A data information traceability method and system for agricultural products

Abstract

This invention relates to the field of data processing technology, specifically to a data information traceability method and system for agricultural products. The method includes: acquiring the quality score of each batch of agricultural products to be traced and determining the differences in quality scores between different batches; acquiring the growth data of the agricultural products to be traced under various key growth conditions and determining the potential influence trend of each extreme point; determining the degree of commonality between different key growth conditions based on the temporal differences between extreme points under different key growth conditions and the differences in the potential influence trend between extreme points under the same key growth conditions; determining the similarity between agricultural products to be traced based on the degree of commonality and the differences in quality scores; classifying different batches of agricultural products to be traced based on similarity, and assigning the same traceability information and data to the blockchain to agricultural products of the same category. This invention improves the representativeness and accuracy of the characteristics of different agricultural products, and improves the representativeness and accuracy of the final cluster.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a data information traceability method and system for agricultural products. Background Technology

[0002] By introducing technologies such as blockchain and smart contracts, problems such as information opacity, data transmission difficulties, and susceptibility to tampering in agricultural product traceability systems can be effectively solved, enabling efficient, accurate, and reliable traceability of the entire agricultural product production process.

[0003] The growth process of crops takes a relatively long time, and the impact of various external factors on crop quality cannot be simply assessed. Furthermore, because crops have different requirements for external conditions, and for any given crop, these conditions need to be kept in a balanced state within a specified range, a surge in a single type of external factor can lead to quality problems or even the death of an entire batch. Simply collecting data on the external conditions of agricultural products and uploading it to the blockchain cannot guarantee the accuracy and reliability of information traceability based on this data. Therefore, it is necessary to consider the short-term changes in various external factors of agricultural products and the overall balance between them, and then process the collected crop data accordingly before uploading it to the blockchain to ensure the accuracy and reliability of the traceability methods and systems.

[0004] Therefore, how to analyze the impact of short-term changes in various external conditions and the overall balance between them on agricultural products, and thus better trace the information of agricultural products, is an issue that the industry urgently needs to address. Summary of the Invention

[0005] To address the technical problem that relying solely on data generated by external conditions is insufficient for accurate information traceability of agricultural products, this invention aims to provide a data information traceability method and system for agricultural products. The specific technical solution adopted is as follows:

[0006] According to a first aspect, embodiments of the present invention provide a data information traceability method for agricultural products, the method comprising:

[0007] Obtain the quality score for each batch of agricultural products to be traced, and determine the differences in quality scores between different batches of the agricultural products to be traced;

[0008] The growth data of the agricultural product to be traced are obtained under various key growth conditions, and the potential impact trend of each extreme point is determined based on the local abnormal data in the growth data; the potential impact trend has a mapping relationship with the quality of agricultural products.

[0009] Based on the temporal differences between extreme points under different key growth conditions and the potential influence trend differences between extreme points under the same key growth conditions, the degree of commonality among different key growth conditions is determined.

[0010] Based on the degree of commonality and the differences in quality scores, the similarity between different batches of the traceable agricultural products is determined;

[0011] Based on the similarity, the agricultural products to be traced are classified into different batches, and the same traceability information is assigned to the agricultural products to be traced in the same category. The agricultural products to be traced with traceability information are then uploaded to the blockchain.

[0012] In conjunction with the first aspect, in the first embodiment of the first aspect, the step of acquiring growth data of the agricultural product to be traced under various key growth conditions, and determining the potential impact trend of each extreme point based on local abnormal data in the growth data, specifically includes:

[0013] The growth data of the agricultural product to be traced under each of the key growth conditions is obtained, the growth data is sorted according to time sequence, and the extreme points in the growth data corresponding to each of the key growth conditions are determined.

[0014] The time interval between adjacent extreme points with the same characteristics is taken as the extreme value time interval, resulting in several extreme value time intervals and the extreme value time intervals corresponding to the extreme points; the same characteristics are that they are both maximum values ​​or both are both minimum values;

[0015] Based on the correspondence between the extreme time period in which the extreme point is located and the suitable range of the corresponding key growth conditions, the potential influence trend of the extreme point is obtained; each phase of the key growth conditions has a corresponding suitable range.

[0016] In conjunction with the first embodiment of the first aspect, in the second embodiment of the first aspect, obtaining the potential influence trend of the extreme point based on the correspondence between the extreme time period in which the extreme point is located and the suitable range of the corresponding key growth conditions specifically includes:

[0017] Determine the extreme time period in which the extreme point is located;

[0018] Obtain a first quantity and a second quantity within the extreme value time period; the first quantity is the total number of data points within the extreme value time period that are lower than the minimum value of the suitable range corresponding to the key growth condition; the second quantity is the total number of data points within the extreme value time period that exceed the maximum value of the suitable range.

[0019] Determine the maximum value within the specified extreme value time period;

[0020] Determine the average amount of data points exceeding the appropriate range;

[0021] Based on the first quantity, the second quantity, the total number of data points within the extreme value time period, the maximum value within the extreme value time period, and the average value of the excess, the potential influence trend of the extreme value point is obtained.

[0022] In conjunction with the first aspect, in the third embodiment of the first aspect, determining the degree of commonality among different key growth conditions based on the temporal differences between extreme points under different key growth conditions and the differences in potential influence trends between extreme points under the same key growth conditions specifically includes:

[0023] Based on the extreme points in the growth data, the temporal differences between two different key growth conditions are obtained, and a difference time period is constructed based on the minimum temporal difference to obtain several difference time periods.

[0024] Obtain the temporal difference between the extreme point of one of the key growth conditions and the extreme point of another key growth condition within each of the difference time periods.

[0025] Based on the temporal differences between the extreme points of the two key growth conditions and the differences in potential influence trends between extreme points under the same key growth conditions, the degree of commonality between the two different key growth conditions is determined.

[0026] In conjunction with the third embodiment of the first aspect, in the fourth embodiment of the first aspect, determining the degree of commonality between the two different key growth conditions based on the temporal differences between the extreme points of the two key growth conditions and the differences in the potential influence trends between extreme points under the same key growth conditions specifically includes:

[0027] The temporal differences between the maximum and minimum points of the current key growth condition and the maximum point of another key growth condition within each difference time period are obtained to obtain the first maximum temporal difference and the first minimum temporal difference.

