Multi-parameter grain condition data management and control and alarm method, equipment and medium

Abstract

The invention discloses a control and alarm method and device for multi-parameter grain condition data and a medium, and relates to the technical field of granary management. The method comprises the following steps: acquiring grain depot data and grain pile data through a sensor, and synchronously acquiring warehouse in-out receipt information; the grain depot data and the grain pile data are compared with a historical database, a dynamic threshold value model is established, and the dynamic threshold value model adjusts a parameter deviation range based on climate data and a storage period of the grain depot in the same region; according to the dynamic threshold model, obtaining a corresponding boundary value, generating a 3D distribution diagram of the grain pile, and calculating an interlayer difference; if the grain depot data and the grain pile data reach boundary values or the interlayer difference exceeds a first preset threshold value, an alarm signal is triggered, and the stock quantity is verified by associating the in-out stock receipt information. According to the method, real-time collection of multi-source data and application of the nano biosensor are achieved, and comprehensive and accurate monitoring of internal and external environmental parameters and grain physiological indexes of the grain depot is achieved through the dynamic threshold value model.

Description

Technical Field

[0001] This application relates to the technical field of granary management, and particularly to a method, device, and medium for controlling and alarming multi-parameter grain condition data. Background Art

[0002] During daily storage, quickly detecting abnormal grain inventory and taking measures can effectively reduce grain losses, such as pest damage, mildew, quantity changes, etc., thus ensuring both the revenue of enterprises and the stability and security of national grain.

[0003] Currently, the judgment rules for inventory abnormalities in each granary are inconsistent and the methods are single. Generally, fixed comparison data is set, and the grain condition is judged by comparing the grain condition data with the pre-prepared comparison data, resulting in a high false alarm rate. In addition, some granaries install in-warehouse quantity detection cameras, and the grain inventory is judged by scanning and dotting with the cameras. However, this type of method is costly. Currently, there are very few granaries with quantity detection in China, and the current related technologies have low precision. For a granary carrying thousands of tons or tens of thousands of tons of grain, the error is large, so the current practicality is not good. In addition, traditional methods lack comprehensive correlation analysis of temperature and humidity gradients, pest densities, and inventory quantities, resulting in the inability to accurately predict potential risks such as mildew and pests.

[0004] Through the above analysis, the problems and defects of the existing technology are as follows:

[0005] The grain condition monitoring technology in the existing technology mostly uses fixed threshold comparison or camera scanning methods, with a high false alarm rate and high costs, and lacks comprehensive correlation analysis of temperature and humidity gradients, pest densities, and inventory quantities. Summary of the Invention

[0006] The embodiments of this application provide a method, device, and medium for controlling and alarming multi-parameter grain condition data, which can solve the problems that the grain condition monitoring technology in the existing technology mostly uses fixed threshold comparison or camera scanning methods, with a high false alarm rate and high costs, and lacks comprehensive correlation analysis of temperature and humidity gradients, pest densities, and inventory quantities.

[0007] In a first aspect, the embodiments of this application provide a method for controlling and alarming multi-parameter grain condition data. The method includes: obtaining granary data and grain pile data through sensors, and synchronously obtaining inbound and outbound document information; comparing the granary data and grain pile data with a historical database to establish a dynamic threshold model, where the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage period of granaries in the same region; obtaining corresponding boundary values according to the dynamic threshold model, generating a 3D distribution map of the grain pile, and calculating the interlayer difference; if the granary data and grain pile data reach the boundary values, or the interlayer difference exceeds a first preset threshold, triggering an alarm signal and verifying the inventory quantity by associating the inbound and outbound document information.

[0008] In one implementation of the present application, grain depot data and grain pile data are obtained through sensors, and the information of incoming and outgoing warehouse documents is synchronously obtained, specifically including: real-time collection of grain depot data through temperature, humidity and water sensors, oxygen sensors and pest traps, and the grain depot data includes the outside temperature of the warehouse, the grain temperature inside the warehouse, the moisture content of the grain, and the types of pests; real-time collection of grain pile data through nano-biosensors implanted in the grain pile, and the grain pile data includes the grain cell respiration intensity, the concentration of microbial metabolites, and bioelectric signals.

