Inventory intelligent supervision method and system for grain reserve warehouse

Abstract

The invention relates to the technical field of grain reserve management, and discloses an intelligent inventory supervision method and system for a grain reserve warehouse, and the method comprises the steps: obtaining the historical data of each sensor from a storage unit, constructing a grain quality prediction model, training the grain quality prediction model based on the historical data, and carrying out the prediction of the grain quality. The data of each sensor in the granary is collected as first data, the first data is input into the grain quality prediction model, a first prediction result is obtained, and based on the first prediction result, the environment adjustment unit adjusts the environment of the granary and / or the logistics scheduling unit schedules in and out of grain. The data of each sensor is collected again based on a first preset period to serve as second data, the difference value between the second prediction result and the first prediction result is compared, and the environment adjustment unit adjusts the environment of the granary again and / or the logistics scheduling unit schedules grain entering and exiting again. And the safety of grain storage is improved.

Description

Technical Field

[0001] This application relates to the technical field of grain reserve management, and particularly to an intelligent inventory supervision method and system for a grain reserve warehouse. Background Art

[0002] With the expansion of the scale of granaries, problems such as mildew and pests are likely to occur inside the granaries. Since grain is a special and complex living entity, the changes in the temperature field, humidity field, and gas concentration inside the grain pile are extremely complex. Therefore, accurately grasping the temperature, humidity, and gas concentration distribution in the granary has become one of the important methods for predicting the quality of stored grain.

[0003] A similar prior art is a Chinese patent application with the publication number CN118536090A, which relates to a method for generating a grain temperature field map based on warehouse temperature and humidity monitoring, including: drawing a spatial temperature and humidity distribution map inside the granary within several monitoring periods; drawing a historical temperature and humidity distribution map of the spatial granary within several historical monitoring periods; obtaining a training sample set based on the spatial temperature and humidity distribution map and the historical temperature and humidity distribution map; training a temperature state prediction model of the grain temperature field map according to the training sample set; and predicting the temperature state of the corresponding granary within the monitoring period according to the temperature state prediction model of the grain temperature field map.

[0004] Another similar prior art is a Chinese patent application with the publication number CN118469310A, which discloses a method and system for managing grain inventory in a granary, relating to the technical field of granary management. In this method, the granary is divided into regions to obtain multiple inventory management regions; the types of grain stored in the inventory management regions are determined; the initial inventory quantity and the starting warehousing time corresponding to the grain type are obtained; the detection images corresponding to the grain type collected by the camera devices arranged in the inventory management regions are obtained, and multiple initial environmental data collected by the sensors arranged in the inventory management regions are obtained; based on the initial inventory quantity, the starting warehousing time, the detection images, and the multiple initial environmental data, the grain inventory situation corresponding to the grain type is obtained; the grain inventory situation includes the first grain inventory and the second grain inventory, where the first grain inventory is the grain inventory that supports continued storage, and the second grain inventory is the grain inventory that has deteriorated or is approaching the expiration date.

[0005] However, the above two applications are not efficient enough in grain inventory management, and in terms of the intelligent management of grain reserves in the granary, the safety of grain storage still needs to be further improved. Summary of the Invention

[0006] To solve the above technical problems, this application provides an intelligent inventory supervision method and system for a grain reserve warehouse, which is used to improve the safety and management efficiency of grain storage.

[0007] To achieve the above object, in a first aspect, the present application provides an intelligent inventory supervision method for a grain storage depot. By installing a temperature sensor, a humidity sensor and a camera device respectively inside each granary, installing a gas concentration sensor at a preset height from the bottom of the granary, and also installing a weight sensor at the bottom of the granary or on the support structure, the intelligent inventory supervision method of the grain storage depot is implemented by performing the following steps:

[0008] Step S1: Obtain the historical data of each of the sensors from the storage unit, and preprocess the historical data to obtain the preprocessed historical data. The historical data includes temperature data, humidity data, gas concentration data, grain weight data and the quality grade of the grain;

[0009] Step S2: Construct a grain quality prediction model, train the grain quality prediction model based on the historical data, and obtain the trained grain quality prediction model. Collect the data of each sensor in the granary as the first data, preprocess the first data, and input the first data into the grain quality prediction model to obtain a first prediction result. Based on the first prediction result, the environment adjustment unit adjusts the environment of the granary and / or the logistics scheduling unit schedules the in and out of the grain;

[0010] Step S3: Collect the data of each sensor again as the second data based on a first preset period, and obtain a second prediction result predicted based on the second data based on the grain quality prediction model. Compare the difference between the second prediction result and the first prediction result. Based on the difference, the environment adjustment unit readjusts the environment of the granary and / or the logistics scheduling unit readjusts the in and out of the grain.

[0011] Combined with the first aspect, in the first implementation manner of the first aspect of the present application, training the grain quality prediction model:

[0012] Divide the historical data into a training data set, a validation data set and a test data set, use the training data set to train the grain quality prediction model, use the validation data set to adjust the parameters of the grain quality prediction model, use the test data set to evaluate the performance of the grain quality prediction model, and obtain the grain quality prediction model when the accuracy rate of the output result of the grain quality prediction model is greater than or equal to a preset threshold.