[0028] Obtain the potential influence trend differences between the maximum points of the key growth conditions described in the current item;

[0029] Based on the temporal differences of the first maximum value, the temporal differences of the first minimum value, and the differences in potential influence trends among the various maximum points in the current key growth conditions, a first degree of commonality among the different key growth conditions is obtained; the first degree of commonality is the degree of commonality among the different key growth conditions with respect to the maximum points.

[0030] The temporal differences between the maximum and minimum points of the current key growth condition and the minimum point of another key growth condition within each difference time period are obtained to obtain the second maximum temporal difference and the second minimum difference.

[0031] Obtain the potential influence trend differences between the minimum points of the key growth conditions described in the current item;

[0032] Based on the temporal differences of the second maximum values, the temporal differences of the second minimum values, and the differences in potential influence trends among the various minimum values ​​in the current key growth conditions, a second degree of commonality among the different key growth conditions is obtained; the second degree of commonality is the degree of commonality among the different key growth conditions with respect to the minimum values.

[0033] Based on the first degree of commonality and the second degree of commonality, the degree of commonality between the two different key growth conditions is obtained.

[0034] In conjunction with the first aspect, in the fifth embodiment of the first aspect, determining the similarity between different batches of the traceable agricultural products based on the degree of commonality and the differences in quality scores specifically includes:

[0035] Based on the degree of commonality, determine the similarity weight of each of the key growth conditions;

[0036] Identify the extreme point where the potential impact trend of each batch of the traceable agricultural products exceeds 0 under the same key growth conditions, and determine the minimum time-series difference and potential impact trend difference between the extreme points where the potential impact trend exceeds 0 of different batches.

[0037] The similarity between different batches of the traceable agricultural products is determined based on the minimum time-series difference in similarity weight, the difference in potential impact trends, and the difference in quality scores.

[0038] In conjunction with the first aspect, in the sixth embodiment of the first aspect, the quality score is obtained by a trained quality evaluation model, which is used to input the key features of the agricultural product to be traced and the scores of the key features and output the quality score of the agricultural product to be traced.

[0039] In conjunction with the first aspect, in the seventh embodiment of the first aspect, the quality evaluation model is obtained by training based on the key features of the sample agricultural products and the scores of the key features using the gradient descent method.

[0040] In conjunction with the sixth embodiment of the first aspect, in the eighth embodiment of the first aspect, the quality assessment model is trained through the following steps:

[0041] Obtain key characteristics of the quality of sample agricultural products;

[0042] Determine the weight of each of the above key features and the score of the sample agricultural products for each key feature;

[0043] The key features, weights, and scores of the sample agricultural products are used as input data and fed into a neural network model. The model is then trained using the gradient descent method to obtain a quality evaluation model for outputting quality scores of agricultural products.

[0044] According to a second aspect, embodiments of the present invention provide a data information traceability system for agricultural products, the system comprising:

[0045] The quality scoring module is used to obtain the quality score of each batch of agricultural products to be traced and to determine the quality score differences between different batches of the agricultural products to be traced.

[0046] The potential impact module is used to acquire growth data of the agricultural product to be traced under various key growth conditions, and determine the potential impact trend of each extreme point based on local abnormal data in the growth data; the potential impact trend has a mapping relationship with the quality of agricultural products;

[0047] The commonality determination module is used to determine the degree of commonality between different key growth conditions based on the temporal differences between extreme points under different key growth conditions and the differences in potential influence trends between extreme points under the same key growth conditions.

[0048] A similarity determination module is used to determine the similarity between different batches of the traceable agricultural products based on the degree of commonality and the differences in quality scores.

[0049] The classification and on-chain module is used to classify different batches of the traceable agricultural products according to the similarity, assign the same traceability information to the traceable agricultural products of the same category, and upload the traceability information of the traceable agricultural products to the blockchain.

[0050] This invention has the following beneficial effects: By determining the potential influence trends of each extreme point in the growth data, and then analyzing the local excess or missing amount of key growth conditions in historical data among the external conditions affecting agricultural product quality, the local abnormal state is judged to obtain the potential influence trend of any extreme point. This avoids the inaccuracy of using historical data from a single time period to judge whether crops are in dynamic equilibrium and the impact on quality, thus improving the representativeness and accuracy of different agricultural products. At the same time, based on the temporal differences between extreme points of the traceable agricultural products under different key growth conditions and the differences in the potential influence trends between extreme points under the same key growth conditions, the degree of commonality between different key growth conditions is determined. By comparing the consistency of changes in different key growth conditions in historical data, the commonality of data changes in key growth conditions is obtained. This avoids the weakening of the impact of short-term anomalies in historical data caused by the long growth time span of crops, resulting in smaller differences in the specific distinctions between different batches of final agricultural products, thus improving the representativeness and accuracy of the final classification and ensuring the accuracy and reliability of the traceability method and system. Attached Figure Description

[0051] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating a data information traceability method for agricultural products provided in an embodiment of the present invention.

[0053] Figure 2 This is a flowchart illustrating step S20 of a data information traceability method for agricultural products provided in an embodiment of the present invention.

[0054] Figure 3 This is a flowchart illustrating step S23 of a data information traceability method for agricultural products provided in an embodiment of the present invention.

[0055] Figure 4 This is a flowchart illustrating step S30 of a data information traceability method for agricultural products provided in an embodiment of the present invention.

[0056] Figure 5 This is a flowchart illustrating step S40 of a data information traceability method for agricultural products provided in an embodiment of the present invention.

[0057] Figure 6This is a schematic diagram of the structure of a data information traceability system for agricultural products provided in an embodiment of the present invention. Detailed Implementation

[0058] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a data information traceability method and system for agricultural products proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0060] By introducing technologies such as blockchain and smart contracts, problems such as information opacity, data transmission difficulties, and susceptibility to tampering in agricultural product traceability systems can be effectively solved, enabling efficient, accurate, and reliable traceability of the entire agricultural production process. Specifically, technologies such as the Internet of Things (IoT) can be used to acquire various data on the agricultural product's growth environment and production process, as well as relevant indicators. After preprocessing this data, it is uploaded to the blockchain network via communication protocols. Smart contracts are then used to verify the data on the blockchain network, ensuring the accuracy of data transmission. Finally, data from the production process is recorded on the blockchain to guarantee the accuracy and reliability of the traceability method and system.