[0009] In one implementation of the present application, after real-time collection of grain pile data through nano-biosensors implanted in the grain pile, the method further includes: inputting the grain pile data into a quantum annealing model to optimize the calculation path of the grain pile health index and generate a risk weight matrix; obtaining high-risk areas with weights greater than a second preset threshold according to the risk weight matrix; performing minimally invasive sampling on the high-risk areas and analyzing the molecular structure changes of the samples; if abnormal metabolites or molecular bond breakage characteristics of the samples are detected, activating the directional electromagnetic pulse device inside the grain pile to inhibit microbial activity and trigger an alarm.

[0010] In one implementation of the present application, the grain depot data and the grain pile data are compared with the historical database to establish a dynamic threshold model, specifically including: classifying and storing the historical database according to regions and meteorological data to form a multi-dimensional database; using machine learning algorithms to analyze the multi-dimensional database, extracting the association rules of the outside temperature of the warehouse, the grain temperature inside the warehouse, the moisture content of the grain, the types and densities of pests, the cell respiration intensity, the concentration of microbial metabolites, and bioelectric signals, and obtaining the corresponding boundary values; generating real-time parameter deviations according to the association rules and according to the geographical location and storage period of the current granary; correcting the real-time parameter deviations in combination with meteorological data.

[0011] In one implementation of the present application, according to the dynamic threshold model, a 3D distribution map of the grain pile is generated and the layer difference is calculated, specifically including: mapping the grain depot data and the grain pile data to corresponding spatial coordinates, filling in the missing data points through an interpolation algorithm, and generating a continuous surface; marking the surface with a chromatographic gradient.

[0012] In one implementation of the present application, if the layer difference exceeds the preset threshold of the layer difference, an alarm signal is triggered, specifically including: using a sliding window algorithm to detect the jump values of the grain depot data and the grain pile data, and eliminating short-term interference through median filtering; performing time series analysis on the grain depot data and the grain pile data to predict the change trend in a future preset time; if the change trend exceeds the boundary value or a jump value is detected, triggering a warning.

[0013] In an implementation manner of the present application, time series analysis is performed on the granary data and the grain heap data to predict the change trend in a preset future time, which specifically includes: analyzing the types and quantities of pests captured by the pest trap through image recognition technology; combining the grain temperature and grain moisture in the warehouse to fit the functional relationships between the hatching rate of eggs, the activity of adults and the environmental parameters; simulating the migration path of the pest population in the grain heap based on cellular automata and marking the high-risk infection areas.

[0014] In an implementation manner of the present application, if the change trend exceeds the boundary value or a jump value is detected, an alarm is triggered, which specifically includes: starting the emergency ventilation system for the high-risk infection area and notifying the fumigation operation; checking the information of the inbound and outbound documents, and if there is no inbound and outbound record, it is determined as an abnormal event and the staff is notified.

[0015] In a second aspect, an embodiment of the present application further provides a control and alarm device for multi-parameter grain condition data. The device includes at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: obtain the granary data and the grain heap data through sensors, and synchronously obtain the information of the inbound and outbound documents; compare the granary data and the grain heap data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage cycle of the granaries in the same region; obtain the corresponding boundary value according to the dynamic threshold model, generate a 3D distribution map of the grain heap, and calculate the interlayer difference; if the granary data and the grain heap data reach the boundary value, or the interlayer difference exceeds the first preset threshold, trigger an alarm signal and verify the inventory quantity in association with the information of the inbound and outbound documents.