[0013] Combined with the first aspect, in the second implementation manner of the first aspect of the present application, adjusting the environment of the granary includes:

[0014] When the first prediction result shows a decrease in the quality grade of the grain compared to the most recent one, compare the temperature data, humidity data, gas concentration data, and grain weight data respectively to obtain the factors causing the decrease in the first prediction result. When the decreasing factor is the temperature data, turn on the refrigeration equipment near the granary. When the decreasing factor is the humidity data, turn on the dehumidification equipment and ventilation equipment near the granary. When the decreasing factor is the gas concentration data, use the controlled atmosphere grain storage technology. When the decreasing factor is the grain weight data, dispatch the grain in the granary for outbound, or transfer some of the grain in the granary to other granaries.

[0015] Combined with the first aspect, in the third implementation manner of the first aspect of this application, adjusting the environment of the granary further includes:

[0016] When there are multiple combined influencing factors, based on the combination of the factors, adjust the corresponding equipment, collect the data of each sensor based on the second preset period, obtain a new prediction result based on the grain quality prediction model, and continue to adjust the environment of the granary based on the new prediction result, where the second preset period is less than the first prediction period.

[0017] Combined with the first aspect, in the fourth implementation manner of the first aspect of this application, dispatching the inbound and outbound of grain includes:

[0018] When the first prediction result shows an increase or remains the same in the quality grade of the grain compared to the most recent one, unload the grain of the same type as the grain in the granary that enters the warehouse into the granary, otherwise unload it into other granaries or newly built granaries.

[0019] Combined with the first aspect, in the fifth implementation manner of the first aspect of this application, dispatching the inbound and outbound of grain further includes:

[0020] After the preset time for adjusting the environment of the granary, when the quality grade of the grain in the granary has not changed, obtain the granary that affects the change of the external environment of the granary as the target granary, dispatch the grain in the target granary for outbound, or transfer some of the grain in the target granary to other granaries.

[0021] Combined with the first aspect, in the sixth implementation manner of the first aspect of this application, obtaining the quality grade of the grain includes:

[0022] Obtain the grain image captured by the imaging device from the storage unit, perform denoising and enhancement operations on the grain image, and obtain the preprocessed grain image. Based on the characteristics of the grain, extract grain samples from the grain image. The characteristics of the grain include the color, texture, and shape of the grain. Identify the characteristic parameters related to the grain quality from the grain samples, and based on the characteristic parameters related to the grain quality, obtain the quality grade of the grain. The characteristic parameters related to the grain quality include the area, perimeter, and aspect ratio of the grain particles.

[0023] Combined with the first aspect, in the seventh implementation manner of the first aspect of this application, obtaining the quality grade of the grain further includes:

[0024] Preset a first quality threshold and a second quality threshold, calculate the quality of each grain particle, count the first number of grain particles in the grain sample whose quality is greater than or equal to the first quality threshold, the second number of grain particles in the grain sample whose quality is less than the first quality threshold and greater than or equal to the second quality threshold, and the third number of grain particles in the grain sample whose quality is less than the second quality threshold. Calculate the first ratio of the first number to the total number of grain particles in the grain sample, the second ratio of the second number to the total number of grain particles in the grain sample, and the third ratio of the third number to the total number of grain particles in the grain sample. Based on the first ratio, the second ratio, and the third ratio, calculate the quality grade of the grain corresponding to the grain sample.

[0025] Combined with the first aspect, in the eighth implementation manner of the first aspect of this application, calculating the quality of each grain particle includes:

[0026] Based on the grain sample, calculate the area, perimeter, and aspect ratio of each grain particle, and calculate the quality of the grain particle through the following formula:

[0027] M = S×α1 + L×α2 + K×α3

[0028] Where M represents the quality of the grain particle, S represents the area of the grain particle, L represents the perimeter of the grain particle, K represents the aspect ratio of the grain particle, α1 represents the first coefficient, α2 represents the second coefficient, α3 represents the third coefficient. The sum of the first coefficient, the second coefficient, and the third coefficient is equal to 1. The first coefficient is greater than the third coefficient, and the third coefficient is greater than the second coefficient.

[0029] Second aspect, the present application provides an inventory intelligent supervision system for a grain storage depot. By installing temperature sensors, humidity sensors and camera devices respectively inside each granary, installing gas concentration sensors at a preset height from the bottom of the granary, and also installing weight sensors at the bottom of the granary or on the support structure, the inventory intelligent supervision system of the grain storage depot includes:

[0030] An acquisition unit, configured to acquire historical data of each of the sensors from a storage unit, preprocess the historical data, and obtain preprocessed historical data, where the historical data includes temperature data, humidity data, gas concentration data, grain weight data, and the quality grade of the grain;

[0031] A prediction unit, configured to construct a grain quality prediction model, train the grain quality prediction model based on the historical data, and obtain the trained grain quality prediction model, collect data of each sensor in the granary as first data, preprocess the first data, and input the first data into the grain quality prediction model to obtain a first prediction result. Based on the first prediction result, an environment adjustment unit adjusts the environment of the granary and / or a logistics scheduling unit schedules the in and out of the grain;

[0032] An adjustment unit, configured to collect data of each sensor again as second data based on a first preset period, obtain a second prediction result predicted based on the second data based on the grain quality prediction model, compare the difference between the second prediction result and the first prediction result, and based on the difference, the environment adjustment unit readjusts the environment of the granary and / or the logistics scheduling unit reschedules the in and out of the grain.

