Multi-objective optimized agricultural product quality safety sampling resource scheduling method

Abstract

The invention relates to the technical field of agricultural product quality safety management, and discloses a multi-objective optimization agricultural product quality safety sampling resource scheduling method, which comprises the following steps: acquiring historical data information of all agricultural products, and calculating a risk weight FQ of a location of each agricultural product according to the acquired historical data information; determining a preliminary priority by adopting a risk weight FQ descending order arrangement mode, determining a final priority according to the location of the agricultural product needing sampling investigation, and performing path optimization according to the final priority; according to the method, the risk weight FQ is calculated, the risk weight FQ is calculated according to the category risk coefficient PL, the credit rating XY and the seasonal pollution index JJ, the calculated risk weight FQ is accurate enough, and the three groups of data have three core advantages of multi-dimensional decision optimization, dynamic adaptability and accurate resource allocation in agricultural product quality safety supervision. And the determined priority is more accurate.

Description

Technical Field

[0001] This invention relates to the field of agricultural product quality and safety management technology, and more specifically to a multi-objective optimized method for allocating sampling resources for agricultural product quality and safety. Background Technology

[0002] Agricultural products refer to primary products derived from crop farming, forestry, animal husbandry, and fisheries, namely plants, animals, microorganisms, and their products obtained in agricultural activities. Agricultural products are the main source of people's daily diet and are of great significance to ensuring people's livelihood and health. Therefore, the quality and safety of agricultural products are extremely important. Sampling and testing of agricultural products is a core regulatory means to prevent risks such as excessive pesticide residues and microbial contamination. Through testing, harmful substances such as pesticide residues, heavy metals, and microbial contamination can be screened to avoid threats to human health. By screening out unqualified products, inferior agricultural products can be prevented from disrupting the market, protecting the rights and interests of legitimate producers and consumers. The test data can promote agricultural technology improvement, increase production efficiency and resource utilization, and improve the quality and safety level of agricultural products. Supervision and sampling can promptly identify potential risks and strengthen the sense of responsibility of operators. Currently, when sampling agricultural products for quality and safety, sampling tasks are mostly carried out on a fixed quarterly plan without considering the dynamic nature of agricultural production. Therefore, it is impossible to select agricultural products in different regions in a good order, which wastes human and material resources for sampling and testing. When selecting sampling routes for agricultural products, the existing methods cannot freely optimize the route length. Furthermore, there will be testing errors when the samples are transported to the testing center after collection. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a multi-objective optimized sampling resource scheduling method for agricultural product quality and safety to solve the technical problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a multi-objective optimized method for resource scheduling of agricultural product quality and safety sampling, comprising the following steps: Step S1: Collect historical data information of all agricultural products and manage the available sampling team members in a unified manner; Step S2: Calculate the risk weight FQ for each agricultural product's location based on the collected historical data. Step S3: Determine the initial priority by sorting the risk weights (FQ) in descending order; In step S4, preliminary priority, the higher the risk weight FQ, the higher the preliminary priority. Step S5: Determine the final priority of the locations of agricultural products to be sampled as needed, and optimize the route based on the final priority; Step S6: When sampling and sending samples for testing, check the transportation status of the samples and determine the sample quality at the testing center.

[0005] In a preferred embodiment, in step S2, the formula for calculating the risk weight FQ is as follows: In the formula, α, β and γ are dynamic adjustment coefficients, PL is the category risk coefficient, XY is the credit rating, and JJ is the seasonal pollution index. The risk weights FQ corresponding to each category of agricultural products are sorted in descending order from largest to smallest, and sampling tests are carried out according to the sorted order.

[0006] In a preferred embodiment, the formula for calculating the category risk coefficient PL in the risk weight FQ calculation is as follows: In the formula, k1, k2, and k3 are all weights, JG is the regulatory difficulty level, which is divided into five levels from simple to difficult, and the five levels are respectively set by the management personnel. NY is the average pesticide exceedance rate of this agricultural product category in the past year, and QK is the stomatal density test value of this agricultural product category.