[0016] In a third aspect, an embodiment of the present application further provides a non-volatile computer storage medium for controlling and alarming multi-parameter grain condition data, storing computer-executable instructions, and the computer-executable instructions are set to: obtain the granary data and the grain heap data through sensors, and synchronously obtain the information of the inbound and outbound documents; compare the granary data and the grain heap data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage cycle of the granaries in the same region; obtain the corresponding boundary value according to the dynamic threshold model, generate a 3D distribution map of the grain heap, and calculate the interlayer difference; if the granary data and the grain heap data reach the boundary value, or the interlayer difference exceeds the first preset threshold, trigger an alarm signal and verify the inventory quantity in association with the information of the inbound and outbound documents.

[0017] A method, device and medium for controlling and alarming multi-parameter grain condition data provided by an embodiment of the present application establish a data decision center by using data such as outdoor air temperature and humidity, indoor air temperature and humidity, indoor grain temperature, grain, moisture, pest density, and inbound and outbound documents; apply a dynamic threshold model, time series analysis, and a quantum annealing model, and adjust the parameter deviation range according to the climate data and storage period of grain depots in the same region to more accurately reflect the changes in grain conditions, thereby reducing the false alarm rate; realize the comprehensive monitoring of the internal and external environment parameters of the grain depot and the physiological indicators of the grain, a comprehensive and accurate monitoring and early warning system, and a rapid emergency response mechanism, effectively ensuring food security and reducing food losses. Brief Description of the Drawings

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0019] Figure 1 is a flowchart of a method for controlling and alarming multi-parameter grain condition data provided by an embodiment of the present application;

[0020] Figure 2 is a schematic internal structure diagram of a device for controlling and alarming multi-parameter grain condition data provided by an embodiment of the present application. Detailed Embodiments

[0021] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0022] An embodiment of the present application provides a method, device and medium for controlling and alarming multi-parameter grain condition data, which solves the problems in the prior art that the grain condition monitoring technology mostly uses fixed threshold comparison or camera scanning methods, has a high false alarm rate and high cost, and lacks comprehensive correlation analysis of temperature and humidity gradients, pest density and inventory quantity.

[0023] The technical solutions proposed by the embodiments of the present application will be described in detail below with reference to the drawings.

[0024] Figure 1 is a flowchart of a method for controlling and alarming multi-parameter grain condition data provided by an embodiment of the present application. As Figure 1 shown, a method for controlling and alarming multi-parameter grain condition data provided by an embodiment of the present application specifically includes the following steps:

[0025] Step 10: Obtain the grain depot data and the grain pile data through sensors, and synchronously obtain the information of the incoming and outgoing warehouse documents.

[0026] In this step, after the grain is put into storage, a grain file is established to record data such as the storage time, variety, harvest year, storage life, and inventory quantity, and the original incoming and outgoing warehouse documents of the grain in this warehouse are incorporated into the file.

[0027] As an alternative embodiment, obtaining the grain depot data and the grain pile data through sensors and synchronously obtaining the information of the incoming and outgoing warehouse documents may specifically include: Step 101: Real-time collect the grain depot data through a temperature, humidity, and moisture sensor, an oxygen sensor, and a pest trap. The grain depot data includes the outdoor air temperature, the in-warehouse grain temperature, the grain moisture, and the pest species; Step 102: Real-time collect the grain pile data through the nano-biosensors implanted in the grain pile. The grain pile data includes the grain cell respiration intensity, the concentration of microbial metabolites, and the bioelectric signal.

[0028] In this step, the grain area is divided. Based on different warehouse types, the cable layout of the flat warehouse is relatively regular, while there are differences between the circles of the silo warehouse. Therefore, no matter what the warehouse type is, it is generally divided into three levels: upper, middle, and lower. The number of detection sensors distributed on each level can also be configured; the silo warehouse can also be further divided into inner, middle, and outer circles. Deploy temperature, humidity, and moisture sensor devices. The sensors are evenly distributed in the grain pile, and then a sensor for measuring the in-warehouse air temperature is deployed on the top of the warehouse. The system will automatically detect the temperature, humidity, and moisture of the grain temperature points. The impact of pests on the inventory is more obvious than the changes in temperature and humidity. Combining the density of pests and the pest species in the grain condition data, judgments can be made and alarms can be triggered. The respiration intensity is an important indicator reflecting the cell metabolism activity of the grain, which can understand the freshness and storage status of the grain and may indicate whether the grain is affected by factors such as pests and diseases, excessive moisture, or improper storage conditions; Monitoring the concentration of microbial metabolites can timely detect the situation of microbial contamination;