[0033] Compared with the prior art, the beneficial effects of the present invention are at least as follows:

[0034] In the technical solution provided by this application, by obtaining the historical data of each sensor from the storage unit and preprocessing the historical data to obtain the preprocessed historical data, the change trend and potential risks of the grain storage environment can be captured more accurately, providing high-quality input data for the subsequent prediction model. A grain quality prediction model is constructed, the grain quality prediction model is trained based on the historical data, and the trained grain quality prediction model is obtained. The data of each sensor in the granary is collected as the first data, the first data is preprocessed, and the first data is input into the grain quality prediction model to obtain the first prediction result. Based on the first prediction result, the environment adjustment unit adjusts the environment of the granary and / or the logistics scheduling unit schedules the inflow and outflow of grain. The real-time monitoring and prediction of grain quality are realized, and by automatically adjusting the environmental conditions and logistics scheduling, the spoilage and loss of grain are effectively prevented, and the safety of grain reserves is improved. The data of each sensor are collected again as the second data based on the first preset period, and the second prediction result predicted based on the second data is obtained based on the grain quality prediction model. The difference between the second prediction result and the first prediction result is compared, and based on the difference, the environment adjustment unit readjusts the environment of the granary and / or the logistics scheduling unit readjusts the inflow and outflow of grain. The change of grain quality can be continuously monitored, the environmental conditions can be adjusted in time, and the grain loss can be reduced. Through the cooperation between the above steps, this application realizes the intelligent management of the inventory of the grain reserve depot and improves the safety of grain storage. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 FIG. is a schematic diagram of an embodiment of an intelligent supervision method for the inventory of a grain reserve depot in an embodiment of this application;

[0037] Figure 2 FIG. is a schematic diagram of an embodiment of an intelligent supervision system for the inventory of a grain reserve depot in an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The embodiments of the present application provide an inventory intelligent supervision method and system for a grain storage depot. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the term "including" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0039] It can be understood that the execution subject of the present application can be an inventory intelligent supervision system for a grain storage depot, or a terminal or a server. Specifically, no limitation is made here. The embodiments of the present application are described by taking the server as the execution subject as an example.

[0040] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 , an embodiment of an inventory intelligent supervision method for a grain storage depot in the embodiments of the present application includes:

[0041] Install temperature sensors, humidity sensors and camera devices respectively inside each granary, install gas concentration sensors at a preset height from the bottom of the granary, and also install weight sensors at the bottom of the granary or on the support structure.

[0042] Step S1: Obtain the historical data of each sensor from the storage unit, and preprocess the historical data to obtain the preprocessed historical data. The historical data includes temperature data, humidity data, gas concentration data, grain weight data and quality grades of grains.

[0043] Specifically, by installing temperature sensors, humidity sensors, camera devices and gas concentration sensors inside each granary, and installing weight sensors at the bottom of the granary or on the support structure, the historical data of these sensors can be collected regularly from the storage unit, and the collected data can be preprocessed, including data cleaning (removing outliers and missing values), normalization processing and feature extraction, etc., to facilitate model training and prediction. Data preprocessing belongs to the prior art and will not be elaborated here. By obtaining historical data, the changing trend and potential risks of the grain storage environment can be captured more accurately, providing high-quality input data for the subsequent prediction model.

[0044] Step S2: Construct a grain quality prediction model, train the grain quality prediction model based on historical data, and obtain the trained grain quality prediction model. Collect the data of each sensor in the granary as the first data, preprocess the first data, and input the first data into the grain quality prediction model to obtain the first prediction result. Based on the first prediction result, the environment adjustment unit adjusts the environment of the granary and / or the logistics scheduling unit schedules the in and out of the grain.

[0045] Specifically, use machine learning algorithms (such as random forest, support vector machine or neural network) to construct a grain quality prediction model. Use the preprocessed historical data to train the model until the model reaches the expected accuracy. Collect the data of the sensors in the granary in real time as the first data, perform the same preprocessing on these data, and input them into the trained grain quality prediction model to obtain the first prediction result. According to the first prediction result, the environment adjustment unit automatically adjusts the environmental conditions of the granary (such as temperature, humidity and gas concentration, etc.), and the logistics scheduling unit schedules the in and out of the grain according to the prediction result to maintain the grain quality. Through this step, the real-time monitoring and prediction of grain quality are realized, and by automatically adjusting the environmental conditions and logistics scheduling, the spoilage and loss of grain are effectively prevented, and the safety of grain storage is improved.

