actual image of the mature stage subject, and determine the sample outline of the mature subject in the sample images of each mature stage;

[0103] Determine the mean similarity and the mean chromaticity difference between the image in the actual outline of the mature subject and the image in the outline of each mature subject sample;

[0104] The average height difference and the average width difference between the actual contour of the mature subject and the contours of each of the mature subject samples are determined.

[0105] It can be understood that the actual image of the subject in the mature stage is the actual image of the subject corresponding to the final verification time node.

[0106] Specifically, there is no limitation on the calculation method of the chromaticity difference. For example, it can be determined based on the CIE color difference formula. It only needs to be able to calculate the chromaticity difference. This is a prior art and will not be described in detail.

[0107] Specifically, the present invention predicts the verification time node to restrict the user terminal to upload the actual image of the subject within the corresponding time, and determines whether the growth status of the monitored subject meets the standard in combination with the comparison result of the subject sample image. In order to avoid the situation in which the monitored subject may develop prematurely in actual conditions, resulting in the destruction of the growth status of the monitored subject and causing food safety problems, the present invention takes into account that fruit and vegetable foods have obvious staged growth patterns, predicts the verification time node of fruit and vegetable foods, compares the actual image of the subject with the sample image, determines whether the growth process of the monitored subject meets the standard, determines the storability of the monitored subject at the verification time node, ensures the authenticity of the food to be uploaded, and improves the efficiency of food traceability.

[0108] Specifically, the process of determining the difference value of maturity characteristics includes:

[0109] Determine the ratio of the similarity threshold to the similarity mean, determine the ratio of the chromaticity difference mean to the standard chromaticity difference threshold, determine the ratio of the height difference mean to the standard height difference threshold, and determine the ratio of the width difference mean to the standard width difference threshold;

[0110] The obtained ratios are weighted and summed to obtain the maturity characteristic difference value.

[0111] Specifically, the weight coefficient of the ratio of the similarity threshold to the similarity mean is 0.32, the weight coefficient of the ratio of the chromaticity difference mean to the standard chromaticity difference threshold is 0.29, the weight coefficient of the ratio of the height difference mean to the standard height difference threshold is 0.2, and the weight coefficient of the ratio of the width difference mean to the standard width difference threshold is 0.19.

[0112] Specifically, the similarity threshold, the standard chromaticity difference threshold, the standard height difference threshold, and the standard width difference threshold are preset, wherein a number of mature stage sample images of the same monitored subject are obtained, the mature subject sample contour is determined, and the mean similarity and the mean chromaticity difference between the images within each mature subject sample contour are solved;

[0113] The mean height difference and the mean width difference of the contour of each mature subject sample are solved, and the similarity mean is set as the similarity threshold, the chromaticity difference mean is set as the standard chromaticity difference threshold, the height difference mean is set as the standard height difference threshold, and the width difference mean is set as the standard width difference threshold.

[0114] Specifically, evaluating the depositability of the monitoring subject based on the maturity characteristic difference value includes:

[0115] If the maturity characteristic difference value is greater than the preset standard maturity characteristic difference value, the depositability does not meet the standard;

[0116] If the maturity feature difference value is less than or equal to a preset standard maturity feature difference value, the depositability meets the standard.

[0117] Specifically, the standard maturity characteristic difference value is selected in the interval [1.0, 1.15].

[0118] Specifically, the present invention determines the subject at the maturity stage based on the comparison between the actual image of the subject and the called sample image of the maturity stage, and determines the maturity feature difference value. In real life, improper application of drugs may cause abnormal enlargement of food, causing harm to the human body. Based on this, the present invention considers calculating and evaluating the storability of the monitoring subject. Preferably, only the monitoring subject whose maturity feature difference value is less than or equal to the preset standard maturity feature difference value can be uploaded to the maturity node, which ensures the authenticity of the food to be uploaded and improves the efficiency of food traceability.

[0119] Specifically, the verification requirement information includes the required sending time and the required sending content.

[0120] It is understandable that the purpose of sending the verification requirement information is to inform the user end of the information upload time and the content to be sent. In implementation, the content to be sent includes the actual image of the monitored subject that needs to be sent at each verification time node.