[0007] In a preferred embodiment, the formula for calculating the credit rating XY is as follows: In the formula, YS is the preset standard value of agricultural product qualification rate, i is the i-th agricultural product qualification test, n is the total number of agricultural product qualification tests, and NYi is the qualification rate of agricultural product qualification test in the i-th test.

[0008] In a preferred embodiment, the seasonal pollution index JJ is divided into four different values ​​for spring, summer, autumn and winter. In spring, the seasonal pollution index JJ is the pesticide leaching pollution value; in summer, the seasonal pollution index JJ is the pesticide photolysis residue value; in autumn, the seasonal pollution index JJ is the heavy metal deposition value; and in winter, the seasonal pollution index JJ is the nitrate accumulation value.

[0009] In a preferred embodiment, in step S3, within the initial priority, the agricultural products corresponding to five adjacent risk weights FQ are grouped together in descending order of risk weight FQ. Each agricultural product in a group has the same initial priority. In step S5, according to the grouping in step S3, the distance data JL between the location of the agricultural product corresponding to risk weight FQ in each group and the sampling survey center is collected. Within the group, the distance data JL is arranged in descending order. The larger the distance data JL, the higher the final priority. The sampling order of agricultural products is determined according to the final priority.

[0010] In a preferred embodiment, in step S5, a forward route is generated based on the sampling order of agricultural products. This agricultural product location is the final sampling target. Other agricultural products along the forward route that are within one kilometer of the forward route can be used as secondary sampling targets for the sampling team. The sampling team goes to the secondary sampling targets to perform sampling. There can be at most two secondary sampling targets, and the two agricultural product locations with the highest initial priority are selected as secondary sampling targets. The final forward route is generated based on the final sampling target and the secondary sampling targets. During sampling, the final sampling target is sampled before the secondary sampling targets.

[0011] In a preferred embodiment, in step S6, after sample collection, preliminary testing of the sample is performed and preliminary data is recorded. When the sample is sent for testing, temperature and humidity data are recorded during the testing process. After the sample arrives at the testing center, the precise data of the sample is tested, and the precise data of the sample is compared with the same data in the preliminary data to determine the loss value of the sample during transportation, and finally determine the sample quality.

[0012] In a preferred embodiment, when the temperature and humidity of the sample exceed the acceptable range during transportation, the sample loss value is compared with the standard threshold. If the sample loss value is greater than the standard threshold, the sample of the agricultural product is collected again. If the sample loss value is not greater than the standard threshold, the sample quality is determined with accurate data. If the temperature and humidity of the sample remain within the acceptable range during transportation, the accurate value is used as the sample quality result.

[0013] The technical effects and advantages of this invention are as follows: This invention calculates a risk weight FQ using three data points: category risk coefficient PL, credit rating XY, and seasonal pollution index JJ. The calculated risk weight FQ is sufficiently accurate. The above three sets of data are used in a multi-objective manner, which has three core advantages in agricultural product quality and safety supervision: multi-dimensional decision optimization, dynamic adaptability, and precise resource allocation. Moreover, the determined priorities are more accurate. After determining the initial priority through risk weights FQ, this invention groups the agricultural products corresponding to five adjacent risk weights FQ in descending order. Distance data JL between the location of the agricultural product and the sampling survey center is collected. The larger the distance data JL, the higher the final priority. Furthermore, the locations of agricultural products within one kilometer of the route can be used as incidental sampling targets for the sampling team. Since the distance is only within one kilometer, route replanning will not waste much time, and other agricultural products can be tested together, improving sampling efficiency. This invention compares the sample's loss value with a standard threshold. If the sample's loss value is not greater than the standard threshold, although there may be transportation issues, it will not affect the test results. Therefore, the accurate test results can be used as the instruction results. Only when the sample's loss value exceeds the standard threshold is the sample collected again, avoiding multiple collections and wasting resources. If the temperature and humidity of the sample remain within the acceptable range during transportation, there are no problems. Therefore, the accurate value can be directly used as the sample quality result. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the sampling resource scheduling method of the present invention. Detailed Implementation

[0015] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Reference Figure 1 This invention provides a multi-objective optimized sampling resource scheduling method for agricultural product quality and safety. Step S1: Collect historical data information of all agricultural products and manage the schedulable sampling team personnel in a unified manner. Step S2: Calculate the risk weight FQ for each agricultural product's location based on the collected historical data. Step S3: Determine the initial priority by sorting the risk weights (FQ) in descending order; In step S4, preliminary priority, the higher the risk weight FQ, the higher the preliminary priority. Step S5: Determine the final priority of the locations of agricultural products to be sampled as needed, and optimize the route based on the final priority.