[0046] Step S3: Collect the data of each sensor again as the second data based on the first preset period, and obtain the second prediction result predicted based on the second data based on the grain quality prediction model. Compare the difference between the second prediction result and the first prediction result. Based on the difference, the environment adjustment unit re-adjusts the environment of the granary and / or the logistics scheduling unit re-schedules the in and out of the grain.

[0047] Specifically, set a preset period (such as every few hours, every day), and collect the data of all sensors again at the end of each period as the second data. Use the grain quality prediction model to obtain the second prediction result based on the second data. Compare the difference between the second prediction result and the first prediction result, and analyze the change trend of grain quality. If the difference exceeds the preset threshold, the environment adjustment unit re-adjusts the environmental conditions of the granary according to the new prediction result and / or the logistics scheduling unit re-schedules the in and out of the grain to more effectively maintain the grain quality. Through periodic data collection and prediction, the change of grain quality can be continuously monitored, the environmental conditions can be adjusted in time, and the grain loss can be reduced.

[0048] Through the cooperation between the above steps, this application realizes the intelligent management of the inventory in the grain reserve depot and improves the safety of grain storage.

[0049] Furthermore, train the grain quality prediction model:

[0050] Divide the historical data into a training dataset, a validation dataset, and a test dataset. Use the training dataset to train the grain quality prediction model, use the validation dataset to adjust the parameters of the grain quality prediction model, and use the test dataset to evaluate the performance of the grain quality prediction model. When the accuracy of the output result of the grain quality prediction model is greater than or equal to the preset threshold, obtain the grain quality prediction model.

[0051] Specifically, randomly divide the preprocessed historical data into three parts: a training dataset, a validation dataset, and a test dataset. A common division ratio is 70% for the training dataset, 15% for the validation dataset, and 15% for the test dataset, but the specific ratio can be adjusted according to the actual situation. The training dataset is used to train the model and learn the patterns and relationships in the data. The validation dataset is used for model parameter tuning, that is, during the training process, it is used to adjust the hyperparameters of the model to prevent overfitting or underfitting of the model. The test dataset is used to finally evaluate the performance of the model, and it provides the performance of the model on unseen data. By dividing the dataset, it can be ensured that the model will not overfit the training data during the training process, and at the same time, the generalization ability of the model can be evaluated through independent validation and test datasets. Select a suitable algorithm (such as random forest, support vector machine, neural network, etc.) and set the initial parameters, and use the training dataset to train the grain quality prediction model. Apply optimization algorithms such as gradient descent to minimize the prediction error and train the model through multiple iterations. The training process enables the model to learn the relationship between grain quality and sensor data, so as to be able to predict grain quality. Use the validation dataset to adjust the parameters of the model, including adjusting the learning rate, the depth of the tree (for decision tree models), regularization parameters, etc. Through techniques such as cross-validation, evaluate the model performance under different parameter settings and select the best parameter combination. Improve the accuracy and robustness of the model to ensure the prediction performance of the model on new data. Use the test dataset to evaluate the performance of the model to ensure the reliability of the model's prediction results. Calculate metrics such as the accuracy of the model output result. If the accuracy of the model is greater than or equal to the preset threshold, it is considered that the model performance meets the standard and can be used for actual grain quality prediction. Through the implementation of this step, the grain quality prediction model can ensure high accuracy while adapting to new data and environmental changes, providing strong technical support for the intelligent inventory supervision of grain depots.

[0052] Furthermore, adjusting the environment of the granary includes:

[0053] When the quality level of grain in the first prediction result is lower than that in the most recent prediction, the temperature data, humidity data, gas concentration data and grain weight data are compared respectively to obtain the factors causing the decline in the first prediction result. When the declining factor is the temperature data, turn on the refrigeration equipment near the granary. When the declining factor is the humidity data, turn on the dehumidification equipment and ventilation equipment near the granary. When the declining factor is the gas concentration data, use the controlled atmosphere grain storage technology to reduce the oxygen concentration in the granary. When the declining factor is the grain weight data, dispatch the grain in the granary for shipment, or transfer part of the grain in the granary to other granaries.