[0029] As an alternative embodiment, after real-time collecting the grain pile data through the nano-biosensors implanted in the grain pile, the method may further include: Step 103: Input the grain pile data into a quantum annealing model to optimize the calculation path of the grain pile health index and generate a risk weight matrix; Step 104: According to the risk weight matrix, obtain the high-risk areas with weights greater than the second preset threshold; Step 105: Perform minimally invasive sampling on the high-risk areas and analyze the molecular structure changes of the samples; Step 106: If abnormal metabolites or molecular bond breakage characteristics of the samples are detected, activate the directional electromagnetic pulse device inside the grain pile to inhibit the microbial activity and trigger an alarm.

[0030] In this step, through the quantum annealing model, a risk weight matrix can be generated, which reflects the influence degree of different regions or factors in the grain pile on the grain pile health index; the directional electromagnetic pulse device is a device that can generate electromagnetic pulses with specific frequencies and intensities, and can be used to inhibit the microbial activity or destroy its cell structure. Here, when abnormal metabolites or molecular bond breakage characteristics are detected, the directional electromagnetic pulse device is activated to inhibit the growth and reproduction of microorganisms.

[0031] Step 20: Compare the grain depot data and the grain pile data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage period of grain depots in the same region.

[0032] In this step, by establishing a grain condition parameter analysis model and combining the massive business data accumulated by tens of thousands of grain depots across the country and the climates of different regions, a method for abnormal alarm of grain depot inventory is formed.

[0033] As an optional embodiment, comparing the grain depot data and the grain pile data with the historical database to establish a dynamic threshold model may specifically include: Step 201: Classify and store the historical database according to regions and meteorological data to form a multi-dimensional database; Step 202: Use machine learning algorithms to analyze the multi-dimensional database, extract the association rules of outdoor temperature, indoor grain temperature, grain moisture, pest species and density data, cell respiration intensity, microbial metabolite concentration, and bioelectric signals, and obtain the corresponding boundary values; Step 203: Generate real-time parameter deviations according to the association rules and according to the geographical location and storage period of the current grain depot.

[0034] In this step, integrate the historical grain condition data of national grain depots, classify and store them according to regional climate types to form a multi-dimensional reference database, use machine learning algorithms to analyze the reference database, and extract the association rules between the temperature and humidity change trends and pest density; train the machine learning model through the national grain depot data to dynamically generate threshold benchmarks suitable for different climates, and solve the problem of poor adaptability of traditional fixed rules.

[0035] According to the association rules, determine the boundary values of each factor within the safe range, apply the association rules extracted in Step 202 to the data of the current grain depot. Through the association rules, the possible changes of the current grain depot under the action of different factors can be predicted. The geographical location and storage period of the current grain depot are important factors affecting the states of the grain depot and the grain pile.

[0036] Step 30: According to the dynamic threshold model, obtain the corresponding boundary values, generate a 3D distribution map of the grain pile, and calculate the interlayer difference.

[0037] As an alternative embodiment, according to the dynamic threshold model, a 3D distribution map of the grain pile is generated, and the difference between layers is calculated, specifically including: Step 304: Map the grain depot data and the grain pile data to the corresponding spatial coordinates, and fill in the missing data points through an interpolation algorithm to generate a continuous surface; Step 305: Mark the surface with a chromatographic gradient.