[0017] In this embodiment, when conducting sampling and testing of agricultural products and scheduling testing resources, the historical information of all agricultural products is first collected. After collection, the risk weight FQ is calculated, and priority is determined using the risk weight FQ. Therefore, sampling and sorting are standardized, which facilitates subsequent path optimization. After sorting, sampling can be performed according to the order, with priority given to more important templates. This makes the overall scheduling process more orderly and avoids chaos. Furthermore, during path optimization, path optimization is performed based on priority and location information, resulting in a path that better matches the sampled agricultural products. During transportation after sampling, status data is collected to prevent problems from occurring during transportation.

[0018] Reference Figure 1 In step S2, the formula for calculating the risk weight FQ is as follows: In the formula, α, β and γ are dynamic adjustment coefficients, PL is the category risk coefficient, XY is the credit rating, and JJ is the seasonal pollution index. The risk weights FQ corresponding to each category of agricultural products are sorted in descending order from largest to smallest, and sampling tests are carried out according to the sorted order.

[0019] In this embodiment, when calculating the risk weight FQ, three data points are used: PL (category risk coefficient), XY (credit rating), and JJ (seasonal pollution index). The calculated risk weight FQ is sufficiently accurate. These three sets of data have three core advantages in agricultural product quality and safety supervision: multi-dimensional decision optimization, dynamic adaptability, and precise resource allocation. The category risk coefficient can quantify the inherent biological attributes of agricultural products, the credit rating can reflect the historical production behavior of agricultural products, and the seasonal pollution index can capture external environmental fluctuations. Therefore, the larger the calculated risk weight FQ, the higher its priority for sampling. Thus, the priority can be preliminarily determined, and the determined priority is more accurate.

[0020] Reference Figure 1 In the calculation of the risk weight FQ, the formula for calculating the category risk coefficient PL is as follows: In the formula, k1, k2, and k3 are all weights, JG is the regulatory difficulty level, which is divided into five levels from simple to difficult, and the five levels are respectively set by the management personnel. NY is the average pesticide exceedance rate of this agricultural product category in the past year, and QK is the stomatal density test value of this agricultural product category.

[0021] In this embodiment of the application, the category risk coefficient refers to the inherent risk probability value of a certain type of agricultural product due to its own characteristics leading to a quality and safety incident. The category risk coefficient PL calculated based on the regulatory difficulty level JG, the average pesticide exceedance rate NY, and the stomatal density detection value QK can accurately reflect the condition of the agricultural product itself. Moreover, the larger the category risk coefficient PL, the higher the inherent risk probability value. Therefore, it is necessary to send the product for testing in a timely manner to avoid the situation where agricultural products have been at risk but have not been tested, resulting in agricultural production reduction.

[0022] Reference Figure 1 The formula for calculating the credit rating XY is as follows: In the formula, YS is the preset standard value for the qualified rate of agricultural products, i is the qualified test of agricultural products conducted in the i-th time, n is the total number of qualified tests of agricultural products, NYi is the qualified rate of the qualified test of agricultural products conducted in the i-th time, and the seasonal pollution index JJ is divided into four different values ​​for spring, summer, autumn and winter. In spring, the seasonal pollution index JJ is the value of pesticide leaching pollution; in summer, the seasonal pollution index JJ is the value of pesticide photolysis residue; in autumn, the seasonal pollution index JJ is the value of heavy metal deposition; and in winter, the seasonal pollution index JJ is the value of nitrate accumulation.