[0054] Specifically, when the output of the grain quality prediction model shows that the grain quality level has decreased compared to the most recent one, the analysis process is automatically triggered. The latest temperature data, humidity data, gas concentration data, and grain weight data are compared with the historical baseline or preset threshold to determine the potential factors that lead to quality degradation. If the analysis results show that the temperature data is the factor that causes the quality degradation, the refrigeration equipment close to the granary is automatically turned on to reduce the temperature in the granary. The opening of the refrigeration equipment will be carried out according to the preset temperature control strategy until the temperature returns to the range suitable for grain storage. If the humidity data is the factor that causes the quality degradation, the dehumidification equipment and ventilation equipment are started to reduce the humidity in the granary. The operation of the dehumidification and ventilation equipment will be adjusted according to the real-time humidity data to ensure that the humidity is controlled within the optimal range. When the gas concentration data is identified as a factor that causes quality degradation, the gas-controlled grain storage technology is used to reduce the oxygen concentration in the granary by filling with gases such as nitrogen or carbon dioxide, inhibit grain respiration and microbial activity, and delay grain aging. The gas concentration will be adjusted according to the real-time monitoring data to ensure that the predetermined gas ratio is achieved. If the change in grain weight data causes the quality grade to decline, it may be due to too much or too little grain storage. Grain will be automatically dispatched out of the warehouse, or part of the grain will be transferred to other granaries to keep the grain storage volume of each granary within an appropriate range. Grain dispatch will be carried out according to the inventory management strategy and the instructions of the logistics dispatch unit to ensure the efficiency and cost-effectiveness of grain flow. By implementing adjustment measures, the monitoring and response of the granary environment will be more accurate, which will help to timely discover and solve problems that may cause the decline in grain quality. At the same time, by accurately controlling temperature, humidity and gas concentration, the best storage environment can be provided for grain, preventing grain from mildew, pests and quality decline, and ensuring food safety. Through the implementation of this step, the intelligent inventory supervision method of the grain reserve warehouse not only improves the quality and efficiency of grain storage, but also enhances the ability to adapt to environmental changes and prevent potential risks.

[0055] Furthermore, regulating the environment of the granary also includes:

[0056] When there are multiple combinations of factors affecting, based on the combination of factors, adjust the corresponding equipment, collect data from each sensor based on the second preset period, obtain a new prediction result based on the grain quality prediction model, and continue to adjust the environment of the granary based on the new prediction result, where the second preset period is less than the first prediction period.

[0057] Specifically, generally, there are multiple factors that affect the decline of grain quality. That is, when the output of the grain quality prediction model shows that the grain quality grade has declined compared to the most recent time, and through comparative analysis, it is determined that multiple factors (such as temperature, humidity, and gas concentration) act together to cause the quality decline, a multi-factor comprehensive regulation strategy will be initiated. If both temperature and humidity are influencing factors, the refrigeration equipment and dehumidification equipment will be started simultaneously, and at the same time, the operation of the ventilation equipment may be increased to quickly adjust the temperature and humidity environment in the granary. When increasing the operation of the ventilation equipment, natural ventilation conditions are preferred, which not only ensures the grain quality but also saves resources. If the gas concentration is also an influencing factor, the controlled atmosphere grain storage technology will be combined to adjust the type and proportion of the gas filled to reduce the oxygen concentration and optimize the grain storage environment. If the grain weight data shows too high, the grain will be dispatched out of the warehouse or allocated between granaries to maintain an appropriate storage volume. By shortening the data collection period, the system can respond more quickly to environmental changes, adjust the equipment in a timely manner, and reduce the risk of grain quality decline. Comprehensively regulating multiple environmental factors makes the granary management more refined, improves the stability of the grain storage environment, reduces grain losses caused by unsuitable environments, and improves the storage quality of grains.

[0058] Furthermore, the scheduling of grain in and out includes:

[0059] When the first prediction result shows an increase or remains the same as the grain quality grade of the most recent grain, unload the grain of the same type as the grain in the granary that enters the warehouse into the granary, otherwise unload it into other granaries or newly built granaries.

[0060] Specifically, when the output of the grain quality prediction model shows that the grain quality grade has increased or remained the same compared to the most recent time, the grain scheduling process is automatically triggered, and the quality grade of the grain in the current granary is compared with that of the grain about to enter the granary. If the grain about to enter the granary is of the same type as the grain stored in the granary, the logistics scheduling unit is notified to unload this grain into the granary. If they are not of the same type, the system will instruct the logistics scheduling unit to unload this grain into other granaries or newly built granaries. The logistics scheduling unit, according to the system instructions, schedules corresponding transportation equipment (such as conveyor belts, forklifts, automated guided vehicles, etc.) to transport the grain to the designated granary. At the same time, the scheduling unit will consider factors such as the current storage capacity of the granary, the shelf life of the grain, and the turnover speed of the grain to optimize the storage space and improve the turnover efficiency. Storing grains with similar quality grades together can reduce cross - contamination between grains of different qualities and maintain the overall quality of the grain. Reasonable grain scheduling can reduce grain losses caused by improper storage, such as avoiding storing perishable grains in unsuitable environments.

[0061] Furthermore, scheduling the inflow and outflow of grain also includes:

[0062] After the preset time for environmental adjustment of the granary, when the quality grade of the grain in the granary has not changed, the granary affected by the external environmental changes of the granary is obtained as the target granary, and the grain in the target granary is scheduled for outbound, or part of the grain in the target granary is transferred to other granaries.