[0038] In this step, the temperature gradient color gradient can be set, with a temperature gradient of every 2 degrees according to the color gradient of blue, green, yellow, and red; a 3D model of the grain temperature is constructed based on the grain temperature details. The model can exclude invalid temperature measurement points, which is achieved through the pre-set division of the grain pile area. According to the color of the grain pile area, the distribution of temperature blocks can be judged assistively. According to the pre-set strategy and the division of the grain pile area, the temperature difference between data such as layers and circles and the standard value are compared, and compared with at least the previous three detection results to judge the change range, which can effectively predict the risk of grain condensation. It can assist in constructing a humidity model, comprehensively judge and predict grain condensation and mildew in combination with the temperature model, and issue an alarm to reduce the risk of grain loss.

[0039] Step 306: Combine meteorological data to correct the deviation of real-time parameters.

[0040] In this step, if it may rain next, the humidity of the grain pile may rise rapidly, so it is necessary to monitor the change of real-time parameters more closely.

[0041] Step 40: If the grain depot data and the grain pile data reach the boundary value, or the difference between layers exceeds the first preset threshold, trigger an alarm signal and verify the inventory quantity by associating the inbound and outbound document information.

[0042] As an alternative embodiment, if the grain depot data and the grain pile data reach the boundary value, or the difference between layers exceeds the first preset threshold, trigger an alarm signal, which may specifically include:

[0043] Step 401: Use a sliding window algorithm to detect the jump values of the grain depot data and the grain pile data, and eliminate short-term interference through median filtering.

[0044] In this step, the window starts from the starting position of the data sequence and moves backward step by step. Within each window, the median of the data is calculated, and the data point at the center of the window is replaced with the median. For the starting and ending parts of the data sequence, since the window cannot completely cover them, special processing methods such as mirror extension and periodic extension can be used. Median filtering can effectively eliminate short-term interference in the data, making the data smoother and more stable.

[0045] Step 402: Conduct time series analysis on the grain depot data and the grain pile data to predict the change trend in the future preset time.

[0046] In this step, time series analysis is performed on the grain depot data and the grain pile data, and the daily increase rate and weekly increase rate eigenvalue are extracted and cached in the local database. A multi-parameter grain condition decision-making mechanism can be constructed. The multi-parameter grain condition decision-making mechanism is divided into two parts: strategy and decision. The basic configuration of the strategy is: result = factor 1 + supplementary description 1 + factor 2 + supplementary description 2 + standard.

[0047] For example: the grain temperature at a certain point + daily increase rate + greater than + 1°C; the grain temperature at a certain point + daily increase rate + greater than + the daily increase rate of the grain temperature of this layer + 0.5°C; the grain temperature of a certain layer + weekly increase rate + greater than + 2°C; the grain temperature of a certain layer + weekly increase rate + greater than + the weekly increase rate of the average grain temperature + 0.5°C

[0048] Among them, the number of factors is not fixed, and the supplementary description is not necessary. On this basis, for each type of strategy, the corresponding decision can be issued through the system model. The decision is divided into system decision and manual correction. The factors pre-set by the system are as follows:

[0049]

[0050]

[0051] As an alternative embodiment, time series analysis is performed on the grain depot data and the grain pile data to predict the change trend in a preset future time. Specifically, it may include: Step 4021: Analyze the types and quantities of pests captured by the pest trap through image recognition technology; Step 4022: Combine the grain temperature and grain moisture in the warehouse to fit the functional relationship between the egg hatching rate, adult activity and environmental parameters; Step 4023: Based on the cellular automaton, simulate the migration path of the pest population in the grain pile and mark the high-risk infection areas. Step 403: If the change trend exceeds the boundary value or a jump value is detected, an alarm is triggered.

[0052] In this step, statistical methods or machine learning algorithms can be used to fit the functional relationship between the egg hatching rate, adult activity and environmental parameters, and the hatching rate and adult activity of pests under different environmental conditions can be predicted. The grain pile is divided into multiple cells, each cell representing a small part in the grain pile. Define the state of the cell, such as whether it is infected by pests and the transfer rules, such as the migration probability of pests. According to the transfer rules of the cellular automaton, simulate the migration path of the pest population in the grain pile. According to the simulation results, mark the areas with high pest density and active migration as high-risk infection areas, and these areas need to be focused on and control measures need to be taken. The sliding window algorithm and other jump value detection methods are used to detect the abnormal change points in the data in real time. When the change trend exceeds the boundary value or a jump value is detected, the system automatically triggers the alarm mechanism.