[0061] However, the growth process of crops takes a relatively long time, and the impact of various external factors on crop quality cannot be simply assessed. Furthermore, because crops have different requirements for external conditions, and for any given crop, these conditions need to be kept in a balanced state within a specified range, a surge in a single type of external factor can lead to quality problems or even the death of an entire batch. If data on agricultural products is simply collected and uploaded to the blockchain based on the various data generated by external conditions, the accuracy and reliability of information traceability based on this data cannot be guaranteed.

[0062] Correspondingly, the data information for agricultural products covers various key data from production to sales. This key data is crucial for ensuring the quality, safety, and traceability of agricultural products. Furthermore, because agricultural products are grown in different regions, the actual environmental requirements and human intervention needs (such as fertilizer type and weight) vary. Agricultural products produced under different external conditions exhibit certain differences in quality. Subsequent processing follows relatively standardized procedures. Therefore, the final quality of agricultural products appearing on the market is closely related to their historical growth conditions. Thus, data traceability can be implemented for various key growth conditions throughout the historical production process of different agricultural products.

[0063] Therefore, how to analyze the impact of short-term changes in various external conditions and the overall balance between them on agricultural products, and thus better trace the information of agricultural products, is an issue that the industry urgently needs to address.

[0064] To address the aforementioned problems, this specification provides a data information traceability method and system for agricultural products. The specific solution of the data information traceability method and system for agricultural products provided by this invention will be described in detail below with reference to the accompanying drawings.

[0065] Please see Figure 1 The diagram illustrates a flowchart of a data information traceability method for agricultural products provided by an embodiment of the present invention, which may include:

[0066] S10. Obtain the quality score for each batch of agricultural products to be traced, and determine the differences in quality scores between different batches of agricultural products to be traced.

[0067] In this embodiment, the quality score is obtained by a trained quality evaluation model. That is, a trained quality evaluation model is used to train a classification network for the actual quality of the corresponding batch of agricultural products in each region, and outputs the quality score value of the batch of agricultural products. The quality evaluation model is a known neural network model for classification. There are no restrictions on the specific form of the neural network model, as long as the quality score value of the agricultural products can be obtained.

[0068] In this embodiment, agricultural products corresponding to a planting area are harvested in batches. The key production conditions of each preset collection interval within the historical period between the sowing of agricultural products in the planting area and the batch harvest are obtained and stored to form offline historical data for convenient subsequent operations.

[0069] Specifically, data is collected on key production conditions of agricultural products over a historical period to provide data support for subsequent quality evaluation. The preset collection interval refers to the time period for data collection, which can be 1 hour, 6 hours, 24 hours, a week, etc., without limitation. In addition, data can also be collected on agricultural products under different conditions, such as the germination period and maturity period, to determine the key production conditions under various circumstances, thereby providing better and more accurate quality evaluation.

[0070] In this embodiment, the key production conditions mentioned above include at least the following multidimensional data: total sunlight, temperature, precipitation, soil pH, and nutrient content.

[0071] This method involves conducting preliminary quality tests on agricultural products before processing and pre-assessing the actual quality of each batch of agricultural products from each region. It should be noted that, considering the large quantity of agricultural products in a single batch, to avoid the impact of a single case on the entire batch, a quality screening and assessment is performed on a sample of all agricultural products in a batch. For example, 20% of the total number of agricultural products in a single batch is selected as a sample, and then the sample is subjected to quality testing. The actual quality of the sample is then used as the actual quality of the entire batch.

[0072] Preferably, the training process of this quality assessment model is as follows:

[0073] A10. Obtain key features that affect the quality of sample agricultural products in a single batch of agricultural products. In this embodiment, the key features mentioned above are the features of interest that affect agricultural products. Key features may include at least the color, size, integrity, taste and other multi-dimensional data of the agricultural products.

[0074] A20. Determine the weight of each of the above key features and the score of the sample agricultural product on each key feature. It can be understood that the higher the score of the sample agricultural product on a certain key feature, the higher (more) the feature information of the sample agricultural product on that key feature.

[0075] In this embodiment, the scores of the sample agricultural products on each key characteristic can be determined by industry experts, consumers, or a combination of assessments from industry experts, consumers, and other groups.

[0076] A30. The key features, weights, and scores of the sample agricultural products are used as input data and fed into a neural network model. Gradient descent is then used for training to obtain a quality assessment model that outputs a quality score for the agricultural products. This model combines the scores of the sample agricultural products on all key features with the weights of each feature to output a quality score. The quality score ranges from 0 to 1. A higher quality score indicates a higher quality sample agricultural product, i.e., a higher batch of agricultural products, meaning a better quality product obtained after a long growth process.

[0077] Taking a five-layer fully connected neural network model as an example, with the cross-entropy function as the loss function, the training ratio in the historical data is set to 7:3. The neural network model is trained by selecting connection data and using gradient descent until the loss function converges.

[0078] By inputting the key features and scores of each batch of traceable agricultural products into the quality evaluation model, the quality score of the corresponding batch of traceable agricultural products and the quality score differences between different batches of the traceable agricultural products can be obtained.

[0079] S20. Obtain growth data of the agricultural products to be traced under various key growth conditions, and determine the potential impact trend of each extreme point in the growth data. The potential impact trend has a mapping relationship with the quality of agricultural products. More specifically, the larger the potential impact trend, the greater the impact on the quality of agricultural products, and vice versa.

[0080] Because any single critical growth condition has a near-positive promoting effect on crop growth and quality when all critical growth conditions are within a reasonable range and in a relative dynamic equilibrium, this promoting effect has a relatively small impact on the quality of agricultural products obtained from agricultural products within a single time period, such as a day. Therefore, using a single time period, such as a day, to judge whether agricultural products are in dynamic equilibrium and whether they have a positive or negative impact on quality is relatively one-sided. Analysis shows that the impact of a single critical data point on crops reflects how much the actual monitored data for that condition exceeds the range (upper or lower limit) corresponding to the crop's growth requirements, and the duration of this situation. For example, regarding rainfall, if a heavy rainstorm occurs in a short period, although it exceeds the standard range required by crops, its short duration means that its impact on the quality of agricultural products is relatively small.