[0063] Specifically, after the preset time for environmental adjustment of the granary, the quality grade of the grain in the granary is re - evaluated. If the evaluation result shows that the grain quality grade has not changed, it indicates that the previous environmental adjustment measures have not effectively improved the grain storage conditions. Analyze and identify factors affecting the external environmental changes of the granary, such as climate change, geographical location, etc. Based on the influencing factors, obtain the affected granary as the target granary and take further grain scheduling measures. For the target granary, formulate specific grain scheduling strategies, including outbound of grain and re - distribution. The scheduling strategy will consider factors such as the grain quality, storage capacity, grain type, and market demand of the target granary. According to the scheduling strategy, instruct the logistics scheduling unit to perform outbound operations on part or all of the grain in the target granary. For the grain that does not need to be outbound, transfer these grains to other granaries with more suitable conditions to optimize the overall grain storage layout. By optimizing the storage and scheduling of grain, the risks during grain storage can be reduced, and the safety of grain can be improved. Through the implementation of this step, the impact of environmental changes on grain storage can be more effectively addressed, ensuring grain quality and improving the efficiency and safety of grain reserves.

[0064] Furthermore, obtaining the quality grade of the grain includes:

[0065] Obtain the grain images captured by the imaging device from the storage unit, perform denoising and enhancement operations on the grain images, and obtain the preprocessed grain images. Based on the characteristics of the grains, extract grain samples from the grain images. The characteristics of the grains include the color, texture, and shape of the grains. Identify the characteristic parameters related to the grain quality from the grain samples, and based on the characteristic parameters related to the grain quality, obtain the quality grade of the grains. The characteristic parameters related to the grain quality include the area, perimeter, and aspect ratio of the grain particles.

[0066] Specifically, use the imaging device installed in the granary to regularly capture images of the grains for quality grade assessment. Perform denoising processing on the collected grain images to eliminate random noise in the images and improve the image quality. Perform enhancement operations on the images, such as adjusting the contrast, brightness, and sharpness, to make the characteristics of the grains more obvious. Use image segmentation technology to extract grain samples from the preprocessed grain images to distinguish the grains from the background. For example, extract the color, texture, and shape characteristics of the grains. The color characteristics can be extracted by methods such as color histograms or color moments; the texture characteristics can be extracted by methods such as gray-level co-occurrence matrices or local binary patterns; the shape characteristics can be extracted by methods such as contour tracking or shape descriptors. Identify the characteristic parameters related to the grain quality from the grain samples, such as the area, perimeter, and aspect ratio of the grain particles. These parameters can be automatically measured by image analysis software, such as using functions in an image processing library (e.g., OpenCV), which is prior art and will not be elaborated here. Based on the identified quality-related characteristic parameters, combined with a preset quality assessment standard or a machine learning model, evaluate the quality grade of the grains. If a machine learning model is used, the model may have been trained with historical data to identify the distribution of characteristic parameters of grains of different quality grades. The output quality grade assessment result of the grains can be used to trigger the above-mentioned granary environment adjustment or grain scheduling operations. Through this step, the accuracy of quality assessment is improved; at the same time, it can also provide real-time grain quality monitoring, timely detect changes in grain quality, reduce the risk of grain spoilage, and improve the safety of the grains.

[0067] Furthermore, obtaining the quality grade of the grains also includes:

[0068] Preset a first quality threshold and a second quality threshold, calculate the mass of each grain of food, count the first quantity of grains of food in the food sample whose mass is greater than or equal to the first quality threshold, the second quantity of grains of food in the food sample whose mass is less than the first quality threshold and greater than or equal to the second quality threshold, and the third quantity of grains of food whose mass is less than the second quality threshold. Calculate the first ratio of the first quantity to the total quantity of grains of food in the food sample, the second ratio of the second quantity to the total quantity of grains of food in the food sample, and the third ratio of the third quantity to the total quantity of grains of food in the food sample. Based on the first ratio, the second ratio, and the third ratio, calculate the quality grade of the food corresponding to the food sample.

[0069] Specifically, preset a first quality threshold and a second quality threshold to distinguish the quality grades of grains of food. Extract the size information of grains of food from the image and use image analysis technology to calculate the mass of each grain of food. Count the mass distribution of grains of food in the food sample: The first quantity is the number of grains of food whose mass is greater than or equal to the first quality threshold. The second quantity is the number of grains of food whose mass is less than the first quality threshold but greater than or equal to the second quality threshold. The third quantity is the number of grains of food whose mass is less than the second quality threshold. Calculate the ratios of the first quantity, the second quantity, and the third quantity to the total quantity of grains of food in the food sample respectively: The first ratio is the ratio of the first quantity to the total quantity. The second ratio is the ratio of the second quantity to the total quantity. The third ratio is the ratio of the third quantity to the total quantity. Based on the first ratio, the second ratio, and the third ratio, calculate the quality grade of the food corresponding to the food sample to more accurately evaluate the quality of the food, thereby triggering the above-mentioned granary environment adjustment or food scheduling operation. Through the implementation of this step, the food quality can be managed and monitored more effectively, ensuring food safety, while improving management efficiency and economic benefits.