[0053] Further, continue to divide the grain area. Based on different bin types, the cable layout of flat storage bins is relatively regular, while there are differences between the circles of silos. Therefore, regardless of the bin type, it is generally divided into three levels: upper, middle, and lower, and the number of detection sensors distributed on each level can also be configured. For silos, they can be further divided into inner, middle, and outer circles.

[0054] As an alternative embodiment, if the change trend exceeds the boundary value or a jump value is detected, an alarm is triggered, which may specifically include:

[0055] Step 4031: Activate the emergency ventilation system for the high-risk infection area and notify the fumigation operation;

[0056] In this step, by combining cellular automata and fumigation parameter optimization, precise pest control is achieved, filling the deficiency of passive response in the existing technology.

[0057] Step 4032: Check the information of the inbound and outbound documents. If there is no inbound or outbound record, it is determined as an abnormal event and the staff is notified.

[0058] For example, it is known that the grain variety is wheat, the grain storage time is August 2023, the total inbound volume is 5000 tons, and the actual grain loading line height is 7.5 meters; the multi-parameter grain condition detection frequency is set at 8:00 am every day; after the system receives the multi-parameter grain condition system data, the detected temperature, humidity, bin temperature, bin humidity, average grain temperature, temperature point details, humidity details, and moisture details of this time are transmitted into the threshold dynamic model; relying on big data, a comparison model is established based on the multi-parameter grain condition data of other grain depots storing grain normally in the same region and at the same time period, a deviation curve is created according to the multi-warehouse model, the layer temperature difference, humidity difference, and point temperature difference of each parameter are obtained, and the deviation range benchmark is used to generate the standard value comparison relationship of the multi-parameter grain condition parser for the deviation correction of the system's multi-parameter grain condition strategy threshold; relying on the multi-parameter grain condition data, the temperature data and air humidity in the bin are known. The saturated vapor pressure at this temperature is obtained according to the current bin temperature. It is known that the relative humidity = (actual water vapor pressure / saturated water vapor pressure) × 100%, and the moisture content = 0.622 × relative humidity × saturated vapor pressure / (1013.25 - relative humidity × saturated vapor pressure). The moisture situation in the air can be calculated using the obtained grain condition data. At the same time, using the grain moisture situation obtained by the temperature, humidity, and moisture sensor, a 3D model of the grain pile can be constructed based on the difference between the grain moisture fluctuation range and the air moisture according to its detailed data, and compared with the previous three detection data of this batch of grain. If a certain range of deviation is found in the model, it can be considered that the grain pile configuration has changed. At the same time, combined with the grain archive data, check whether there are inbound and outbound documents after the current detection time. If not, an alarm is triggered at this time, and the storekeeper is asked to verify it, which is the quantity abnormal alarm.

[0059] In summary, the embodiments of the present application utilize the existing equipment in the storage area: the temperature, humidity, and water sensors in the granary, the oxygen sensor, and the pest trap to collect data on the temperature in the granary, the humidity in the granary, the temperature of the air, the humidity of the air, the temperature of the grain, the moisture content, the gas concentration, and the pest density, and perform analysis. By establishing a grain condition data grid, drawing the grain surface configuration, and combining with the warehousing and outbound system of the granary system, an abnormal alarm system for the granary inventory is finally realized without additional equipment procurement.

[0060] The above is the method embodiment proposed by the present application. Based on the same inventive concept, the embodiments of the present application also provide a control and alarm device for multi-parameter grain condition data, and its structure is as Figure 2 shown.