[0081] In step S20, the potential impact trend is obtained by analyzing local abnormal data (including local excess and missing amounts) to determine its local abnormal state. This avoids the inaccuracy of using relevant data from a single time period to determine whether agricultural products are in dynamic equilibrium and the impact on quality, and improves the representativeness and accuracy of the characteristics of different agricultural products.

[0082] S30. Based on the temporal differences between extreme points under different critical growth conditions and the potential impact trend differences between extreme points under the same critical growth conditions, determine the degree of commonality among different critical growth conditions.

[0083] In this embodiment, considering that the actual production quality of crops depends on the combined influence of multiple key growth conditions, the so-called dynamic equilibrium—that is, an increase in one key growth condition within a certain period of time—is theoretically accompanied by an increase in other strongly correlated key growth conditions (i.e., external factors), thus reducing its impact on crops. Since there are inherent interrelationships among some key growth conditions, such as a negative correlation between precipitation and temperature, a negative correlation between precipitation and sunlight, and random fluctuations in soil pH and precipitation, the degree of commonality between any two key growth conditions is first determined. This avoids weakening the influence of short-term anomalies in historical data caused by the long growth period of agricultural products, resulting in smaller differences between different batches of final agricultural products and improving the representativeness and accuracy of the final clusters.

[0084] S40. Determine the similarity between different batches of agricultural products to be traced based on the degree of commonality and differences in quality scores.

[0085] For any batch of agricultural products, the higher the commonality (value) between a certain key growth condition and other key production conditions, the lower its own influence trend. This indicates that the actual numerical fluctuations caused by the current key growth conditions have a smaller impact on the quality of agricultural products. Therefore, different batches of agricultural products can be clustered based on features such as potential influence trends and common values, so that the same traceability information, such as traceability codes, can be assigned to agricultural products of the same category.

[0086] S50. Classify different batches of agricultural products to be traced based on similarity, assign the same traceability information to agricultural products of the same category, and upload the data of agricultural products with traceability information to the blockchain.

[0087] For example, based on the k-means clustering algorithm, the elbow method is used to obtain the optimal k, and agricultural product batches are clustered using the above method. Unsupervised learning clustering operation is performed, and the data is divided into multiple clusters based on the similarity within the data, so that the similarity within the cluster is as large as possible, while the similarity between clusters is as small as possible. For agricultural products in the same cluster calculated above, quality score-related information is assigned to agricultural products in different clusters based on the mean of the quality score, and traceability information such as traceability code is assigned to agricultural products in the same cluster, and the information is uploaded to the blockchain.

[0088] The present invention provides a data information traceability method for agricultural products. By determining the potential influence trends of each extreme point in the growth data, it analyzes the local excess or deficiency of key growth conditions in historical data among the external conditions affecting agricultural product quality, judges their local abnormal states, and obtains the potential influence trend of any extreme point. This avoids the inaccuracy of using historical data from a single time period to determine whether crops are in dynamic equilibrium and their impact on quality, thus improving the representativeness and accuracy of different agricultural products. Furthermore, based on the temporal differences between extreme points under different key growth conditions and the differences in potential influence trends between extreme points under the same key growth conditions, the method determines the degree of commonality among different key growth conditions. By comparing the consistency of changes in different key growth conditions in historical data, it obtains the commonality of data changes in key growth conditions. This avoids the weakening of the impact of short-term anomalies in historical data caused by long crop growth periods, resulting in smaller differences between different batches of final agricultural products, thus improving the representativeness and accuracy of the final classification and ensuring the accuracy and reliability of the traceability method and system.

[0089] Please see Figure 2 Step S20 specifically includes:

[0090] S21. Obtain the growth data of the agricultural products to be traced under each key growth condition, sort the growth data according to time sequence, and determine the extreme points in the growth data corresponding to each key growth condition.

[0091] For any key data point, it is first arranged chronologically on the coordinate axis using relevant historical data. Then, based on prior knowledge about the theoretically most suitable range of production environment conditions for any crop and any key data point, this theoretically most suitable range of production environment conditions can be used as the ideal adaptation range for the current key data point.

[0092] S22. Take the time interval between adjacent extreme points with the same characteristics as the extreme value time interval, and obtain several extreme value time intervals and the extreme value time intervals corresponding to the extreme points. The same characteristics are that they are both maximum values ​​or both are both minimum values.

[0093] At this point, for the key growth conditions data collected in history, the difference between the maximum and minimum values ​​of the data and the adaptive range is obtained at any given time. The maximum and minimum values ​​are then used as the subtrahend and minuend, respectively, so that the data within the range are always negative and the values ​​outside the range are positive. Thus, two differences can be obtained for the data at any given time.

[0094] Next, for any key growth condition, obtain all extreme points (maximum and minimum values) from its collected historical data. Define any pair of adjacent maxima or adjacent pair of minimums as an extreme value time interval, where each extreme value time interval represents the prominence of the corresponding minimum or maximum value. Obtain the length N of each extreme value time interval. i , where i represents the local extreme time period corresponding to the i-th extreme point (maximum or minimum).

[0095] S23. Based on the correspondence between the extreme time period in which the extreme point is located and the suitable range of the corresponding key growth conditions, the potential influence trend of the extreme point is obtained, where each key growth condition has a corresponding suitable range.

[0096] Please see Figure 3 Taking the time interval between a pair of adjacent minimum values ​​as an example, step S23 specifically includes:

[0097] S231. Determine the extreme time period in which the extreme point is located.

[0098] S232. Obtain the first quantity and the second quantity within the extreme value time period, wherein the first quantity is the total number of data points within the extreme value time period that are lower than the minimum value of the suitable range corresponding to the key growth conditions, and the second quantity is the total number of data points within the extreme value time period that exceed the maximum value of the suitable range.

[0099] Because the extreme value time interval N between the two minima i There may be data points within the range that are below the minimum value of the appropriate range. The time period N for obtaining this extreme value is determined. i The total number M of data points below the minimum value of the suitable range min That is, the first quantity, and simultaneously obtaining the time period N of the extreme value. i The total number M of data points exceeding the maximum value within the appropriate range max That is, the second quantity.

[0100] S233. Determine the time period N of this extreme value. i The maximum value ΔT t max .

[0101] S234. Determine the time period N of this extreme value. iThe mean of the number of data points exceeding the appropriate range

[0102] S235. Based on the first quantity, the second quantity, the total number of data points within the extreme value time period, the maximum value within the extreme value time period, and the average value of the excess quantity, the potential influence trend of the extreme value point is obtained.