[0023] In this embodiment, when calculating the credit rating XY, the difference between the average past pass rate of agricultural products and the standard value of the pass rate of agricultural products is collected. The higher the credit rating XY, the higher the pass rate. Therefore, agricultural products with high pass rates are sampled first, so that they can have a long-term virtuous cycle. When calculating the seasonal pollution index JJ, four different values ​​are used in spring, summer, autumn and winter, so that the risk weight FQ calculated in this application can be calculated well in different seasons.

[0024] Reference Figure 1In step S3, within the initial priority, five adjacent agricultural products corresponding to risk weights FQ are grouped in descending order. Each agricultural product in a group has the same initial priority. In step S5, according to the grouping in step S3, distance data JL between the location of the agricultural product corresponding to risk weight FQ in each group and the sampling survey center is collected. Within the group, the distance data JL is arranged in descending order. The larger the distance data JL, the higher the final priority. The sampling order of agricultural products is determined according to the final priority. In step S5, a forward route for the location of agricultural products is generated according to the sampling order. This location of agricultural products is the final sampling target. The locations of other agricultural products on the forward route that are within one kilometer of the forward route can be used as secondary sampling targets for the sampling team. The sampling team goes to the secondary sampling targets for sampling. There can be at most two secondary sampling targets, and the two locations of agricultural products with the highest initial priority are selected as secondary sampling targets. The final forward route is generated according to the final sampling target and the secondary sampling targets. During sampling, the final sampling target is sampled before the secondary sampling target.

[0025] In this embodiment, after determining the initial priority using risk weights FQ, the agricultural products corresponding to five adjacent risk weights FQ are grouped in descending order of FQ. The higher the risk weight FQ, the higher the sampling priority. The top five risk weights FQ are grouped together, the next five (6-10) are grouped into a second group, and so on. Agricultural products within a group have relatively similar calculated risk weights FQ. Distance data JL between the location of the agricultural product and the sampling survey center is then collected. A larger distance JL results in a higher final priority, as more distant agricultural products may encounter problems during transport, thus increasing their priority. Furthermore, since they are in the same group, the sampling time for other agricultural products in the same group will not be delayed. In order, the five locations of agricultural products in the first group are the final sampling targets. Agricultural product locations within one kilometer of the route can be used as incidental sampling targets for the sampling team. Since the distance is only within one kilometer, route replanning will not waste much time, and other agricultural products can be tested together to improve sampling efficiency. When selecting the two agricultural product locations with the highest initial priority as incidental sampling targets, a maximum of two locations can be selected. If there are no other agricultural products within one kilometer, only the final sampling targets will be sampled. The final sampling targets will be sampled before the incidental sampling targets to ensure the priority of the final sampling targets.

[0026] Reference Figure 1In step S6, after sample collection, preliminary testing of the sample is conducted and preliminary data is recorded. When the sample is sent for testing, temperature and humidity data are recorded during the testing process. After the sample arrives at the testing center, the precise data of the sample is tested, and the precise data is compared with the same data in the preliminary data to determine the loss value of the sample during transportation. Finally, the sample quality is determined. When the temperature and humidity of the sample exceed the qualified range during transportation, the loss value of the sample is compared with the standard threshold. If the loss value of the sample is greater than the standard threshold, the sample of the agricultural product is collected again. If the loss value of the sample is not greater than the standard threshold, the sample quality is determined with precise data. If the temperature and humidity of the sample are always within the qualified range during transportation, the precise value is used as the sample quality result.

[0027] In this embodiment, during sample collection, preliminary sample information is collected, and temperature and humidity data during transportation are detected. If the temperature and humidity exceed the acceptable range, it indicates that there are some problems during transportation. At this time, the sample loss value is compared with the standard threshold. If the sample loss value is not greater than the standard threshold, although there are problems during transportation, it will not affect the test results. Therefore, the accurate test results can be used as the instruction results. Only when the sample loss value is greater than the standard threshold is the data collected again to avoid wasting resources by collecting data multiple times. If the temperature and humidity of the sample are always within the acceptable range during transportation, there are no problems. Therefore, the accurate values ​​are directly used as the sample quality results.