[0061] Figure 2 FIG. is a schematic internal structure diagram of a control and alarm device for multi-parameter grain condition data provided by an embodiment of the present application. As Figure 2 shown, the device includes:

[0062] At least one processor 201;

[0063] And a memory 202 communicatively connected to the at least one processor;

[0064] Wherein, the memory 202 stores instructions executable by the at least one processor. The instructions are executed by the at least one processor 201 so that the at least one processor 201 can: obtain grain depot data and grain pile data through sensors, and synchronously obtain warehousing and outbound document information; compare the grain depot data and grain pile data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage cycle of grain depots in the same region; according to the dynamic threshold model, obtain the corresponding boundary values, generate a 3D distribution map of the grain pile, and calculate the layer difference; if the grain depot data and grain pile data reach the boundary values, or the layer difference exceeds the first preset threshold, trigger an alarm signal and verify the inventory quantity in association with the warehousing and outbound document information.

[0065] Some embodiments of the present application provide a non-volatile computer storage medium corresponding to Figure 1 for controlling and alarming multi-parameter grain condition data, storing computer-executable instructions, and the computer-executable instructions are set to: obtain grain depot data and grain pile data through sensors, and synchronously obtain warehousing and outbound document information; compare the grain depot data and grain pile data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage cycle of grain depots in the same region; according to the dynamic threshold model, obtain the corresponding boundary values, generate a 3D distribution map of the grain pile, and calculate the layer difference; if the grain depot data and grain pile data reach the boundary values, or the layer difference exceeds the first preset threshold, trigger an alarm signal and verify the inventory quantity in association with the warehousing and outbound document information.

[0066] The various embodiments in this application are described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the Internet of Things devices and media, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiments.

[0067] The systems and media provided by the embodiments of this application correspond one-to-one with the methods. Therefore, the systems and media also have beneficial technical effects similar to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be elaborated here.

[0068] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) that contain computer-usable program code.

[0069] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more flows and / or Figure 1 blocks.

[0070] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one or more flows and / or Figure 1 blocks.

[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, causing a series of operational steps to be performed on the computer or other programmable apparatus to generate a computer-implemented process, so that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one process Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for implementing the functions specified in one block or a plurality of blocks.

[0072] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0073] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0074] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0075] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0076] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for controlling and alarming multi-parameter grain condition data, characterized in that, The method includes: Obtaining grain depot data and grain pile data through sensors, and synchronously obtaining information on incoming and outgoing warehouse documents; Comparing the grain depot data and grain pile data with a historical database to establish a dynamic threshold model, where the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage period of grain depots in the same region; According to the dynamic threshold model, obtaining corresponding boundary values, generating a 3D distribution map of the grain pile, and calculating the interlayer difference; If the grain depot data and grain pile data reach the boundary values, or the interlayer difference exceeds a first preset threshold, triggering an alarm signal and verifying the inventory quantity by associating the information on incoming and outgoing warehouse documents.

2. The control and alarm method for multi-parameter grain condition data according to claim 1, characterized in that, Obtaining grain depot data and grain pile data through sensors, and synchronously obtaining information on incoming and outgoing warehouse documents, specifically including: Real-time collecting grain depot data through temperature, humidity, moisture sensors, oxygen sensors, and pest traps, where the grain depot data includes outdoor temperature of the warehouse, grain temperature inside the warehouse, grain moisture, and pest species; Real-time collecting grain pile data through nano-biosensors implanted in the grain pile, where the grain pile data includes grain cell respiration intensity, concentration of microbial metabolites, and bioelectric signals.

3. A method for controlling and alarming multi-parameter grain condition data according to claim 2, characterized in that, After real-time collecting grain pile data through nano-biosensors implanted in the grain pile, the method further includes: Inputting the grain pile data into a quantum annealing model to optimize the calculation path of the grain pile health index and generating a risk weight matrix; According to the risk weight matrix, obtaining high-risk areas with weights greater than a second preset threshold; Performing minimally invasive sampling on the high-risk areas and analyzing the molecular structure changes of the samples; If abnormal metabolites or molecular bond breakage characteristics of the samples are detected, activating the directional electromagnetic pulse device inside the grain pile to inhibit microbial activity and trigger an alarm.