[0103] Therefore, the potential impact trend of the key growth conditions on the current type of agricultural products can be obtained.

[0104]

[0105] Among them, P i Indicates the potential impact trend; M min N represents the time period of extreme values. i The total number of data points below the minimum value of the suitable range; M max N represents the time period of extreme values. i The total number of data points exceeding the maximum value within the appropriate range; N i N represents the time period of extreme values. i The total number of internal data points, i.e., N i -M min N represents the time period of extreme values. i The total number of data points within the range, excluding those exceeding the minimum range; N represents the time period of extreme values. i The maximum value; N represents the time period of extreme values. i The average amount of data points exceeding the appropriate range; This represents the extreme value time period N. i The percentage of data points exceeding the maximum range indicates the duration and potential impact of the negative influence on the current critical growth conditions. A larger percentage suggests a longer period of negative impact and a stronger trend. Furthermore, the larger the mean and maximum values ​​of these data points exceeding the maximum range, the greater the extent of the exceedance and the stronger the influence. Therefore, multiplying these two factors yields P. i The larger this value, the greater its influence on the trend.

[0106] It should be noted that the calculation principle for the potential impact trend of the minimum point is the same as described above. For data points within the normal range, since M... max The value is 0, therefore the potential impact trend is 0.

[0107] By iterating through all the maximum and minimum values ​​of a certain key growth condition, each extreme value or the extreme time period corresponding to the extreme value can correspond to a potential influence trend. After the above processing, we can obtain every extreme value corresponding to any batch of agricultural products, and at the same time, we can also obtain the potential influence trend of these extreme values.

[0108] Please see Figure 4 Step S30 specifically includes:

[0109] S31. Based on the extreme points in the growth data, obtain the temporal differences between two different key growth conditions, and construct a difference time period based on the minimum temporal difference to obtain several difference time periods.

[0110] For each critical growth condition, several time intervals between the maximum and minimum values ​​can be obtained. At this time, for any extreme point of any critical growth condition, other critical growth conditions have temporal differences (values) with this extreme point, and the extreme point with the smallest temporal difference between other critical growth conditions and this extreme point can also be obtained.

[0111] A new time period, or difference time period, is constructed by finding the extreme point of the current critical growth conditions and other external conditions that minimize the temporal difference.

[0112] S32. Obtain the temporal difference between the extreme point of one of the key growth conditions and the extreme point of the other key growth condition within each difference time period.

[0113] S33. Based on the temporal differences between the extreme points of the two key growth conditions and the differences in the potential influence trends between the extreme points under the same key growth conditions, determine the degree of commonality between the two different key growth conditions.

[0114] More specifically, step S33 includes:

[0115] S331. Traverse all the maximum points of the current critical growth condition, and obtain the maximum and minimum points of another critical growth condition within different time intervals corresponding to each maximum point. Then, calculate the difference in the numerical change of the temporal difference between the maximum and minimum points of the other critical growth condition and the maximum point of the current critical growth condition, and obtain Δt. i,max and Δt i,min , where Δt i,max The time series difference of the first maximum is represented by Δt. i,min This indicates the time series difference of the first minimum value.

[0116] S332. Obtain the potential influence trend differences between the maximum points of the current key growth conditions.

[0117] S333. Based on the temporal differences of the first maximum, the temporal differences of the first minimum and maximum, and the differences in potential influence trends among the various maximum points in the current key growth conditions, the first commonality degree among different key growth conditions is obtained. The first commonality degree is the degree of commonality among different key growth conditions regarding the maximum points:

[0118]

[0119] Among them, E x m ,y ax This represents the degree of commonality between the current critical growth condition x and another critical growth condition y regarding their maximum points, i.e., the first degree of commonality; n x,max Δt represents the total number of maxima in the current critical growth condition x; i,max Δt represents the numerical change in the temporal difference between the first maximum (i.e., the maximum point of another critical growth condition y) and the maximum point of the current critical growth condition x. i,min Δt represents the numerical change in the temporal difference between the first minimum (i.e., the minimum point of another critical growth condition y) and the maximum point of the current critical growth condition x. i,max -Δt j,max Δt i,min -Δt j,min The smaller the value, the more similar the patterns of numerical changes between the maxima of the two key growth conditions. Using the Euclidean norm, we can obtain... P i P represents the potential influence trend difference of the maximum point i of the critical growth condition x. j This represents the potential influence trend difference of the maximum point j of the critical growth condition x, |P i -P j | represents the potential influence trend difference between the maximum points i and j of any current key growth condition x. The smaller this value, the higher the similarity between the key growth conditions. The more similar the numerical change patterns calculated above are, the greater the reference weight for judging common features, and the more weight is applied to the maximum regularity of the latter.

[0120] By iterating through and summing all the maximum points, we can obtain... The smaller the value, the greater the commonality between the current critical growth conditions and other critical growth conditions.

[0121] S334. Traverse all minimum points of the current key growth condition, and obtain the temporal difference between the maximum and minimum points of the current key growth condition and the minimum point of another key growth condition within each difference time period, to obtain the second maximum temporal difference and the second minimum difference.

[0122] S335. Obtain the potential influence trend differences between the minimum points of the key growth conditions described in the current item.

[0123] S336. Based on the temporal differences of the second maximum value, the temporal differences of the second minimum value, and the differences in potential influence trends of each minimum point in the current key growth conditions, the second commonality degree among different key growth conditions is obtained; the second commonality degree is the degree of commonality among different key growth conditions regarding the minimum point.

[0124] Similarly, for the minimum point, we can obtain... This indicates the degree of commonality between the current critical growth condition x and another critical growth condition y regarding their minimum points. The calculation process will not be elaborated here.

[0125] S337. Based on the first and second commonality levels, the degree of commonality between the two different key growth conditions is obtained. Then, for any two key growth conditions, the actual commonality value between them can be obtained:

[0126]

[0127] Among them, E x,y This represents the common value between the current critical growth condition x and another critical growth condition y.

[0128] By traversing all the key growth conditions, we can obtain the corresponding common values. The larger the common value, the more regular the changes of any two key growth conditions in historical data are, which also indicates that the current batch of agricultural products is more in line with the actual growth needs of crops.