[0028] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. The units and algorithm steps of the various examples described in the embodiments can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0029] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0030] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0031] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-objective optimization method for resource allocation in agricultural product quality and safety sampling, characterized by: Includes the following steps: Step S1: Collect historical data information of all agricultural products and manage the available sampling team members in a unified manner; Step S2: Calculate the risk weight FQ for each agricultural product's location based on the collected historical data. Step S3: Determine the initial priority by sorting the risk weights (FQ) in descending order; In step S4, preliminary priority, the higher the risk weight FQ, the higher the preliminary priority. Step S5: Determine the final priority of the locations of agricultural products to be sampled as needed, and optimize the route based on the final priority; Step S6: When sampling and sending samples for testing, check the transportation status of the samples and determine the sample quality at the testing center.

2. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 1, characterized in that: In step S2, the formula for calculating the risk weight FQ is as follows: In the formula, α, β and γ are dynamic adjustment coefficients, PL is the category risk coefficient, XY is the credit rating, and JJ is the seasonal pollution index. The risk weights FQ corresponding to each category of agricultural products are sorted in descending order from largest to smallest, and sampling tests are carried out according to the sorted order.

3. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 1, characterized in that: In the calculation of the risk weight FQ, the formula for calculating the category risk coefficient PL is as follows: In the formula, k1, k2, and k3 are all weights, JG is the regulatory difficulty level, which is divided into five levels from simple to difficult, and the five levels are respectively set by the management personnel. NY is the average pesticide exceedance rate of this agricultural product category in the past year, and QK is the stomatal density test value of this agricultural product category.

4. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 2, characterized in that: The formula for calculating the credit rating XY is as follows: In the formula, YS is the preset standard value of agricultural product qualification rate, i is the i-th agricultural product qualification test, n is the total number of agricultural product qualification tests, and NYi is the qualification rate of agricultural product qualification test in the i-th test.

5. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 2, characterized in that: The seasonal pollution index JJ is divided into four different values ​​for spring, summer, autumn and winter. In spring, the seasonal pollution index JJ is the pesticide leaching pollution value; in summer, the seasonal pollution index JJ is the pesticide photolysis residue value; in autumn, the seasonal pollution index JJ is the heavy metal deposition value; and in winter, the seasonal pollution index JJ is the nitrate accumulation value.

6. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 1, characterized in that: In step S3, within the initial priority, the agricultural products corresponding to five adjacent risk weights FQ are grouped together in descending order of risk weight FQ. Each agricultural product in a group has the same initial priority. In step S5, according to the grouping in step S3, the distance data JL between the location of the agricultural product corresponding to risk weight FQ in each group and the sampling survey center is collected. Within the group, the distance data JL is arranged in descending order. The larger the distance data JL, the higher the final priority. The sampling order of agricultural products is determined according to the final priority.

7. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 6, characterized in that: In step S5, a forward route is generated based on the sampling order of agricultural products. This agricultural product location is the final sampling target. Other agricultural products on the forward route that are within one kilometer of the forward route can be used as secondary sampling targets for the sampling team. The sampling team goes to the secondary sampling targets to conduct sampling. There can be at most two secondary sampling targets, and the two agricultural product locations with the highest initial priority are selected as secondary sampling targets. The final forward route is generated based on the final sampling target and the secondary sampling targets. During sampling, the final sampling target is sampled before the secondary sampling targets.

8. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 1, characterized in that: In step S6, after the sample is collected, preliminary testing of the sample is performed and preliminary data is recorded. When the sample is sent for testing, temperature and humidity data are recorded during the testing process. After the sample arrives at the testing center, the precise data of the sample is tested, and the precise data of the sample is compared with the same data in the preliminary data to determine the loss value of the sample during transportation and finally determine the sample quality.

9. The multi-objective optimized sampling resource scheduling method for agricultural product quality and safety according to claim 8, characterized in that: When the temperature and humidity of a sample exceed the acceptable range during transportation, the sample loss value is compared with the standard threshold. If the sample loss value is greater than the standard threshold, the sample of the agricultural product is collected again. If the sample loss value is not greater than the standard threshold, the sample quality is determined with accurate data. When the temperature and humidity of the sample are moderate and within the acceptable range during transportation, the accurate value is used as the sample quality result.

Images