[0070] Further, calculating the mass of each grain of food includes:

[0071] Based on the food sample, calculate the area, perimeter, and aspect ratio of each grain of food, and calculate the mass of the grain of food through the following formula:

[0072] M = S×α1 + L×α2 + K×α3

[0073] Where, M represents the mass of the grain of food, S represents the area of the grain of food, L represents the perimeter of the grain of food, K represents the aspect ratio of the grain of food, α1 represents the first coefficient, α2 represents the second coefficient, α3 represents the third coefficient. The sum of the first coefficient, the second coefficient, and the third coefficient is equal to 1. The first coefficient is greater than the third coefficient, and the third coefficient is greater than the second coefficient.

[0074] Specifically, through the implementation of this step, by comprehensively considering the area, perimeter, and aspect ratio of grain particles, the quality of each grain can be more accurately evaluated, changes in grain quality can be detected in a timely manner, and corresponding measures can be taken to improve the safety of grain.

[0075] The above describes an inventory intelligent supervision method for a grain storage depot in an embodiment of the present application. Next, an inventory intelligent supervision system for a grain storage depot in an embodiment of the present application will be described. Please refer to Figure 2 An embodiment of an inventory intelligent supervision system for a grain storage depot in an embodiment of the present application includes:

[0076] Temperature sensors, humidity sensors, and imaging devices are respectively installed inside each granary. Gas concentration sensors are installed at a preset height from the bottom of the granary, and weight sensors are also installed at the bottom of the granary or on the support structure.

[0077] An acquisition unit 201, configured to obtain historical data of each sensor from the storage unit, preprocess the historical data, and obtain the preprocessed historical data. The historical data includes temperature data, humidity data, gas concentration data, grain weight data, and the quality grade of the grain;

[0078] A prediction unit 202, configured to construct a grain quality prediction model, train the grain quality prediction model based on the historical data, and obtain the trained grain quality prediction model. Collect data of each sensor in the granary as first data, preprocess the first data, and input the first data into the grain quality prediction model to obtain a first prediction result. Based on the first prediction result, an environment adjustment unit adjusts the environment of the granary and / or a logistics scheduling unit schedules the in and out of the grain;

[0079] An adjustment unit 203, configured to collect data of each sensor again as second data based on a first preset period, and obtain a second prediction result predicted based on the second data based on the grain quality prediction model. Compare the difference between the second prediction result and the first prediction result. Based on the difference, the environment adjustment unit readjusts the environment of the granary and / or the logistics scheduling unit reschedules the in and out of the grain.

[0080] Through the collaborative cooperation of the above-mentioned various components, the present application realizes the intelligent monitoring and management of the inventory of the grain storage depot, and improves the safety of grain storage.

[0081] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, system, and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0082] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0083] As described above, the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. An intelligent inventory monitoring method for a grain storage warehouse, wherein a temperature sensor, a humidity sensor and a camera device are installed in each granary, a gas concentration sensor is installed at a preset height from the bottom of the granary, and a weight sensor is installed at the bottom of the granary or on a supporting structure, characterized in that: The intelligent inventory supervision method of the grain reserve warehouse includes: Step S1: acquiring historical data of each sensor from a storage unit, and preprocessing the historical data to acquire the preprocessed historical data, wherein the historical data includes temperature data, humidity data, gas concentration data, grain weight data, and grain quality grade; Step S2: constructing a grain quality prediction model, training the grain quality prediction model based on the historical data, and obtaining the trained grain quality prediction model, collecting data from each sensor in the granary as first data, preprocessing the first data, and inputting the first data into the grain quality prediction model to obtain a first prediction result, and based on the first prediction result, the environment adjustment unit adjusts the environment of the granary and / or the logistics scheduling unit schedules the entry and exit of grain; Step S3: Based on the first preset period, the data of each sensor is collected again as the second data, and based on the grain quality prediction model, a second prediction result predicted based on the second data is obtained, and the difference between the second prediction result and the first prediction result is compared. Based on the difference, the environmental adjustment unit readjusts the environment of the granary and / or the logistics scheduling unit reschedules the entry and exit of grain.

2. The method for intelligent inventory supervision of a grain reserve warehouse according to claim 1 is characterized in that: Training the grain quality prediction model: The historical data is divided into a training data set, a validation data set and a test data set; the food quality prediction model is trained using the training data set, and the parameters of the food quality prediction model are adjusted using the validation data set; the performance of the food quality prediction model is evaluated using the test data set; and the food quality prediction model is acquired when the accuracy of the output result of the food quality prediction model is greater than or equal to a preset threshold.

3. The method for intelligent inventory supervision of a grain reserve according to claim 1 is characterized in that: Conditioning the environment of the granary includes: When the quality level of grain in the first prediction result is lower than that in the most recent prediction result, the temperature data, humidity data, gas concentration data and grain weight data are compared respectively to obtain factors causing the decrease in the first prediction result; when the decrease factor is the temperature data, the refrigeration equipment near the granary is turned on; when the decrease factor is the humidity data, the dehumidification equipment and ventilation equipment near the granary are turned on; when the decrease factor is the gas concentration data, the controlled atmosphere grain storage technology is used; when the decrease factor is the grain weight data, the grain in the granary is dispatched for shipment, or part of the grain in the granary is transferred to other granaries.