[0129] Please see Figure 5 Step S40 specifically includes:

[0130] S41. Determine the similarity weight of each key growth condition based on the degree of commonality.

[0131] For any batch of agricultural products, the higher the common value between a certain key growth condition and other key production conditions, the lower its own influence trend is. This indicates that the actual numerical fluctuations caused by the current key growth conditions have a smaller impact on the quality of agricultural products. Therefore, different batches of agricultural products can be clustered based on features such as potential influence trends and common values, so that agricultural products of the same category can be assigned the same traceability information, such as traceability codes.

[0132] In this embodiment, the similarity weights of common values ​​of key growth conditions will also be determined:

[0133]

[0134] Where, μ x E represents the similarity weight of the key growth condition x; x,y This represents the common value between the current critical growth condition x and another critical growth condition y; n x,max This represents the total number of data points for the current critical growth condition x.

[0135] S42. Determine the extreme point where the potential influence trend of each batch of traceable agricultural products exceeds 0 under the same critical growth conditions, and determine the minimum time series difference and potential influence trend difference between extreme points where the potential influence trend exceeds 0 of different batches.

[0136] S43. Determine the similarity between different batches of agricultural products to be traced based on the minimum time-series difference in similarity weight, the difference in potential impact trends, and the difference in quality scores.

[0137] Therefore, by representing the historical external condition data changes of the current batch of agricultural products as curves, for all batches of agricultural products, by comparing the minimum temporal difference between the extreme points of the potential influence trend greater than 0 in the curves of the same external condition data and the extreme points of other batches of agricultural products, the above data points of different batches are compared one by one. Thus, for any two batches of agricultural products with the same external growth conditions, G can be obtained. x Each data point corresponds to a combination, and the minimum time series difference Δd is recorded. r The difference ΔP between the potential impact trend and the trend r Simultaneously, the commonalities (values) and differences among individuals under the same key growth conditions, as well as the differences in quality scores ΔQ during the final quality inspection process, were obtained. a,b .

[0138] This leads to the following similarity between any two different batches of agricultural product data:

[0139]

[0140] Where f represents the similarity between a certain agricultural product in batches a and b; ΔQ a,b This represents the difference in quality scores of a certain agricultural product between batch a and batch b; μ a,x μ represents the similarity weight of a certain agricultural product in batch a under the critical growth condition x; b,x G represents the similarity weight of a certain agricultural product in batch b under the critical growth condition x; x This represents the corresponding combination of data for a certain agricultural product in batches a and b; Δd r ΔP represents the minimum temporal difference between data of a certain agricultural product in batches a and b; rThis represents the difference in the potential influence trend between extreme points of a certain agricultural product data set in batches a and b. For a certain agricultural product in batches a and b, which contains a total of m key growth conditions, for the same key growth condition x, the minimum time-series difference Δd between the data points (extreme points) with a potential influence trend greater than 0 in the two batches of agricultural products and the data points in other batches is considered. r The smaller the value, the greater the potential difference ΔP between the two data points in terms of their trends. r The smaller the value, the more likely it is to iterate through all data points with a potential influence trend greater than 0, and obtain... The smaller the value, the more similar the variation characteristics of the two batches under the current critical growth condition x.

[0141] Furthermore, for any key growth condition, the smaller the difference in common values ​​between two batches of agricultural products, the lower the specificity of the change caused by the condition itself, the higher the overall similarity between the two key growth conditions, and the greater the similarity discrimination weight of the current key growth condition. By traversing m key growth conditions and combining the differences in quality scores, the similarity f between a certain agricultural product of batch a and batch b is obtained. The greater the similarity, the more similar the changes in external conditions between these two batches of agricultural products.

[0142] The following describes the data information traceability system for agricultural products provided by the embodiments of the present invention. The data information traceability system for agricultural products described below can be referred to in correspondence with the data information traceability method for agricultural products described above.

[0143] Please see Figure 6 The diagram illustrates the structure of a data information traceability system for agricultural products according to an embodiment of the present invention. This system may include:

[0144] The quality scoring module 10 is used to obtain the quality score of each batch of agricultural products to be traced and to determine the quality score differences between different batches of agricultural products to be traced.

[0145] In this embodiment, the quality score is obtained by a trained quality evaluation model. That is, a trained quality evaluation model is used to train a classification network for the actual quality of the corresponding batch of agricultural products in each region, and outputs the quality score value of the batch of agricultural products. The quality evaluation model is a known neural network model for classification. There are no restrictions on the specific form of the neural network model, as long as the quality score value of the agricultural products can be obtained.

[0146] In this embodiment, agricultural products corresponding to a planting area are harvested in batches. The key production conditions of each preset collection interval within the historical period between the sowing of agricultural products in the planting area and the batch harvest are obtained and stored to form offline historical data for convenient subsequent operations.

[0147] Specifically, data is collected on key production conditions of agricultural products over a historical period to provide data support for subsequent quality evaluation. The preset collection interval refers to the time period for data collection, which can be 1 hour, 6 hours, 24 hours, a week, etc., without limitation. In addition, data can also be collected on agricultural products under different conditions, such as the germination period and maturity period, to determine the key production conditions under various circumstances, thereby providing better and more accurate quality evaluation.

[0148] In this embodiment, the key production conditions mentioned above include at least the following multidimensional data: total sunlight, temperature, precipitation, soil pH, and nutrient content.

[0149] Before processing agricultural products, this system conducts preliminary quality testing and pre-assesses the actual quality of each batch of agricultural products from each region. It should be noted that, considering the large quantity of agricultural products in a single batch, to avoid the impact of a single case on the entire batch, a quality screening and assessment is performed on a sample of all agricultural products in a batch. For example, 20% of the total number of agricultural products in a single batch is selected as a sample, and then the sample is tested for quality. The actual quality of the sample is then used as the actual quality of the entire batch.

[0150] By inputting the key features and scores of each batch of traceable agricultural products into the quality evaluation model, the quality score of the corresponding batch of traceable agricultural products and the quality score differences between different batches of the traceable agricultural products can be obtained.

[0151] The potential impact module 20 is used to acquire growth data of the agricultural products to be traced under various key growth conditions and determine the potential impact trend of each extreme point in the growth data. The potential impact trend has a mapping relationship with the quality of agricultural products. More specifically, the larger the potential impact trend, the greater the impact on the quality of agricultural products, and vice versa.