4. A method for controlling and alarming multi-parameter grain condition data according to claim 2, characterized in that, Comparing the grain depot data and grain pile data with a historical database to establish a dynamic threshold model, specifically including: Classifying and storing the historical database by region and meteorological data to form a multi-dimensional database; Using machine learning algorithms to analyze the multi-dimensional database, extracting the association rules of outdoor temperature of the warehouse, grain temperature inside the warehouse, grain moisture, pest species and density data, cell respiration intensity, concentration of microbial metabolites, and bioelectric signals, and obtaining corresponding boundary values; According to the association rules and based on the geographical location and storage period of the current granary, generating real-time parameter deviations; Combining the meteorological data to correct the real-time parameter deviations.

5. A method for controlling and alarming multi-parameter grain condition data according to claim 1, characterized in that, Generating a 3D distribution map of the grain pile and calculating the interlayer difference, specifically including: Mapping the grain depot data and grain pile data to corresponding spatial coordinates and filling in missing data points through an interpolation algorithm to generate a continuous surface; Marking the surface with a chromatographic gradient.

6. The control and alarm method for multi-parameter grain condition data according to claim 2, characterized in that, If the grain depot data and grain pile data reach the boundary values, or the interlayer difference exceeds a first preset threshold, specifically including: Using a sliding window algorithm to detect the jump values of the grain depot data and grain pile data, and eliminating short-term interference through median filtering; Performing time series analysis on the grain depot data and grain pile data to predict the change trend in a future preset time; If the change trend exceeds the boundary values or a jump value is detected, triggering a warning.

7. A method for controlling and alarming multi-parameter grain condition data according to claim 6, characterized in that Perform time series analysis on the grain depot data and grain pile data to predict the change trend in a preset future time, specifically including: Analyze the species and quantity of pests captured by the pest trap through image recognition technology; Combine the grain temperature and grain moisture in the warehouse to fit the functional relationship between the egg hatching rate, adult activity and environmental parameters; Based on cellular automata, simulate the migration path of the insect swarm in the grain pile and mark the high-risk infection areas.

8. A method for controlling and alarming multi-parameter grain condition data according to claim 7, characterized in that, If the change trend exceeds the boundary value or the jump value is detected, trigger an alarm, specifically including: Start the emergency ventilation system for the high-risk infection area and notify the fumigation operation; Check the information of the inbound and outbound documents. If there is no inbound and outbound record, it is determined as an abnormal event and the staff is notified.

9. A device for controlling and alarming multi-parameter grain condition data, characterized in that, The device includes: At least one processor; And a memory communicatively connected to the at least one processor; Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: Obtain grain depot data and grain pile data through sensors, and synchronously obtain the information of inbound and outbound documents; Compare the grain depot data and grain pile data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage period of grain depots in the same region; According to the dynamic threshold model, obtain the corresponding boundary value, generate a 3D distribution map of the grain pile, and calculate the interlayer difference; If the grain depot data and grain pile data reach the boundary value, or the interlayer difference exceeds the preset threshold, trigger an alarm signal and verify the inventory quantity in association with the information of the inbound and outbound documents.

10. A non-volatile computer storage medium for controlling and alarming multi-parameter grain condition data, storing computer-executable instructions, characterized in that, The computer-executable instructions are set to: Obtain grain depot data and grain pile data through sensors, and synchronously obtain the information of inbound and outbound documents; Compare the grain depot data and grain pile data with the historical database to establish a dynamic threshold model, and the dynamic threshold model adjusts the parameter deviation range based on the climate data and storage period of grain depots in the same region; According to the dynamic threshold model, obtain the corresponding boundary value, generate a 3D distribution map of the grain pile, and calculate the interlayer difference; If the grain depot data and grain pile data reach the boundary value, or the interlayer difference exceeds the preset threshold, trigger an alarm signal and verify the inventory quantity in association with the information of the inbound and outbound documents.

Images