4. The method for intelligent inventory supervision of a grain reserve according to claim 3 is characterized in that: Adjusting the environment of the granary also includes: When there are multiple factors affecting the environment, the corresponding equipment is adjusted based on the combination of the factors, and the data of each sensor is collected based on a second preset period. Based on the grain quality prediction model, a new prediction result is obtained, and the environment of the granary is continued to be adjusted based on the new prediction result, wherein the second preset period is smaller than the first prediction period.

5. The method for intelligent inventory supervision of a grain reserve warehouse according to claim 1 is characterized in that: The dispatch of food in and out includes: When the quality level of the grain in the first prediction result is higher than or equal to the most recent grain quality level, the grain of the same type as the grain in the granary entering the warehouse will be unloaded into the granary, otherwise it will be unloaded into other granaries or a newly built granary.

6. The method for intelligent inventory supervision of a grain reserve according to claim 5 is characterized in that: The dispatch of food in and out also includes: After the preset time of environmental adjustment of the granary, if the quality level of the grain in the granary does not change, the granary that affects the change of the external environment of the granary is obtained as the target granary, and the grain in the target granary is dispatched for shipment, or part of the grain in the target granary is transferred to other granaries.

7. The method for intelligent inventory supervision of a grain reserve according to claim 1, characterized in that: The quality grades for obtaining the said grain include: A grain image taken by a camera device is obtained from the storage unit, denoising and enhancing operations are performed on the grain image, and a preprocessed grain image is obtained. A grain sample is extracted from the grain image based on characteristics of the grain, wherein the characteristics of the grain include the color, texture and shape of the grain. Feature parameters related to the grain quality are identified from the grain sample, and based on the feature parameters related to the grain quality, the quality grade of the grain is obtained, wherein the feature parameters related to the grain quality include the area, perimeter and aspect ratio of grain particles.

8. The method for intelligent monitoring of grain storage inventory according to claim 7 is characterized in that: Obtaining the quality grade of the food also includes: A first quality threshold and a second quality threshold are preset, the quality of each grain of the food grain is calculated, a first number of the food grains in the food sample whose quality is greater than or equal to the first quality threshold, a second number of the food grains in the food sample whose quality is less than the first quality threshold and greater than or equal to the second quality threshold, and a third number of the food grains whose quality is less than the second quality threshold are counted, a first ratio of the first number to the total number of food grains in the food sample, a second ratio of the second number to the total number of food grains in the food sample, and a third ratio of the third number to the total number of food grains in the food sample are calculated, and based on the first ratio, the second ratio and the third ratio, the quality grade of the food corresponding to the food sample is calculated.

9. The method for intelligent inventory supervision of a grain reserve warehouse according to claim 8, characterized in that: Calculating the mass of each grain particle includes: Based on the grain sample, the area, perimeter and aspect ratio of each grain particle are calculated, and the mass of the grain particle is calculated by the following formula: M=S×α1+L×α2+K×α3 Among them, M represents the mass of the grain particles, S represents the area of ​​the grain particles, L represents the circumference of the grain particles, K represents the aspect ratio of the grain particles, α1 represents the first coefficient, α2 represents the second coefficient, α3 represents the third coefficient, the sum of the first coefficient, the second coefficient and the third coefficient is equal to 1, the first coefficient is greater than the third coefficient, and the third coefficient is greater than the second coefficient.

10. An intelligent inventory monitoring system for a grain reserve warehouse, comprising: installing a temperature sensor, a humidity sensor and a camera device in each grain bin, installing a gas concentration sensor at a preset height from the bottom of the grain bin, and installing a weight sensor at the bottom of the grain bin or on a supporting structure, for implementing the intelligent inventory monitoring method for a grain reserve warehouse as claimed in any one of claims 1 to 9, characterized in that: The intelligent inventory supervision system of the grain reserve warehouse includes: An acquisition unit, used for acquiring historical data of each sensor from a storage unit, and preprocessing the historical data to acquire the preprocessed historical data, wherein the historical data includes temperature data, humidity data, gas concentration data, grain weight data, and grain quality grade; A prediction unit is used to construct a grain quality prediction model, train the grain quality prediction model based on the historical data, obtain the trained grain quality prediction model, collect data from each sensor in the granary as first data, pre-process the first data, and input the first data into the grain quality prediction model to obtain a first prediction result. Based on the first prediction result, the environment adjustment unit adjusts the environment of the granary and / or the logistics scheduling unit schedules the entry and exit of grain; An adjustment unit is used to collect the data of each sensor again as the second data based on the first preset period, and obtain a second prediction result based on the second data based on the grain quality prediction model, and compare the difference between the second prediction result and the first prediction result. Based on the difference, the environment adjustment unit readjusts the environment of the granary and / or the logistics scheduling unit reschedules the entry and exit of grain.

Images