[0121] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A food traceability method based on smart IoT information, characterized in that: include: Pre-store sample information corresponding to several monitoring subjects, including seed information, origin information, growth law characteristics, and subject sample images at different verification time nodes; Obtain the seed information, origin information and initial subject actual image of the monitoring subject uploaded by the user end, so as to determine whether the monitoring subject meets the continuous verification standard based on the uploaded IP and the initial subject sample image; In response to the determination result of the continuous verification standard, calling the growth law feature, predicting the required verification time node based on the growth law feature, and sending verification requirement information to the user terminal at the corresponding verification time node; Obtaining feedback information from the user terminal based on the verification requirement information, including actual images of the subject corresponding to each verification time node; Based on the feedback information, the subject sample image corresponding to the verification time node is called for comparison, and based on the comparison result, whether the growth process of the monitored subject meets the standard; In response to the determination result of the growth process of the monitored subject, the actual image of the monitored subject at the maturity stage is obtained for comparison with the called sample image of the maturity stage, and the maturity feature difference value is determined. The storability of the monitored subject is evaluated based on the maturity feature difference value, so as to store the seed information, origin information and actual image of the subject at each verification time node of the monitored subject into the blockchain.

2. The food traceability method based on smart IoT information according to claim 1 is characterized in that: The process of determining whether the monitoring subject meets the continuous verification standard includes: Determine whether the uploading IP is consistent with the origin information; Determining whether the seed category corresponding to the initial subject actual image is consistent with the seed information; If the upload IP is consistent with the origin information and the seed category corresponding to the actual image of the initial subject is consistent with the seed information, it is determined that the monitored subject meets the continuous verification standard; The initial subject actual image is a seed image for the monitored subject.

3. The food traceability method based on smart IoT information according to claim 1 is characterized in that: In response to the determination result for the continuous verification criterion, calling the growth law feature includes, If the monitored subject meets the continuous verification criteria, the corresponding growth law characteristics are called; Among them, the growth law characteristics include the growth height and total growth time of the plant corresponding to the monitoring subject at different time nodes.

4. The food traceability method based on smart IoT information according to claim 1 is characterized in that: The process of predicting the required verification time node based on the growth law characteristics includes: Obtaining the height change rate of the plant corresponding to the monitoring subject in different time periods; If the height change rate in a time period is greater than a predetermined height change rate threshold, the end time of the time period is determined as a verification time node; The length of the time period division is determined based on the total growth time.

5. The food traceability method based on smart IoT information according to claim 1 is characterized in that: The process of calling the subject sample image corresponding to the verification time node for comparison based on the feedback information includes: Determine the subject actual contour in the subject actual image, and determine the subject sample contour in each subject sample image; Determining a mean value of similarity between the image in the actual outline of the subject and the image in each subject sample outline; The average height difference and the average width difference between the actual contour of the subject and each of the sample contours of the subject are determined.

6. The food traceability method based on smart IoT information according to claim 5 is characterized in that: The process of determining whether the growth process of the monitoring subject meets the standard based on the comparison result includes: Compare the similarity mean with a preset similarity threshold, Determine whether the height difference mean is within a predetermined height difference range, and determine whether the width difference mean is within a predetermined width difference range; If the similarity mean is greater than a preset similarity threshold and the height difference mean is within a predetermined height difference range and the width difference mean is within a predetermined width difference range, it is determined that the growth process of the monitored subject meets the standard.

7. The food traceability method based on smart IoT information according to claim 1 is characterized in that: If the growth process of the monitored subject meets the standard, the actual image of the monitored subject at the mature stage is obtained and compared with the called sample image at the mature stage. The comparison process includes: Determine the actual outline of the mature subject in the actual image of the mature stage subject, and determine the sample outline of the mature subject in the sample images of each mature stage; Determine the mean similarity and the mean chromaticity difference between the image in the actual outline of the mature subject and the image in the outline of each mature subject sample; The average height difference and the average width difference between the actual contour of the mature subject and the contours of each of the mature subject samples are determined.

8. The food traceability method based on smart IoT information according to claim 1 is characterized in that: The process of determining the difference value of maturity characteristics includes, Determine the ratio of the similarity threshold to the similarity mean, determine the ratio of the chromaticity difference mean to the standard chromaticity difference threshold, determine the ratio of the height difference mean to the standard height difference threshold, and determine the ratio of the width difference mean to the standard width difference threshold; The obtained ratios are weighted and summed to obtain the maturity characteristic difference value.

9. The food traceability method based on smart IoT information according to claim 1 is characterized in that: The depositability of the monitoring subject is evaluated based on the maturity characteristic difference value, including: If the maturity characteristic difference value is greater than the preset standard maturity characteristic difference value, the depositability does not meet the standard; If the maturity feature difference value is less than or equal to a preset standard maturity feature difference value, the depositability meets the standard.

10. The food traceability method based on smart IoT information according to claim 1 is characterized in that: The verification requirement information includes the required sending time and the required sending content.

Images