[0152] Because any single critical growth condition has a near-positive promoting effect on crop growth and quality when all critical growth conditions are within a reasonable range and in a relative dynamic equilibrium, this promoting effect has a relatively small impact on the quality of agricultural products obtained from agricultural products within a single time period, such as a day. Therefore, using a single time period, such as a day, to judge whether agricultural products are in dynamic equilibrium and whether they have a positive or negative impact on quality is relatively one-sided. Analysis shows that the impact of a single critical data point on crops reflects how much the actual monitored data for that condition exceeds the range (upper or lower limit) corresponding to the crop's growth requirements, and the duration of this situation. For example, regarding rainfall, if a heavy rainstorm occurs in a short period, although it exceeds the standard range required by crops, its short duration means that its impact on the quality of agricultural products is relatively small.

[0153] Among them, the potential impact trend is obtained by analyzing local abnormal data (including local excess and missing data) to determine its local abnormal state. This can avoid the inaccuracy of using relevant data in a single time period to judge whether agricultural products are in dynamic equilibrium and the impact on quality, and improve the representativeness and accuracy of the characteristics of different agricultural products.

[0154] The commonality determination module 30 is used to determine the degree of commonality among different key growth conditions based on the temporal differences between extreme points under different key growth conditions and the differences in potential impact trends between extreme points under the same key growth conditions.

[0155] In this embodiment, considering that the actual production quality of crops depends on the combined influence of multiple key growth conditions, the so-called dynamic equilibrium—that is, an increase in one key growth condition within a certain period of time—is theoretically accompanied by an increase in other strongly correlated key growth conditions (i.e., external factors), thus reducing its impact on crops. Since there are inherent interrelationships among some key growth conditions, such as a negative correlation between precipitation and temperature, a negative correlation between precipitation and sunlight, and random fluctuations in soil pH and precipitation, the degree of commonality between any two key growth conditions is first determined. This avoids weakening the influence of short-term anomalies in historical data caused by the long growth period of agricultural products, resulting in smaller differences between different batches of final agricultural products and improving the representativeness and accuracy of the final clusters.

[0156] The similarity determination module 40 is used to determine the similarity between different batches of traceable agricultural products based on the degree of commonality and differences in quality scores.

[0157] For any batch of agricultural products, the higher the common value between a certain key growth condition and other key production conditions, the lower its own influence trend is. This indicates that the actual numerical fluctuations caused by the current key growth conditions have a smaller impact on the quality of agricultural products. Therefore, different batches of agricultural products can be clustered based on features such as potential influence trends and common values, so that agricultural products of the same category can be assigned the same traceability information, such as traceability codes.

[0158] The classification and on-chain module 50 is used to classify different batches of traceable agricultural products based on similarity and to upload the data of traceable agricultural products of the same category to the blockchain.

[0159] For example, based on the k-means clustering algorithm, the elbow method is used to obtain the optimal k, and agricultural product batches are clustered using the above method. Unsupervised learning clustering operation is performed, and the data is divided into multiple clusters based on the similarity within the data, so that the similarity within the cluster is as large as possible, while the similarity between clusters is as small as possible. For agricultural products in the same cluster calculated above, quality score-related information is assigned to agricultural products in different clusters based on the mean of the quality score, and traceability information such as traceability code is assigned to agricultural products in the same cluster, and the information is uploaded to the blockchain.

[0160] The present invention provides a data information traceability system for agricultural products. By determining the potential impact trends of each extreme point in the growth data, it analyzes the local excesses or omissions of key growth conditions in historical data that affect the quality of agricultural products, and judges their local anomalies to obtain the potential impact trends of any extreme point. This avoids the inaccuracy of using historical data from a single time period to determine whether crops are in dynamic equilibrium and their impact on quality, thus improving the representativeness and accuracy of different agricultural products. Furthermore, based on the temporal differences between extreme points under different key growth conditions and the differences in potential impact trends between extreme points under the same key growth conditions, the system determines the degree of commonality among different key growth conditions. By comparing the consistency of changes in different key growth conditions in historical data, it obtains the commonalities in the data changes of key growth conditions. This avoids the weakening of the impact of short-term anomalies in historical data caused by long crop growth periods, which would result in smaller differences between different batches of final agricultural products. This improves the representativeness and accuracy of the final classification, ensuring the accuracy and reliability of the traceability method and system.

[0161] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0162] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A data information traceability method for agricultural products, characterized by, The method comprises: obtaining the quality score of each batch of agricultural products to be traced, and determining the quality score difference between different batches of the agricultural products to be traced; obtaining the growth data of the agricultural products to be traced under each key growth condition, and determining the potential influence trend of each extreme point according to the local abnormal data in the growth data; the potential influence trend has a mapping relationship with the quality of agricultural products; determining the commonality degree between different key growth conditions according to the time sequence difference between extreme points under different key growth conditions and the potential influence trend difference between extreme points under the same key growth condition; determining the similarity between different batches of the agricultural products to be traced according to the commonality degree and the quality score difference; classifying different batches of the agricultural products to be traced according to the similarity, assigning the same traceability information to the agricultural products to be traced in the same category, and performing data chaining on the agricultural products to be traced with traceability information; the obtaining of the growth data of the agricultural products to be traced under each key growth condition, and the determination of the potential influence trend of each extreme point according to the local abnormal data in the growth data, specifically comprises: obtaining the growth data of the agricultural products to be traced under each key growth condition, sorting the growth data in time sequence, and determining the extreme points in the growth data corresponding to each key growth condition; the time period between adjacent extreme points with the same characteristics is taken as the extreme time period, and a plurality of extreme time periods and the extreme time periods corresponding to the extreme points are obtained; the same characteristics are both maximum or both minimum; obtaining the potential influence trend of the extreme point according to the corresponding relationship between the extreme time period where the extreme point is located and the suitable range of the corresponding key growth condition; each key growth condition has a corresponding suitable range; determining the commonality degree between different key growth conditions according to the time sequence difference between extreme points under different key growth conditions and the potential influence trend difference between extreme points under the same key growth condition, specifically comprising: obtaining the time sequence difference between different two key growth conditions according to the extreme points in the growth data, and constructing a difference time period according to the minimum time sequence difference, to obtain a plurality of difference time periods; obtaining the time sequence difference between the extreme points of one key growth condition in each difference time period and the extreme points of another key growth condition; determining the commonality degree between the different two key growth conditions according to the time sequence difference between the extreme points of the two key growth conditions and the potential influence trend difference between the extreme points under the same key growth condition.

2. The data information traceability method for agricultural products according to claim 1, characterized in that, determining the potential influence trend of the extreme point according to the corresponding relationship between the extreme time period where the extreme point is located and the suitable range of the corresponding key growth condition, specifically comprising: determining the extreme time period where the extreme point is located; obtaining a first number and a second number in the extreme time period; the first number is the total number of data points lower than the minimum value of the suitable range corresponding to the critical growth condition in the extreme time period; the second number is the total number of data points higher than the maximum value of the suitable range in the extreme time period; determining the maximum value of the extreme time period; determining the average of the exceeding amount of data points exceeding the suitable range; obtaining the potential impact trend of the extreme point according to the first number, the second number, the total number of data points in the extreme time period, the maximum value of the extreme time period, and the average of the exceeding amount.

3. The data information traceability method for agricultural products as claimed in claim 1 wherein, According to the time difference between the extreme points of the two different critical growth conditions and the potential impact trend difference between the extreme points of the same critical growth condition, the commonality degree between the two different critical growth conditions is determined, which specifically includes: obtaining the time difference between the maximum point and the minimum point of the current critical growth condition and the maximum point of the other critical growth condition in each difference time period to obtain the first maximum time difference and the first minimum time difference; obtaining the potential impact trend difference between each maximum point of the current critical growth condition; obtaining the first commonality degree between different critical growth conditions according to the first maximum time difference, the first minimum time difference and the potential impact trend difference of each maximum point of the current critical growth condition; the first commonality degree is the commonality degree between different critical growth conditions about the maximum points; obtaining the time difference between the maximum point and the minimum point of the current critical growth condition and the minimum point of the other critical growth condition in each difference time period to obtain the second maximum time difference and the second minimum time difference; obtaining the potential impact trend difference between each minimum point of the current critical growth condition; obtaining the second commonality degree between different critical growth conditions according to the second maximum time difference, the second minimum time difference and the potential impact trend difference of each minimum point of the current critical growth condition; the second commonality degree is the commonality degree between different critical growth conditions about the minimum points; obtaining the commonality degree between the two different critical growth conditions based on the first commonality degree and the second commonality degree.

4. The data information traceability method for agricultural products as claimed in claim 1, wherein, According to the commonality degree and the quality score difference, the similarity between different batches of the traceable agricultural products is determined, which specifically includes: determining the similarity weight of each critical growth condition according to the commonality degree; determining the extreme point of the potential impact trend exceeding 0 of the traceable agricultural products in the same critical growth condition of each batch, and determining the minimum time difference and the potential impact trend difference between the extreme points of the potential impact trend exceeding 0 of different batches; determining the similarity between different batches of the traceable agricultural products according to the minimum time difference, the potential impact trend difference and the quality score difference.

5. The data information traceability method for agricultural products as claimed in claim 1 wherein, The quality score is obtained by a trained quality evaluation model, the quality evaluation model is used for inputting the key features of the to-be-traced agricultural products and the scores of the key features and outputting the quality score of the to-be-traced agricultural products.

6. The data information traceability method for agricultural products as claimed in claim 5, wherein, The quality evaluation model is obtained by training based on the key features of sample agricultural products and the scores of the key features and by using a gradient descent method.

7. The data information traceability method for agricultural products as claimed in claim 5 wherein, The quality evaluation model is obtained by the following steps: obtaining the key features of the quality of sample agricultural products; determining the weight of each key feature and determining the score of each key feature of the sample agricultural products; inputting the key features of the sample agricultural products, the weight of the key features and the score of the key features into a neural network model and training by using a gradient descent method to obtain a quality evaluation model used for outputting the quality score of agricultural products.

8. A data information traceability system for agricultural products, characterized by, The system comprises: a quality score module, configured to obtain the quality score of each batch of to-be-traced agricultural products and determine the quality score difference between different batches of the to-be-traced agricultural products; a potential influence module, configured to obtain the growth data of the to-be-traced agricultural products under each key growth condition and determine the potential influence trend of each extreme point according to the local abnormal data in the growth data; the potential influence trend has a mapping relationship with the quality of agricultural products; a commonality determination module, configured to determine the commonality degree between different key growth conditions according to the time sequence difference between extreme points under different key growth conditions and the potential influence trend difference between extreme points under the same key growth condition; a similarity determination module, configured to determine the similarity between different batches of the to-be-traced agricultural products according to the commonality degree and the quality score difference; a classification and chain module, configured to classify different batches of the to-be-traced agricultural products according to the similarity, assign the same traceability information to the to-be-traced agricultural products of the same category, and perform data chaining on the to-be-traced agricultural products with traceability information; the obtaining of the growth data of the to-be-traced agricultural products under each key growth condition and the determination of the potential influence trend of each extreme point according to the local abnormal data in the growth data specifically comprises: obtaining the growth data of the to-be-traced agricultural products under each key growth condition, sorting the growth data in time sequence, and determining the extreme points in the growth data corresponding to each key growth condition; taking the time period between adjacent extreme points with the same feature as an extreme time period to obtain a plurality of extreme time periods and the extreme time periods corresponding to the extreme points; the same feature is the same maximum value or the same minimum value; obtaining the potential influence trend of the extreme points according to the correspondence between the extreme time periods where the extreme points are located and the suitable ranges of the corresponding key growth conditions; each key growth condition has a corresponding suitable range; the determination of the commonality degree between different key growth conditions according to the time sequence difference between extreme points under different key growth conditions and the potential influence trend difference between extreme points under the same key growth condition specifically comprises: According to extreme points in the growth data, time sequence differences between different two of the key growth conditions are obtained, and difference time periods are constructed according to minimum time sequence differences, to obtain a plurality of the difference time periods; Time sequence differences between extreme points of one of the key growth conditions and extreme points of another of the key growth conditions in each of the difference time periods are obtained; According to the time sequence differences between the extreme points of the two of the key growth conditions and potential influence trend differences between the extreme points under the same key growth condition, a commonality degree between the different two of the key growth conditions is determined.

Images